modelId stringlengths 4 111 | lastModified stringlengths 24 24 | tags list | pipeline_tag stringlengths 5 30 ⌀ | author stringlengths 2 34 ⌀ | config null | securityStatus null | id stringlengths 4 111 | likes int64 0 9.53k | downloads int64 2 73.6M | library_name stringlengths 2 84 ⌀ | created timestamp[us] | card stringlengths 101 901k | card_len int64 101 901k | embeddings list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
lmsys/vicuna-13b-v1.5-16k | 2023-10-06T19:46:12.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2307.09288",
"arxiv:2306.05685",
"license:llama2",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | lmsys | null | null | lmsys/vicuna-13b-v1.5-16k | 179 | 48,048 | transformers | 2023-08-01T16:51:46 | ---
inference: false
license: llama2
---
# Vicuna Model Card
## Model Details
Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.
- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture
- **License:** Llama 2 Community License Agreement
- **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)
### Model Sources
- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/
## Uses
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
## How to Get Started with the Model
- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api
## Training Details
Vicuna v1.5 (16k) is fine-tuned from Llama 2 with supervised instruction fine-tuning and linear RoPE scaling.
The training data is around 125K conversations collected from ShareGPT.com. These conversations are packed into sequences that contain 16K tokens each.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
## Difference between different versions of Vicuna
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md) | 2,071 | [
[
-0.0212554931640625,
-0.0655517578125,
0.029632568359375,
0.02392578125,
-0.045684814453125,
-0.0137481689453125,
-0.00615692138671875,
-0.0474853515625,
0.0212860107421875,
0.0247039794921875,
-0.0447998046875,
-0.0465087890625,
-0.038238525390625,
-0.0037250518798828125,
-0.01166534423828125,
0.056915283203125,
0.01467132568359375,
0.009735107421875,
-0.003070831298828125,
-0.0186004638671875,
-0.0697021484375,
-0.04180908203125,
-0.073486328125,
-0.0177764892578125,
0.043243408203125,
0.034454345703125,
0.0445556640625,
0.04620361328125,
0.0291748046875,
0.0243682861328125,
-0.00360870361328125,
0.0292205810546875,
-0.039306640625,
0.0038318634033203125,
0.0201568603515625,
-0.07025146484375,
-0.0540771484375,
-0.0212860107421875,
0.035552978515625,
-0.005126953125,
-0.01186370849609375,
0.0174560546875,
0.0013446807861328125,
0.0311279296875,
-0.0239105224609375,
0.0214080810546875,
-0.042449951171875,
-0.0134429931640625,
-0.021087646484375,
-0.042388916015625,
-0.016876220703125,
-0.0254974365234375,
-0.0137176513671875,
-0.03411865234375,
0.002899169921875,
-0.005126953125,
0.08380126953125,
0.040435791015625,
-0.0251922607421875,
-0.0119476318359375,
-0.05499267578125,
0.03228759765625,
-0.0638427734375,
0.0269012451171875,
0.0303192138671875,
0.044921875,
-0.0200347900390625,
-0.040985107421875,
-0.045013427734375,
-0.0171966552734375,
0.004589080810546875,
0.009490966796875,
-0.019805908203125,
0.010528564453125,
0.00978851318359375,
0.0360107421875,
-0.03515625,
0.031494140625,
-0.0413818359375,
0.00988006591796875,
0.0418701171875,
0.031829833984375,
0.01171112060546875,
-0.0182952880859375,
-0.0310821533203125,
-0.0258636474609375,
-0.0255889892578125,
-0.0002503395080566406,
0.0311279296875,
0.03192138671875,
-0.031280517578125,
0.0391845703125,
-0.0126190185546875,
0.038543701171875,
-0.0097808837890625,
-0.01403045654296875,
0.0233001708984375,
-0.005725860595703125,
-0.036773681640625,
-0.0218048095703125,
0.08807373046875,
0.0341796875,
-0.005840301513671875,
0.010162353515625,
0.0028076171875,
0.0023670196533203125,
0.01654052734375,
-0.0604248046875,
0.00608062744140625,
0.049346923828125,
-0.0227813720703125,
-0.036529541015625,
-0.00377655029296875,
-0.034332275390625,
-0.03204345703125,
-0.0171661376953125,
0.0277557373046875,
-0.0301513671875,
-0.02789306640625,
0.0121917724609375,
-0.0006189346313476562,
0.032470703125,
0.0268707275390625,
-0.051177978515625,
0.0250396728515625,
0.052001953125,
0.0802001953125,
-0.00757598876953125,
-0.0292205810546875,
-0.00995635986328125,
-0.0235443115234375,
-0.0234527587890625,
0.07061767578125,
-0.0033817291259765625,
-0.025787353515625,
-0.0043792724609375,
0.01039886474609375,
-0.0017118453979492188,
-0.0413818359375,
0.045135498046875,
-0.0205535888671875,
0.01904296875,
-0.0128173828125,
-0.0386962890625,
-0.0013637542724609375,
0.018341064453125,
-0.048126220703125,
0.0897216796875,
0.0026187896728515625,
-0.053619384765625,
0.014923095703125,
-0.052642822265625,
0.00957489013671875,
0.0091094970703125,
-0.005962371826171875,
-0.0333251953125,
-0.00630950927734375,
-0.0036144256591796875,
0.0389404296875,
-0.0443115234375,
0.042205810546875,
-0.0184173583984375,
-0.0382080078125,
0.0226593017578125,
-0.04486083984375,
0.0743408203125,
0.0217437744140625,
-0.029693603515625,
0.03485107421875,
-0.058319091796875,
-0.01319122314453125,
0.0208282470703125,
-0.0142822265625,
-0.0201263427734375,
-0.0190582275390625,
0.002162933349609375,
0.00780487060546875,
0.0290374755859375,
-0.0175323486328125,
0.0246124267578125,
-0.0023021697998046875,
0.01446533203125,
0.05078125,
0.00414276123046875,
0.01012420654296875,
-0.0340576171875,
0.031585693359375,
0.00004214048385620117,
0.05975341796875,
0.00838470458984375,
-0.03887939453125,
-0.084228515625,
-0.0323486328125,
0.002689361572265625,
0.0482177734375,
-0.045196533203125,
0.046783447265625,
-0.0248870849609375,
-0.08148193359375,
-0.0699462890625,
0.012237548828125,
0.031402587890625,
0.00664520263671875,
0.0225067138671875,
-0.035552978515625,
-0.04644775390625,
-0.0753173828125,
-0.0064544677734375,
-0.0295257568359375,
-0.003917694091796875,
0.032470703125,
0.01806640625,
-0.041015625,
0.0634765625,
-0.029998779296875,
-0.02880859375,
-0.0044097900390625,
-0.00528717041015625,
0.005504608154296875,
0.030914306640625,
0.050048828125,
-0.046722412109375,
-0.022735595703125,
-0.005771636962890625,
-0.064697265625,
0.0002944469451904297,
-0.008697509765625,
-0.03631591796875,
0.01666259765625,
0.0288848876953125,
-0.047576904296875,
0.0406494140625,
0.0543212890625,
-0.03912353515625,
0.033477783203125,
-0.020721435546875,
0.006961822509765625,
-0.10198974609375,
0.01256561279296875,
0.0005865097045898438,
-0.02899169921875,
-0.04302978515625,
0.004299163818359375,
-0.009063720703125,
0.0178070068359375,
-0.0491943359375,
0.0648193359375,
-0.0271759033203125,
0.0036449432373046875,
-0.035736083984375,
-0.0146636962890625,
-0.004230499267578125,
0.0589599609375,
0.0074615478515625,
0.05352783203125,
0.0294952392578125,
-0.06146240234375,
0.0367431640625,
0.0160980224609375,
-0.0127410888671875,
0.0272369384765625,
-0.06787109375,
0.0230712890625,
0.0072174072265625,
0.01461029052734375,
-0.06915283203125,
-0.006412506103515625,
0.046600341796875,
-0.037017822265625,
0.0088043212890625,
-0.003314971923828125,
-0.0439453125,
-0.01491546630859375,
-0.01251220703125,
0.0127716064453125,
0.03399658203125,
-0.0447998046875,
0.0294189453125,
0.032684326171875,
0.0160675048828125,
-0.03912353515625,
-0.043365478515625,
-0.0014286041259765625,
-0.033050537109375,
-0.0127410888671875,
0.0007090568542480469,
-0.02410888671875,
-0.0168609619140625,
-0.0094757080078125,
0.01139068603515625,
-0.007541656494140625,
0.008026123046875,
0.036376953125,
0.0173492431640625,
-0.0062408447265625,
0.01148223876953125,
-0.006549835205078125,
-0.006061553955078125,
-0.01031494140625,
-0.00026154518127441406,
0.075927734375,
-0.0369873046875,
-0.0025005340576171875,
-0.06689453125,
-0.0032901763916015625,
0.04803466796875,
0.00667572021484375,
0.08831787109375,
0.05120849609375,
-0.0162200927734375,
0.01288604736328125,
-0.055572509765625,
-0.014312744140625,
-0.035064697265625,
0.0214385986328125,
-0.0268096923828125,
-0.052276611328125,
0.05181884765625,
0.019744873046875,
0.027191162109375,
0.03717041015625,
0.0589599609375,
0.00823211669921875,
0.0333251953125,
0.061248779296875,
-0.003582000732421875,
0.0673828125,
-0.0291595458984375,
-0.0102386474609375,
-0.05572509765625,
-0.0321044921875,
-0.04302978515625,
-0.00786590576171875,
-0.054779052734375,
-0.052032470703125,
-0.0037441253662109375,
-0.0016012191772460938,
-0.0252532958984375,
0.054840087890625,
-0.043304443359375,
0.01354217529296875,
0.045623779296875,
0.0199432373046875,
0.020904541015625,
-0.0108795166015625,
0.02001953125,
0.0104522705078125,
-0.05450439453125,
-0.05218505859375,
0.07958984375,
0.051025390625,
0.036224365234375,
0.0130462646484375,
0.05340576171875,
0.020050048828125,
0.035064697265625,
-0.06890869140625,
0.041046142578125,
0.01763916015625,
-0.0552978515625,
-0.032135009765625,
-0.0426025390625,
-0.08184814453125,
0.0273895263671875,
-0.01561737060546875,
-0.0487060546875,
0.02630615234375,
0.01055908203125,
-0.01532745361328125,
0.023406982421875,
-0.05377197265625,
0.06805419921875,
-0.02984619140625,
-0.02899169921875,
-0.003025054931640625,
-0.030548095703125,
0.041290283203125,
0.00537872314453125,
0.006107330322265625,
-0.0142822265625,
-0.004032135009765625,
0.058990478515625,
-0.044464111328125,
0.0809326171875,
-0.011077880859375,
-0.017974853515625,
0.0219573974609375,
-0.002361297607421875,
0.01328277587890625,
0.0047149658203125,
0.007061004638671875,
0.032989501953125,
0.0100860595703125,
-0.03814697265625,
-0.045379638671875,
0.04583740234375,
-0.0863037109375,
-0.034912109375,
-0.029266357421875,
-0.0225067138671875,
0.0011796951293945312,
0.007305145263671875,
0.0303192138671875,
0.020843505859375,
-0.02130126953125,
0.01285552978515625,
0.038116455078125,
-0.0241546630859375,
0.005157470703125,
0.029266357421875,
-0.0220794677734375,
-0.033782958984375,
0.04913330078125,
-0.004634857177734375,
0.01251220703125,
0.03173828125,
0.01233673095703125,
-0.018585205078125,
-0.01074981689453125,
-0.01593017578125,
0.03240966796875,
-0.042938232421875,
-0.0181427001953125,
-0.053436279296875,
-0.02203369140625,
-0.0226898193359375,
0.031951904296875,
-0.062164306640625,
-0.018646240234375,
-0.030303955078125,
-0.00876617431640625,
0.046875,
0.03515625,
0.015869140625,
0.054107666015625,
-0.0411376953125,
0.020477294921875,
0.0224761962890625,
0.0257568359375,
0.0018529891967773438,
-0.0521240234375,
-0.0198974609375,
0.006946563720703125,
-0.019287109375,
-0.0657958984375,
0.040863037109375,
-0.01262664794921875,
0.04095458984375,
0.038177490234375,
-0.001041412353515625,
0.06854248046875,
-0.00970458984375,
0.046905517578125,
0.0123138427734375,
-0.0400390625,
0.038299560546875,
-0.01806640625,
0.01486968994140625,
0.049560546875,
0.0239715576171875,
-0.047515869140625,
-0.02313232421875,
-0.06939697265625,
-0.055419921875,
0.038360595703125,
0.019287109375,
0.0215301513671875,
-0.005474090576171875,
0.036773681640625,
0.01171875,
0.013153076171875,
-0.0562744140625,
-0.043853759765625,
-0.00925445556640625,
-0.01151275634765625,
-0.01519775390625,
-0.032470703125,
-0.004123687744140625,
-0.024017333984375,
0.052398681640625,
-0.0023860931396484375,
0.04144287109375,
0.00856781005859375,
0.006114959716796875,
0.0010061264038085938,
0.01059722900390625,
0.05145263671875,
0.0267181396484375,
-0.031951904296875,
-0.021453857421875,
0.0071563720703125,
-0.034271240234375,
-0.00341796875,
0.0005774497985839844,
0.0032024383544921875,
0.01385498046875,
0.0224609375,
0.1099853515625,
0.010894775390625,
-0.035888671875,
0.024200439453125,
-0.05340576171875,
-0.017578125,
-0.041168212890625,
0.0212860107421875,
0.0119476318359375,
0.03631591796875,
0.00997161865234375,
-0.0069122314453125,
0.0003535747528076172,
-0.0538330078125,
-0.02197265625,
0.02056884765625,
-0.0305023193359375,
-0.0166473388671875,
0.048919677734375,
0.012908935546875,
-0.04852294921875,
0.0308685302734375,
0.00969696044921875,
-0.020721435546875,
0.036468505859375,
0.0168914794921875,
0.06854248046875,
-0.0184783935546875,
0.01326751708984375,
0.04302978515625,
0.0205841064453125,
-0.01094818115234375,
0.01276397705078125,
-0.0125732421875,
-0.04779052734375,
0.0096435546875,
-0.0430908203125,
-0.044158935546875,
0.0288848876953125,
-0.05499267578125,
0.03692626953125,
-0.0303955078125,
-0.036895751953125,
-0.0290374755859375,
0.032958984375,
-0.0733642578125,
0.00037741661071777344,
-0.0036163330078125,
0.069580078125,
-0.0667724609375,
0.07354736328125,
0.03228759765625,
-0.036224365234375,
-0.07012939453125,
-0.02252197265625,
-0.007320404052734375,
-0.0631103515625,
0.01508331298828125,
0.00376129150390625,
-0.0007638931274414062,
-0.01166534423828125,
-0.043609619140625,
-0.045684814453125,
0.10894775390625,
0.028778076171875,
-0.05865478515625,
-0.004718780517578125,
0.0006666183471679688,
0.0538330078125,
-0.01178741455078125,
0.042449951171875,
0.042999267578125,
0.012237548828125,
0.015655517578125,
-0.08489990234375,
-0.0006937980651855469,
-0.038116455078125,
0.00415802001953125,
-0.01922607421875,
-0.08489990234375,
0.05743408203125,
0.00628662109375,
-0.005916595458984375,
0.016998291015625,
0.060699462890625,
0.0484619140625,
0.0147247314453125,
0.033416748046875,
0.0201416015625,
0.07861328125,
0.00785064697265625,
0.0850830078125,
-0.01146697998046875,
0.0114593505859375,
0.08258056640625,
0.01522064208984375,
0.07220458984375,
0.03668212890625,
0.004337310791015625,
0.035888671875,
0.060546875,
0.01031494140625,
0.019866943359375,
-0.004230499267578125,
0.003482818603515625,
-0.007305145263671875,
0.0030841827392578125,
-0.037078857421875,
0.03790283203125,
0.021392822265625,
-0.0172576904296875,
0.01708984375,
-0.010772705078125,
0.02093505859375,
-0.017822265625,
-0.0007433891296386719,
0.0626220703125,
0.01702880859375,
-0.049713134765625,
0.0667724609375,
0.004230499267578125,
0.06878662109375,
-0.049835205078125,
0.006084442138671875,
-0.046051025390625,
0.0239105224609375,
-0.0026798248291015625,
-0.018798828125,
0.00827789306640625,
0.01468658447265625,
0.01338958740234375,
0.0129852294921875,
0.0316162109375,
-0.0218658447265625,
-0.02459716796875,
0.0286712646484375,
0.037261962890625,
0.044219970703125,
0.00684356689453125,
-0.05682373046875,
0.0352783203125,
-0.01049041748046875,
-0.0379638671875,
0.016998291015625,
0.0308685302734375,
-0.0149993896484375,
0.06988525390625,
0.04638671875,
0.0094451904296875,
-0.0006041526794433594,
0.017822265625,
0.0638427734375,
-0.04022216796875,
-0.03704833984375,
-0.06591796875,
0.028564453125,
-0.0069732666015625,
-0.041839599609375,
0.0579833984375,
0.04736328125,
0.043212890625,
0.007061004638671875,
0.04144287109375,
0.0064544677734375,
0.019775390625,
-0.0369873046875,
0.04864501953125,
-0.052978515625,
0.024688720703125,
-0.0177764892578125,
-0.071044921875,
-0.01824951171875,
0.04779052734375,
-0.01617431640625,
0.0008234977722167969,
0.0379638671875,
0.057647705078125,
0.005336761474609375,
-0.0179901123046875,
0.033843994140625,
0.01314544677734375,
0.0418701171875,
0.03643798828125,
0.0499267578125,
-0.055633544921875,
0.039581298828125,
-0.013458251953125,
-0.01898193359375,
-0.038909912109375,
-0.042236328125,
-0.09075927734375,
-0.0477294921875,
-0.01494598388671875,
-0.02862548828125,
0.015350341796875,
0.074951171875,
0.047943115234375,
-0.024200439453125,
-0.045806884765625,
-0.0011987686157226562,
-0.011871337890625,
-0.0143585205078125,
-0.01446533203125,
0.025787353515625,
-0.0008592605590820312,
-0.06451416015625,
0.00795745849609375,
-0.0133819580078125,
0.01519775390625,
-0.02630615234375,
-0.0292816162109375,
-0.0094757080078125,
0.0108795166015625,
0.0239105224609375,
0.041351318359375,
-0.04559326171875,
-0.002681732177734375,
0.004547119140625,
-0.0341796875,
0.0169830322265625,
0.0258331298828125,
-0.045684814453125,
0.01087188720703125,
0.0224456787109375,
0.012054443359375,
0.050506591796875,
0.002521514892578125,
0.028045654296875,
-0.0390625,
0.041748046875,
-0.0003619194030761719,
0.0242462158203125,
0.029541015625,
-0.0290985107421875,
0.0345458984375,
0.0024585723876953125,
-0.02764892578125,
-0.07196044921875,
-0.010009765625,
-0.0794677734375,
-0.01528167724609375,
0.10211181640625,
0.01108551025390625,
-0.04803466796875,
0.006168365478515625,
-0.041656494140625,
0.049163818359375,
-0.0211944580078125,
0.0557861328125,
0.0297393798828125,
0.0157470703125,
-0.036895751953125,
-0.05352783203125,
0.036041259765625,
0.00738525390625,
-0.07257080078125,
0.0037708282470703125,
0.0196685791015625,
0.0340576171875,
0.0011129379272460938,
0.09033203125,
-0.00534820556640625,
0.0093841552734375,
0.004833221435546875,
0.035675048828125,
-0.0290679931640625,
-0.032958984375,
-0.0195465087890625,
-0.0233306884765625,
0.01873779296875,
-0.03460693359375
]
] |
nbroad/ESG-BERT | 2023-04-26T04:50:33.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"en",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | text-classification | nbroad | null | null | nbroad/ESG-BERT | 42 | 48,041 | transformers | 2022-03-02T23:29:05 | ---
language:
- en
widget:
- text: "In fiscal year 2019, we reduced our comprehensive carbon footprint for the fourth consecutive year—down 35 percent compared to 2015, when Apple’s carbon emissions peaked, even as net revenue increased by 11 percent over that same period. In the past year, we avoided over 10 million metric tons from our emissions reduction initiatives—like our Supplier Clean Energy Program, which lowered our footprint by 4.4 million metric tons. "
example_title: "Reduced carbon footprint"
- text: "We believe it is essential to establish validated conflict-free sources of 3TG within the Democratic Republic of the Congo (the “DRC”) and adjoining countries (together, with the DRC, the “Covered Countries”), so that these minerals can be procured in a way that contributes to economic growth and development in the region. To aid in this effort, we have established a conflict minerals policy and an internal team to implement the policy."
example_title: "Conflict minerals policy"
---
# Model Card for ESG-BERT
Domain Specific BERT Model for Text Mining in Sustainable Investing
# Model Details
## Model Description
- **Developed by:** [Mukut Mukherjee](https://www.linkedin.com/in/mukutm/), [Charan Pothireddi](https://www.linkedin.com/in/sree-charan-pothireddi-6a0a3587/) and [Parabole.ai](https://www.linkedin.com/in/sree-charan-pothireddi-6a0a3587/)
- **Shared by [Optional]:** HuggingFace
- **Model type:** Language model
- **Language(s) (NLP):** en
- **License:** More information needed
- **Related Models:**
- **Parent Model:** BERT
- **Resources for more information:**
- [GitHub Repo](https://github.com/mukut03/ESG-BERT)
- [Blog Post](https://towardsdatascience.com/nlp-meets-sustainable-investing-d0542b3c264b?source=friends_link&sk=1f7e6641c3378aaff319a81decf387bf)
# Uses
## Direct Use
Text Mining in Sustainable Investing
## Downstream Use [Optional]
The applications of ESG-BERT can be expanded way beyond just text classification. It can be fine-tuned to perform various other downstream NLP tasks in the domain of Sustainable Investing.
## Out-of-Scope Use
The model should not be used to intentionally create hostile or alienating environments for people.
# Bias, Risks, and Limitations
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
## Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recomendations.
# Training Details
## Training Data
More information needed
## Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
### Preprocessing
More information needed
### Speeds, Sizes, Times
More information needed
# Evaluation
## Testing Data, Factors & Metrics
### Testing Data
The fine-tuned model for text classification is also available [here](https://drive.google.com/drive/folders/1Qz4HP3xkjLfJ6DGCFNeJ7GmcPq65_HVe?usp=sharing). It can be used directly to make predictions using just a few steps. First, download the fine-tuned pytorch_model.bin, config.json, and vocab.txt
### Factors
More information needed
### Metrics
More information needed
## Results
ESG-BERT was further trained on unstructured text data with accuracies of 100% and 98% for Next Sentence Prediction and Masked Language Modelling tasks. Fine-tuning ESG-BERT for text classification yielded an F-1 score of 0.90. For comparison, the general BERT (BERT-base) model scored 0.79 after fine-tuning, and the sci-kit learn approach scored 0.67.
# Model Examination
More information needed
# Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** More information needed
- **Hours used:** More information needed
- **Cloud Provider:** information needed
- **Compute Region:** More information needed
- **Carbon Emitted:** More information needed
# Technical Specifications [optional]
## Model Architecture and Objective
More information needed
## Compute Infrastructure
More information needed
### Hardware
More information needed
### Software
JDK 11 is needed to serve the model
# Citation
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
More information needed
**APA:**
More information needed
# Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
More information needed
# More Information [optional]
More information needed
# Model Card Authors [optional]
[Mukut Mukherjee](https://www.linkedin.com/in/mukutm/), [Charan Pothireddi](https://www.linkedin.com/in/sree-charan-pothireddi-6a0a3587/) and [Parabole.ai](https://www.linkedin.com/in/sree-charan-pothireddi-6a0a3587/), in collaboration with the Ezi Ozoani and the HuggingFace Team
# Model Card Contact
More information needed
# How to Get Started with the Model
Use the code below to get started with the model.
<details>
<summary> Click to expand </summary>
```
pip install torchserve torch-model-archiver
pip install torchvision
pip install transformers
```
Next up, we'll set up the handler script. It is a basic handler for text classification that can be improved upon. Save this script as "handler.py" in your directory. [1]
```
from abc import ABC
import json
import logging
import os
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
from ts.torch_handler.base_handler import BaseHandler
logger = logging.getLogger(__name__)
class TransformersClassifierHandler(BaseHandler, ABC):
"""
Transformers text classifier handler class. This handler takes a text (string) and
as input and returns the classification text based on the serialized transformers checkpoint.
"""
def __init__(self):
super(TransformersClassifierHandler, self).__init__()
self.initialized = False
def initialize(self, ctx):
self.manifest = ctx.manifest
properties = ctx.system_properties
model_dir = properties.get("model_dir")
self.device = torch.device("cuda:" + str(properties.get("gpu_id")) if torch.cuda.is_available() else "cpu")
# Read model serialize/pt file
self.model = AutoModelForSequenceClassification.from_pretrained(model_dir)
self.tokenizer = AutoTokenizer.from_pretrained(model_dir)
self.model.to(self.device)
self.model.eval()
logger.debug('Transformer model from path {0} loaded successfully'.format(model_dir))
# Read the mapping file, index to object name
mapping_file_path = os.path.join(model_dir, "index_to_name.json")
if os.path.isfile(mapping_file_path):
with open(mapping_file_path) as f:
self.mapping = json.load(f)
else:
logger.warning('Missing the index_to_name.json file. Inference output will not include class name.')
self.initialized = True
def preprocess(self, data):
""" Very basic preprocessing code - only tokenizes.
Extend with your own preprocessing steps as needed.
"""
text = data[0].get("data")
if text is None:
text = data[0].get("body")
sentences = text.decode('utf-8')
logger.info("Received text: '%s'", sentences)
inputs = self.tokenizer.encode_plus(
sentences,
add_special_tokens=True,
return_tensors="pt"
)
return inputs
def inference(self, inputs):
"""
Predict the class of a text using a trained transformer model.
"""
# NOTE: This makes the assumption that your model expects text to be tokenized
# with "input_ids" and "token_type_ids" - which is true for some popular transformer models, e.g. bert.
# If your transformer model expects different tokenization, adapt this code to suit
# its expected input format.
prediction = self.model(
inputs['input_ids'].to(self.device),
token_type_ids=inputs['token_type_ids'].to(self.device)
)[0].argmax().item()
logger.info("Model predicted: '%s'", prediction)
if self.mapping:
prediction = self.mapping[str(prediction)]
return [prediction]
def postprocess(self, inference_output):
# TODO: Add any needed post-processing of the model predictions here
return inference_output
_service = TransformersClassifierHandler()
def handle(data, context):
try:
if not _service.initialized:
_service.initialize(context)
if data is None:
return None
data = _service.preprocess(data)
data = _service.inference(data)
data = _service.postprocess(data)
return data
except Exception as e:
raise e
```
TorcheServe uses a format called MAR (Model Archive). We can convert our PyTorch model to a .mar file using this command:
```
torch-model-archiver --model-name "bert" --version 1.0 --serialized-file ./bert_model/pytorch_model.bin --extra-files "./bert_model/config.json,./bert_model/vocab.txt" --handler "./handler.py"
```
Move the .mar file into a new directory:
```
mkdir model_store && mv bert.mar model_store
```
Finally, we can start TorchServe using the command:
```
torchserve --start --model-store model_store --models bert=bert.mar
```
We can now query the model from another terminal window using the Inference API. We pass a text file containing text that the model will try to classify.
```
curl -X POST http://127.0.0.1:8080/predictions/bert -T predict.txt
```
This returns a label number which correlates to a textual label. This is stored in the label_dict.txt dictionary file.
```
__label__Business_Ethics : 0
__label__Data_Security : 1
__label__Access_And_Affordability : 2
__label__Business_Model_Resilience : 3
__label__Competitive_Behavior : 4
__label__Critical_Incident_Risk_Management : 5
__label__Customer_Welfare : 6
__label__Director_Removal : 7
__label__Employee_Engagement_Inclusion_And_Diversity : 8
__label__Employee_Health_And_Safety : 9
__label__Human_Rights_And_Community_Relations : 10
__label__Labor_Practices : 11
__label__Management_Of_Legal_And_Regulatory_Framework : 12
__label__Physical_Impacts_Of_Climate_Change : 13
__label__Product_Quality_And_Safety : 14
__label__Product_Design_And_Lifecycle_Management : 15
__label__Selling_Practices_And_Product_Labeling : 16
__label__Supply_Chain_Management : 17
__label__Systemic_Risk_Management : 18
__label__Waste_And_Hazardous_Materials_Management : 19
__label__Water_And_Wastewater_Management : 20
__label__Air_Quality : 21
__label__Customer_Privacy : 22
__label__Ecological_Impacts : 23
__label__Energy_Management : 24
__label__GHG_Emissions : 25
```
<\details>
| 11,665 | [
[
-0.0164794921875,
-0.05377197265625,
0.0256805419921875,
0.00656890869140625,
-0.01331329345703125,
-0.01300048828125,
-0.0168914794921875,
-0.038299560546875,
0.001018524169921875,
0.03314208984375,
-0.03704833984375,
-0.051055908203125,
-0.059234619140625,
0.004150390625,
-0.02825927734375,
0.0985107421875,
0.0004394054412841797,
0.0005636215209960938,
-0.001605987548828125,
0.007740020751953125,
-0.022308349609375,
-0.046661376953125,
-0.055450439453125,
-0.03228759765625,
0.0227203369140625,
0.00629425048828125,
0.02764892578125,
0.037445068359375,
0.038543701171875,
0.0293121337890625,
-0.01629638671875,
-0.00246429443359375,
-0.0207672119140625,
-0.00994873046875,
-0.004985809326171875,
-0.03045654296875,
-0.0310821533203125,
0.00885009765625,
0.0296630859375,
0.01971435546875,
-0.007755279541015625,
0.0223236083984375,
0.0009188652038574219,
0.0199737548828125,
-0.0249176025390625,
0.0289154052734375,
-0.04901123046875,
-0.0014867782592773438,
-0.0009899139404296875,
-0.0097503662109375,
-0.048004150390625,
-0.01509857177734375,
0.0281829833984375,
-0.04046630859375,
0.034576416015625,
0.01140594482421875,
0.09783935546875,
0.012725830078125,
-0.0289154052734375,
-0.0311126708984375,
-0.038970947265625,
0.0673828125,
-0.064453125,
0.0217742919921875,
0.02813720703125,
0.007755279541015625,
0.005859375,
-0.07208251953125,
-0.048370361328125,
-0.00933837890625,
-0.0213470458984375,
0.0194091796875,
-0.003101348876953125,
0.013397216796875,
0.0249786376953125,
0.023040771484375,
-0.033843994140625,
-0.0060577392578125,
-0.04058837890625,
-0.01056671142578125,
0.05462646484375,
0.005645751953125,
0.0218963623046875,
-0.03656005859375,
-0.0325927734375,
-0.02667236328125,
-0.01666259765625,
0.002899169921875,
0.040924072265625,
0.0297393798828125,
-0.0237274169921875,
0.0361328125,
0.004180908203125,
0.03485107421875,
-0.00006890296936035156,
-0.005268096923828125,
0.0312347412109375,
-0.02069091796875,
-0.028656005859375,
0.00008213520050048828,
0.06536865234375,
0.0195159912109375,
0.0057830810546875,
0.00038170814514160156,
-0.0123748779296875,
-0.0018472671508789062,
0.0175018310546875,
-0.066650390625,
-0.03338623046875,
0.0249786376953125,
-0.05084228515625,
-0.038238525390625,
0.0033111572265625,
-0.07177734375,
-0.0091552734375,
-0.01062774658203125,
0.04315185546875,
-0.034149169921875,
-0.0207061767578125,
0.010223388671875,
-0.0229339599609375,
0.0227203369140625,
0.00977325439453125,
-0.08538818359375,
0.013641357421875,
0.0294036865234375,
0.060760498046875,
0.007190704345703125,
-0.02301025390625,
0.0009660720825195312,
-0.0008516311645507812,
0.014404296875,
0.054931640625,
-0.0244293212890625,
-0.041351318359375,
0.0042266845703125,
0.01474761962890625,
-0.02142333984375,
-0.009857177734375,
0.06787109375,
-0.0257568359375,
0.038818359375,
-0.00433349609375,
-0.0477294921875,
-0.0304412841796875,
0.01389312744140625,
-0.036376953125,
0.10858154296875,
-0.0010251998901367188,
-0.0823974609375,
0.020111083984375,
-0.06011962890625,
-0.031402587890625,
-0.0007357597351074219,
0.006282806396484375,
-0.06365966796875,
-0.0128173828125,
0.01328277587890625,
0.0467529296875,
-0.01177215576171875,
0.03204345703125,
-0.01256561279296875,
-0.0140838623046875,
0.001514434814453125,
-0.0251922607421875,
0.0762939453125,
0.0191192626953125,
-0.032073974609375,
0.0106201171875,
-0.063232421875,
0.002948760986328125,
0.0185699462890625,
-0.021484375,
-0.0083465576171875,
0.005931854248046875,
0.041229248046875,
0.006500244140625,
0.0235137939453125,
-0.043853759765625,
0.0162811279296875,
-0.023895263671875,
0.042877197265625,
0.0611572265625,
-0.00030732154846191406,
0.020965576171875,
-0.01904296875,
0.0193328857421875,
-0.01444244384765625,
0.01389312744140625,
-0.01184844970703125,
-0.043487548828125,
-0.07513427734375,
-0.0098114013671875,
0.029052734375,
0.044921875,
-0.034332275390625,
0.06439208984375,
-0.0164337158203125,
-0.06689453125,
-0.0280914306640625,
-0.0152130126953125,
0.01513671875,
0.046051025390625,
0.03369140625,
0.003940582275390625,
-0.057159423828125,
-0.05096435546875,
-0.017333984375,
-0.0183868408203125,
-0.004314422607421875,
0.024505615234375,
0.06732177734375,
-0.03472900390625,
0.06695556640625,
-0.0545654296875,
-0.0221710205078125,
-0.023681640625,
0.024993896484375,
0.0278167724609375,
0.04498291015625,
0.041595458984375,
-0.061920166015625,
-0.033233642578125,
-0.00556182861328125,
-0.057830810546875,
0.002857208251953125,
-0.01490020751953125,
0.0006251335144042969,
0.00975799560546875,
0.0307769775390625,
-0.0367431640625,
0.033233642578125,
0.035552978515625,
-0.040802001953125,
0.0389404296875,
-0.025482177734375,
-0.0012979507446289062,
-0.0904541015625,
0.021453857421875,
0.0140228271484375,
-0.0180206298828125,
-0.04718017578125,
-0.007965087890625,
-0.001743316650390625,
-0.012115478515625,
-0.0197296142578125,
0.05572509765625,
-0.01158905029296875,
0.026824951171875,
-0.019256591796875,
-0.00466156005859375,
0.0011854171752929688,
0.04443359375,
0.0223236083984375,
0.045257568359375,
0.04168701171875,
-0.053955078125,
0.01495361328125,
0.0299530029296875,
-0.0166168212890625,
0.01303863525390625,
-0.062042236328125,
0.01092529296875,
-0.006137847900390625,
0.0143280029296875,
-0.06298828125,
-0.009918212890625,
0.0167694091796875,
-0.050567626953125,
0.033203125,
0.0024051666259765625,
-0.0377197265625,
-0.03436279296875,
-0.01091766357421875,
0.007396697998046875,
0.044342041015625,
-0.05133056640625,
0.070068359375,
0.0252685546875,
-0.005893707275390625,
-0.04193115234375,
-0.054779052734375,
-0.015716552734375,
-0.01922607421875,
-0.038970947265625,
0.043121337890625,
-0.00913238525390625,
0.01239013671875,
0.004512786865234375,
0.01076507568359375,
-0.00646209716796875,
0.00753021240234375,
0.0205230712890625,
0.03521728515625,
0.0142669677734375,
0.016815185546875,
-0.00542449951171875,
-0.017364501953125,
0.0056304931640625,
-0.00759124755859375,
0.042694091796875,
-0.0186767578125,
0.0031604766845703125,
-0.036102294921875,
0.005615234375,
0.026824951171875,
-0.00542449951171875,
0.075439453125,
0.06219482421875,
-0.04107666015625,
-0.01201629638671875,
-0.035552978515625,
-0.01800537109375,
-0.039306640625,
0.043121337890625,
-0.0157470703125,
-0.041046142578125,
0.04339599609375,
-0.0003192424774169922,
0.014739990234375,
0.06866455078125,
0.042327880859375,
-0.0089874267578125,
0.0792236328125,
0.0743408203125,
-0.004688262939453125,
0.04931640625,
-0.04730224609375,
0.030426025390625,
-0.05352783203125,
-0.03521728515625,
-0.051483154296875,
-0.0009908676147460938,
-0.052490234375,
-0.0008764266967773438,
0.0034351348876953125,
0.00283050537109375,
-0.03387451171875,
0.046295166015625,
-0.06689453125,
0.016021728515625,
0.04302978515625,
0.006763458251953125,
0.0010633468627929688,
-0.007427215576171875,
-0.0029392242431640625,
-0.0034961700439453125,
-0.049896240234375,
-0.05120849609375,
0.08447265625,
0.052215576171875,
0.04156494140625,
-0.0174102783203125,
0.05206298828125,
0.02032470703125,
0.037353515625,
-0.049102783203125,
0.03387451171875,
-0.0039825439453125,
-0.059326171875,
-0.01265716552734375,
-0.026153564453125,
-0.05670166015625,
0.01465606689453125,
-0.02679443359375,
-0.05657958984375,
0.01003265380859375,
-0.000053763389587402344,
-0.02386474609375,
0.032958984375,
-0.07000732421875,
0.076904296875,
-0.023834228515625,
-0.004383087158203125,
0.00008553266525268555,
-0.040008544921875,
0.01546478271484375,
-0.0004911422729492188,
0.01531219482421875,
-0.005802154541015625,
0.0130615234375,
0.08251953125,
-0.0330810546875,
0.07196044921875,
-0.0170440673828125,
0.0152587890625,
0.0249481201171875,
-0.0372314453125,
0.04144287109375,
-0.003414154052734375,
-0.0166473388671875,
0.0247802734375,
0.0090789794921875,
-0.0269012451171875,
-0.0231475830078125,
0.041351318359375,
-0.07904052734375,
-0.0183563232421875,
-0.060546875,
-0.026641845703125,
0.0072021484375,
0.024322509765625,
0.043975830078125,
0.005153656005859375,
-0.01114654541015625,
0.00855255126953125,
0.053497314453125,
-0.0279998779296875,
0.043701171875,
0.019073486328125,
-0.00394439697265625,
-0.032989501953125,
0.057525634765625,
-0.000014007091522216797,
0.0013608932495117188,
0.0207672119140625,
0.0159454345703125,
-0.04449462890625,
-0.0352783203125,
-0.0135040283203125,
0.0172576904296875,
-0.054779052734375,
-0.0277862548828125,
-0.07159423828125,
-0.036376953125,
-0.041107177734375,
-0.0157470703125,
-0.020050048828125,
-0.003421783447265625,
-0.0452880859375,
-0.0263671875,
0.05206298828125,
0.041778564453125,
0.01108551025390625,
0.049560546875,
-0.05133056640625,
0.004825592041015625,
0.0162811279296875,
0.0287628173828125,
0.005504608154296875,
-0.052734375,
-0.0220184326171875,
-0.006015777587890625,
-0.0382080078125,
-0.0614013671875,
0.050201416015625,
0.01385498046875,
0.034820556640625,
0.023284912109375,
0.0009975433349609375,
0.035797119140625,
-0.03289794921875,
0.06500244140625,
0.0196380615234375,
-0.08087158203125,
0.0455322265625,
-0.0274810791015625,
0.0008754730224609375,
0.04058837890625,
0.0290069580078125,
-0.043853759765625,
-0.0133209228515625,
-0.06903076171875,
-0.0728759765625,
0.060699462890625,
0.0228729248046875,
0.0148162841796875,
0.0005192756652832031,
0.030029296875,
-0.00676727294921875,
0.010986328125,
-0.0986328125,
-0.033050537109375,
-0.0214996337890625,
-0.0297088623046875,
0.0011415481567382812,
-0.01287841796875,
0.006717681884765625,
-0.0308990478515625,
0.0777587890625,
0.007457733154296875,
0.04327392578125,
0.0258026123046875,
-0.0009441375732421875,
0.01287078857421875,
0.005039215087890625,
0.03350830078125,
0.017425537109375,
-0.03619384765625,
-0.004245758056640625,
0.032012939453125,
-0.049102783203125,
-0.0016927719116210938,
0.023651123046875,
-0.0194854736328125,
0.01134490966796875,
0.0220489501953125,
0.065673828125,
0.00925445556640625,
-0.03668212890625,
0.0325927734375,
-0.01432037353515625,
-0.0205535888671875,
-0.0307464599609375,
-0.0054168701171875,
0.005542755126953125,
0.006969451904296875,
0.0263214111328125,
0.0121612548828125,
0.0031585693359375,
-0.03448486328125,
0.006900787353515625,
0.0155181884765625,
-0.01751708984375,
-0.01235198974609375,
0.0699462890625,
0.022979736328125,
-0.02801513671875,
0.050445556640625,
-0.0160064697265625,
-0.05657958984375,
0.05938720703125,
0.04443359375,
0.0762939453125,
-0.01195526123046875,
0.007083892822265625,
0.0557861328125,
0.0269927978515625,
-0.007091522216796875,
0.01446533203125,
0.00795745849609375,
-0.056884765625,
-0.0123138427734375,
-0.0584716796875,
-0.0169525146484375,
0.01131439208984375,
-0.037994384765625,
0.042205810546875,
-0.037567138671875,
-0.019439697265625,
0.00868988037109375,
0.0228729248046875,
-0.06353759765625,
0.0305938720703125,
-0.0005979537963867188,
0.068359375,
-0.08062744140625,
0.06591796875,
0.037139892578125,
-0.050628662109375,
-0.059173583984375,
-0.0115509033203125,
-0.026641845703125,
-0.049407958984375,
0.042388916015625,
0.0273590087890625,
0.0088348388671875,
0.005489349365234375,
-0.04345703125,
-0.055419921875,
0.091796875,
0.002979278564453125,
-0.0330810546875,
-0.0101165771484375,
-0.010040283203125,
0.047698974609375,
-0.019378662109375,
0.05328369140625,
0.0297393798828125,
0.03900146484375,
0.00128173828125,
-0.055633544921875,
0.0009851455688476562,
-0.021697998046875,
0.002010345458984375,
0.00830841064453125,
-0.05523681640625,
0.061798095703125,
-0.00965118408203125,
-0.0181121826171875,
0.005390167236328125,
0.055877685546875,
0.0130615234375,
0.02337646484375,
0.0286712646484375,
0.051055908203125,
0.06768798828125,
-0.018096923828125,
0.0811767578125,
-0.03070068359375,
0.06884765625,
0.0628662109375,
0.0014848709106445312,
0.071044921875,
0.01580810546875,
-0.0243072509765625,
0.04266357421875,
0.0718994140625,
-0.03143310546875,
0.04144287109375,
-0.0004010200500488281,
-0.01934814453125,
0.0002880096435546875,
0.0008053779602050781,
-0.036590576171875,
0.0235137939453125,
0.018829345703125,
-0.051910400390625,
-0.004512786865234375,
0.00293731689453125,
0.006336212158203125,
-0.006160736083984375,
-0.01373291015625,
0.043121337890625,
-0.00246429443359375,
-0.03570556640625,
0.02142333984375,
0.0256195068359375,
0.0787353515625,
-0.053253173828125,
0.004230499267578125,
0.0185394287109375,
0.0176239013671875,
-0.0231781005859375,
-0.045440673828125,
0.024505615234375,
-0.0011644363403320312,
-0.02197265625,
-0.029296875,
0.05926513671875,
-0.0362548828125,
-0.04925537109375,
0.02587890625,
0.0012226104736328125,
0.014129638671875,
0.00684356689453125,
-0.0667724609375,
-0.005222320556640625,
0.010589599609375,
-0.02386474609375,
0.007305145263671875,
0.0139312744140625,
0.0275421142578125,
0.042694091796875,
0.05035400390625,
-0.00620269775390625,
0.004558563232421875,
-0.0077667236328125,
0.0523681640625,
-0.05133056640625,
-0.0380859375,
-0.057861328125,
0.04046630859375,
-0.0242462158203125,
-0.03607177734375,
0.05828857421875,
0.05303955078125,
0.06951904296875,
-0.01462554931640625,
0.0633544921875,
-0.0152740478515625,
0.028533935546875,
-0.0276336669921875,
0.0672607421875,
-0.0281829833984375,
0.00394439697265625,
-0.0229644775390625,
-0.060699462890625,
-0.01505279541015625,
0.06927490234375,
-0.032684326171875,
0.01490020751953125,
0.0478515625,
0.0494384765625,
0.002269744873046875,
0.014251708984375,
0.007793426513671875,
0.0130767822265625,
0.0296630859375,
0.0255584716796875,
0.0301971435546875,
-0.06915283203125,
0.042327880859375,
-0.023345947265625,
-0.0130462646484375,
-0.013336181640625,
-0.0718994140625,
-0.0738525390625,
-0.05035400390625,
-0.03729248046875,
-0.0309295654296875,
-0.0140228271484375,
0.0631103515625,
0.05706787109375,
-0.0625,
-0.007476806640625,
-0.0290069580078125,
0.005039215087890625,
-0.00733184814453125,
-0.023040771484375,
0.047393798828125,
-0.0262603759765625,
-0.07733154296875,
-0.0077667236328125,
-0.004451751708984375,
0.0195770263671875,
-0.00897216796875,
-0.0022640228271484375,
-0.0304718017578125,
0.005252838134765625,
0.037872314453125,
0.0229644775390625,
-0.04510498046875,
-0.021484375,
-0.0005478858947753906,
-0.009918212890625,
-0.001842498779296875,
0.036529541015625,
-0.0408935546875,
0.035064697265625,
0.0384521484375,
0.03961181640625,
0.05731201171875,
-0.018280029296875,
0.025421142578125,
-0.04718017578125,
0.01349639892578125,
0.0202178955078125,
0.039794921875,
0.0130157470703125,
-0.0484619140625,
0.0391845703125,
0.0209503173828125,
-0.058685302734375,
-0.06036376953125,
-0.0109405517578125,
-0.07659912109375,
-0.016021728515625,
0.07861328125,
-0.011322021484375,
-0.0225372314453125,
-0.0007805824279785156,
-0.0289764404296875,
0.03338623046875,
-0.027496337890625,
0.06292724609375,
0.063232421875,
-0.001415252685546875,
-0.00983428955078125,
-0.036529541015625,
0.04107666015625,
0.0200653076171875,
-0.06658935546875,
-0.00412750244140625,
0.0000095367431640625,
0.028656005859375,
0.0217742919921875,
0.04248046875,
-0.00019299983978271484,
0.003398895263671875,
0.01216888427734375,
0.032928466796875,
0.00421142578125,
-0.010101318359375,
-0.0203857421875,
-0.0015306472778320312,
-0.017425537109375,
-0.02099609375
]
] |
KoboldAI/OPT-6B-nerys-v2 | 2022-07-04T07:45:47.000Z | [
"transformers",
"pytorch",
"opt",
"text-generation",
"en",
"arxiv:2205.01068",
"license:other",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | KoboldAI | null | null | KoboldAI/OPT-6B-nerys-v2 | 21 | 47,884 | transformers | 2022-06-26T10:24:25 | ---
language: en
license: other
commercial: no
---
# OPT 6B - Nerys
## Model Description
OPT 6B-Nerys is a finetune created using Facebook's OPT model.
## Training data
The training data contains around 2500 ebooks in various genres (the "Pike" dataset), a CYOA dataset called "CYS" and 50 Asian "Light Novels" (the "Manga-v1" dataset).
Most parts of the dataset have been prepended using the following text: `[Genre: <genre1>, <genre2>]`
This dataset has been cleaned in the same way as fairseq-dense-13B-Nerys-v2
### How to use
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
```py
>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='KoboldAI/OPT-6B-Nerys-v2')
>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt's all right," Janeway said. "I'm certain that you're doing your best to keep me informed of what\'s going on."'}]
```
### Limitations and Biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).
### License
OPT-6B is licensed under the OPT-175B license, Copyright (c) Meta Platforms, Inc. All Rights Reserved.
### BibTeX entry and citation info
```
@misc{zhang2022opt,
title={OPT: Open Pre-trained Transformer Language Models},
author={Susan Zhang and Stephen Roller and Naman Goyal and Mikel Artetxe and Moya Chen and Shuohui Chen and Christopher Dewan and Mona Diab and Xian Li and Xi Victoria Lin and Todor Mihaylov and Myle Ott and Sam Shleifer and Kurt Shuster and Daniel Simig and Punit Singh Koura and Anjali Sridhar and Tianlu Wang and Luke Zettlemoyer},
year={2022},
eprint={2205.01068},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` | 1,924 | [
[
-0.0146942138671875,
-0.041259765625,
0.0053558349609375,
-0.0030803680419921875,
-0.00899505615234375,
-0.034515380859375,
-0.00804901123046875,
-0.0225830078125,
0.0113372802734375,
0.060943603515625,
-0.07958984375,
-0.03179931640625,
-0.02838134765625,
0.03741455078125,
-0.039093017578125,
0.0731201171875,
0.022857666015625,
-0.00001901388168334961,
0.017578125,
0.0075836181640625,
-0.024749755859375,
-0.0238494873046875,
-0.049468994140625,
-0.0178375244140625,
0.0221710205078125,
0.039337158203125,
0.0655517578125,
0.0394287109375,
0.0391845703125,
0.0196990966796875,
-0.01129913330078125,
0.00705718994140625,
-0.056060791015625,
-0.0161285400390625,
0.0024013519287109375,
-0.0364990234375,
-0.028167724609375,
-0.0074310302734375,
0.059814453125,
0.049530029296875,
0.0182952880859375,
0.01157379150390625,
-0.0018491744995117188,
0.040802001953125,
-0.03521728515625,
-0.01282501220703125,
-0.05560302734375,
0.00887298583984375,
-0.0210418701171875,
0.004993438720703125,
-0.0548095703125,
-0.029266357421875,
0.0235137939453125,
-0.040771484375,
0.037506103515625,
0.0117034912109375,
0.0865478515625,
0.029205322265625,
-0.041259765625,
-0.006927490234375,
-0.042938232421875,
0.07183837890625,
-0.0909423828125,
0.0205841064453125,
0.0219268798828125,
0.01366424560546875,
-0.00983428955078125,
-0.065185546875,
-0.047332763671875,
-0.0010318756103515625,
-0.01061248779296875,
0.0170745849609375,
-0.00792694091796875,
-0.0007815361022949219,
0.03338623046875,
0.0335693359375,
-0.04583740234375,
0.003475189208984375,
-0.051300048828125,
-0.0257568359375,
0.05767822265625,
0.016357421875,
0.017669677734375,
-0.0355224609375,
-0.019927978515625,
-0.0103607177734375,
-0.0447998046875,
-0.00867462158203125,
0.0537109375,
0.029052734375,
-0.02935791015625,
0.0548095703125,
-0.0177001953125,
0.06573486328125,
0.01995849609375,
-0.002399444580078125,
0.054443359375,
-0.0216217041015625,
-0.0171051025390625,
0.01157379150390625,
0.0765380859375,
0.03204345703125,
0.0231475830078125,
0.001232147216796875,
0.0013036727905273438,
0.00965118408203125,
0.020904541015625,
-0.0709228515625,
-0.0079345703125,
0.0225372314453125,
-0.047698974609375,
-0.0284881591796875,
0.0044403076171875,
-0.0552978515625,
-0.01116180419921875,
-0.022918701171875,
0.028289794921875,
-0.046142578125,
-0.0222015380859375,
0.015655517578125,
-0.00275421142578125,
0.034423828125,
-0.00839996337890625,
-0.07415771484375,
0.00860595703125,
0.01068878173828125,
0.04339599609375,
-0.005512237548828125,
-0.02777099609375,
-0.01666259765625,
-0.004917144775390625,
-0.027252197265625,
0.04449462890625,
-0.0213470458984375,
-0.0030651092529296875,
0.0186614990234375,
0.0289764404296875,
-0.015167236328125,
-0.032379150390625,
0.055450439453125,
-0.02874755859375,
0.04083251953125,
0.00006747245788574219,
-0.04803466796875,
-0.0256195068359375,
-0.006103515625,
-0.06365966796875,
0.07000732421875,
0.0189056396484375,
-0.06439208984375,
0.0250091552734375,
-0.038970947265625,
-0.0283203125,
0.0011739730834960938,
0.0034008026123046875,
-0.037841796875,
0.009429931640625,
0.0142669677734375,
0.033355712890625,
-0.0160369873046875,
0.0208282470703125,
-0.01605224609375,
-0.0244598388671875,
0.01214599609375,
-0.047332763671875,
0.0762939453125,
0.017120361328125,
-0.0301513671875,
0.006137847900390625,
-0.0816650390625,
0.00428009033203125,
0.005115509033203125,
-0.0120391845703125,
0.00467681884765625,
0.002330780029296875,
0.0275726318359375,
0.014373779296875,
0.0263214111328125,
-0.040679931640625,
0.0034503936767578125,
-0.06817626953125,
0.042083740234375,
0.041168212890625,
-0.0026531219482421875,
0.037750244140625,
-0.025848388671875,
0.034942626953125,
0.0017414093017578125,
0.0250091552734375,
-0.0191497802734375,
-0.036590576171875,
-0.0765380859375,
0.00943756103515625,
0.0198516845703125,
0.032989501953125,
-0.06182861328125,
0.041259765625,
-0.0170135498046875,
-0.059234619140625,
-0.05059814453125,
-0.011138916015625,
0.0210418701171875,
0.0219879150390625,
0.04327392578125,
-0.00019276142120361328,
-0.041656494140625,
-0.06805419921875,
-0.025787353515625,
0.00888824462890625,
0.0228424072265625,
0.0163116455078125,
0.03729248046875,
-0.045318603515625,
0.08355712890625,
-0.039215087890625,
-0.0181732177734375,
-0.034881591796875,
-0.0027484893798828125,
0.052337646484375,
0.035491943359375,
0.044281005859375,
-0.07208251953125,
-0.044189453125,
-0.009918212890625,
-0.037811279296875,
-0.0206451416015625,
-0.0201416015625,
-0.025634765625,
0.0229949951171875,
0.0287933349609375,
-0.026885986328125,
0.0296783447265625,
0.0517578125,
-0.039459228515625,
0.055999755859375,
0.01161956787109375,
-0.00762939453125,
-0.1112060546875,
-0.006160736083984375,
-0.00634765625,
-0.004974365234375,
-0.049957275390625,
-0.0256500244140625,
-0.00038623809814453125,
-0.00592803955078125,
-0.051666259765625,
0.044342041015625,
-0.0249786376953125,
0.007480621337890625,
-0.00724029541015625,
-0.0018835067749023438,
-0.0088043212890625,
0.034088134765625,
0.00933074951171875,
0.033905029296875,
0.035858154296875,
-0.055328369140625,
0.0141448974609375,
0.04449462890625,
-0.0165252685546875,
0.026031494140625,
-0.051727294921875,
-0.00720977783203125,
-0.006198883056640625,
-0.00670623779296875,
-0.06671142578125,
-0.02984619140625,
0.0167236328125,
-0.03997802734375,
0.007465362548828125,
-0.004116058349609375,
-0.030548095703125,
-0.0307464599609375,
0.0131072998046875,
0.0249786376953125,
0.043701171875,
-0.03302001953125,
0.0499267578125,
0.00005137920379638672,
-0.0022716522216796875,
-0.052001953125,
-0.060516357421875,
-0.0206146240234375,
-0.0202789306640625,
-0.050811767578125,
0.044647216796875,
-0.01617431640625,
0.0130615234375,
0.00333404541015625,
0.01033782958984375,
-0.02001953125,
-0.018585205078125,
-0.000028133392333984375,
0.0154266357421875,
-0.0095672607421875,
0.0026721954345703125,
0.0257720947265625,
-0.0246734619140625,
0.0021800994873046875,
-0.0180206298828125,
0.046905517578125,
-0.0035572052001953125,
-0.0162353515625,
-0.03900146484375,
0.01251983642578125,
0.0279541015625,
-0.01438140869140625,
0.06390380859375,
0.056396484375,
-0.033905029296875,
-0.02374267578125,
-0.0270538330078125,
-0.027740478515625,
-0.038970947265625,
0.04473876953125,
-0.004581451416015625,
-0.050537109375,
0.034271240234375,
0.00478363037109375,
0.032745361328125,
0.06903076171875,
0.03955078125,
0.0184478759765625,
0.062347412109375,
0.049346923828125,
0.008056640625,
0.041290283203125,
-0.040008544921875,
0.020721435546875,
-0.039642333984375,
-0.007350921630859375,
-0.035980224609375,
-0.0193939208984375,
-0.033905029296875,
-0.00783538818359375,
0.00746917724609375,
0.00005048513412475586,
-0.0372314453125,
0.0455322265625,
-0.04248046875,
0.02178955078125,
0.043914794921875,
0.0016002655029296875,
0.0120391845703125,
0.0030364990234375,
-0.00946044921875,
-0.01551055908203125,
-0.0679931640625,
-0.035400390625,
0.08929443359375,
0.01824951171875,
0.061248779296875,
0.0121917724609375,
0.0643310546875,
0.0023956298828125,
0.01270294189453125,
-0.049407958984375,
0.03277587890625,
-0.026885986328125,
-0.06744384765625,
-0.01325225830078125,
-0.03472900390625,
-0.073486328125,
-0.0008616447448730469,
-0.030609130859375,
-0.036163330078125,
0.032684326171875,
0.0131683349609375,
-0.0245819091796875,
0.0090789794921875,
-0.060211181640625,
0.0789794921875,
-0.01873779296875,
-0.02191162109375,
0.01380157470703125,
-0.0555419921875,
0.0158538818359375,
-0.0024356842041015625,
0.007114410400390625,
0.01273345947265625,
0.025421142578125,
0.06109619140625,
-0.0262451171875,
0.07861328125,
0.0113677978515625,
-0.00537109375,
0.03228759765625,
-0.021759033203125,
0.0183563232421875,
-0.0091400146484375,
-0.01108551025390625,
0.01161956787109375,
-0.0054473876953125,
-0.01181793212890625,
-0.008270263671875,
0.0259857177734375,
-0.0703125,
0.007083892822265625,
-0.034515380859375,
-0.043304443359375,
0.015960693359375,
0.054534912109375,
0.075439453125,
0.06817626953125,
0.007770538330078125,
0.03424072265625,
0.041290283203125,
-0.032257080078125,
0.045745849609375,
0.0225067138671875,
-0.01438140869140625,
-0.05364990234375,
0.060333251953125,
0.0223541259765625,
0.037567138671875,
0.0307159423828125,
0.005863189697265625,
-0.037078857421875,
-0.0298614501953125,
-0.0170440673828125,
0.0310821533203125,
-0.05120849609375,
-0.0196380615234375,
-0.048736572265625,
-0.03839111328125,
-0.037353515625,
-0.0174713134765625,
-0.035675048828125,
-0.01031494140625,
-0.044097900390625,
-0.0006847381591796875,
0.021697998046875,
0.044708251953125,
0.01119232177734375,
0.0565185546875,
-0.062103271484375,
0.025726318359375,
-0.0101470947265625,
0.0139312744140625,
-0.006214141845703125,
-0.05596923828125,
-0.03680419921875,
0.0178375244140625,
-0.03472900390625,
-0.08270263671875,
0.05352783203125,
0.0165252685546875,
0.0428466796875,
0.04217529296875,
0.0304718017578125,
0.0310516357421875,
-0.039154052734375,
0.0654296875,
0.0164642333984375,
-0.06549072265625,
0.0296173095703125,
-0.040771484375,
0.0289764404296875,
0.0386962890625,
0.036407470703125,
-0.0244140625,
-0.0246734619140625,
-0.071533203125,
-0.0703125,
0.064697265625,
0.0300750732421875,
0.01910400390625,
-0.0059967041015625,
0.022735595703125,
0.00980377197265625,
0.0247955322265625,
-0.10528564453125,
-0.04107666015625,
-0.0206298828125,
-0.048492431640625,
-0.00913238525390625,
-0.0235443115234375,
0.0182952880859375,
-0.00916290283203125,
0.078125,
-0.0179901123046875,
0.03387451171875,
0.021087646484375,
-0.01551055908203125,
0.0105438232421875,
0.0121917724609375,
0.02142333984375,
0.03179931640625,
-0.01256561279296875,
-0.01898193359375,
0.00160980224609375,
-0.04376220703125,
-0.01100921630859375,
0.0231170654296875,
-0.0382080078125,
0.01357269287109375,
0.031402587890625,
0.07763671875,
0.0121612548828125,
-0.0384521484375,
0.0238494873046875,
0.00968170166015625,
-0.038055419921875,
-0.049896240234375,
0.0042572021484375,
-0.0033245086669921875,
0.019073486328125,
0.0198974609375,
0.01074981689453125,
0.020599365234375,
-0.0168304443359375,
0.01006317138671875,
0.003856658935546875,
-0.034820556640625,
-0.0054473876953125,
0.04901123046875,
0.011810302734375,
-0.0244903564453125,
0.0616455078125,
-0.0270538330078125,
-0.031341552734375,
0.0465087890625,
0.060943603515625,
0.07110595703125,
-0.008636474609375,
0.02020263671875,
0.050689697265625,
0.045928955078125,
0.001041412353515625,
0.02947998046875,
0.0435791015625,
-0.07098388671875,
-0.0364990234375,
-0.05279541015625,
-0.01222991943359375,
0.022369384765625,
-0.046142578125,
0.048797607421875,
-0.00634765625,
-0.030914306640625,
-0.0110626220703125,
-0.002780914306640625,
-0.04522705078125,
0.028839111328125,
0.00400543212890625,
0.061553955078125,
-0.07501220703125,
0.022735595703125,
0.0543212890625,
-0.03472900390625,
-0.07781982421875,
0.00005507469177246094,
-0.015777587890625,
-0.0214691162109375,
0.0250396728515625,
0.042266845703125,
0.01416015625,
0.03985595703125,
-0.048828125,
-0.08038330078125,
0.0726318359375,
0.0291748046875,
-0.04144287109375,
-0.00481414794921875,
0.013885498046875,
0.0301513671875,
-0.024871826171875,
0.0281524658203125,
0.030670166015625,
0.02459716796875,
-0.00640106201171875,
-0.04473876953125,
-0.01654052734375,
-0.034149169921875,
-0.005229949951171875,
0.002933502197265625,
-0.045257568359375,
0.07916259765625,
-0.0110626220703125,
-0.00994873046875,
0.0213470458984375,
0.049041748046875,
0.012664794921875,
0.015380859375,
0.0272216796875,
0.04119873046875,
0.037811279296875,
-0.0180816650390625,
0.06103515625,
-0.027130126953125,
0.0496826171875,
0.0731201171875,
0.00311279296875,
0.052337646484375,
0.0159149169921875,
-0.01198577880859375,
0.054229736328125,
0.0577392578125,
-0.0179901123046875,
0.042938232421875,
-0.0078887939453125,
0.012939453125,
-0.0198211669921875,
-0.0008616447448730469,
-0.03973388671875,
0.018768310546875,
0.02215576171875,
-0.048187255859375,
0.0022525787353515625,
-0.0030803680419921875,
0.0038909912109375,
-0.00530242919921875,
-0.0158233642578125,
0.042755126953125,
0.00811004638671875,
-0.043212890625,
0.050079345703125,
-0.00469207763671875,
0.05255126953125,
-0.058441162109375,
-0.00014412403106689453,
0.00772857666015625,
0.0281982421875,
-0.033233642578125,
-0.0267333984375,
0.01548004150390625,
-0.012054443359375,
-0.03692626953125,
-0.00020194053649902344,
0.0499267578125,
-0.042144775390625,
-0.061920166015625,
0.01354217529296875,
0.01605224609375,
0.012847900390625,
0.01397705078125,
-0.050933837890625,
-0.0092620849609375,
0.0223388671875,
-0.01544189453125,
-0.013336181640625,
0.0200042724609375,
0.0176544189453125,
0.03814697265625,
0.04559326171875,
-0.01306915283203125,
0.032928466796875,
0.01108551025390625,
0.047271728515625,
-0.0369873046875,
-0.053192138671875,
-0.056640625,
0.06353759765625,
-0.01517486572265625,
-0.048583984375,
0.061767578125,
0.0428466796875,
0.06585693359375,
-0.026031494140625,
0.0654296875,
-0.0174102783203125,
0.0362548828125,
-0.04144287109375,
0.055419921875,
-0.043731689453125,
-0.0086669921875,
-0.043914794921875,
-0.09014892578125,
-0.0004892349243164062,
0.071044921875,
-0.02825927734375,
0.020782470703125,
0.06646728515625,
0.061065673828125,
0.0014009475708007812,
0.018768310546875,
-0.004215240478515625,
0.0352783203125,
0.01055145263671875,
0.042938232421875,
0.0501708984375,
-0.062347412109375,
0.035858154296875,
-0.0271148681640625,
-0.00942230224609375,
-0.0144805908203125,
-0.06475830078125,
-0.08056640625,
-0.036712646484375,
-0.0218505859375,
-0.033721923828125,
-0.02471923828125,
0.053009033203125,
0.04327392578125,
-0.05145263671875,
-0.0139007568359375,
-0.033538818359375,
-0.0024852752685546875,
-0.028717041015625,
-0.0213775634765625,
0.0235137939453125,
-0.02459716796875,
-0.07403564453125,
0.00970458984375,
-0.0184783935546875,
0.014129638671875,
-0.0099639892578125,
-0.01114654541015625,
-0.019256591796875,
-0.0088958740234375,
0.021697998046875,
-0.00621795654296875,
-0.039642333984375,
0.0114593505859375,
0.016357421875,
0.008636474609375,
-0.0165557861328125,
0.0107574462890625,
-0.04296875,
0.02685546875,
0.036773681640625,
0.04400634765625,
0.01467132568359375,
-0.01125335693359375,
0.0494384765625,
-0.043670654296875,
0.01039886474609375,
0.0193939208984375,
0.0248260498046875,
0.020751953125,
-0.02691650390625,
0.033203125,
0.027679443359375,
-0.046661376953125,
-0.05560302734375,
0.0200042724609375,
-0.067626953125,
-0.002559661865234375,
0.10052490234375,
0.00920867919921875,
-0.00836944580078125,
-0.003543853759765625,
-0.0236053466796875,
0.02197265625,
-0.018646240234375,
0.01433563232421875,
0.0384521484375,
0.0204010009765625,
-0.007366180419921875,
-0.0426025390625,
0.036651611328125,
0.0277252197265625,
-0.0548095703125,
-0.0117034912109375,
0.0433349609375,
0.01250457763671875,
0.02410888671875,
0.04852294921875,
-0.005222320556640625,
0.0132598876953125,
0.006763458251953125,
0.0081634521484375,
0.003490447998046875,
-0.032470703125,
-0.01207733154296875,
-0.0034427642822265625,
-0.027374267578125,
0.00794219970703125
]
] |
cross-encoder/ms-marco-TinyBERT-L-2 | 2021-08-05T08:39:52.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"text-classification",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | cross-encoder | null | null | cross-encoder/ms-marco-TinyBERT-L-2 | 5 | 47,632 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
---
# Cross-Encoder for MS Marco
This model was trained on the [MS Marco Passage Ranking](https://github.com/microsoft/MSMARCO-Passage-Ranking) task.
The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. The training code is available here: [SBERT.net Training MS Marco](https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/ms_marco)
## Usage with Transformers
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
model = AutoModelForSequenceClassification.from_pretrained('model_name')
tokenizer = AutoTokenizer.from_pretrained('model_name')
features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'], padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
scores = model(**features).logits
print(scores)
```
## Usage with SentenceTransformers
The usage becomes easier when you have [SentenceTransformers](https://www.sbert.net/) installed. Then, you can use the pre-trained models like this:
```python
from sentence_transformers import CrossEncoder
model = CrossEncoder('model_name', max_length=512)
scores = model.predict([('Query', 'Paragraph1'), ('Query', 'Paragraph2') , ('Query', 'Paragraph3')])
```
## Performance
In the following table, we provide various pre-trained Cross-Encoders together with their performance on the [TREC Deep Learning 2019](https://microsoft.github.io/TREC-2019-Deep-Learning/) and the [MS Marco Passage Reranking](https://github.com/microsoft/MSMARCO-Passage-Ranking/) dataset.
| Model-Name | NDCG@10 (TREC DL 19) | MRR@10 (MS Marco Dev) | Docs / Sec |
| ------------- |:-------------| -----| --- |
| **Version 2 models** | | |
| cross-encoder/ms-marco-TinyBERT-L-2-v2 | 69.84 | 32.56 | 9000
| cross-encoder/ms-marco-MiniLM-L-2-v2 | 71.01 | 34.85 | 4100
| cross-encoder/ms-marco-MiniLM-L-4-v2 | 73.04 | 37.70 | 2500
| cross-encoder/ms-marco-MiniLM-L-6-v2 | 74.30 | 39.01 | 1800
| cross-encoder/ms-marco-MiniLM-L-12-v2 | 74.31 | 39.02 | 960
| **Version 1 models** | | |
| cross-encoder/ms-marco-TinyBERT-L-2 | 67.43 | 30.15 | 9000
| cross-encoder/ms-marco-TinyBERT-L-4 | 68.09 | 34.50 | 2900
| cross-encoder/ms-marco-TinyBERT-L-6 | 69.57 | 36.13 | 680
| cross-encoder/ms-marco-electra-base | 71.99 | 36.41 | 340
| **Other models** | | |
| nboost/pt-tinybert-msmarco | 63.63 | 28.80 | 2900
| nboost/pt-bert-base-uncased-msmarco | 70.94 | 34.75 | 340
| nboost/pt-bert-large-msmarco | 73.36 | 36.48 | 100
| Capreolus/electra-base-msmarco | 71.23 | 36.89 | 340
| amberoad/bert-multilingual-passage-reranking-msmarco | 68.40 | 35.54 | 330
| sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco | 72.82 | 37.88 | 720
Note: Runtime was computed on a V100 GPU.
| 3,233 | [
[
-0.032318115234375,
-0.043670654296875,
0.0250396728515625,
0.0116729736328125,
-0.01270294189453125,
0.01074981689453125,
-0.01340484619140625,
-0.0384521484375,
0.025146484375,
0.0255584716796875,
-0.041229248046875,
-0.05108642578125,
-0.0579833984375,
0.0030574798583984375,
-0.0333251953125,
0.059326171875,
-0.0015039443969726562,
0.012298583984375,
-0.01374053955078125,
-0.00827789306640625,
-0.0193939208984375,
-0.03082275390625,
-0.04132080078125,
-0.0218048095703125,
0.035980224609375,
0.0159454345703125,
0.05816650390625,
0.02978515625,
0.0419921875,
0.032958984375,
-0.00838470458984375,
0.00704193115234375,
-0.01416015625,
0.00012576580047607422,
0.00521087646484375,
-0.028656005859375,
-0.041717529296875,
-0.0091400146484375,
0.033416748046875,
0.0265960693359375,
0.0005497932434082031,
0.0199737548828125,
-0.0002181529998779297,
0.04327392578125,
-0.029388427734375,
-0.003780364990234375,
-0.02587890625,
0.0184326171875,
-0.01494598388671875,
-0.0187530517578125,
-0.035186767578125,
-0.0162811279296875,
0.013275146484375,
-0.043914794921875,
0.0299072265625,
0.0117340087890625,
0.09521484375,
0.026275634765625,
-0.016448974609375,
-0.0196533203125,
-0.035400390625,
0.05419921875,
-0.051513671875,
0.053314208984375,
0.01372528076171875,
0.01324462890625,
0.0088958740234375,
-0.07318115234375,
-0.033660888671875,
-0.0162506103515625,
-0.01438140869140625,
0.01922607421875,
-0.031829833984375,
-0.006412506103515625,
0.0313720703125,
0.0309600830078125,
-0.074951171875,
-0.00608062744140625,
-0.05377197265625,
-0.00921630859375,
0.04913330078125,
0.020233154296875,
0.0201873779296875,
-0.0188446044921875,
-0.024200439453125,
-0.010711669921875,
-0.03790283203125,
0.016326904296875,
0.0207366943359375,
0.0008745193481445312,
-0.01546478271484375,
0.03082275390625,
-0.017791748046875,
0.059600830078125,
0.0084075927734375,
0.0070953369140625,
0.058074951171875,
-0.019500732421875,
-0.0178985595703125,
0.0018815994262695312,
0.07373046875,
0.021514892578125,
0.0078277587890625,
-0.009552001953125,
-0.0169677734375,
-0.01284027099609375,
0.0303802490234375,
-0.06622314453125,
-0.020111083984375,
0.0219879150390625,
-0.040252685546875,
-0.01009368896484375,
0.01227569580078125,
-0.06396484375,
0.01207733154296875,
-0.0098876953125,
0.045440673828125,
-0.030059814453125,
0.0024089813232421875,
0.017730712890625,
-0.0106658935546875,
0.02166748046875,
0.01343536376953125,
-0.0557861328125,
0.001026153564453125,
0.0260009765625,
0.070556640625,
-0.00865936279296875,
-0.028472900390625,
-0.0121612548828125,
-0.00284576416015625,
-0.0124969482421875,
0.04266357421875,
-0.03546142578125,
-0.0235137939453125,
-0.005458831787109375,
0.021514892578125,
-0.01131439208984375,
-0.0229034423828125,
0.053619384765625,
-0.034820556640625,
0.038299560546875,
-0.00945281982421875,
-0.0261993408203125,
-0.01183319091796875,
0.0177001953125,
-0.059112548828125,
0.091064453125,
0.0029773712158203125,
-0.0638427734375,
0.0123443603515625,
-0.052947998046875,
-0.0257110595703125,
-0.01207733154296875,
0.0030841827392578125,
-0.05743408203125,
0.0034465789794921875,
0.0306243896484375,
0.019378662109375,
-0.0240936279296875,
0.007495880126953125,
-0.01306915283203125,
-0.0340576171875,
0.0123138427734375,
-0.03125,
0.08184814453125,
0.0298309326171875,
-0.037017822265625,
0.004062652587890625,
-0.050628662109375,
0.0089111328125,
0.02142333984375,
-0.0318603515625,
-0.0004360675811767578,
-0.021514892578125,
0.0103912353515625,
0.03009033203125,
0.032958984375,
-0.037689208984375,
0.007801055908203125,
-0.02099609375,
0.036376953125,
0.03466796875,
-0.0081939697265625,
0.025909423828125,
-0.022613525390625,
0.05029296875,
0.009490966796875,
0.032623291015625,
0.0006861686706542969,
-0.047607421875,
-0.06622314453125,
-0.010162353515625,
0.038299560546875,
0.044158935546875,
-0.055450439453125,
0.04083251953125,
-0.038970947265625,
-0.0531005859375,
-0.062042236328125,
-0.00751495361328125,
0.031524658203125,
0.0255126953125,
0.04974365234375,
-0.00669097900390625,
-0.055084228515625,
-0.074951171875,
-0.025146484375,
0.0017728805541992188,
0.00301361083984375,
0.0179595947265625,
0.048370361328125,
-0.0197906494140625,
0.055328369140625,
-0.040008544921875,
-0.0162811279296875,
-0.034423828125,
0.0002484321594238281,
0.01898193359375,
0.050018310546875,
0.04730224609375,
-0.052642822265625,
-0.0408935546875,
-0.014251708984375,
-0.052215576171875,
0.00533294677734375,
0.0027637481689453125,
-0.0104522705078125,
0.02032470703125,
0.04638671875,
-0.051971435546875,
0.0511474609375,
0.037109375,
-0.034393310546875,
0.027984619140625,
-0.03302001953125,
0.0218505859375,
-0.09063720703125,
0.00763702392578125,
-0.0024852752685546875,
-0.01190948486328125,
-0.038787841796875,
-0.011932373046875,
0.00698089599609375,
-0.0018825531005859375,
-0.0261077880859375,
0.0248565673828125,
-0.045440673828125,
-0.0025653839111328125,
0.0092010498046875,
0.0058135986328125,
0.01276397705078125,
0.047637939453125,
0.024566650390625,
0.05841064453125,
0.039031982421875,
-0.0266571044921875,
0.0180816650390625,
0.027587890625,
-0.046142578125,
0.02850341796875,
-0.0693359375,
-0.0006136894226074219,
-0.00975799560546875,
0.0081024169921875,
-0.0748291015625,
0.01265716552734375,
0.0179290771484375,
-0.0655517578125,
0.0234832763671875,
-0.01027679443359375,
-0.02960205078125,
-0.049560546875,
-0.01345062255859375,
0.024688720703125,
0.037750244140625,
-0.03564453125,
0.04351806640625,
0.0255279541015625,
0.0005350112915039062,
-0.052947998046875,
-0.091552734375,
0.01372528076171875,
-0.00420379638671875,
-0.055206298828125,
0.047576904296875,
-0.01538848876953125,
0.0110931396484375,
0.0029468536376953125,
-0.0033512115478515625,
-0.00311279296875,
-0.0084075927734375,
0.0145721435546875,
0.0247650146484375,
-0.0140838623046875,
0.0011625289916992188,
0.0009379386901855469,
-0.016387939453125,
0.005237579345703125,
-0.0156707763671875,
0.048004150390625,
-0.013275146484375,
-0.009521484375,
-0.018951416015625,
0.01490020751953125,
0.037261962890625,
-0.042388916015625,
0.054046630859375,
0.061004638671875,
-0.0242919921875,
-0.00827789306640625,
-0.031402587890625,
-0.007579803466796875,
-0.037811279296875,
0.03387451171875,
-0.04351806640625,
-0.058013916015625,
0.039794921875,
0.02276611328125,
0.0020275115966796875,
0.038360595703125,
0.036651611328125,
-0.0015001296997070312,
0.07733154296875,
0.036346435546875,
-0.00365447998046875,
0.04937744140625,
-0.053619384765625,
0.022308349609375,
-0.058074951171875,
-0.044281005859375,
-0.049591064453125,
-0.033447265625,
-0.05133056640625,
-0.02642822265625,
0.0228424072265625,
-0.01009368896484375,
-0.01702880859375,
0.05230712890625,
-0.056427001953125,
0.0242919921875,
0.0546875,
0.0208892822265625,
0.007762908935546875,
0.01097869873046875,
-0.0191802978515625,
-0.0092620849609375,
-0.06256103515625,
-0.02447509765625,
0.09783935546875,
0.012603759765625,
0.0526123046875,
0.0012569427490234375,
0.057952880859375,
0.023101806640625,
-0.0028591156005859375,
-0.03240966796875,
0.03302001953125,
-0.01134490966796875,
-0.058319091796875,
-0.0172882080078125,
-0.0316162109375,
-0.08074951171875,
0.0255279541015625,
-0.015960693359375,
-0.043701171875,
0.038543701171875,
-0.006702423095703125,
-0.029266357421875,
0.02374267578125,
-0.0419921875,
0.09814453125,
-0.03125,
-0.02685546875,
-0.00734710693359375,
-0.0555419921875,
0.01275634765625,
0.01555633544921875,
0.00254058837890625,
0.006908416748046875,
-0.012481689453125,
0.056854248046875,
-0.0276641845703125,
0.026123046875,
-0.0109405517578125,
0.01148223876953125,
0.014068603515625,
-0.007427215576171875,
0.02874755859375,
-0.0006003379821777344,
-0.007793426513671875,
0.0250396728515625,
-0.003253936767578125,
-0.029876708984375,
-0.03192138671875,
0.061004638671875,
-0.06878662109375,
-0.031341552734375,
-0.040771484375,
-0.0272369384765625,
-0.0022296905517578125,
0.01548004150390625,
0.057769775390625,
0.031707763671875,
0.00030803680419921875,
0.0323486328125,
0.05584716796875,
-0.0235748291015625,
0.04302978515625,
0.02838134765625,
-0.0039825439453125,
-0.055389404296875,
0.05816650390625,
0.022918701171875,
0.0124664306640625,
0.0430908203125,
-0.01367950439453125,
-0.0357666015625,
-0.040557861328125,
-0.0266571044921875,
0.01265716552734375,
-0.039947509765625,
-0.0167694091796875,
-0.054840087890625,
-0.0308074951171875,
-0.037567138671875,
-0.005519866943359375,
-0.03125,
-0.032012939453125,
-0.0180511474609375,
-0.01311492919921875,
0.0164794921875,
0.045745849609375,
0.00983428955078125,
0.0153045654296875,
-0.046051025390625,
0.0160369873046875,
0.00048661231994628906,
0.0118255615234375,
-0.007965087890625,
-0.0657958984375,
-0.03411865234375,
-0.00513458251953125,
-0.0308685302734375,
-0.06207275390625,
0.051055908203125,
-0.006526947021484375,
0.054962158203125,
0.01136016845703125,
0.004329681396484375,
0.056396484375,
-0.029205322265625,
0.0675048828125,
0.0123138427734375,
-0.064697265625,
0.050018310546875,
0.0020122528076171875,
0.02935791015625,
0.04730224609375,
0.041900634765625,
-0.040008544921875,
-0.0193939208984375,
-0.057861328125,
-0.07098388671875,
0.0675048828125,
0.0224761962890625,
-0.00823974609375,
0.005527496337890625,
0.00151824951171875,
-0.009033203125,
0.02117919921875,
-0.07275390625,
-0.036865234375,
-0.034027099609375,
-0.028533935546875,
-0.0236968994140625,
-0.01242828369140625,
0.01544952392578125,
-0.047027587890625,
0.0582275390625,
0.01316070556640625,
0.042999267578125,
0.0455322265625,
-0.0310516357421875,
0.0066070556640625,
0.00827789306640625,
0.05181884765625,
0.048309326171875,
-0.0203857421875,
-0.0017452239990234375,
0.01593017578125,
-0.03839111328125,
-0.01055145263671875,
0.01776123046875,
-0.034820556640625,
0.0290069580078125,
0.0253753662109375,
0.07574462890625,
0.0168304443359375,
-0.0290374755859375,
0.048858642578125,
0.0038394927978515625,
-0.02093505859375,
-0.037689208984375,
-0.014923095703125,
0.0015058517456054688,
0.0286865234375,
0.018463134765625,
0.004810333251953125,
0.0191497802734375,
-0.031005859375,
0.0117645263671875,
0.0269012451171875,
-0.044158935546875,
-0.01540374755859375,
0.0682373046875,
0.0130615234375,
-0.032073974609375,
0.05169677734375,
0.0017728805541992188,
-0.061553955078125,
0.03900146484375,
0.02734375,
0.078857421875,
-0.021392822265625,
0.0133514404296875,
0.05218505859375,
0.051361083984375,
0.005535125732421875,
0.0262603759765625,
-0.011871337890625,
-0.039825439453125,
-0.0011167526245117188,
-0.041351318359375,
-0.008880615234375,
-0.005016326904296875,
-0.05072021484375,
0.02227783203125,
-0.01331329345703125,
-0.0245513916015625,
-0.01438140869140625,
0.0204925537109375,
-0.0631103515625,
0.01245880126953125,
0.004146575927734375,
0.083740234375,
-0.04107666015625,
0.08038330078125,
0.04351806640625,
-0.066162109375,
-0.04376220703125,
-0.0097808837890625,
-0.0299835205078125,
-0.052215576171875,
0.042724609375,
0.00948333740234375,
0.00875091552734375,
-0.000024080276489257812,
-0.0267181396484375,
-0.061737060546875,
0.111083984375,
0.015289306640625,
-0.05126953125,
-0.01378631591796875,
0.033111572265625,
0.038604736328125,
-0.02593994140625,
0.050933837890625,
0.032623291015625,
0.037109375,
-0.014556884765625,
-0.0706787109375,
0.011260986328125,
-0.03704833984375,
-0.0032482147216796875,
0.006015777587890625,
-0.062255859375,
0.07940673828125,
-0.0166473388671875,
0.0127410888671875,
0.012542724609375,
0.04534912109375,
0.0154571533203125,
0.025848388671875,
0.02642822265625,
0.0634765625,
0.05157470703125,
-0.029876708984375,
0.0665283203125,
-0.042266845703125,
0.042877197265625,
0.06787109375,
0.0153045654296875,
0.06707763671875,
0.032379150390625,
-0.0245819091796875,
0.055999755859375,
0.054779052734375,
-0.016357421875,
0.038787841796875,
0.002902984619140625,
0.0012197494506835938,
-0.0310211181640625,
0.0289459228515625,
-0.05096435546875,
0.0179901123046875,
0.01178741455078125,
-0.060302734375,
-0.005710601806640625,
-0.00397491455078125,
-0.00833892822265625,
-0.0123291015625,
-0.0185546875,
0.03387451171875,
-0.005794525146484375,
-0.043060302734375,
0.051513671875,
0.002288818359375,
0.056427001953125,
-0.04998779296875,
0.01390838623046875,
-0.0194549560546875,
0.020294189453125,
-0.01708984375,
-0.06591796875,
0.00714874267578125,
-0.0036945343017578125,
-0.0112762451171875,
-0.0208587646484375,
0.036865234375,
-0.04400634765625,
-0.043060302734375,
0.03094482421875,
0.0240936279296875,
0.0159912109375,
-0.007198333740234375,
-0.07806396484375,
0.0167083740234375,
0.0159759521484375,
-0.037811279296875,
0.00846099853515625,
0.031829833984375,
0.00978851318359375,
0.0504150390625,
0.03662109375,
-0.00910186767578125,
0.031524658203125,
0.0025615692138671875,
0.053253173828125,
-0.06591796875,
-0.039642333984375,
-0.04345703125,
0.045806884765625,
-0.0219879150390625,
-0.040008544921875,
0.0679931640625,
0.07818603515625,
0.0748291015625,
-0.0241851806640625,
0.0504150390625,
-0.01110076904296875,
0.0186614990234375,
-0.0294189453125,
0.05877685546875,
-0.06414794921875,
0.0188446044921875,
-0.0164794921875,
-0.0625,
-0.01320648193359375,
0.048004150390625,
-0.033172607421875,
0.0194549560546875,
0.050384521484375,
0.07061767578125,
0.0005831718444824219,
-0.001934051513671875,
0.018524169921875,
0.01190185546875,
0.0135498046875,
0.06591796875,
0.04888916015625,
-0.06964111328125,
0.075927734375,
-0.032958984375,
0.01220703125,
-0.0166473388671875,
-0.031829833984375,
-0.06414794921875,
-0.043914794921875,
-0.0248870849609375,
-0.031707763671875,
0.01236724853515625,
0.0626220703125,
0.054840087890625,
-0.0562744140625,
-0.01556396484375,
-0.0017452239990234375,
0.007503509521484375,
-0.01044464111328125,
-0.0172119140625,
0.032562255859375,
-0.0207366943359375,
-0.07183837890625,
0.0252227783203125,
0.001007080078125,
0.0006628036499023438,
-0.01849365234375,
-0.03289794921875,
-0.0222015380859375,
0.0032596588134765625,
0.034393310546875,
0.00815582275390625,
-0.054962158203125,
-0.00933837890625,
0.0142364501953125,
-0.022430419921875,
0.0221710205078125,
0.04583740234375,
-0.058868408203125,
0.017303466796875,
0.062286376953125,
0.03155517578125,
0.068359375,
-0.01568603515625,
0.0208282470703125,
-0.0311279296875,
-0.0031070709228515625,
0.01171112060546875,
0.043365478515625,
0.0107879638671875,
-0.01446533203125,
0.045318603515625,
0.0296478271484375,
-0.04547119140625,
-0.061737060546875,
-0.01361083984375,
-0.086669921875,
-0.026580810546875,
0.06787109375,
-0.01013946533203125,
-0.033416748046875,
0.0134124755859375,
-0.0111236572265625,
0.017822265625,
-0.0283660888671875,
0.0355224609375,
0.049591064453125,
0.00438690185546875,
-0.0205078125,
-0.043365478515625,
0.0310211181640625,
0.01763916015625,
-0.052276611328125,
-0.01372528076171875,
0.01337432861328125,
0.03564453125,
0.01512908935546875,
0.033233642578125,
-0.0309600830078125,
0.0238189697265625,
0.0120086669921875,
0.031036376953125,
-0.02178955078125,
-0.031280517578125,
-0.0253143310546875,
0.0130615234375,
-0.031219482421875,
-0.038604736328125
]
] |
timm/convnext_base.fb_in22k_ft_in1k | 2023-03-31T22:03:16.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2201.03545",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/convnext_base.fb_in22k_ft_in1k | 0 | 47,529 | timm | 2022-12-13T07:07:23 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for convnext_base.fb_in22k_ft_in1k
A ConvNeXt image classification model. Pretrained on ImageNet-22k and fine-tuned on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 88.6
- GMACs: 15.4
- Activations (M): 28.8
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
- **Original:** https://github.com/facebookresearch/ConvNeXt
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-22k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('convnext_base.fb_in22k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'convnext_base.fb_in22k_ft_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 128, 56, 56])
# torch.Size([1, 256, 28, 28])
# torch.Size([1, 512, 14, 14])
# torch.Size([1, 1024, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'convnext_base.fb_in22k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1024, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
| model |top1 |top5 |img_size|param_count|gmacs |macts |samples_per_sec|batch_size|
|------------------------------------------------------------------------------------------------------------------------------|------|------|--------|-----------|------|------|---------------|----------|
| [convnextv2_huge.fcmae_ft_in22k_in1k_512](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_512) |88.848|98.742|512 |660.29 |600.81|413.07|28.58 |48 |
| [convnextv2_huge.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in22k_in1k_384) |88.668|98.738|384 |660.29 |337.96|232.35|50.56 |64 |
| [convnext_xxlarge.clip_laion2b_soup_ft_in1k](https://huggingface.co/timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k) |88.612|98.704|256 |846.47 |198.09|124.45|122.45 |256 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_384) |88.312|98.578|384 |200.13 |101.11|126.74|196.84 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k_384) |88.196|98.532|384 |197.96 |101.1 |126.74|128.94 |128 |
| [convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_soup_ft_in12k_in1k_320) |87.968|98.47 |320 |200.13 |70.21 |88.02 |283.42 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k_384) |87.75 |98.556|384 |350.2 |179.2 |168.99|124.85 |192 |
| [convnextv2_base.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k_384) |87.646|98.422|384 |88.72 |45.21 |84.49 |209.51 |256 |
| [convnext_large.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k_384) |87.476|98.382|384 |197.77 |101.1 |126.74|194.66 |256 |
| [convnext_large_mlp.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k) |87.344|98.218|256 |200.13 |44.94 |56.33 |438.08 |256 |
| [convnextv2_large.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in22k_in1k) |87.26 |98.248|224 |197.96 |34.4 |43.13 |376.84 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k_384) |87.138|98.212|384 |88.59 |45.21 |84.49 |365.47 |256 |
| [convnext_xlarge.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_xlarge.fb_in22k_ft_in1k) |87.002|98.208|224 |350.2 |60.98 |57.5 |368.01 |256 |
| [convnext_base.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k_384) |86.796|98.264|384 |88.59 |45.21 |84.49 |366.54 |256 |
| [convnextv2_base.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in22k_in1k) |86.74 |98.022|224 |88.72 |15.38 |28.75 |624.23 |256 |
| [convnext_large.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_large.fb_in22k_ft_in1k) |86.636|98.028|224 |197.77 |34.4 |43.13 |581.43 |256 |
| [convnext_base.clip_laiona_augreg_ft_in1k_384](https://huggingface.co/timm/convnext_base.clip_laiona_augreg_ft_in1k_384) |86.504|97.97 |384 |88.59 |45.21 |84.49 |368.14 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in12k_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in12k_in1k) |86.344|97.97 |256 |88.59 |20.09 |37.55 |816.14 |256 |
| [convnextv2_huge.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_huge.fcmae_ft_in1k) |86.256|97.75 |224 |660.29 |115.0 |79.07 |154.72 |256 |
| [convnext_small.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_small.in12k_ft_in1k_384) |86.182|97.92 |384 |50.22 |25.58 |63.37 |516.19 |256 |
| [convnext_base.clip_laion2b_augreg_ft_in1k](https://huggingface.co/timm/convnext_base.clip_laion2b_augreg_ft_in1k) |86.154|97.68 |256 |88.59 |20.09 |37.55 |819.86 |256 |
| [convnext_base.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_base.fb_in22k_ft_in1k) |85.822|97.866|224 |88.59 |15.38 |28.75 |1037.66 |256 |
| [convnext_small.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k_384) |85.778|97.886|384 |50.22 |25.58 |63.37 |518.95 |256 |
| [convnextv2_large.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_large.fcmae_ft_in1k) |85.742|97.584|224 |197.96 |34.4 |43.13 |375.23 |256 |
| [convnext_small.in12k_ft_in1k](https://huggingface.co/timm/convnext_small.in12k_ft_in1k) |85.174|97.506|224 |50.22 |8.71 |21.56 |1474.31 |256 |
| [convnext_tiny.in12k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k_384) |85.118|97.608|384 |28.59 |13.14 |39.48 |856.76 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384) |85.112|97.63 |384 |28.64 |13.14 |39.48 |491.32 |256 |
| [convnextv2_base.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_base.fcmae_ft_in1k) |84.874|97.09 |224 |88.72 |15.38 |28.75 |625.33 |256 |
| [convnext_small.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_small.fb_in22k_ft_in1k) |84.562|97.394|224 |50.22 |8.71 |21.56 |1478.29 |256 |
| [convnext_large.fb_in1k](https://huggingface.co/timm/convnext_large.fb_in1k) |84.282|96.892|224 |197.77 |34.4 |43.13 |584.28 |256 |
| [convnext_tiny.in12k_ft_in1k](https://huggingface.co/timm/convnext_tiny.in12k_ft_in1k) |84.186|97.124|224 |28.59 |4.47 |13.44 |2433.7 |256 |
| [convnext_tiny.fb_in22k_ft_in1k_384](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k_384) |84.084|97.14 |384 |28.59 |13.14 |39.48 |862.95 |256 |
| [convnextv2_tiny.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in22k_in1k) |83.894|96.964|224 |28.64 |4.47 |13.44 |1452.72 |256 |
| [convnext_base.fb_in1k](https://huggingface.co/timm/convnext_base.fb_in1k) |83.82 |96.746|224 |88.59 |15.38 |28.75 |1054.0 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k_384](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k_384) |83.37 |96.742|384 |15.62 |7.22 |24.61 |801.72 |256 |
| [convnext_small.fb_in1k](https://huggingface.co/timm/convnext_small.fb_in1k) |83.142|96.434|224 |50.22 |8.71 |21.56 |1464.0 |256 |
| [convnextv2_tiny.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_tiny.fcmae_ft_in1k) |82.92 |96.284|224 |28.64 |4.47 |13.44 |1425.62 |256 |
| [convnext_tiny.fb_in22k_ft_in1k](https://huggingface.co/timm/convnext_tiny.fb_in22k_ft_in1k) |82.898|96.616|224 |28.59 |4.47 |13.44 |2480.88 |256 |
| [convnext_nano.in12k_ft_in1k](https://huggingface.co/timm/convnext_nano.in12k_ft_in1k) |82.282|96.344|224 |15.59 |2.46 |8.37 |3926.52 |256 |
| [convnext_tiny_hnf.a2h_in1k](https://huggingface.co/timm/convnext_tiny_hnf.a2h_in1k) |82.216|95.852|224 |28.59 |4.47 |13.44 |2529.75 |256 |
| [convnext_tiny.fb_in1k](https://huggingface.co/timm/convnext_tiny.fb_in1k) |82.066|95.854|224 |28.59 |4.47 |13.44 |2346.26 |256 |
| [convnextv2_nano.fcmae_ft_in22k_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in22k_in1k) |82.03 |96.166|224 |15.62 |2.46 |8.37 |2300.18 |256 |
| [convnextv2_nano.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_nano.fcmae_ft_in1k) |81.83 |95.738|224 |15.62 |2.46 |8.37 |2321.48 |256 |
| [convnext_nano_ols.d1h_in1k](https://huggingface.co/timm/convnext_nano_ols.d1h_in1k) |80.866|95.246|224 |15.65 |2.65 |9.38 |3523.85 |256 |
| [convnext_nano.d1h_in1k](https://huggingface.co/timm/convnext_nano.d1h_in1k) |80.768|95.334|224 |15.59 |2.46 |8.37 |3915.58 |256 |
| [convnextv2_pico.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_pico.fcmae_ft_in1k) |80.304|95.072|224 |9.07 |1.37 |6.1 |3274.57 |256 |
| [convnext_pico.d1_in1k](https://huggingface.co/timm/convnext_pico.d1_in1k) |79.526|94.558|224 |9.05 |1.37 |6.1 |5686.88 |256 |
| [convnext_pico_ols.d1_in1k](https://huggingface.co/timm/convnext_pico_ols.d1_in1k) |79.522|94.692|224 |9.06 |1.43 |6.5 |5422.46 |256 |
| [convnextv2_femto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_femto.fcmae_ft_in1k) |78.488|93.98 |224 |5.23 |0.79 |4.57 |4264.2 |256 |
| [convnext_femto_ols.d1_in1k](https://huggingface.co/timm/convnext_femto_ols.d1_in1k) |77.86 |93.83 |224 |5.23 |0.82 |4.87 |6910.6 |256 |
| [convnext_femto.d1_in1k](https://huggingface.co/timm/convnext_femto.d1_in1k) |77.454|93.68 |224 |5.22 |0.79 |4.57 |7189.92 |256 |
| [convnextv2_atto.fcmae_ft_in1k](https://huggingface.co/timm/convnextv2_atto.fcmae_ft_in1k) |76.664|93.044|224 |3.71 |0.55 |3.81 |4728.91 |256 |
| [convnext_atto_ols.a2_in1k](https://huggingface.co/timm/convnext_atto_ols.a2_in1k) |75.88 |92.846|224 |3.7 |0.58 |4.11 |7963.16 |256 |
| [convnext_atto.d2_in1k](https://huggingface.co/timm/convnext_atto.d2_in1k) |75.664|92.9 |224 |3.7 |0.55 |3.81 |8439.22 |256 |
## Citation
```bibtex
@article{liu2022convnet,
author = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
title = {A ConvNet for the 2020s},
journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022},
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 15,738 | [
[
-0.0672607421875,
-0.032623291015625,
-0.0042724609375,
0.0382080078125,
-0.0322265625,
-0.01523590087890625,
-0.012664794921875,
-0.035400390625,
0.064697265625,
0.017181396484375,
-0.044769287109375,
-0.041748046875,
-0.050140380859375,
-0.0032329559326171875,
0.007045745849609375,
0.06854248046875,
-0.0033721923828125,
-0.0094757080078125,
0.0189666748046875,
-0.027984619140625,
-0.0160369873046875,
-0.0291900634765625,
-0.06317138671875,
-0.0155181884765625,
0.0196380615234375,
0.0223846435546875,
0.057373046875,
0.04443359375,
0.0298004150390625,
0.041229248046875,
-0.0181732177734375,
0.01221466064453125,
-0.0151214599609375,
-0.025970458984375,
0.041290283203125,
-0.0311737060546875,
-0.06793212890625,
0.0171661376953125,
0.061981201171875,
0.040313720703125,
0.00411224365234375,
0.014801025390625,
0.025726318359375,
0.035675048828125,
0.0027446746826171875,
-0.004657745361328125,
-0.0070343017578125,
0.0135040283203125,
-0.0202789306640625,
0.0015802383422851562,
0.00386810302734375,
-0.053009033203125,
0.0261688232421875,
-0.043487548828125,
0.0023479461669921875,
0.00002467632293701172,
0.1019287109375,
-0.008514404296875,
-0.016387939453125,
0.0009279251098632812,
0.01123809814453125,
0.053314208984375,
-0.06005859375,
0.023834228515625,
0.03179931640625,
-0.01097869873046875,
-0.0150146484375,
-0.047210693359375,
-0.04620361328125,
-0.00484466552734375,
-0.02813720703125,
0.0175628662109375,
-0.026885986328125,
-0.004795074462890625,
0.04144287109375,
0.03411865234375,
-0.037933349609375,
-0.00665283203125,
-0.024322509765625,
-0.0085296630859375,
0.0601806640625,
-0.00658416748046875,
0.046783447265625,
-0.0256805419921875,
-0.0479736328125,
-0.0208282470703125,
-0.01529693603515625,
0.0343017578125,
0.016632080078125,
-0.002216339111328125,
-0.07366943359375,
0.03814697265625,
0.006778717041015625,
0.0206146240234375,
0.027069091796875,
-0.0145263671875,
0.05938720703125,
-0.0194549560546875,
-0.04119873046875,
-0.024261474609375,
0.08953857421875,
0.05267333984375,
0.0308837890625,
0.00922393798828125,
0.004131317138671875,
-0.006435394287109375,
-0.03564453125,
-0.07470703125,
-0.01174163818359375,
0.0278472900390625,
-0.041961669921875,
-0.0098724365234375,
0.026611328125,
-0.059906005859375,
0.01045989990234375,
-0.00928497314453125,
0.01459503173828125,
-0.0628662109375,
-0.02984619140625,
-0.00738525390625,
-0.02703857421875,
0.0307159423828125,
0.0217132568359375,
-0.0261993408203125,
0.02288818359375,
0.0207672119140625,
0.07403564453125,
0.0220184326171875,
-0.01169586181640625,
-0.031524658203125,
-0.01171875,
-0.027191162109375,
0.025146484375,
0.01050567626953125,
-0.0121612548828125,
-0.019744873046875,
0.033111572265625,
-0.01303863525390625,
-0.0304107666015625,
0.0306854248046875,
0.0216827392578125,
0.007373809814453125,
-0.0286407470703125,
-0.02703857421875,
-0.0203857421875,
0.028839111328125,
-0.03802490234375,
0.07891845703125,
0.037078857421875,
-0.0784912109375,
0.0233306884765625,
-0.03509521484375,
-0.004764556884765625,
-0.021484375,
0.00621795654296875,
-0.0572509765625,
-0.00856781005859375,
0.0174713134765625,
0.055419921875,
-0.0085296630859375,
-0.010406494140625,
-0.028594970703125,
-0.004764556884765625,
0.0269622802734375,
0.00872039794921875,
0.07244873046875,
0.01348114013671875,
-0.034576416015625,
0.0007309913635253906,
-0.04840087890625,
0.0238037109375,
0.028717041015625,
-0.0036869049072265625,
-0.0054779052734375,
-0.060699462890625,
0.0041656494140625,
0.039306640625,
0.0148162841796875,
-0.040191650390625,
0.020751953125,
-0.018218994140625,
0.0283660888671875,
0.0477294921875,
-0.004657745361328125,
0.0221099853515625,
-0.04412841796875,
0.042266845703125,
0.00623321533203125,
0.0196075439453125,
-0.0033740997314453125,
-0.0293731689453125,
-0.055694580078125,
-0.05108642578125,
0.015869140625,
0.035919189453125,
-0.033660888671875,
0.055694580078125,
0.0128631591796875,
-0.0467529296875,
-0.05499267578125,
0.0153350830078125,
0.03973388671875,
0.0187225341796875,
0.01593017578125,
-0.027191162109375,
-0.04937744140625,
-0.0694580078125,
-0.00896453857421875,
0.005573272705078125,
-0.0017671585083007812,
0.046295166015625,
0.0274810791015625,
-0.006801605224609375,
0.040985107421875,
-0.031829833984375,
-0.0202484130859375,
-0.0092620849609375,
-0.006122589111328125,
0.032806396484375,
0.05877685546875,
0.08612060546875,
-0.06451416015625,
-0.06964111328125,
0.002605438232421875,
-0.08380126953125,
0.001239776611328125,
-0.00374603271484375,
-0.032745361328125,
0.0216827392578125,
0.0200653076171875,
-0.07452392578125,
0.052215576171875,
0.027923583984375,
-0.04669189453125,
0.03533935546875,
-0.020111083984375,
0.024566650390625,
-0.07305908203125,
0.0172271728515625,
0.02093505859375,
-0.0234375,
-0.039642333984375,
0.005306243896484375,
-0.007293701171875,
0.01288604736328125,
-0.048065185546875,
0.06793212890625,
-0.05096435546875,
0.00820159912109375,
0.0031414031982421875,
0.00879669189453125,
0.0006132125854492188,
0.037261962890625,
-0.002750396728515625,
0.03265380859375,
0.058624267578125,
-0.021942138671875,
0.0347900390625,
0.039886474609375,
-0.001964569091796875,
0.0584716796875,
-0.046478271484375,
0.009033203125,
0.0085906982421875,
0.036590576171875,
-0.06890869140625,
-0.03143310546875,
0.043701171875,
-0.057159423828125,
0.036468505859375,
-0.0175018310546875,
-0.0267791748046875,
-0.0599365234375,
-0.0643310546875,
0.0180511474609375,
0.04296875,
-0.04644775390625,
0.01308441162109375,
0.0201416015625,
0.003826141357421875,
-0.046295166015625,
-0.0489501953125,
-0.00536346435546875,
-0.031646728515625,
-0.06585693359375,
0.03143310546875,
0.006580352783203125,
-0.00861358642578125,
0.0011796951293945312,
-0.0020389556884765625,
-0.00286865234375,
-0.012786865234375,
0.039459228515625,
0.03173828125,
-0.0181121826171875,
-0.026641845703125,
-0.023468017578125,
-0.0089569091796875,
0.001125335693359375,
-0.00841522216796875,
0.041595458984375,
-0.0255126953125,
0.01158905029296875,
-0.0789794921875,
0.0160369873046875,
0.047760009765625,
-0.00264739990234375,
0.06768798828125,
0.07623291015625,
-0.03350830078125,
0.010711669921875,
-0.0284881591796875,
-0.01035308837890625,
-0.038116455078125,
-0.0084075927734375,
-0.0400390625,
-0.048065185546875,
0.061553955078125,
0.01397705078125,
-0.00627899169921875,
0.052490234375,
0.0239715576171875,
-0.0179595947265625,
0.06390380859375,
0.03961181640625,
-0.00720977783203125,
0.045318603515625,
-0.06683349609375,
0.0010852813720703125,
-0.061553955078125,
-0.04669189453125,
-0.0096435546875,
-0.04254150390625,
-0.0556640625,
-0.02813720703125,
0.01995849609375,
0.035858154296875,
-0.00975799560546875,
0.05023193359375,
-0.042938232421875,
-0.0067596435546875,
0.03692626953125,
0.025177001953125,
-0.019378662109375,
-0.0178375244140625,
-0.0115203857421875,
-0.01509857177734375,
-0.0413818359375,
-0.01085662841796875,
0.0517578125,
0.0487060546875,
0.029541015625,
-0.002002716064453125,
0.03900146484375,
-0.0063323974609375,
0.0234375,
-0.03656005859375,
0.0550537109375,
-0.004741668701171875,
-0.039276123046875,
-0.0150604248046875,
-0.034088134765625,
-0.0732421875,
0.0100555419921875,
-0.0274810791015625,
-0.06329345703125,
-0.0107421875,
0.015625,
-0.0223388671875,
0.040496826171875,
-0.0509033203125,
0.055755615234375,
-0.00630950927734375,
-0.037017822265625,
0.00799560546875,
-0.06591796875,
0.017852783203125,
0.0306549072265625,
-0.0056915283203125,
-0.01244354248046875,
0.01171112060546875,
0.060455322265625,
-0.0634765625,
0.037017822265625,
-0.0301361083984375,
0.00359344482421875,
0.03961181640625,
-0.00484466552734375,
0.031890869140625,
0.010040283203125,
-0.0006098747253417969,
0.0023403167724609375,
0.011138916015625,
-0.0482177734375,
-0.0283050537109375,
0.048614501953125,
-0.049774169921875,
-0.028106689453125,
-0.0406494140625,
-0.0237579345703125,
0.01326751708984375,
0.0010976791381835938,
0.0482177734375,
0.04278564453125,
-0.0111846923828125,
0.01523590087890625,
0.0396728515625,
-0.0288238525390625,
0.03814697265625,
-0.013916015625,
-0.002414703369140625,
-0.03948974609375,
0.058685302734375,
0.0042724609375,
0.00835418701171875,
0.00394439697265625,
0.00537872314453125,
-0.03204345703125,
-0.0117340087890625,
-0.01094818115234375,
0.05096435546875,
-0.0172271728515625,
-0.0271759033203125,
-0.047943115234375,
-0.032745361328125,
-0.04388427734375,
-0.0258026123046875,
-0.0293121337890625,
-0.02001953125,
-0.025726318359375,
0.005580902099609375,
0.05523681640625,
0.04150390625,
-0.028076171875,
0.0338134765625,
-0.0478515625,
0.0240478515625,
0.004199981689453125,
0.032623291015625,
-0.021575927734375,
-0.04364013671875,
0.0015773773193359375,
0.0017833709716796875,
-0.018218994140625,
-0.05828857421875,
0.047882080078125,
0.0112762451171875,
0.029052734375,
0.0404052734375,
-0.0236968994140625,
0.0595703125,
-0.006870269775390625,
0.037353515625,
0.04205322265625,
-0.0653076171875,
0.032196044921875,
-0.0305633544921875,
0.0071563720703125,
0.01238250732421875,
0.0283050537109375,
-0.0372314453125,
-0.0258026123046875,
-0.0733642578125,
-0.044342041015625,
0.0517578125,
0.01103973388671875,
-0.0007920265197753906,
0.005893707275390625,
0.0478515625,
-0.00603485107421875,
0.0111236572265625,
-0.040985107421875,
-0.054534912109375,
-0.01702880859375,
-0.0109100341796875,
-0.007328033447265625,
-0.0018911361694335938,
-0.0016231536865234375,
-0.051544189453125,
0.036834716796875,
-0.00986480712890625,
0.04290771484375,
0.0192108154296875,
0.0007390975952148438,
-0.0030612945556640625,
-0.0237884521484375,
0.04095458984375,
0.0269012451171875,
-0.022735595703125,
-0.01032257080078125,
0.0281982421875,
-0.03802490234375,
0.0015668869018554688,
0.0218505859375,
0.0058746337890625,
0.01544952392578125,
0.0247039794921875,
0.045745849609375,
0.0189666748046875,
-0.0125885009765625,
0.04302978515625,
-0.0164031982421875,
-0.0302581787109375,
-0.0227813720703125,
-0.0021762847900390625,
0.01482391357421875,
0.034576416015625,
0.0155792236328125,
0.004322052001953125,
-0.0233917236328125,
-0.0438232421875,
0.04132080078125,
0.05950927734375,
-0.033660888671875,
-0.04180908203125,
0.048095703125,
-0.0069732666015625,
-0.008056640625,
0.040802001953125,
-0.006061553955078125,
-0.053985595703125,
0.07489013671875,
0.0208740234375,
0.042999267578125,
-0.042938232421875,
0.0181884765625,
0.066162109375,
-0.0013141632080078125,
0.00980377197265625,
0.0271759033203125,
0.0282135009765625,
-0.033111572265625,
0.00440216064453125,
-0.047943115234375,
0.01305389404296875,
0.04296875,
-0.034759521484375,
0.02655029296875,
-0.05694580078125,
-0.02679443359375,
0.01474761962890625,
0.03338623046875,
-0.06280517578125,
0.024444580078125,
0.0042724609375,
0.08404541015625,
-0.05938720703125,
0.0665283203125,
0.05523681640625,
-0.027740478515625,
-0.0711669921875,
-0.01113128662109375,
0.0157928466796875,
-0.057525634765625,
0.0294647216796875,
0.018646240234375,
0.0170135498046875,
-0.0160980224609375,
-0.046478271484375,
-0.036346435546875,
0.09051513671875,
0.03656005859375,
-0.01190185546875,
0.0089111328125,
-0.0257720947265625,
0.0297393798828125,
-0.020416259765625,
0.034881591796875,
0.04022216796875,
0.04052734375,
0.0155181884765625,
-0.06927490234375,
0.02764892578125,
-0.032073974609375,
-0.01432037353515625,
0.022186279296875,
-0.10321044921875,
0.07891845703125,
-0.0259552001953125,
-0.002437591552734375,
0.013946533203125,
0.061798095703125,
0.030059814453125,
0.004749298095703125,
0.0298309326171875,
0.054534912109375,
0.035797119140625,
-0.014862060546875,
0.07928466796875,
0.00140380859375,
0.03033447265625,
0.0191192626953125,
0.03961181640625,
0.0302886962890625,
0.0279541015625,
-0.032501220703125,
0.00975799560546875,
0.0662841796875,
-0.01404571533203125,
0.00887298583984375,
0.0164031982421875,
-0.01299285888671875,
-0.00982666015625,
-0.0162200927734375,
-0.046630859375,
0.032257080078125,
0.011962890625,
-0.020111083984375,
0.0009608268737792969,
-0.0070343017578125,
0.0379638671875,
-0.0007834434509277344,
-0.01117706298828125,
0.0335693359375,
0.0191802978515625,
-0.043670654296875,
0.03985595703125,
-0.00640869140625,
0.07452392578125,
-0.0272674560546875,
0.0009703636169433594,
-0.0240478515625,
0.0238800048828125,
-0.0194244384765625,
-0.08734130859375,
0.0239715576171875,
-0.01134490966796875,
0.01468658447265625,
-0.006011962890625,
0.046783447265625,
-0.034271240234375,
-0.0181732177734375,
0.040069580078125,
0.0255126953125,
0.029541015625,
0.00426483154296875,
-0.08734130859375,
0.0177764892578125,
0.011138916015625,
-0.041748046875,
0.03155517578125,
0.037200927734375,
0.0185699462890625,
0.051544189453125,
0.03173828125,
0.01438140869140625,
0.006793975830078125,
-0.0274810791015625,
0.059783935546875,
-0.04986572265625,
-0.0357666015625,
-0.065185546875,
0.033966064453125,
-0.0237884521484375,
-0.049072265625,
0.059600830078125,
0.033416748046875,
0.039825439453125,
0.0086517333984375,
0.0399169921875,
-0.03680419921875,
0.0281982421875,
-0.032867431640625,
0.053924560546875,
-0.060516357421875,
-0.024322509765625,
-0.033905029296875,
-0.061309814453125,
-0.0217437744140625,
0.0550537109375,
0.00445556640625,
0.0178375244140625,
0.026458740234375,
0.04473876953125,
-0.0031604766845703125,
-0.017578125,
-0.004840850830078125,
0.0194091796875,
0.0038394927978515625,
0.061126708984375,
0.040802001953125,
-0.056365966796875,
0.0150604248046875,
-0.04803466796875,
-0.0249786376953125,
-0.02545166015625,
-0.055572509765625,
-0.08154296875,
-0.06005859375,
-0.037109375,
-0.0498046875,
-0.0235748291015625,
0.08380126953125,
0.0716552734375,
-0.04071044921875,
-0.01267242431640625,
0.022735595703125,
0.00788116455078125,
-0.01678466796875,
-0.019744873046875,
0.039398193359375,
0.0243377685546875,
-0.07635498046875,
-0.0209197998046875,
0.006244659423828125,
0.042022705078125,
0.0234832763671875,
-0.0303802490234375,
-0.0196990966796875,
-0.005146026611328125,
0.03070068359375,
0.06170654296875,
-0.051727294921875,
-0.03436279296875,
0.00386810302734375,
-0.0196380615234375,
0.0189361572265625,
0.021270751953125,
-0.0294647216796875,
-0.0068359375,
0.040557861328125,
0.010040283203125,
0.056976318359375,
0.01108551025390625,
0.0185546875,
-0.046844482421875,
0.049774169921875,
-0.0038127899169921875,
0.0263824462890625,
0.0277862548828125,
-0.03033447265625,
0.055572509765625,
0.037628173828125,
-0.03448486328125,
-0.07293701171875,
-0.0222320556640625,
-0.107177734375,
0.0006070137023925781,
0.0577392578125,
-0.01525115966796875,
-0.04052734375,
0.0396728515625,
-0.0255126953125,
0.04034423828125,
-0.0189971923828125,
0.019744873046875,
0.0284423828125,
-0.02655029296875,
-0.0341796875,
-0.041259765625,
0.05438232421875,
0.0247650146484375,
-0.051300048828125,
-0.0263519287109375,
-0.0018901824951171875,
0.036865234375,
0.0178375244140625,
0.059783935546875,
-0.014984130859375,
0.011962890625,
0.0017223358154296875,
0.01279449462890625,
0.003971099853515625,
0.0016937255859375,
-0.0121307373046875,
-0.016876220703125,
-0.025543212890625,
-0.044952392578125
]
] |
facebook/m2m100_1.2B | 2023-01-24T16:30:46.000Z | [
"transformers",
"pytorch",
"rust",
"m2m_100",
"text2text-generation",
"multilingual",
"af",
"am",
"ar",
"ast",
"az",
"ba",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"ceb",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"fa",
"ff",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"ht",
"hu",
"hy",
"id",
"ig",
"ilo",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"lb",
"lg",
"ln",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"ns",
"oc",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"ss",
"su",
"sv",
"sw",
"ta",
"th",
"tl",
"tn",
"tr",
"uk",
"ur",
"uz",
"vi",
"wo",
"xh",
"yi",
"yo",
"zh",
"zu",
"arxiv:2010.11125",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | text2text-generation | facebook | null | null | facebook/m2m100_1.2B | 55 | 47,469 | transformers | 2022-03-02T23:29:05 | ---
language:
- multilingual
- af
- am
- ar
- ast
- az
- ba
- be
- bg
- bn
- br
- bs
- ca
- ceb
- cs
- cy
- da
- de
- el
- en
- es
- et
- fa
- ff
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- ht
- hu
- hy
- id
- ig
- ilo
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- lb
- lg
- ln
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- no
- ns
- oc
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sd
- si
- sk
- sl
- so
- sq
- sr
- ss
- su
- sv
- sw
- ta
- th
- tl
- tn
- tr
- uk
- ur
- uz
- vi
- wo
- xh
- yi
- yo
- zh
- zu
license: mit
tags:
---
# M2M100 1.2B
M2M100 is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation.
It was introduced in this [paper](https://arxiv.org/abs/2010.11125) and first released in [this](https://github.com/pytorch/fairseq/tree/master/examples/m2m_100) repository.
The model that can directly translate between the 9,900 directions of 100 languages.
To translate into a target language, the target language id is forced as the first generated token.
To force the target language id as the first generated token, pass the `forced_bos_token_id` parameter to the `generate` method.
*Note: `M2M100Tokenizer` depends on `sentencepiece`, so make sure to install it before running the example.*
To install `sentencepiece` run `pip install sentencepiece`
```python
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
hi_text = "जीवन एक चॉकलेट बॉक्स की तरह है।"
chinese_text = "生活就像一盒巧克力。"
model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_1.2B")
tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_1.2B")
# translate Hindi to French
tokenizer.src_lang = "hi"
encoded_hi = tokenizer(hi_text, return_tensors="pt")
generated_tokens = model.generate(**encoded_hi, forced_bos_token_id=tokenizer.get_lang_id("fr"))
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
# => "La vie est comme une boîte de chocolat."
# translate Chinese to English
tokenizer.src_lang = "zh"
encoded_zh = tokenizer(chinese_text, return_tensors="pt")
generated_tokens = model.generate(**encoded_zh, forced_bos_token_id=tokenizer.get_lang_id("en"))
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
# => "Life is like a box of chocolate."
```
See the [model hub](https://huggingface.co/models?filter=m2m_100) to look for more fine-tuned versions.
## Languages covered
Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Breton (br), Bosnian (bs), Catalan; Valencian (ca), Cebuano (ceb), Czech (cs), Welsh (cy), Danish (da), German (de), Greeek (el), English (en), Spanish (es), Estonian (et), Persian (fa), Fulah (ff), Finnish (fi), French (fr), Western Frisian (fy), Irish (ga), Gaelic; Scottish Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Croatian (hr), Haitian; Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Igbo (ig), Iloko (ilo), Icelandic (is), Italian (it), Japanese (ja), Javanese (jv), Georgian (ka), Kazakh (kk), Central Khmer (km), Kannada (kn), Korean (ko), Luxembourgish; Letzeburgesch (lb), Ganda (lg), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Burmese (my), Nepali (ne), Dutch; Flemish (nl), Norwegian (no), Northern Sotho (ns), Occitan (post 1500) (oc), Oriya (or), Panjabi; Punjabi (pa), Polish (pl), Pushto; Pashto (ps), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Russian (ru), Sindhi (sd), Sinhala; Sinhalese (si), Slovak (sk), Slovenian (sl), Somali (so), Albanian (sq), Serbian (sr), Swati (ss), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Thai (th), Tagalog (tl), Tswana (tn), Turkish (tr), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Wolof (wo), Xhosa (xh), Yiddish (yi), Yoruba (yo), Chinese (zh), Zulu (zu)
## BibTeX entry and citation info
```
@misc{fan2020englishcentric,
title={Beyond English-Centric Multilingual Machine Translation},
author={Angela Fan and Shruti Bhosale and Holger Schwenk and Zhiyi Ma and Ahmed El-Kishky and Siddharth Goyal and Mandeep Baines and Onur Celebi and Guillaume Wenzek and Vishrav Chaudhary and Naman Goyal and Tom Birch and Vitaliy Liptchinsky and Sergey Edunov and Edouard Grave and Michael Auli and Armand Joulin},
year={2020},
eprint={2010.11125},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` | 4,538 | [
[
-0.03436279296875,
-0.037933349609375,
0.0032405853271484375,
0.0246734619140625,
0.0009751319885253906,
-0.00675201416015625,
-0.01308441162109375,
-0.03143310546875,
0.031768798828125,
0.0250396728515625,
-0.051513671875,
-0.042449951171875,
-0.055206298828125,
0.0278167724609375,
-0.007801055908203125,
0.061065673828125,
-0.00885772705078125,
0.0197601318359375,
-0.007274627685546875,
-0.02813720703125,
-0.01641845703125,
-0.03076171875,
-0.03411865234375,
-0.0206756591796875,
0.0221405029296875,
0.021728515625,
0.054595947265625,
0.0386962890625,
0.0196533203125,
0.0240478515625,
-0.023193359375,
0.0289154052734375,
-0.01380157470703125,
-0.0310516357421875,
-0.00978851318359375,
-0.0292205810546875,
-0.052581787109375,
-0.003185272216796875,
0.024566650390625,
0.050048828125,
0.00743865966796875,
0.02734375,
0.00945281982421875,
0.06610107421875,
-0.0238494873046875,
0.01494598388671875,
-0.0205230712890625,
0.011444091796875,
-0.0157928466796875,
-0.00331878662109375,
-0.0218353271484375,
-0.02130126953125,
-0.015960693359375,
-0.03680419921875,
-0.01457977294921875,
0.0061187744140625,
0.08660888671875,
-0.01503753662109375,
-0.045074462890625,
-0.0218963623046875,
-0.026092529296875,
0.05792236328125,
-0.051300048828125,
0.037078857421875,
0.0489501953125,
0.0125579833984375,
-0.021453857421875,
-0.04107666015625,
-0.04315185546875,
0.01435089111328125,
-0.017608642578125,
0.0254974365234375,
-0.022735595703125,
-0.018829345703125,
0.0091705322265625,
0.0262908935546875,
-0.05804443359375,
-0.01849365234375,
-0.03521728515625,
-0.0120849609375,
0.038970947265625,
0.00897216796875,
0.042022705078125,
-0.047149658203125,
-0.0223541259765625,
0.01154327392578125,
-0.042327880859375,
0.0262451171875,
0.0207366943359375,
0.02044677734375,
-0.032958984375,
0.050567626953125,
-0.0266571044921875,
0.05499267578125,
0.0025005340576171875,
-0.0205230712890625,
0.047332763671875,
-0.05133056640625,
-0.002105712890625,
-0.01247406005859375,
0.07330322265625,
0.0352783203125,
0.0166778564453125,
-0.002635955810546875,
-0.0009655952453613281,
-0.0077362060546875,
-0.01544952392578125,
-0.07452392578125,
0.007175445556640625,
0.0352783203125,
-0.047698974609375,
-0.006378173828125,
0.0150146484375,
-0.054962158203125,
0.0042266845703125,
-0.0006461143493652344,
0.0298919677734375,
-0.044403076171875,
-0.01739501953125,
0.011383056640625,
-0.0012378692626953125,
0.0256500244140625,
0.016845703125,
-0.06597900390625,
-0.002048492431640625,
0.038726806640625,
0.0634765625,
0.003917694091796875,
-0.039306640625,
-0.0276336669921875,
0.0160369873046875,
-0.0252532958984375,
0.045257568359375,
-0.0226898193359375,
-0.0286407470703125,
0.0036907196044921875,
0.045257568359375,
-0.0130157470703125,
-0.0396728515625,
0.041168212890625,
-0.0214691162109375,
0.03717041015625,
-0.031341552734375,
-0.018310546875,
-0.018768310546875,
0.035003662109375,
-0.045379638671875,
0.08087158203125,
0.0250701904296875,
-0.053619384765625,
0.0242156982421875,
-0.03558349609375,
-0.04522705078125,
-0.002513885498046875,
-0.007045745849609375,
-0.037506103515625,
-0.01186370849609375,
0.03021240234375,
0.029022216796875,
-0.0246429443359375,
0.0178070068359375,
-0.00579071044921875,
-0.0194854736328125,
-0.0023651123046875,
-0.0205841064453125,
0.0960693359375,
0.032623291015625,
-0.028228759765625,
0.010467529296875,
-0.05731201171875,
-0.001560211181640625,
0.0282135009765625,
-0.038818359375,
-0.00341033935546875,
-0.01776123046875,
0.01129150390625,
0.04669189453125,
0.0229034423828125,
-0.048583984375,
0.00807952880859375,
-0.037841796875,
0.03778076171875,
0.03839111328125,
-0.00315093994140625,
0.03125,
-0.039825439453125,
0.04278564453125,
0.0170440673828125,
0.01403045654296875,
-0.0240020751953125,
-0.048675537109375,
-0.055419921875,
-0.0181884765625,
0.02655029296875,
0.06219482421875,
-0.05450439453125,
0.052490234375,
-0.039306640625,
-0.033782958984375,
-0.055419921875,
0.0214691162109375,
0.027587890625,
0.01416015625,
0.0196533203125,
-0.01226043701171875,
-0.04876708984375,
-0.061920166015625,
-0.0221405029296875,
-0.00717926025390625,
0.0078582763671875,
0.0280609130859375,
0.05255126953125,
-0.037200927734375,
0.057708740234375,
-0.0164947509765625,
-0.03472900390625,
-0.020050048828125,
-0.0210418701171875,
0.02947998046875,
0.050140380859375,
0.039093017578125,
-0.060028076171875,
-0.05511474609375,
0.02459716796875,
-0.06549072265625,
0.0190887451171875,
0.006183624267578125,
-0.03765869140625,
0.035003662109375,
0.0350341796875,
-0.04449462890625,
0.036102294921875,
0.06390380859375,
-0.043792724609375,
0.034423828125,
-0.00882720947265625,
0.0262908935546875,
-0.1201171875,
0.01425933837890625,
-0.022003173828125,
-0.01328277587890625,
-0.031585693359375,
-0.007152557373046875,
0.0172119140625,
-0.0106353759765625,
-0.04486083984375,
0.06622314453125,
-0.047271728515625,
0.0238189697265625,
0.0003566741943359375,
0.007175445556640625,
0.01352691650390625,
0.0292205810546875,
-0.00652313232421875,
0.052642822265625,
0.0333251953125,
-0.0330810546875,
0.023895263671875,
0.031951904296875,
-0.0312042236328125,
0.0577392578125,
-0.034881591796875,
-0.0222015380859375,
-0.018829345703125,
0.018096923828125,
-0.072021484375,
-0.0229034423828125,
0.03179931640625,
-0.055694580078125,
0.01366424560546875,
-0.018829345703125,
-0.052581787109375,
-0.050506591796875,
-0.0198516845703125,
0.01259613037109375,
0.0286407470703125,
-0.033355712890625,
0.05792236328125,
0.0145263671875,
0.00009882450103759766,
-0.046539306640625,
-0.0863037109375,
0.016021728515625,
-0.01068115234375,
-0.06915283203125,
0.0212860107421875,
-0.0137786865234375,
0.002513885498046875,
0.01369476318359375,
-0.007724761962890625,
0.00640869140625,
0.01242828369140625,
0.01708984375,
0.01384735107421875,
-0.01035308837890625,
-0.012603759765625,
0.00026917457580566406,
-0.00875091552734375,
-0.00995635986328125,
-0.023773193359375,
0.06201171875,
-0.00992584228515625,
-0.01352691650390625,
-0.0360107421875,
0.032562255859375,
0.0350341796875,
-0.048004150390625,
0.09246826171875,
0.07861328125,
-0.032623291015625,
0.0142974853515625,
-0.0249481201171875,
0.000022649765014648438,
-0.033782958984375,
0.0347900390625,
-0.057830810546875,
-0.0626220703125,
0.06024169921875,
-0.003170013427734375,
0.00601959228515625,
0.043304443359375,
0.051239013671875,
0.0038738250732421875,
0.06964111328125,
0.03729248046875,
-0.0054931640625,
0.039703369140625,
-0.0360107421875,
-0.0031070709228515625,
-0.061492919921875,
-0.026702880859375,
-0.03759765625,
-0.006561279296875,
-0.0628662109375,
-0.04742431640625,
0.0192718505859375,
0.0090789794921875,
-0.0156097412109375,
0.04217529296875,
-0.01806640625,
0.0179595947265625,
0.0389404296875,
0.0118255615234375,
0.017486572265625,
0.004619598388671875,
-0.0190277099609375,
-0.007419586181640625,
-0.055419921875,
-0.04669189453125,
0.08648681640625,
0.01043701171875,
0.0274505615234375,
0.0347900390625,
0.062286376953125,
-0.007724761962890625,
0.0126953125,
-0.043243408203125,
0.032989501953125,
-0.0204925537109375,
-0.07257080078125,
-0.005725860595703125,
-0.0394287109375,
-0.091552734375,
0.0222930908203125,
-0.0034160614013671875,
-0.049346923828125,
0.01837158203125,
-0.00583648681640625,
-0.01788330078125,
0.0146636962890625,
-0.053619384765625,
0.08349609375,
-0.0206756591796875,
-0.0284271240234375,
0.00823211669921875,
-0.048492431640625,
0.0217437744140625,
0.000568389892578125,
0.047576904296875,
-0.01837158203125,
-0.004985809326171875,
0.052398681640625,
-0.0216064453125,
0.046112060546875,
-0.001026153564453125,
-0.01241302490234375,
0.01406097412109375,
0.0103607177734375,
0.042755126953125,
0.0055999755859375,
-0.0228271484375,
0.0260772705078125,
0.0112762451171875,
-0.06103515625,
-0.01800537109375,
0.05279541015625,
-0.058349609375,
-0.040191650390625,
-0.037841796875,
-0.036865234375,
0.005054473876953125,
0.046478271484375,
0.032745361328125,
0.0159759521484375,
-0.00453948974609375,
0.025543212890625,
0.0253753662109375,
-0.0291595458984375,
0.035308837890625,
0.0291748046875,
-0.0364990234375,
-0.05645751953125,
0.072265625,
0.028961181640625,
0.0243377685546875,
0.0256195068359375,
0.01447296142578125,
-0.007228851318359375,
-0.0135955810546875,
-0.055633544921875,
0.025634765625,
-0.03729248046875,
-0.012481689453125,
-0.06390380859375,
0.0014934539794921875,
-0.057586669921875,
-0.0203399658203125,
-0.031005859375,
-0.0236053466796875,
-0.016693115234375,
0.0007948875427246094,
0.0159454345703125,
0.0287017822265625,
0.00024330615997314453,
0.005527496337890625,
-0.053619384765625,
0.03125,
0.0007395744323730469,
0.017059326171875,
-0.012115478515625,
-0.0582275390625,
-0.031280517578125,
0.01021575927734375,
-0.01513671875,
-0.0655517578125,
0.040771484375,
0.018280029296875,
0.04156494140625,
0.026702880859375,
-0.0008544921875,
0.06072998046875,
-0.040985107421875,
0.0618896484375,
0.010040283203125,
-0.06689453125,
0.044830322265625,
-0.0286407470703125,
0.042327880859375,
0.045166015625,
0.049407958984375,
-0.07037353515625,
-0.015350341796875,
-0.034027099609375,
-0.08038330078125,
0.06396484375,
0.01216888427734375,
0.0265045166015625,
-0.009033203125,
-0.0001672506332397461,
0.0058746337890625,
0.013580322265625,
-0.07147216796875,
-0.050048828125,
-0.01239013671875,
-0.029327392578125,
-0.0116424560546875,
-0.0235595703125,
-0.0190277099609375,
-0.0292816162109375,
0.06402587890625,
0.00136566162109375,
0.0223846435546875,
0.0177154541015625,
-0.010345458984375,
-0.0123138427734375,
0.02020263671875,
0.042144775390625,
0.042633056640625,
-0.01186370849609375,
0.00547027587890625,
0.0119476318359375,
-0.0291748046875,
0.009246826171875,
0.01220703125,
-0.0312042236328125,
0.004619598388671875,
0.035797119140625,
0.053436279296875,
0.0029773712158203125,
-0.041046142578125,
0.038726806640625,
0.0044403076171875,
-0.0223236083984375,
-0.03619384765625,
-0.0172119140625,
0.03033447265625,
0.01206207275390625,
0.018096923828125,
0.004184722900390625,
-0.0079498291015625,
-0.06353759765625,
0.0196075439453125,
0.035614013671875,
-0.036956787109375,
-0.0242462158203125,
0.05401611328125,
0.01201629638671875,
-0.0164031982421875,
0.02728271484375,
-0.03204345703125,
-0.044921875,
0.0296783447265625,
0.048004150390625,
0.051300048828125,
-0.0226593017578125,
0.01494598388671875,
0.050811767578125,
0.049041748046875,
0.003765106201171875,
0.040679931640625,
0.0108489990234375,
-0.04840087890625,
-0.007656097412109375,
-0.06097412109375,
0.003192901611328125,
-0.0099945068359375,
-0.04608154296875,
0.0243377685546875,
-0.0135040283203125,
-0.01151275634765625,
-0.01428985595703125,
0.0106964111328125,
-0.052337646484375,
-0.001018524169921875,
0.00003266334533691406,
0.0640869140625,
-0.0606689453125,
0.07470703125,
0.06842041015625,
-0.045013427734375,
-0.050872802734375,
0.0031032562255859375,
0.007419586181640625,
-0.050384521484375,
0.040679931640625,
0.0243682861328125,
0.011383056640625,
0.0161285400390625,
-0.00955963134765625,
-0.0634765625,
0.09027099609375,
0.021942138671875,
-0.0168914794921875,
0.0175933837890625,
0.021453857421875,
0.0323486328125,
-0.01361846923828125,
0.01445770263671875,
0.032745361328125,
0.05072021484375,
-0.00200653076171875,
-0.07293701171875,
0.01209259033203125,
-0.047943115234375,
0.0008974075317382812,
0.008758544921875,
-0.07476806640625,
0.07000732421875,
-0.00960540771484375,
-0.01467132568359375,
0.0072174072265625,
0.053192138671875,
0.025543212890625,
0.020843505859375,
0.01080322265625,
0.04339599609375,
0.04425048828125,
-0.01454925537109375,
0.07183837890625,
-0.041595458984375,
0.029632568359375,
0.05438232421875,
0.006397247314453125,
0.05615234375,
0.040985107421875,
-0.03619384765625,
0.01983642578125,
0.044525146484375,
0.0117645263671875,
0.018035888671875,
-0.01143646240234375,
-0.00968170166015625,
-0.015716552734375,
-0.0220489501953125,
-0.03460693359375,
0.032470703125,
0.00592803955078125,
-0.041717529296875,
0.0013275146484375,
0.0130462646484375,
0.046295166015625,
0.0037174224853515625,
-0.01274871826171875,
0.044281005859375,
0.0043487548828125,
-0.043792724609375,
0.062408447265625,
0.0125885009765625,
0.0670166015625,
-0.044647216796875,
0.016937255859375,
-0.029693603515625,
0.0163116455078125,
-0.0291595458984375,
-0.04931640625,
0.0204010009765625,
-0.007762908935546875,
-0.0247650146484375,
-0.00931549072265625,
0.02069091796875,
-0.049835205078125,
-0.05865478515625,
0.034454345703125,
0.043609619140625,
0.005840301513671875,
-0.0019054412841796875,
-0.066650390625,
0.007762908935546875,
0.0264434814453125,
-0.041900634765625,
0.03131103515625,
0.043975830078125,
-0.0010538101196289062,
0.046051025390625,
0.047698974609375,
0.00759124755859375,
0.0231170654296875,
-0.009918212890625,
0.0487060546875,
-0.06103515625,
-0.0266571044921875,
-0.06671142578125,
0.0382080078125,
0.0153961181640625,
-0.0234832763671875,
0.09259033203125,
0.059661865234375,
0.08135986328125,
-0.01416015625,
0.0516357421875,
-0.025970458984375,
0.022247314453125,
-0.030426025390625,
0.05889892578125,
-0.0704345703125,
-0.006404876708984375,
-0.0224609375,
-0.05633544921875,
-0.0261688232421875,
0.040771484375,
-0.0234222412109375,
0.01947021484375,
0.044097900390625,
0.060455322265625,
0.0013456344604492188,
-0.025146484375,
0.02508544921875,
0.01428985595703125,
0.015869140625,
0.041412353515625,
0.0270538330078125,
-0.061614990234375,
0.057037353515625,
-0.03863525390625,
0.00218963623046875,
-0.02093505859375,
-0.04547119140625,
-0.05633544921875,
-0.043792724609375,
-0.0144500732421875,
-0.05072021484375,
-0.0066070556640625,
0.08465576171875,
0.051422119140625,
-0.06494140625,
-0.0277862548828125,
0.00934600830078125,
0.0022792816162109375,
-0.02349853515625,
-0.0145263671875,
0.035308837890625,
0.0012969970703125,
-0.07550048828125,
0.015625,
0.01690673828125,
0.005390167236328125,
-0.007274627685546875,
-0.029205322265625,
-0.0343017578125,
0.0137481689453125,
0.0611572265625,
0.0118560791015625,
-0.055938720703125,
0.0029163360595703125,
-0.0012407302856445312,
-0.0262908935546875,
0.014434814453125,
0.001377105712890625,
-0.0222930908203125,
0.03961181640625,
0.037078857421875,
0.0276031494140625,
0.030792236328125,
0.004741668701171875,
0.01428985595703125,
-0.039306640625,
0.034881591796875,
-0.0033779144287109375,
0.0313720703125,
0.0229949951171875,
-0.0177001953125,
0.045074462890625,
0.035888671875,
-0.0238189697265625,
-0.0670166015625,
0.012237548828125,
-0.0762939453125,
-0.0240020751953125,
0.09814453125,
-0.026092529296875,
-0.04949951171875,
-0.005786895751953125,
-0.01416015625,
0.027008056640625,
-0.0242919921875,
0.0213775634765625,
0.053131103515625,
0.004302978515625,
-0.01116180419921875,
-0.059051513671875,
0.02728271484375,
0.03692626953125,
-0.06640625,
-0.00044918060302734375,
0.00775146484375,
0.024383544921875,
0.01097869873046875,
0.051177978515625,
-0.03509521484375,
0.016632080078125,
-0.0011434555053710938,
0.034088134765625,
-0.001712799072265625,
-0.00525665283203125,
-0.0195159912109375,
-0.0009675025939941406,
-0.006389617919921875,
-0.00991058349609375
]
] |
guillaumekln/faster-whisper-base.en | 2023-05-12T18:57:21.000Z | [
"ctranslate2",
"audio",
"automatic-speech-recognition",
"en",
"license:mit",
"region:us"
] | automatic-speech-recognition | guillaumekln | null | null | guillaumekln/faster-whisper-base.en | 2 | 47,165 | ctranslate2 | 2023-03-23T10:18:04 | ---
language:
- en
tags:
- audio
- automatic-speech-recognition
license: mit
library_name: ctranslate2
---
# Whisper base.en model for CTranslate2
This repository contains the conversion of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/guillaumekln/faster-whisper).
## Example
```python
from faster_whisper import WhisperModel
model = WhisperModel("base.en")
segments, info = model.transcribe("audio.mp3")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
```
## Conversion details
The original model was converted with the following command:
```
ct2-transformers-converter --model openai/whisper-base.en --output_dir faster-whisper-base.en \
--copy_files tokenizer.json --quantization float16
```
Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html).
## More information
**For more information about the original model, see its [model card](https://huggingface.co/openai/whisper-base.en).**
| 1,328 | [
[
0.0062255859375,
-0.027496337890625,
0.01474761962890625,
0.03631591796875,
-0.031585693359375,
-0.0192108154296875,
-0.035980224609375,
-0.0298004150390625,
0.0008211135864257812,
0.05792236328125,
-0.035430908203125,
-0.047119140625,
-0.045867919921875,
-0.022979736328125,
-0.0224151611328125,
0.06646728515625,
-0.0160675048828125,
0.0178375244140625,
0.031219482421875,
-0.007808685302734375,
-0.0271148681640625,
-0.0196533203125,
-0.051177978515625,
-0.020904541015625,
0.0060272216796875,
0.016571044921875,
0.042510986328125,
0.024200439453125,
0.03106689453125,
0.0198822021484375,
-0.0216217041015625,
-0.00511932373046875,
-0.0246734619140625,
-0.0066680908203125,
0.015899658203125,
-0.05133056640625,
-0.052520751953125,
0.0074310302734375,
0.0460205078125,
0.01467132568359375,
-0.0215911865234375,
0.0276641845703125,
-0.017364501953125,
0.0286865234375,
-0.040374755859375,
0.0239105224609375,
-0.043060302734375,
-0.001369476318359375,
-0.009765625,
-0.0189361572265625,
-0.04388427734375,
-0.0264739990234375,
0.041412353515625,
-0.06134033203125,
0.013519287109375,
-0.00811004638671875,
0.065673828125,
0.0160369873046875,
-0.03643798828125,
-0.026397705078125,
-0.0653076171875,
0.07110595703125,
-0.055908203125,
0.024566650390625,
0.020416259765625,
0.03533935546875,
0.01454925537109375,
-0.077392578125,
-0.0111236572265625,
-0.0076751708984375,
0.0117034912109375,
0.0268707275390625,
-0.029571533203125,
0.0213623046875,
0.01116180419921875,
0.036834716796875,
-0.048980712890625,
-0.0159149169921875,
-0.055419921875,
-0.032562255859375,
0.036376953125,
0.0038318634033203125,
0.0191192626953125,
-0.0159912109375,
-0.0277099609375,
-0.044708251953125,
-0.041656494140625,
0.0014934539794921875,
0.038848876953125,
0.021636962890625,
-0.051177978515625,
0.047821044921875,
0.00399017333984375,
0.0283966064453125,
0.0103607177734375,
-0.0227813720703125,
0.034027099609375,
-0.016754150390625,
-0.01247406005859375,
0.037628173828125,
0.045013427734375,
0.038177490234375,
0.0135955810546875,
0.01397705078125,
-0.0165252685546875,
-0.0009579658508300781,
0.00464630126953125,
-0.0809326171875,
-0.0278472900390625,
0.0229949951171875,
-0.06463623046875,
-0.01708984375,
0.006244659423828125,
-0.018707275390625,
0.00995635986328125,
-0.0110321044921875,
0.042510986328125,
-0.03790283203125,
-0.0479736328125,
0.034942626953125,
-0.04205322265625,
0.01263427734375,
0.0255279541015625,
-0.058349609375,
0.03411865234375,
0.040863037109375,
0.0811767578125,
0.0016269683837890625,
-0.0064544677734375,
-0.01287841796875,
0.019989013671875,
-0.006237030029296875,
0.036102294921875,
-0.0009403228759765625,
-0.04534912109375,
-0.0011472702026367188,
-0.004596710205078125,
-0.0108642578125,
-0.043853759765625,
0.04498291015625,
-0.0173797607421875,
0.0295257568359375,
0.019378662109375,
-0.0160369873046875,
-0.0173187255859375,
0.0024852752685546875,
-0.0501708984375,
0.076904296875,
0.04071044921875,
-0.0550537109375,
-0.01233673095703125,
-0.0577392578125,
-0.01383209228515625,
-0.01299285888671875,
0.0367431640625,
-0.0249481201171875,
0.01910400390625,
-0.002960205078125,
-0.005626678466796875,
-0.0288238525390625,
0.0237884521484375,
-0.0026607513427734375,
-0.02825927734375,
0.016387939453125,
-0.03448486328125,
0.079833984375,
0.0252685546875,
-0.0009050369262695312,
0.020172119140625,
-0.048004150390625,
0.00487518310546875,
-0.004871368408203125,
-0.0301361083984375,
-0.0234527587890625,
-0.0112762451171875,
0.03857421875,
-0.0037746429443359375,
0.0261688232421875,
-0.04705810546875,
0.0190277099609375,
-0.048675537109375,
0.056304931640625,
0.0257415771484375,
-0.0003237724304199219,
0.03387451171875,
-0.0277557373046875,
0.007312774658203125,
0.0170135498046875,
0.02972412109375,
0.0010023117065429688,
-0.042816162109375,
-0.05645751953125,
-0.00559234619140625,
0.0248870849609375,
0.037200927734375,
-0.03790283203125,
0.0246124267578125,
-0.0266571044921875,
-0.06787109375,
-0.0709228515625,
-0.035064697265625,
0.020416259765625,
0.025115966796875,
0.04473876953125,
-0.00769805908203125,
-0.06414794921875,
-0.06353759765625,
-0.00824737548828125,
-0.03192138671875,
-0.0156707763671875,
0.0120697021484375,
0.039154052734375,
-0.01293182373046875,
0.0513916015625,
-0.04254150390625,
-0.03192138671875,
-0.0185089111328125,
0.0257415771484375,
0.0234832763671875,
0.06298828125,
0.046661376953125,
-0.059326171875,
-0.021697998046875,
-0.01373291015625,
-0.02606201171875,
-0.00225067138671875,
-0.00499725341796875,
-0.01062774658203125,
0.0034694671630859375,
0.0029926300048828125,
-0.059478759765625,
0.03448486328125,
0.055206298828125,
-0.0273895263671875,
0.038421630859375,
0.004116058349609375,
0.0010833740234375,
-0.09527587890625,
0.0099945068359375,
-0.0012903213500976562,
-0.00960540771484375,
-0.04937744140625,
0.00392913818359375,
0.01678466796875,
0.00957489013671875,
-0.059051513671875,
0.04705810546875,
-0.01313018798828125,
-0.00147247314453125,
-0.0100860595703125,
-0.02386474609375,
-0.00507354736328125,
0.023681640625,
0.03656005859375,
0.0577392578125,
0.036346435546875,
-0.03094482421875,
0.0111846923828125,
0.0450439453125,
-0.0166015625,
0.01078033447265625,
-0.0767822265625,
0.01055908203125,
0.016387939453125,
0.0335693359375,
-0.0445556640625,
0.003021240234375,
0.0198516845703125,
-0.055694580078125,
0.01131439208984375,
-0.050537109375,
-0.035064697265625,
-0.0140380859375,
-0.03265380859375,
0.03338623046875,
0.05194091796875,
-0.027923583984375,
0.055450439453125,
0.01708984375,
0.008087158203125,
-0.013519287109375,
-0.07855224609375,
-0.005741119384765625,
-0.00907135009765625,
-0.05914306640625,
0.05657958984375,
-0.020263671875,
-0.0126190185546875,
-0.00922393798828125,
-0.005191802978515625,
-0.018707275390625,
-0.00879669189453125,
0.035888671875,
0.024200439453125,
-0.033905029296875,
-0.0237579345703125,
0.0290985107421875,
-0.0273895263671875,
0.00934600830078125,
-0.041107177734375,
0.055877685546875,
-0.012481689453125,
-0.00015282630920410156,
-0.045562744140625,
0.00957489013671875,
0.04052734375,
-0.01800537109375,
0.03497314453125,
0.04779052734375,
-0.0295562744140625,
-0.01430511474609375,
-0.033538818359375,
-0.0125885009765625,
-0.03607177734375,
0.0196380615234375,
-0.0296630859375,
-0.05267333984375,
0.035736083984375,
0.010498046875,
0.00627899169921875,
0.06011962890625,
0.04412841796875,
0.006732940673828125,
0.0799560546875,
0.031768798828125,
0.019073486328125,
0.0290985107421875,
-0.057586669921875,
-0.01788330078125,
-0.08502197265625,
-0.0279998779296875,
-0.048919677734375,
-0.00899505615234375,
-0.026031494140625,
-0.021514892578125,
0.037200927734375,
0.01251220703125,
-0.034698486328125,
0.0540771484375,
-0.052093505859375,
-0.002368927001953125,
0.03704833984375,
0.01462554931640625,
0.022735595703125,
0.00325775146484375,
0.01467132568359375,
-0.01030731201171875,
-0.0225677490234375,
-0.0276031494140625,
0.08319091796875,
0.04473876953125,
0.0517578125,
0.0245513916015625,
0.046356201171875,
0.00713348388671875,
0.01113128662109375,
-0.0634765625,
0.0174102783203125,
-0.0146484375,
-0.042236328125,
-0.00008976459503173828,
-0.021514892578125,
-0.0499267578125,
0.00618743896484375,
0.0052490234375,
-0.04339599609375,
0.00777435302734375,
-0.00411224365234375,
-0.002918243408203125,
0.0266265869140625,
-0.037445068359375,
0.05194091796875,
0.0034809112548828125,
0.025726318359375,
-0.0146942138671875,
-0.0288238525390625,
0.034088134765625,
0.0166778564453125,
-0.0232391357421875,
0.004238128662109375,
-0.00437164306640625,
0.07525634765625,
-0.050079345703125,
0.0609130859375,
-0.03350830078125,
-0.014862060546875,
0.052215576171875,
0.013519287109375,
0.0272216796875,
0.01050567626953125,
-0.0171661376953125,
0.040283203125,
0.024383544921875,
-0.0025653839111328125,
-0.0245208740234375,
0.03948974609375,
-0.096435546875,
-0.00799560546875,
-0.01446533203125,
-0.039093017578125,
0.0223541259765625,
0.00878143310546875,
0.045135498046875,
0.045074462890625,
-0.0041351318359375,
0.0147857666015625,
0.04876708984375,
0.00739288330078125,
0.0291748046875,
0.051971435546875,
-0.0012845993041992188,
-0.057586669921875,
0.05047607421875,
0.01506805419921875,
0.0218048095703125,
0.032196044921875,
0.0219879150390625,
-0.04052734375,
-0.07257080078125,
-0.0338134765625,
0.003978729248046875,
-0.04840087890625,
-0.02679443359375,
-0.05194091796875,
-0.0418701171875,
-0.0379638671875,
0.008209228515625,
-0.049102783203125,
-0.053253173828125,
-0.03851318359375,
0.013824462890625,
0.051971435546875,
0.0305938720703125,
-0.0007538795471191406,
0.050537109375,
-0.0791015625,
0.0198516845703125,
-0.0033168792724609375,
0.01259613037109375,
0.01079559326171875,
-0.071044921875,
-0.00839996337890625,
0.0142364501953125,
-0.0197906494140625,
-0.06494140625,
0.036895751953125,
0.004589080810546875,
0.0175628662109375,
0.00862884521484375,
0.006084442138671875,
0.056060791015625,
-0.0141143798828125,
0.0736083984375,
0.0231781005859375,
-0.08642578125,
0.053619384765625,
-0.03582763671875,
0.01299285888671875,
0.038909912109375,
0.0094757080078125,
-0.045501708984375,
-0.006832122802734375,
-0.04638671875,
-0.0606689453125,
0.061187744140625,
0.0330810546875,
-0.0016832351684570312,
0.0140380859375,
0.0140380859375,
0.0130615234375,
0.01233673095703125,
-0.05462646484375,
-0.0270233154296875,
-0.051025390625,
-0.033050537109375,
0.021728515625,
-0.0203704833984375,
-0.00487518310546875,
-0.0157012939453125,
0.0579833984375,
-0.0127716064453125,
0.030364990234375,
0.040008544921875,
-0.021148681640625,
-0.01070404052734375,
0.0006136894226074219,
0.048675537109375,
0.009613037109375,
-0.042999267578125,
-0.00951385498046875,
0.01233673095703125,
-0.061676025390625,
-0.0036296844482421875,
-0.00118255615234375,
-0.0278472900390625,
0.018280029296875,
0.036376953125,
0.0638427734375,
0.029449462890625,
-0.0206451416015625,
0.0478515625,
-0.006458282470703125,
-0.033477783203125,
-0.05926513671875,
0.006893157958984375,
0.018280029296875,
0.0118255615234375,
0.033050537109375,
0.0213623046875,
0.019805908203125,
-0.028228759765625,
-0.01290130615234375,
0.006725311279296875,
-0.035888671875,
-0.03997802734375,
0.055511474609375,
0.0160064697265625,
-0.026336669921875,
0.048858642578125,
0.0097198486328125,
-0.018218994140625,
0.04571533203125,
0.058135986328125,
0.09417724609375,
-0.00830841064453125,
0.0054931640625,
0.04833984375,
0.021514892578125,
-0.016571044921875,
0.055328369140625,
-0.0113372802734375,
-0.034332275390625,
-0.026580810546875,
-0.053375244140625,
-0.0276641845703125,
0.0054931640625,
-0.07208251953125,
0.023712158203125,
-0.0367431640625,
-0.01593017578125,
0.0010862350463867188,
0.0028533935546875,
-0.045806884765625,
-0.0015468597412109375,
0.01727294921875,
0.10931396484375,
-0.04705810546875,
0.08233642578125,
0.0394287109375,
-0.0295257568359375,
-0.06561279296875,
-0.0224151611328125,
-0.00585174560546875,
-0.053802490234375,
0.046234130859375,
0.01141357421875,
-0.00469207763671875,
0.004863739013671875,
-0.0550537109375,
-0.07257080078125,
0.099365234375,
0.004451751708984375,
-0.0421142578125,
-0.01557159423828125,
0.01145172119140625,
0.03692626953125,
-0.042816162109375,
0.05352783203125,
0.029144287109375,
0.0601806640625,
0.00262451171875,
-0.0897216796875,
-0.0008497238159179688,
-0.0159454345703125,
0.017364501953125,
0.004268646240234375,
-0.0596923828125,
0.08782958984375,
-0.01015472412109375,
-0.0090789794921875,
0.05560302734375,
0.051025390625,
0.027099609375,
0.0175628662109375,
0.033050537109375,
0.034027099609375,
0.0255279541015625,
-0.025054931640625,
0.04266357421875,
-0.021575927734375,
0.038787841796875,
0.0654296875,
-0.019805908203125,
0.07366943359375,
0.02484130859375,
-0.004055023193359375,
0.06085205078125,
0.03173828125,
-0.0233917236328125,
0.045867919921875,
-0.0018434524536132812,
-0.0010356903076171875,
-0.002239227294921875,
-0.0034198760986328125,
-0.039581298828125,
0.053619384765625,
0.03582763671875,
-0.0277252197265625,
-0.01538848876953125,
-0.00870513916015625,
0.003643035888671875,
-0.016357421875,
-0.0285186767578125,
0.050323486328125,
-0.00759124755859375,
-0.035491943359375,
0.053741455078125,
0.030059814453125,
0.07098388671875,
-0.072265625,
-0.0115509033203125,
0.0178070068359375,
0.01100921630859375,
-0.020355224609375,
-0.056671142578125,
0.033416748046875,
-0.01340484619140625,
-0.0242767333984375,
-0.004543304443359375,
0.04827880859375,
-0.0474853515625,
-0.0272216796875,
0.030303955078125,
0.0176849365234375,
0.0239715576171875,
-0.0208740234375,
-0.0577392578125,
0.0289306640625,
0.018585205078125,
-0.026580810546875,
0.014862060546875,
-0.007007598876953125,
-0.00211334228515625,
0.031219482421875,
0.06646728515625,
0.01226043701171875,
0.0012464523315429688,
0.00911712646484375,
0.0501708984375,
-0.047637939453125,
-0.052093505859375,
-0.02972412109375,
0.048065185546875,
-0.00017178058624267578,
-0.054779052734375,
0.0379638671875,
0.065673828125,
0.042816162109375,
-0.024810791015625,
0.05438232421875,
0.00017881393432617188,
0.02581787109375,
-0.057281494140625,
0.056610107421875,
-0.02001953125,
-0.010223388671875,
0.003574371337890625,
-0.06219482421875,
0.0046844482421875,
0.0284576416015625,
0.00323486328125,
-0.016937255859375,
0.044097900390625,
0.064208984375,
-0.00897216796875,
0.01806640625,
-0.0018014907836914062,
0.0302886962890625,
0.0225067138671875,
0.046783447265625,
0.04632568359375,
-0.0755615234375,
0.05096435546875,
-0.0283966064453125,
-0.0006303787231445312,
-0.0017728805541992188,
-0.047027587890625,
-0.068115234375,
-0.043792724609375,
-0.03472900390625,
-0.048675537109375,
-0.002613067626953125,
0.069580078125,
0.07098388671875,
-0.0552978515625,
-0.02960205078125,
0.0002944469451904297,
-0.009246826171875,
-0.0021076202392578125,
-0.021575927734375,
0.03643798828125,
0.0258941650390625,
-0.05926513671875,
0.04547119140625,
0.0054168701171875,
0.03460693359375,
-0.0223236083984375,
-0.03466796875,
0.0218505859375,
-0.0014743804931640625,
0.0258331298828125,
0.006378173828125,
-0.06451416015625,
-0.0088653564453125,
-0.0111541748046875,
-0.0020732879638671875,
0.016693115234375,
0.053741455078125,
-0.058441162109375,
0.0102081298828125,
0.04937744140625,
-0.018768310546875,
0.053466796875,
-0.0214080810546875,
0.0228424072265625,
-0.042266845703125,
0.035247802734375,
0.0201873779296875,
0.02972412109375,
0.01190948486328125,
-0.00858306884765625,
0.0318603515625,
0.0173797607421875,
-0.0167083740234375,
-0.0675048828125,
-0.002071380615234375,
-0.10205078125,
-0.004528045654296875,
0.0826416015625,
-0.0013446807861328125,
-0.026092529296875,
0.00958251953125,
-0.044281005859375,
0.028533935546875,
-0.04833984375,
0.01093292236328125,
0.0124053955078125,
0.029205322265625,
-0.0034580230712890625,
-0.0283660888671875,
0.0302886962890625,
-0.005535125732421875,
-0.0269012451171875,
0.0026264190673828125,
0.00528717041015625,
0.039794921875,
0.0306549072265625,
0.04388427734375,
-0.037750244140625,
0.0338134765625,
0.02117919921875,
0.037261962890625,
-0.0295257568359375,
-0.0287322998046875,
-0.02227783203125,
0.00199127197265625,
-0.0071868896484375,
-0.0208892822265625
]
] |
StanfordAIMI/stanford-deidentifier-only-i2b2 | 2022-11-23T19:45:04.000Z | [
"transformers",
"pytorch",
"bert",
"token-classification",
"sequence-tagger-model",
"pubmedbert",
"uncased",
"radiology",
"biomedical",
"en",
"dataset:radreports",
"license:mit",
"endpoints_compatible",
"region:us"
] | token-classification | StanfordAIMI | null | null | StanfordAIMI/stanford-deidentifier-only-i2b2 | 3 | 47,009 | transformers | 2022-06-09T08:10:52 | ---
widget:
- text: "PROCEDURE: Chest xray. COMPARISON: last seen on 1/1/2020 and also record dated of March 1st, 2019. FINDINGS: patchy airspace opacities. IMPRESSION: The results of the chest xray of January 1 2020 are the most concerning ones. The patient was transmitted to another service of UH Medical Center under the responsability of Dr. Perez. We used the system MedClinical data transmitter and sent the data on 2/1/2020, under the ID 5874233. We received the confirmation of Dr Perez. He is reachable at 567-493-1234."
- text: "Dr. Curt Langlotz chose to schedule a meeting on 06/23."
tags:
- token-classification
- sequence-tagger-model
- pytorch
- transformers
- pubmedbert
- uncased
- radiology
- biomedical
datasets:
- radreports
language:
- en
license: mit
---
Stanford de-identifier was trained on a variety of radiology and biomedical documents with the goal of automatising the de-identification process while reaching satisfactory accuracy for use in production. Manuscript in-proceedings.
Associated github repo: https://github.com/MIDRC/Stanford_Penn_Deidentifier
## Citation
```bibtex
@article{10.1093/jamia/ocac219,
author = {Chambon, Pierre J and Wu, Christopher and Steinkamp, Jackson M and Adleberg, Jason and Cook, Tessa S and Langlotz, Curtis P},
title = "{Automated deidentification of radiology reports combining transformer and “hide in plain sight” rule-based methods}",
journal = {Journal of the American Medical Informatics Association},
year = {2022},
month = {11},
abstract = "{To develop an automated deidentification pipeline for radiology reports that detect protected health information (PHI) entities and replaces them with realistic surrogates “hiding in plain sight.”In this retrospective study, 999 chest X-ray and CT reports collected between November 2019 and November 2020 were annotated for PHI at the token level and combined with 3001 X-rays and 2193 medical notes previously labeled, forming a large multi-institutional and cross-domain dataset of 6193 documents. Two radiology test sets, from a known and a new institution, as well as i2b2 2006 and 2014 test sets, served as an evaluation set to estimate model performance and to compare it with previously released deidentification tools. Several PHI detection models were developed based on different training datasets, fine-tuning approaches and data augmentation techniques, and a synthetic PHI generation algorithm. These models were compared using metrics such as precision, recall and F1 score, as well as paired samples Wilcoxon tests.Our best PHI detection model achieves 97.9 F1 score on radiology reports from a known institution, 99.6 from a new institution, 99.5 on i2b2 2006, and 98.9 on i2b2 2014. On reports from a known institution, it achieves 99.1 recall of detecting the core of each PHI span.Our model outperforms all deidentifiers it was compared to on all test sets as well as human labelers on i2b2 2014 data. It enables accurate and automatic deidentification of radiology reports.A transformer-based deidentification pipeline can achieve state-of-the-art performance for deidentifying radiology reports and other medical documents.}",
issn = {1527-974X},
doi = {10.1093/jamia/ocac219},
url = {https://doi.org/10.1093/jamia/ocac219},
note = {ocac219},
eprint = {https://academic.oup.com/jamia/advance-article-pdf/doi/10.1093/jamia/ocac219/47220191/ocac219.pdf},
}
``` | 3,445 | [
[
-0.01535797119140625,
-0.0154876708984375,
0.049041748046875,
-0.0109405517578125,
-0.032928466796875,
-0.004528045654296875,
0.0161285400390625,
-0.0391845703125,
0.01129150390625,
0.00902557373046875,
-0.0241546630859375,
-0.049530029296875,
-0.054229736328125,
0.0258636474609375,
-0.0259857177734375,
0.048126220703125,
0.009185791015625,
-0.006038665771484375,
0.0196685791015625,
0.004329681396484375,
-0.025970458984375,
-0.00908660888671875,
-0.0173187255859375,
-0.0224456787109375,
0.033111572265625,
0.0173187255859375,
0.045013427734375,
0.0828857421875,
0.0850830078125,
0.017791748046875,
0.004535675048828125,
0.00872802734375,
-0.029022216796875,
-0.0123291015625,
-0.004467010498046875,
0.00800323486328125,
-0.036224365234375,
0.00011157989501953125,
0.048309326171875,
0.059295654296875,
0.0244293212890625,
0.00011801719665527344,
-0.01641845703125,
0.054840087890625,
-0.070068359375,
0.0291290283203125,
-0.01995849609375,
-0.0006170272827148438,
-0.0252685546875,
-0.0291290283203125,
-0.03900146484375,
-0.040008544921875,
0.031463623046875,
-0.028350830078125,
0.021331787109375,
-0.0165557861328125,
0.08721923828125,
0.02081298828125,
-0.036285400390625,
-0.0213165283203125,
-0.061309814453125,
0.041656494140625,
-0.04132080078125,
0.0257110595703125,
0.033203125,
0.0158538818359375,
0.013519287109375,
-0.079345703125,
0.0012331008911132812,
-0.0192413330078125,
-0.037261962890625,
0.02862548828125,
-0.0189056396484375,
0.00856781005859375,
0.03277587890625,
0.043060302734375,
-0.058258056640625,
0.0173187255859375,
-0.07623291015625,
-0.00566864013671875,
0.054351806640625,
0.004131317138671875,
0.01107025146484375,
-0.0266876220703125,
-0.021270751953125,
-0.0174560546875,
-0.03759765625,
-0.033935546875,
-0.00007325410842895508,
0.014190673828125,
-0.00896453857421875,
0.0159759521484375,
-0.0313720703125,
0.020294189453125,
0.023681640625,
-0.0191192626953125,
0.05792236328125,
0.0107269287109375,
-0.034149169921875,
0.036651611328125,
0.058502197265625,
0.00884246826171875,
-0.007465362548828125,
0.0003795623779296875,
0.0035648345947265625,
-0.0025539398193359375,
0.01523590087890625,
-0.05792236328125,
-0.0460205078125,
0.002246856689453125,
-0.0556640625,
-0.0416259765625,
0.052459716796875,
-0.03106689453125,
-0.04443359375,
-0.0279083251953125,
0.0202178955078125,
-0.053558349609375,
-0.0183868408203125,
0.0096588134765625,
-0.01496124267578125,
0.02301025390625,
0.0236358642578125,
-0.058502197265625,
0.00044727325439453125,
0.04656982421875,
0.053375244140625,
-0.01177978515625,
0.0009050369262695312,
-0.0262451171875,
0.0291595458984375,
-0.02825927734375,
0.0447998046875,
-0.0167694091796875,
-0.0416259765625,
-0.01482391357421875,
0.027191162109375,
-0.0176239013671875,
-0.044219970703125,
0.052734375,
-0.034820556640625,
0.0247650146484375,
-0.021392822265625,
-0.0149688720703125,
-0.02850341796875,
0.003803253173828125,
-0.06512451171875,
0.0714111328125,
0.0186614990234375,
-0.070068359375,
0.027191162109375,
-0.0234527587890625,
-0.031494140625,
0.027099609375,
-0.0210723876953125,
-0.04718017578125,
0.0122528076171875,
0.01206207275390625,
0.0106353759765625,
-0.036224365234375,
0.03790283203125,
-0.00937652587890625,
-0.043853759765625,
0.01078033447265625,
-0.045501708984375,
0.087890625,
0.01323699951171875,
-0.033172607421875,
-0.02960205078125,
-0.06292724609375,
0.0022754669189453125,
0.004322052001953125,
-0.02691650390625,
-0.0294952392578125,
-0.037353515625,
-0.0181884765625,
-0.0010499954223632812,
0.00298309326171875,
-0.0491943359375,
0.007755279541015625,
-0.029693603515625,
0.0168609619140625,
0.039031982421875,
0.0087738037109375,
0.0083465576171875,
-0.0364990234375,
0.026580810546875,
0.01091766357421875,
0.02325439453125,
-0.0196685791015625,
-0.033050537109375,
-0.038665771484375,
-0.0665283203125,
0.03717041015625,
0.047515869140625,
0.01442718505859375,
0.0509033203125,
-0.050201416015625,
-0.044036865234375,
-0.0286865234375,
-0.036163330078125,
0.0221099853515625,
0.0645751953125,
0.032012939453125,
-0.033843994140625,
-0.0482177734375,
-0.07562255859375,
0.0246429443359375,
-0.020111083984375,
-0.02117919921875,
0.01128387451171875,
0.028289794921875,
-0.033477783203125,
0.0599365234375,
-0.05377197265625,
-0.043243408203125,
-0.0007882118225097656,
0.023193359375,
0.01458740234375,
0.0361328125,
0.030914306640625,
-0.06292724609375,
-0.044921875,
-0.01312255859375,
-0.0850830078125,
-0.027557373046875,
-0.0033397674560546875,
0.00417327880859375,
0.011077880859375,
0.049835205078125,
-0.020782470703125,
0.06695556640625,
-0.0031261444091796875,
0.018463134765625,
-0.00439453125,
-0.04144287109375,
0.0237884521484375,
-0.05523681640625,
0.04510498046875,
-0.005512237548828125,
0.004421234130859375,
-0.035919189453125,
-0.0254364013671875,
0.033721923828125,
-0.01412200927734375,
-0.034271240234375,
0.0221405029296875,
-0.05804443359375,
0.01322174072265625,
0.008575439453125,
-0.00870513916015625,
0.01157379150390625,
0.0204620361328125,
0.01187896728515625,
0.018157958984375,
0.029693603515625,
-0.041473388671875,
0.0111846923828125,
0.01479339599609375,
-0.018280029296875,
0.0384521484375,
-0.0548095703125,
0.007289886474609375,
-0.039337158203125,
0.0264739990234375,
-0.07843017578125,
-0.0174407958984375,
0.037384033203125,
-0.008575439453125,
0.044647216796875,
-0.01458740234375,
-0.01214599609375,
-0.061614990234375,
-0.046234130859375,
0.0301971435546875,
0.03717041015625,
-0.031402587890625,
0.042510986328125,
0.02789306640625,
0.006031036376953125,
-0.044189453125,
-0.0687255859375,
-0.00278472900390625,
-0.0258636474609375,
-0.03460693359375,
0.06805419921875,
-0.00792694091796875,
-0.0205535888671875,
-0.00814056396484375,
0.0001842975616455078,
-0.03173828125,
0.00691986083984375,
0.054962158203125,
0.044219970703125,
-0.0106658935546875,
0.0170135498046875,
0.00896453857421875,
-0.0491943359375,
0.0014667510986328125,
-0.0087432861328125,
0.0096282958984375,
-0.00015854835510253906,
-0.05560302734375,
-0.0782470703125,
0.0209808349609375,
0.060943603515625,
0.00016963481903076172,
0.027313232421875,
0.03472900390625,
-0.045440673828125,
0.03375244140625,
-0.044921875,
-0.021331787109375,
-0.032867431640625,
0.01085662841796875,
-0.030914306640625,
-0.00841522216796875,
0.0295867919921875,
-0.0190277099609375,
-0.0001729726791381836,
0.06085205078125,
0.0263214111328125,
-0.00826263427734375,
0.0677490234375,
0.0333251953125,
-0.00997161865234375,
0.01055145263671875,
-0.037200927734375,
0.031982421875,
-0.061737060546875,
-0.024993896484375,
-0.04705810546875,
-0.02850341796875,
-0.045074462890625,
-0.0016508102416992188,
0.0513916015625,
-0.01078033447265625,
-0.0017786026000976562,
0.0169219970703125,
-0.07421875,
0.035064697265625,
0.041961669921875,
0.0274810791015625,
0.040863037109375,
-0.004276275634765625,
0.016571044921875,
-0.023284912109375,
-0.030364990234375,
-0.0307464599609375,
0.09735107421875,
0.0295867919921875,
0.0648193359375,
0.01203155517578125,
0.076904296875,
0.0445556640625,
0.0160980224609375,
-0.0472412109375,
0.0187835693359375,
-0.0275726318359375,
-0.028411865234375,
-0.0175323486328125,
-0.002010345458984375,
-0.07940673828125,
-0.0025577545166015625,
0.015899658203125,
-0.041778564453125,
0.0472412109375,
-0.020294189453125,
-0.046142578125,
-0.003864288330078125,
-0.0279998779296875,
0.045501708984375,
-0.00919342041015625,
0.0061798095703125,
-0.01325225830078125,
-0.0479736328125,
0.0257110595703125,
-0.01983642578125,
-0.008148193359375,
-0.016265869140625,
0.0181427001953125,
0.04254150390625,
-0.03857421875,
0.06378173828125,
0.005283355712890625,
-0.00492095947265625,
0.009613037109375,
-0.005558013916015625,
0.017852783203125,
0.01531982421875,
-0.01303863525390625,
0.02996826171875,
0.016693115234375,
0.010528564453125,
-0.0079345703125,
0.054931640625,
-0.05413818359375,
-0.038787841796875,
-0.0638427734375,
-0.037322998046875,
0.0290679931640625,
0.040069580078125,
0.05126953125,
0.06292724609375,
-0.01210784912109375,
0.0228424072265625,
0.07232666015625,
-0.011199951171875,
0.023529052734375,
0.050872802734375,
0.034423828125,
-0.041015625,
0.051788330078125,
0.0267486572265625,
-0.0123291015625,
0.049560546875,
0.0299224853515625,
-0.02587890625,
-0.02587890625,
-0.02740478515625,
0.0504150390625,
-0.062042236328125,
-0.02423095703125,
-0.061737060546875,
-0.049346923828125,
-0.04815673828125,
-0.0169677734375,
-0.0137786865234375,
-0.03271484375,
-0.039337158203125,
-0.0020351409912109375,
0.01035308837890625,
0.038238525390625,
-0.03643798828125,
-0.002285003662109375,
-0.053558349609375,
0.0233154296875,
0.0139923095703125,
-0.002635955810546875,
-0.0204010009765625,
-0.0611572265625,
0.004711151123046875,
-0.0006628036499023438,
-0.0168304443359375,
-0.06683349609375,
0.032135009765625,
0.01277923583984375,
0.043670654296875,
0.04736328125,
0.050079345703125,
0.0447998046875,
0.0005397796630859375,
0.021759033203125,
-0.006801605224609375,
-0.059173583984375,
0.069091796875,
-0.0170135498046875,
0.032073974609375,
0.06304931640625,
0.041473388671875,
-0.0291290283203125,
-0.0226287841796875,
-0.06005859375,
-0.0589599609375,
0.06585693359375,
-0.020751953125,
-0.0067291259765625,
-0.014556884765625,
0.024078369140625,
-0.005397796630859375,
-0.0201263427734375,
-0.035430908203125,
-0.01000213623046875,
0.0224761962890625,
-0.034271240234375,
0.0460205078125,
-0.03460693359375,
-0.03070068359375,
-0.0187530517578125,
0.0738525390625,
-0.01171112060546875,
0.0157623291015625,
0.02850341796875,
-0.036834716796875,
-0.0012845993041992188,
-0.01439666748046875,
0.033721923828125,
0.0648193359375,
-0.0291290283203125,
0.0186767578125,
0.00011515617370605469,
-0.0621337890625,
-0.00501251220703125,
0.0185546875,
-0.03375244140625,
0.01947021484375,
0.0285491943359375,
0.01329803466796875,
0.00823211669921875,
-0.032806396484375,
0.047821044921875,
-0.0113372802734375,
-0.0272674560546875,
-0.03948974609375,
-0.0025920867919921875,
-0.0244140625,
0.0035152435302734375,
0.03228759765625,
-0.011138916015625,
0.032806396484375,
-0.00734710693359375,
0.01546478271484375,
0.016265869140625,
-0.052520751953125,
-0.00516510009765625,
0.05078125,
0.00827789306640625,
0.0134124755859375,
0.09283447265625,
-0.00997161865234375,
-0.01351165771484375,
0.059295654296875,
0.0094146728515625,
0.08111572265625,
-0.031951904296875,
0.0163116455078125,
0.054290771484375,
0.0301971435546875,
0.00018107891082763672,
0.00710296630859375,
0.001129150390625,
-0.01505279541015625,
0.01482391357421875,
-0.00992584228515625,
-0.0007052421569824219,
0.0323486328125,
-0.065185546875,
0.057098388671875,
-0.04705810546875,
-0.0115814208984375,
0.018218994140625,
-0.00585174560546875,
-0.032684326171875,
0.016265869140625,
0.0301971435546875,
0.06390380859375,
-0.07147216796875,
0.05340576171875,
0.0196685791015625,
-0.05108642578125,
-0.04705810546875,
0.0027008056640625,
0.0277252197265625,
-0.030609130859375,
0.06732177734375,
0.039886474609375,
0.00463104248046875,
-0.005527496337890625,
0.021881103515625,
-0.08465576171875,
0.11700439453125,
0.0225677490234375,
-0.03570556640625,
-0.0051727294921875,
0.0307159423828125,
0.026702880859375,
0.001239776611328125,
0.046478271484375,
0.045806884765625,
0.034881591796875,
0.019134521484375,
-0.088134765625,
0.01824951171875,
-0.01207733154296875,
-0.001422882080078125,
0.007183074951171875,
-0.037384033203125,
0.056854248046875,
-0.0217132568359375,
-0.040679931640625,
0.0013427734375,
0.0325927734375,
0.005901336669921875,
0.03253173828125,
0.0215301513671875,
0.056915283203125,
0.08392333984375,
-0.0183258056640625,
0.042724609375,
-0.03546142578125,
0.0193939208984375,
0.065185546875,
-0.018585205078125,
0.00872802734375,
0.0071563720703125,
0.00554656982421875,
0.050201416015625,
0.047515869140625,
-0.0182342529296875,
0.06524658203125,
-0.0019893646240234375,
-0.018463134765625,
0.0022029876708984375,
-0.005725860595703125,
-0.05963134765625,
0.03369140625,
0.0211639404296875,
-0.0780029296875,
-0.016937255859375,
0.00908660888671875,
0.00496673583984375,
-0.0288848876953125,
0.0124664306640625,
0.061279296875,
-0.01116180419921875,
-0.037445068359375,
0.06329345703125,
0.006816864013671875,
0.0220947265625,
-0.044830322265625,
0.0091552734375,
-0.0236968994140625,
0.048431396484375,
-0.0304718017578125,
-0.0222015380859375,
0.048736572265625,
-0.0267791748046875,
-0.0251617431640625,
-0.0129547119140625,
0.04541015625,
-0.006252288818359375,
-0.038330078125,
-0.0023097991943359375,
0.01210784912109375,
0.01313018798828125,
0.0141448974609375,
-0.035919189453125,
0.023468017578125,
-0.00649261474609375,
-0.0006771087646484375,
0.0165252685546875,
0.03765869140625,
-0.029754638671875,
0.03814697265625,
0.02471923828125,
-0.0132598876953125,
-0.0251922607421875,
0.020172119140625,
0.06182861328125,
-0.01556396484375,
-0.04241943359375,
-0.045806884765625,
0.021240234375,
-0.0109405517578125,
-0.0227203369140625,
0.0310821533203125,
0.06976318359375,
0.047607421875,
-0.0012636184692382812,
0.053253173828125,
-0.0215606689453125,
0.038726806640625,
-0.00667572021484375,
0.051025390625,
-0.01395416259765625,
0.03753662109375,
-0.026947021484375,
-0.04351806640625,
-0.03912353515625,
0.0509033203125,
-0.037689208984375,
-0.006999969482421875,
0.0616455078125,
0.0711669921875,
-0.03338623046875,
-0.004024505615234375,
0.0012960433959960938,
-0.00722503662109375,
0.0307769775390625,
0.036285400390625,
0.027191162109375,
-0.059844970703125,
0.038970947265625,
-0.05145263671875,
-0.041473388671875,
-0.02520751953125,
-0.05517578125,
-0.04547119140625,
-0.05511474609375,
-0.07806396484375,
-0.0183258056640625,
0.0008726119995117188,
0.026611328125,
0.06964111328125,
-0.047027587890625,
0.01171112060546875,
0.0031795501708984375,
-0.01326751708984375,
-0.0247650146484375,
-0.0180511474609375,
0.0662841796875,
0.0092620849609375,
-0.05938720703125,
0.032989501953125,
0.039215087890625,
0.00823974609375,
-0.022064208984375,
0.01219940185546875,
0.0022792816162109375,
-0.01468658447265625,
0.01163482666015625,
0.037445068359375,
-0.04541015625,
-0.006763458251953125,
-0.0130767822265625,
-0.04998779296875,
0.002796173095703125,
0.048919677734375,
-0.07733154296875,
0.039031982421875,
0.054473876953125,
0.0240325927734375,
0.03271484375,
-0.00135040283203125,
0.0024471282958984375,
-0.0281219482421875,
0.0217132568359375,
0.0188446044921875,
0.00717926025390625,
0.0198211669921875,
-0.05267333984375,
0.057586669921875,
0.0411376953125,
-0.024383544921875,
-0.07049560546875,
-0.0186309814453125,
-0.059295654296875,
-0.008056640625,
0.05023193359375,
-0.00823211669921875,
-0.0149688720703125,
-0.00884246826171875,
0.0029621124267578125,
0.0224151611328125,
-0.0051422119140625,
0.09295654296875,
-0.0008840560913085938,
-0.00966644287109375,
-0.0078277587890625,
0.0003426074981689453,
0.0306396484375,
-0.0005259513854980469,
-0.0650634765625,
0.0033130645751953125,
0.045806884765625,
0.0197296142578125,
0.032470703125,
0.07940673828125,
-0.030029296875,
0.041595458984375,
-0.02587890625,
-0.01026153564453125,
-0.024871826171875,
-0.030914306640625,
-0.03277587890625,
-0.0011167526245117188,
-0.02197265625,
-0.037322998046875
]
] |
jinaai/jina-embeddings-v2-base-en | 2023-11-03T18:11:58.000Z | [
"sentence-transformers",
"pytorch",
"coreml",
"onnx",
"safetensors",
"bert",
"finetuner",
"mteb",
"feature-extraction",
"sentence-similarity",
"alibi",
"custom_code",
"en",
"dataset:allenai/c4",
"arxiv:2108.12409",
"arxiv:2310.19923",
"arxiv:2307.11224",
"license:apache-2.0",
"model-index",
"has_space",
"region:us"
] | feature-extraction | jinaai | null | null | jinaai/jina-embeddings-v2-base-en | 413 | 46,988 | sentence-transformers | 2023-09-27T17:04:00 | ---
tags:
- finetuner
- mteb
- sentence-transformers
- feature-extraction
- sentence-similarity
- alibi
datasets:
- allenai/c4
language: en
inference: false
license: apache-2.0
model-index:
- name: jina-embedding-b-en-v2
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 74.73134328358209
- type: ap
value: 37.765427081831035
- type: f1
value: 68.79367444339518
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 88.544275
- type: ap
value: 84.61328675662887
- type: f1
value: 88.51879035862375
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 45.263999999999996
- type: f1
value: 43.778759656699435
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.693
- type: map_at_10
value: 35.487
- type: map_at_100
value: 36.862
- type: map_at_1000
value: 36.872
- type: map_at_3
value: 30.049999999999997
- type: map_at_5
value: 32.966
- type: mrr_at_1
value: 21.977
- type: mrr_at_10
value: 35.565999999999995
- type: mrr_at_100
value: 36.948
- type: mrr_at_1000
value: 36.958
- type: mrr_at_3
value: 30.121
- type: mrr_at_5
value: 33.051
- type: ndcg_at_1
value: 21.693
- type: ndcg_at_10
value: 44.181
- type: ndcg_at_100
value: 49.982
- type: ndcg_at_1000
value: 50.233000000000004
- type: ndcg_at_3
value: 32.830999999999996
- type: ndcg_at_5
value: 38.080000000000005
- type: precision_at_1
value: 21.693
- type: precision_at_10
value: 7.248
- type: precision_at_100
value: 0.9769999999999999
- type: precision_at_1000
value: 0.1
- type: precision_at_3
value: 13.632
- type: precision_at_5
value: 10.725
- type: recall_at_1
value: 21.693
- type: recall_at_10
value: 72.475
- type: recall_at_100
value: 97.653
- type: recall_at_1000
value: 99.57300000000001
- type: recall_at_3
value: 40.896
- type: recall_at_5
value: 53.627
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 45.39242428696777
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 36.675626784714
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 62.247725694904034
- type: mrr
value: 74.91359978894604
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 82.68003802970496
- type: cos_sim_spearman
value: 81.23438110096286
- type: euclidean_pearson
value: 81.87462986142582
- type: euclidean_spearman
value: 81.23438110096286
- type: manhattan_pearson
value: 81.61162566600755
- type: manhattan_spearman
value: 81.11329400456184
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 84.01298701298701
- type: f1
value: 83.31690714969382
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 37.050108150972086
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 30.15731442819715
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 31.391999999999996
- type: map_at_10
value: 42.597
- type: map_at_100
value: 44.07
- type: map_at_1000
value: 44.198
- type: map_at_3
value: 38.957
- type: map_at_5
value: 40.961
- type: mrr_at_1
value: 37.196
- type: mrr_at_10
value: 48.152
- type: mrr_at_100
value: 48.928
- type: mrr_at_1000
value: 48.964999999999996
- type: mrr_at_3
value: 45.446
- type: mrr_at_5
value: 47.205999999999996
- type: ndcg_at_1
value: 37.196
- type: ndcg_at_10
value: 49.089
- type: ndcg_at_100
value: 54.471000000000004
- type: ndcg_at_1000
value: 56.385
- type: ndcg_at_3
value: 43.699
- type: ndcg_at_5
value: 46.22
- type: precision_at_1
value: 37.196
- type: precision_at_10
value: 9.313
- type: precision_at_100
value: 1.478
- type: precision_at_1000
value: 0.198
- type: precision_at_3
value: 20.839
- type: precision_at_5
value: 14.936
- type: recall_at_1
value: 31.391999999999996
- type: recall_at_10
value: 61.876
- type: recall_at_100
value: 84.214
- type: recall_at_1000
value: 95.985
- type: recall_at_3
value: 46.6
- type: recall_at_5
value: 53.588
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 29.083
- type: map_at_10
value: 38.812999999999995
- type: map_at_100
value: 40.053
- type: map_at_1000
value: 40.188
- type: map_at_3
value: 36.111
- type: map_at_5
value: 37.519000000000005
- type: mrr_at_1
value: 36.497
- type: mrr_at_10
value: 44.85
- type: mrr_at_100
value: 45.546
- type: mrr_at_1000
value: 45.593
- type: mrr_at_3
value: 42.686
- type: mrr_at_5
value: 43.909
- type: ndcg_at_1
value: 36.497
- type: ndcg_at_10
value: 44.443
- type: ndcg_at_100
value: 48.979
- type: ndcg_at_1000
value: 51.154999999999994
- type: ndcg_at_3
value: 40.660000000000004
- type: ndcg_at_5
value: 42.193000000000005
- type: precision_at_1
value: 36.497
- type: precision_at_10
value: 8.433
- type: precision_at_100
value: 1.369
- type: precision_at_1000
value: 0.185
- type: precision_at_3
value: 19.894000000000002
- type: precision_at_5
value: 13.873
- type: recall_at_1
value: 29.083
- type: recall_at_10
value: 54.313
- type: recall_at_100
value: 73.792
- type: recall_at_1000
value: 87.629
- type: recall_at_3
value: 42.257
- type: recall_at_5
value: 47.066
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 38.556000000000004
- type: map_at_10
value: 50.698
- type: map_at_100
value: 51.705
- type: map_at_1000
value: 51.768
- type: map_at_3
value: 47.848
- type: map_at_5
value: 49.358000000000004
- type: mrr_at_1
value: 43.95
- type: mrr_at_10
value: 54.191
- type: mrr_at_100
value: 54.852999999999994
- type: mrr_at_1000
value: 54.885
- type: mrr_at_3
value: 51.954
- type: mrr_at_5
value: 53.13
- type: ndcg_at_1
value: 43.95
- type: ndcg_at_10
value: 56.516
- type: ndcg_at_100
value: 60.477000000000004
- type: ndcg_at_1000
value: 61.746
- type: ndcg_at_3
value: 51.601
- type: ndcg_at_5
value: 53.795
- type: precision_at_1
value: 43.95
- type: precision_at_10
value: 9.009
- type: precision_at_100
value: 1.189
- type: precision_at_1000
value: 0.135
- type: precision_at_3
value: 22.989
- type: precision_at_5
value: 15.473
- type: recall_at_1
value: 38.556000000000004
- type: recall_at_10
value: 70.159
- type: recall_at_100
value: 87.132
- type: recall_at_1000
value: 96.16
- type: recall_at_3
value: 56.906
- type: recall_at_5
value: 62.332
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.238
- type: map_at_10
value: 32.5
- type: map_at_100
value: 33.637
- type: map_at_1000
value: 33.719
- type: map_at_3
value: 30.026999999999997
- type: map_at_5
value: 31.555
- type: mrr_at_1
value: 26.328000000000003
- type: mrr_at_10
value: 34.44
- type: mrr_at_100
value: 35.455999999999996
- type: mrr_at_1000
value: 35.521
- type: mrr_at_3
value: 32.034
- type: mrr_at_5
value: 33.565
- type: ndcg_at_1
value: 26.328000000000003
- type: ndcg_at_10
value: 37.202
- type: ndcg_at_100
value: 42.728
- type: ndcg_at_1000
value: 44.792
- type: ndcg_at_3
value: 32.368
- type: ndcg_at_5
value: 35.008
- type: precision_at_1
value: 26.328000000000003
- type: precision_at_10
value: 5.7059999999999995
- type: precision_at_100
value: 0.8880000000000001
- type: precision_at_1000
value: 0.11100000000000002
- type: precision_at_3
value: 13.672
- type: precision_at_5
value: 9.74
- type: recall_at_1
value: 24.238
- type: recall_at_10
value: 49.829
- type: recall_at_100
value: 75.21
- type: recall_at_1000
value: 90.521
- type: recall_at_3
value: 36.867
- type: recall_at_5
value: 43.241
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 15.378
- type: map_at_10
value: 22.817999999999998
- type: map_at_100
value: 23.977999999999998
- type: map_at_1000
value: 24.108
- type: map_at_3
value: 20.719
- type: map_at_5
value: 21.889
- type: mrr_at_1
value: 19.03
- type: mrr_at_10
value: 27.022000000000002
- type: mrr_at_100
value: 28.011999999999997
- type: mrr_at_1000
value: 28.096
- type: mrr_at_3
value: 24.855
- type: mrr_at_5
value: 26.029999999999998
- type: ndcg_at_1
value: 19.03
- type: ndcg_at_10
value: 27.526
- type: ndcg_at_100
value: 33.040000000000006
- type: ndcg_at_1000
value: 36.187000000000005
- type: ndcg_at_3
value: 23.497
- type: ndcg_at_5
value: 25.334
- type: precision_at_1
value: 19.03
- type: precision_at_10
value: 4.963
- type: precision_at_100
value: 0.893
- type: precision_at_1000
value: 0.13
- type: precision_at_3
value: 11.360000000000001
- type: precision_at_5
value: 8.134
- type: recall_at_1
value: 15.378
- type: recall_at_10
value: 38.061
- type: recall_at_100
value: 61.754
- type: recall_at_1000
value: 84.259
- type: recall_at_3
value: 26.788
- type: recall_at_5
value: 31.326999999999998
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 27.511999999999997
- type: map_at_10
value: 37.429
- type: map_at_100
value: 38.818000000000005
- type: map_at_1000
value: 38.924
- type: map_at_3
value: 34.625
- type: map_at_5
value: 36.064
- type: mrr_at_1
value: 33.300999999999995
- type: mrr_at_10
value: 43.036
- type: mrr_at_100
value: 43.894
- type: mrr_at_1000
value: 43.936
- type: mrr_at_3
value: 40.825
- type: mrr_at_5
value: 42.028
- type: ndcg_at_1
value: 33.300999999999995
- type: ndcg_at_10
value: 43.229
- type: ndcg_at_100
value: 48.992000000000004
- type: ndcg_at_1000
value: 51.02100000000001
- type: ndcg_at_3
value: 38.794000000000004
- type: ndcg_at_5
value: 40.65
- type: precision_at_1
value: 33.300999999999995
- type: precision_at_10
value: 7.777000000000001
- type: precision_at_100
value: 1.269
- type: precision_at_1000
value: 0.163
- type: precision_at_3
value: 18.351
- type: precision_at_5
value: 12.762
- type: recall_at_1
value: 27.511999999999997
- type: recall_at_10
value: 54.788000000000004
- type: recall_at_100
value: 79.105
- type: recall_at_1000
value: 92.49199999999999
- type: recall_at_3
value: 41.924
- type: recall_at_5
value: 47.026
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.117
- type: map_at_10
value: 33.32
- type: map_at_100
value: 34.677
- type: map_at_1000
value: 34.78
- type: map_at_3
value: 30.233999999999998
- type: map_at_5
value: 31.668000000000003
- type: mrr_at_1
value: 29.566
- type: mrr_at_10
value: 38.244
- type: mrr_at_100
value: 39.245000000000005
- type: mrr_at_1000
value: 39.296
- type: mrr_at_3
value: 35.864000000000004
- type: mrr_at_5
value: 36.919999999999995
- type: ndcg_at_1
value: 29.566
- type: ndcg_at_10
value: 39.127
- type: ndcg_at_100
value: 44.989000000000004
- type: ndcg_at_1000
value: 47.189
- type: ndcg_at_3
value: 34.039
- type: ndcg_at_5
value: 35.744
- type: precision_at_1
value: 29.566
- type: precision_at_10
value: 7.385999999999999
- type: precision_at_100
value: 1.204
- type: precision_at_1000
value: 0.158
- type: precision_at_3
value: 16.286
- type: precision_at_5
value: 11.484
- type: recall_at_1
value: 24.117
- type: recall_at_10
value: 51.559999999999995
- type: recall_at_100
value: 77.104
- type: recall_at_1000
value: 91.79899999999999
- type: recall_at_3
value: 36.82
- type: recall_at_5
value: 41.453
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.17625
- type: map_at_10
value: 34.063916666666664
- type: map_at_100
value: 35.255500000000005
- type: map_at_1000
value: 35.37275
- type: map_at_3
value: 31.351666666666667
- type: map_at_5
value: 32.80608333333333
- type: mrr_at_1
value: 29.59783333333333
- type: mrr_at_10
value: 38.0925
- type: mrr_at_100
value: 38.957249999999995
- type: mrr_at_1000
value: 39.01608333333333
- type: mrr_at_3
value: 35.77625
- type: mrr_at_5
value: 37.04991666666667
- type: ndcg_at_1
value: 29.59783333333333
- type: ndcg_at_10
value: 39.343666666666664
- type: ndcg_at_100
value: 44.488249999999994
- type: ndcg_at_1000
value: 46.83358333333334
- type: ndcg_at_3
value: 34.69708333333333
- type: ndcg_at_5
value: 36.75075
- type: precision_at_1
value: 29.59783333333333
- type: precision_at_10
value: 6.884083333333332
- type: precision_at_100
value: 1.114
- type: precision_at_1000
value: 0.15108333333333332
- type: precision_at_3
value: 15.965250000000003
- type: precision_at_5
value: 11.246500000000001
- type: recall_at_1
value: 25.17625
- type: recall_at_10
value: 51.015999999999984
- type: recall_at_100
value: 73.60174999999998
- type: recall_at_1000
value: 89.849
- type: recall_at_3
value: 37.88399999999999
- type: recall_at_5
value: 43.24541666666666
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.537
- type: map_at_10
value: 31.081999999999997
- type: map_at_100
value: 32.042
- type: map_at_1000
value: 32.141
- type: map_at_3
value: 29.137
- type: map_at_5
value: 30.079
- type: mrr_at_1
value: 27.454
- type: mrr_at_10
value: 33.694
- type: mrr_at_100
value: 34.579
- type: mrr_at_1000
value: 34.649
- type: mrr_at_3
value: 32.004
- type: mrr_at_5
value: 32.794000000000004
- type: ndcg_at_1
value: 27.454
- type: ndcg_at_10
value: 34.915
- type: ndcg_at_100
value: 39.641
- type: ndcg_at_1000
value: 42.105
- type: ndcg_at_3
value: 31.276
- type: ndcg_at_5
value: 32.65
- type: precision_at_1
value: 27.454
- type: precision_at_10
value: 5.337
- type: precision_at_100
value: 0.8250000000000001
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 13.241
- type: precision_at_5
value: 8.895999999999999
- type: recall_at_1
value: 24.537
- type: recall_at_10
value: 44.324999999999996
- type: recall_at_100
value: 65.949
- type: recall_at_1000
value: 84.017
- type: recall_at_3
value: 33.857
- type: recall_at_5
value: 37.316
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 17.122
- type: map_at_10
value: 24.32
- type: map_at_100
value: 25.338
- type: map_at_1000
value: 25.462
- type: map_at_3
value: 22.064
- type: map_at_5
value: 23.322000000000003
- type: mrr_at_1
value: 20.647
- type: mrr_at_10
value: 27.858
- type: mrr_at_100
value: 28.743999999999996
- type: mrr_at_1000
value: 28.819
- type: mrr_at_3
value: 25.769
- type: mrr_at_5
value: 26.964
- type: ndcg_at_1
value: 20.647
- type: ndcg_at_10
value: 28.849999999999998
- type: ndcg_at_100
value: 33.849000000000004
- type: ndcg_at_1000
value: 36.802
- type: ndcg_at_3
value: 24.799
- type: ndcg_at_5
value: 26.682
- type: precision_at_1
value: 20.647
- type: precision_at_10
value: 5.2170000000000005
- type: precision_at_100
value: 0.906
- type: precision_at_1000
value: 0.134
- type: precision_at_3
value: 11.769
- type: precision_at_5
value: 8.486
- type: recall_at_1
value: 17.122
- type: recall_at_10
value: 38.999
- type: recall_at_100
value: 61.467000000000006
- type: recall_at_1000
value: 82.716
- type: recall_at_3
value: 27.601
- type: recall_at_5
value: 32.471
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.396
- type: map_at_10
value: 33.415
- type: map_at_100
value: 34.521
- type: map_at_1000
value: 34.631
- type: map_at_3
value: 30.703999999999997
- type: map_at_5
value: 32.166
- type: mrr_at_1
value: 28.825
- type: mrr_at_10
value: 37.397000000000006
- type: mrr_at_100
value: 38.286
- type: mrr_at_1000
value: 38.346000000000004
- type: mrr_at_3
value: 35.028
- type: mrr_at_5
value: 36.32
- type: ndcg_at_1
value: 28.825
- type: ndcg_at_10
value: 38.656
- type: ndcg_at_100
value: 43.856
- type: ndcg_at_1000
value: 46.31
- type: ndcg_at_3
value: 33.793
- type: ndcg_at_5
value: 35.909
- type: precision_at_1
value: 28.825
- type: precision_at_10
value: 6.567
- type: precision_at_100
value: 1.0330000000000001
- type: precision_at_1000
value: 0.135
- type: precision_at_3
value: 15.516
- type: precision_at_5
value: 10.914
- type: recall_at_1
value: 24.396
- type: recall_at_10
value: 50.747
- type: recall_at_100
value: 73.477
- type: recall_at_1000
value: 90.801
- type: recall_at_3
value: 37.1
- type: recall_at_5
value: 42.589
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.072
- type: map_at_10
value: 34.307
- type: map_at_100
value: 35.725
- type: map_at_1000
value: 35.943999999999996
- type: map_at_3
value: 30.906
- type: map_at_5
value: 32.818000000000005
- type: mrr_at_1
value: 29.644
- type: mrr_at_10
value: 38.673
- type: mrr_at_100
value: 39.459
- type: mrr_at_1000
value: 39.527
- type: mrr_at_3
value: 35.771
- type: mrr_at_5
value: 37.332
- type: ndcg_at_1
value: 29.644
- type: ndcg_at_10
value: 40.548
- type: ndcg_at_100
value: 45.678999999999995
- type: ndcg_at_1000
value: 48.488
- type: ndcg_at_3
value: 34.887
- type: ndcg_at_5
value: 37.543
- type: precision_at_1
value: 29.644
- type: precision_at_10
value: 7.688000000000001
- type: precision_at_100
value: 1.482
- type: precision_at_1000
value: 0.23600000000000002
- type: precision_at_3
value: 16.206
- type: precision_at_5
value: 12.016
- type: recall_at_1
value: 25.072
- type: recall_at_10
value: 53.478
- type: recall_at_100
value: 76.07300000000001
- type: recall_at_1000
value: 93.884
- type: recall_at_3
value: 37.583
- type: recall_at_5
value: 44.464
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 20.712
- type: map_at_10
value: 27.467999999999996
- type: map_at_100
value: 28.502
- type: map_at_1000
value: 28.610000000000003
- type: map_at_3
value: 24.887999999999998
- type: map_at_5
value: 26.273999999999997
- type: mrr_at_1
value: 22.736
- type: mrr_at_10
value: 29.553
- type: mrr_at_100
value: 30.485
- type: mrr_at_1000
value: 30.56
- type: mrr_at_3
value: 27.078999999999997
- type: mrr_at_5
value: 28.401
- type: ndcg_at_1
value: 22.736
- type: ndcg_at_10
value: 32.023
- type: ndcg_at_100
value: 37.158
- type: ndcg_at_1000
value: 39.823
- type: ndcg_at_3
value: 26.951999999999998
- type: ndcg_at_5
value: 29.281000000000002
- type: precision_at_1
value: 22.736
- type: precision_at_10
value: 5.213
- type: precision_at_100
value: 0.832
- type: precision_at_1000
value: 0.116
- type: precision_at_3
value: 11.459999999999999
- type: precision_at_5
value: 8.244
- type: recall_at_1
value: 20.712
- type: recall_at_10
value: 44.057
- type: recall_at_100
value: 67.944
- type: recall_at_1000
value: 87.925
- type: recall_at_3
value: 30.305
- type: recall_at_5
value: 36.071999999999996
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 10.181999999999999
- type: map_at_10
value: 16.66
- type: map_at_100
value: 18.273
- type: map_at_1000
value: 18.45
- type: map_at_3
value: 14.141
- type: map_at_5
value: 15.455
- type: mrr_at_1
value: 22.15
- type: mrr_at_10
value: 32.062000000000005
- type: mrr_at_100
value: 33.116
- type: mrr_at_1000
value: 33.168
- type: mrr_at_3
value: 28.827
- type: mrr_at_5
value: 30.892999999999997
- type: ndcg_at_1
value: 22.15
- type: ndcg_at_10
value: 23.532
- type: ndcg_at_100
value: 30.358
- type: ndcg_at_1000
value: 33.783
- type: ndcg_at_3
value: 19.222
- type: ndcg_at_5
value: 20.919999999999998
- type: precision_at_1
value: 22.15
- type: precision_at_10
value: 7.185999999999999
- type: precision_at_100
value: 1.433
- type: precision_at_1000
value: 0.207
- type: precision_at_3
value: 13.941
- type: precision_at_5
value: 10.906
- type: recall_at_1
value: 10.181999999999999
- type: recall_at_10
value: 28.104000000000003
- type: recall_at_100
value: 51.998999999999995
- type: recall_at_1000
value: 71.311
- type: recall_at_3
value: 17.698
- type: recall_at_5
value: 22.262999999999998
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 6.669
- type: map_at_10
value: 15.552
- type: map_at_100
value: 21.865000000000002
- type: map_at_1000
value: 23.268
- type: map_at_3
value: 11.309
- type: map_at_5
value: 13.084000000000001
- type: mrr_at_1
value: 55.50000000000001
- type: mrr_at_10
value: 66.46600000000001
- type: mrr_at_100
value: 66.944
- type: mrr_at_1000
value: 66.956
- type: mrr_at_3
value: 64.542
- type: mrr_at_5
value: 65.717
- type: ndcg_at_1
value: 44.75
- type: ndcg_at_10
value: 35.049
- type: ndcg_at_100
value: 39.073
- type: ndcg_at_1000
value: 46.208
- type: ndcg_at_3
value: 39.525
- type: ndcg_at_5
value: 37.156
- type: precision_at_1
value: 55.50000000000001
- type: precision_at_10
value: 27.800000000000004
- type: precision_at_100
value: 9.013
- type: precision_at_1000
value: 1.8800000000000001
- type: precision_at_3
value: 42.667
- type: precision_at_5
value: 36.0
- type: recall_at_1
value: 6.669
- type: recall_at_10
value: 21.811
- type: recall_at_100
value: 45.112
- type: recall_at_1000
value: 67.806
- type: recall_at_3
value: 13.373
- type: recall_at_5
value: 16.615
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 48.769999999999996
- type: f1
value: 42.91448356376592
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 54.013
- type: map_at_10
value: 66.239
- type: map_at_100
value: 66.62599999999999
- type: map_at_1000
value: 66.644
- type: map_at_3
value: 63.965
- type: map_at_5
value: 65.45400000000001
- type: mrr_at_1
value: 58.221000000000004
- type: mrr_at_10
value: 70.43700000000001
- type: mrr_at_100
value: 70.744
- type: mrr_at_1000
value: 70.75099999999999
- type: mrr_at_3
value: 68.284
- type: mrr_at_5
value: 69.721
- type: ndcg_at_1
value: 58.221000000000004
- type: ndcg_at_10
value: 72.327
- type: ndcg_at_100
value: 73.953
- type: ndcg_at_1000
value: 74.312
- type: ndcg_at_3
value: 68.062
- type: ndcg_at_5
value: 70.56400000000001
- type: precision_at_1
value: 58.221000000000004
- type: precision_at_10
value: 9.521
- type: precision_at_100
value: 1.045
- type: precision_at_1000
value: 0.109
- type: precision_at_3
value: 27.348
- type: precision_at_5
value: 17.794999999999998
- type: recall_at_1
value: 54.013
- type: recall_at_10
value: 86.957
- type: recall_at_100
value: 93.911
- type: recall_at_1000
value: 96.38
- type: recall_at_3
value: 75.555
- type: recall_at_5
value: 81.671
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.254
- type: map_at_10
value: 33.723
- type: map_at_100
value: 35.574
- type: map_at_1000
value: 35.730000000000004
- type: map_at_3
value: 29.473
- type: map_at_5
value: 31.543
- type: mrr_at_1
value: 41.358
- type: mrr_at_10
value: 49.498
- type: mrr_at_100
value: 50.275999999999996
- type: mrr_at_1000
value: 50.308
- type: mrr_at_3
value: 47.016000000000005
- type: mrr_at_5
value: 48.336
- type: ndcg_at_1
value: 41.358
- type: ndcg_at_10
value: 41.579
- type: ndcg_at_100
value: 48.455
- type: ndcg_at_1000
value: 51.165000000000006
- type: ndcg_at_3
value: 37.681
- type: ndcg_at_5
value: 38.49
- type: precision_at_1
value: 41.358
- type: precision_at_10
value: 11.543000000000001
- type: precision_at_100
value: 1.87
- type: precision_at_1000
value: 0.23600000000000002
- type: precision_at_3
value: 24.743000000000002
- type: precision_at_5
value: 17.994
- type: recall_at_1
value: 21.254
- type: recall_at_10
value: 48.698
- type: recall_at_100
value: 74.588
- type: recall_at_1000
value: 91.00200000000001
- type: recall_at_3
value: 33.939
- type: recall_at_5
value: 39.367000000000004
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 35.922
- type: map_at_10
value: 52.32599999999999
- type: map_at_100
value: 53.18000000000001
- type: map_at_1000
value: 53.245
- type: map_at_3
value: 49.294
- type: map_at_5
value: 51.202999999999996
- type: mrr_at_1
value: 71.843
- type: mrr_at_10
value: 78.24600000000001
- type: mrr_at_100
value: 78.515
- type: mrr_at_1000
value: 78.527
- type: mrr_at_3
value: 77.17500000000001
- type: mrr_at_5
value: 77.852
- type: ndcg_at_1
value: 71.843
- type: ndcg_at_10
value: 61.379
- type: ndcg_at_100
value: 64.535
- type: ndcg_at_1000
value: 65.888
- type: ndcg_at_3
value: 56.958
- type: ndcg_at_5
value: 59.434
- type: precision_at_1
value: 71.843
- type: precision_at_10
value: 12.686
- type: precision_at_100
value: 1.517
- type: precision_at_1000
value: 0.16999999999999998
- type: precision_at_3
value: 35.778
- type: precision_at_5
value: 23.422
- type: recall_at_1
value: 35.922
- type: recall_at_10
value: 63.43
- type: recall_at_100
value: 75.868
- type: recall_at_1000
value: 84.88900000000001
- type: recall_at_3
value: 53.666000000000004
- type: recall_at_5
value: 58.555
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 79.4408
- type: ap
value: 73.52820871620366
- type: f1
value: 79.36240238685001
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 21.826999999999998
- type: map_at_10
value: 34.04
- type: map_at_100
value: 35.226
- type: map_at_1000
value: 35.275
- type: map_at_3
value: 30.165999999999997
- type: map_at_5
value: 32.318000000000005
- type: mrr_at_1
value: 22.464000000000002
- type: mrr_at_10
value: 34.631
- type: mrr_at_100
value: 35.752
- type: mrr_at_1000
value: 35.795
- type: mrr_at_3
value: 30.798
- type: mrr_at_5
value: 32.946999999999996
- type: ndcg_at_1
value: 22.464000000000002
- type: ndcg_at_10
value: 40.919
- type: ndcg_at_100
value: 46.632
- type: ndcg_at_1000
value: 47.833
- type: ndcg_at_3
value: 32.992
- type: ndcg_at_5
value: 36.834
- type: precision_at_1
value: 22.464000000000002
- type: precision_at_10
value: 6.494
- type: precision_at_100
value: 0.9369999999999999
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 14.021
- type: precision_at_5
value: 10.347000000000001
- type: recall_at_1
value: 21.826999999999998
- type: recall_at_10
value: 62.132
- type: recall_at_100
value: 88.55199999999999
- type: recall_at_1000
value: 97.707
- type: recall_at_3
value: 40.541
- type: recall_at_5
value: 49.739
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 95.68399452804377
- type: f1
value: 95.25490609832268
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 83.15321477428182
- type: f1
value: 60.35476439087966
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.92669804976462
- type: f1
value: 69.22815107207565
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.4855413584398
- type: f1
value: 72.92107516103387
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 32.412679360205544
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 28.09211869875204
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 30.540919056982545
- type: mrr
value: 31.529904607063536
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.745
- type: map_at_10
value: 12.013
- type: map_at_100
value: 15.040000000000001
- type: map_at_1000
value: 16.427
- type: map_at_3
value: 8.841000000000001
- type: map_at_5
value: 10.289
- type: mrr_at_1
value: 45.201
- type: mrr_at_10
value: 53.483999999999995
- type: mrr_at_100
value: 54.20700000000001
- type: mrr_at_1000
value: 54.252
- type: mrr_at_3
value: 51.29
- type: mrr_at_5
value: 52.73
- type: ndcg_at_1
value: 43.808
- type: ndcg_at_10
value: 32.445
- type: ndcg_at_100
value: 30.031000000000002
- type: ndcg_at_1000
value: 39.007
- type: ndcg_at_3
value: 37.204
- type: ndcg_at_5
value: 35.07
- type: precision_at_1
value: 45.201
- type: precision_at_10
value: 23.684
- type: precision_at_100
value: 7.600999999999999
- type: precision_at_1000
value: 2.043
- type: precision_at_3
value: 33.953
- type: precision_at_5
value: 29.412
- type: recall_at_1
value: 5.745
- type: recall_at_10
value: 16.168
- type: recall_at_100
value: 30.875999999999998
- type: recall_at_1000
value: 62.686
- type: recall_at_3
value: 9.75
- type: recall_at_5
value: 12.413
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 37.828
- type: map_at_10
value: 53.239000000000004
- type: map_at_100
value: 54.035999999999994
- type: map_at_1000
value: 54.067
- type: map_at_3
value: 49.289
- type: map_at_5
value: 51.784
- type: mrr_at_1
value: 42.497
- type: mrr_at_10
value: 55.916999999999994
- type: mrr_at_100
value: 56.495
- type: mrr_at_1000
value: 56.516999999999996
- type: mrr_at_3
value: 52.800000000000004
- type: mrr_at_5
value: 54.722
- type: ndcg_at_1
value: 42.468
- type: ndcg_at_10
value: 60.437
- type: ndcg_at_100
value: 63.731
- type: ndcg_at_1000
value: 64.41799999999999
- type: ndcg_at_3
value: 53.230999999999995
- type: ndcg_at_5
value: 57.26
- type: precision_at_1
value: 42.468
- type: precision_at_10
value: 9.47
- type: precision_at_100
value: 1.1360000000000001
- type: precision_at_1000
value: 0.12
- type: precision_at_3
value: 23.724999999999998
- type: precision_at_5
value: 16.593
- type: recall_at_1
value: 37.828
- type: recall_at_10
value: 79.538
- type: recall_at_100
value: 93.646
- type: recall_at_1000
value: 98.72999999999999
- type: recall_at_3
value: 61.134
- type: recall_at_5
value: 70.377
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 70.548
- type: map_at_10
value: 84.466
- type: map_at_100
value: 85.10600000000001
- type: map_at_1000
value: 85.123
- type: map_at_3
value: 81.57600000000001
- type: map_at_5
value: 83.399
- type: mrr_at_1
value: 81.24
- type: mrr_at_10
value: 87.457
- type: mrr_at_100
value: 87.574
- type: mrr_at_1000
value: 87.575
- type: mrr_at_3
value: 86.507
- type: mrr_at_5
value: 87.205
- type: ndcg_at_1
value: 81.25
- type: ndcg_at_10
value: 88.203
- type: ndcg_at_100
value: 89.457
- type: ndcg_at_1000
value: 89.563
- type: ndcg_at_3
value: 85.465
- type: ndcg_at_5
value: 87.007
- type: precision_at_1
value: 81.25
- type: precision_at_10
value: 13.373
- type: precision_at_100
value: 1.5270000000000001
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.417
- type: precision_at_5
value: 24.556
- type: recall_at_1
value: 70.548
- type: recall_at_10
value: 95.208
- type: recall_at_100
value: 99.514
- type: recall_at_1000
value: 99.988
- type: recall_at_3
value: 87.214
- type: recall_at_5
value: 91.696
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 53.04822095496839
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 60.30778476474675
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.692
- type: map_at_10
value: 11.766
- type: map_at_100
value: 13.904
- type: map_at_1000
value: 14.216999999999999
- type: map_at_3
value: 8.245
- type: map_at_5
value: 9.92
- type: mrr_at_1
value: 23.0
- type: mrr_at_10
value: 33.78
- type: mrr_at_100
value: 34.922
- type: mrr_at_1000
value: 34.973
- type: mrr_at_3
value: 30.2
- type: mrr_at_5
value: 32.565
- type: ndcg_at_1
value: 23.0
- type: ndcg_at_10
value: 19.863
- type: ndcg_at_100
value: 28.141
- type: ndcg_at_1000
value: 33.549
- type: ndcg_at_3
value: 18.434
- type: ndcg_at_5
value: 16.384
- type: precision_at_1
value: 23.0
- type: precision_at_10
value: 10.39
- type: precision_at_100
value: 2.235
- type: precision_at_1000
value: 0.35300000000000004
- type: precision_at_3
value: 17.133000000000003
- type: precision_at_5
value: 14.44
- type: recall_at_1
value: 4.692
- type: recall_at_10
value: 21.025
- type: recall_at_100
value: 45.324999999999996
- type: recall_at_1000
value: 71.675
- type: recall_at_3
value: 10.440000000000001
- type: recall_at_5
value: 14.64
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 84.96178184892842
- type: cos_sim_spearman
value: 79.6487740813199
- type: euclidean_pearson
value: 82.06661161625023
- type: euclidean_spearman
value: 79.64876769031183
- type: manhattan_pearson
value: 82.07061164575131
- type: manhattan_spearman
value: 79.65197039464537
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 84.15305604100027
- type: cos_sim_spearman
value: 74.27447427941591
- type: euclidean_pearson
value: 80.52737337565307
- type: euclidean_spearman
value: 74.27416077132192
- type: manhattan_pearson
value: 80.53728571140387
- type: manhattan_spearman
value: 74.28853605753457
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 83.44386080639279
- type: cos_sim_spearman
value: 84.17947648159536
- type: euclidean_pearson
value: 83.34145388129387
- type: euclidean_spearman
value: 84.17947648159536
- type: manhattan_pearson
value: 83.30699061927966
- type: manhattan_spearman
value: 84.18125737380451
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 81.57392220985612
- type: cos_sim_spearman
value: 78.80745014464101
- type: euclidean_pearson
value: 80.01660371487199
- type: euclidean_spearman
value: 78.80741240102256
- type: manhattan_pearson
value: 79.96810779507953
- type: manhattan_spearman
value: 78.75600400119448
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 86.85421063026625
- type: cos_sim_spearman
value: 87.55320285299192
- type: euclidean_pearson
value: 86.69750143323517
- type: euclidean_spearman
value: 87.55320284326378
- type: manhattan_pearson
value: 86.63379169960379
- type: manhattan_spearman
value: 87.4815029877984
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 84.31314130411842
- type: cos_sim_spearman
value: 85.3489588181433
- type: euclidean_pearson
value: 84.13240933463535
- type: euclidean_spearman
value: 85.34902871403281
- type: manhattan_pearson
value: 84.01183086503559
- type: manhattan_spearman
value: 85.19316703166102
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 89.09979781689536
- type: cos_sim_spearman
value: 88.87813323759015
- type: euclidean_pearson
value: 88.65413031123792
- type: euclidean_spearman
value: 88.87813323759015
- type: manhattan_pearson
value: 88.61818758256024
- type: manhattan_spearman
value: 88.81044100494604
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 62.30693258111531
- type: cos_sim_spearman
value: 62.195516523251946
- type: euclidean_pearson
value: 62.951283701049476
- type: euclidean_spearman
value: 62.195516523251946
- type: manhattan_pearson
value: 63.068322281439535
- type: manhattan_spearman
value: 62.10621171028406
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.27092833763909
- type: cos_sim_spearman
value: 84.84429717949759
- type: euclidean_pearson
value: 84.8516966060792
- type: euclidean_spearman
value: 84.84429717949759
- type: manhattan_pearson
value: 84.82203139242881
- type: manhattan_spearman
value: 84.8358503952945
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 83.10290863981409
- type: mrr
value: 95.31168450286097
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 52.161
- type: map_at_10
value: 62.138000000000005
- type: map_at_100
value: 62.769
- type: map_at_1000
value: 62.812
- type: map_at_3
value: 59.111000000000004
- type: map_at_5
value: 60.995999999999995
- type: mrr_at_1
value: 55.333
- type: mrr_at_10
value: 63.504000000000005
- type: mrr_at_100
value: 64.036
- type: mrr_at_1000
value: 64.08
- type: mrr_at_3
value: 61.278
- type: mrr_at_5
value: 62.778
- type: ndcg_at_1
value: 55.333
- type: ndcg_at_10
value: 66.678
- type: ndcg_at_100
value: 69.415
- type: ndcg_at_1000
value: 70.453
- type: ndcg_at_3
value: 61.755
- type: ndcg_at_5
value: 64.546
- type: precision_at_1
value: 55.333
- type: precision_at_10
value: 9.033
- type: precision_at_100
value: 1.043
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 24.221999999999998
- type: precision_at_5
value: 16.333000000000002
- type: recall_at_1
value: 52.161
- type: recall_at_10
value: 79.156
- type: recall_at_100
value: 91.333
- type: recall_at_1000
value: 99.333
- type: recall_at_3
value: 66.43299999999999
- type: recall_at_5
value: 73.272
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.81287128712871
- type: cos_sim_ap
value: 95.30034785910676
- type: cos_sim_f1
value: 90.28629856850716
- type: cos_sim_precision
value: 92.36401673640168
- type: cos_sim_recall
value: 88.3
- type: dot_accuracy
value: 99.81287128712871
- type: dot_ap
value: 95.30034785910676
- type: dot_f1
value: 90.28629856850716
- type: dot_precision
value: 92.36401673640168
- type: dot_recall
value: 88.3
- type: euclidean_accuracy
value: 99.81287128712871
- type: euclidean_ap
value: 95.30034785910676
- type: euclidean_f1
value: 90.28629856850716
- type: euclidean_precision
value: 92.36401673640168
- type: euclidean_recall
value: 88.3
- type: manhattan_accuracy
value: 99.80990099009901
- type: manhattan_ap
value: 95.26880751950654
- type: manhattan_f1
value: 90.22177419354838
- type: manhattan_precision
value: 90.95528455284553
- type: manhattan_recall
value: 89.5
- type: max_accuracy
value: 99.81287128712871
- type: max_ap
value: 95.30034785910676
- type: max_f1
value: 90.28629856850716
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 58.518662504351184
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 34.96168178378587
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 52.04862593471896
- type: mrr
value: 52.97238402936932
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 30.092545236479946
- type: cos_sim_spearman
value: 31.599851000175498
- type: dot_pearson
value: 30.092542723901676
- type: dot_spearman
value: 31.599851000175498
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.189
- type: map_at_10
value: 1.662
- type: map_at_100
value: 9.384
- type: map_at_1000
value: 22.669
- type: map_at_3
value: 0.5559999999999999
- type: map_at_5
value: 0.9039999999999999
- type: mrr_at_1
value: 68.0
- type: mrr_at_10
value: 81.01899999999999
- type: mrr_at_100
value: 81.01899999999999
- type: mrr_at_1000
value: 81.01899999999999
- type: mrr_at_3
value: 79.333
- type: mrr_at_5
value: 80.733
- type: ndcg_at_1
value: 63.0
- type: ndcg_at_10
value: 65.913
- type: ndcg_at_100
value: 51.895
- type: ndcg_at_1000
value: 46.967
- type: ndcg_at_3
value: 65.49199999999999
- type: ndcg_at_5
value: 66.69699999999999
- type: precision_at_1
value: 68.0
- type: precision_at_10
value: 71.6
- type: precision_at_100
value: 53.66
- type: precision_at_1000
value: 21.124000000000002
- type: precision_at_3
value: 72.667
- type: precision_at_5
value: 74.0
- type: recall_at_1
value: 0.189
- type: recall_at_10
value: 1.913
- type: recall_at_100
value: 12.601999999999999
- type: recall_at_1000
value: 44.296
- type: recall_at_3
value: 0.605
- type: recall_at_5
value: 1.018
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.701
- type: map_at_10
value: 10.445
- type: map_at_100
value: 17.324
- type: map_at_1000
value: 19.161
- type: map_at_3
value: 5.497
- type: map_at_5
value: 7.278
- type: mrr_at_1
value: 30.612000000000002
- type: mrr_at_10
value: 45.534
- type: mrr_at_100
value: 45.792
- type: mrr_at_1000
value: 45.806999999999995
- type: mrr_at_3
value: 37.755
- type: mrr_at_5
value: 43.469
- type: ndcg_at_1
value: 26.531
- type: ndcg_at_10
value: 26.235000000000003
- type: ndcg_at_100
value: 39.17
- type: ndcg_at_1000
value: 51.038
- type: ndcg_at_3
value: 23.625
- type: ndcg_at_5
value: 24.338
- type: precision_at_1
value: 30.612000000000002
- type: precision_at_10
value: 24.285999999999998
- type: precision_at_100
value: 8.224
- type: precision_at_1000
value: 1.6179999999999999
- type: precision_at_3
value: 24.490000000000002
- type: precision_at_5
value: 24.898
- type: recall_at_1
value: 2.701
- type: recall_at_10
value: 17.997
- type: recall_at_100
value: 51.766999999999996
- type: recall_at_1000
value: 87.863
- type: recall_at_3
value: 6.295000000000001
- type: recall_at_5
value: 9.993
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 73.3474
- type: ap
value: 15.393431414459924
- type: f1
value: 56.466681887882416
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 62.062818336163
- type: f1
value: 62.11230840463252
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 42.464892820845115
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 86.15962329379508
- type: cos_sim_ap
value: 74.73674057919256
- type: cos_sim_f1
value: 68.81245642574947
- type: cos_sim_precision
value: 61.48255813953488
- type: cos_sim_recall
value: 78.12664907651715
- type: dot_accuracy
value: 86.15962329379508
- type: dot_ap
value: 74.7367634988281
- type: dot_f1
value: 68.81245642574947
- type: dot_precision
value: 61.48255813953488
- type: dot_recall
value: 78.12664907651715
- type: euclidean_accuracy
value: 86.15962329379508
- type: euclidean_ap
value: 74.7367761466634
- type: euclidean_f1
value: 68.81245642574947
- type: euclidean_precision
value: 61.48255813953488
- type: euclidean_recall
value: 78.12664907651715
- type: manhattan_accuracy
value: 86.21326816474935
- type: manhattan_ap
value: 74.64416473733951
- type: manhattan_f1
value: 68.80924855491331
- type: manhattan_precision
value: 61.23456790123457
- type: manhattan_recall
value: 78.52242744063325
- type: max_accuracy
value: 86.21326816474935
- type: max_ap
value: 74.7367761466634
- type: max_f1
value: 68.81245642574947
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.97620988085536
- type: cos_sim_ap
value: 86.08680845745758
- type: cos_sim_f1
value: 78.02793637114438
- type: cos_sim_precision
value: 73.11082699683736
- type: cos_sim_recall
value: 83.65414228518632
- type: dot_accuracy
value: 88.97620988085536
- type: dot_ap
value: 86.08681149437946
- type: dot_f1
value: 78.02793637114438
- type: dot_precision
value: 73.11082699683736
- type: dot_recall
value: 83.65414228518632
- type: euclidean_accuracy
value: 88.97620988085536
- type: euclidean_ap
value: 86.08681215460771
- type: euclidean_f1
value: 78.02793637114438
- type: euclidean_precision
value: 73.11082699683736
- type: euclidean_recall
value: 83.65414228518632
- type: manhattan_accuracy
value: 88.88888888888889
- type: manhattan_ap
value: 86.02916327562438
- type: manhattan_f1
value: 78.02063045516843
- type: manhattan_precision
value: 73.38851947346994
- type: manhattan_recall
value: 83.2768709578072
- type: max_accuracy
value: 88.97620988085536
- type: max_ap
value: 86.08681215460771
- type: max_f1
value: 78.02793637114438
---
<!-- TODO: add evaluation results here -->
<br><br>
<p align="center">
<img src="https://github.com/jina-ai/finetuner/blob/main/docs/_static/finetuner-logo-ani.svg?raw=true" alt="Finetuner logo: Finetuner helps you to create experiments in order to improve embeddings on search tasks. It accompanies you to deliver the last mile of performance-tuning for neural search applications." width="150px">
</p>
<p align="center">
<b>The text embedding set trained by <a href="https://jina.ai/"><b>Jina AI</b></a>, <a href="https://github.com/jina-ai/finetuner"><b>Finetuner</b></a> team.</b>
</p>
## Intended Usage & Model Info
`jina-embeddings-v2-base-en` is an English, monolingual **embedding model** supporting **8192 sequence length**.
It is based on a Bert architecture (JinaBert) that supports the symmetric bidirectional variant of [ALiBi](https://arxiv.org/abs/2108.12409) to allow longer sequence length.
The backbone `jina-bert-v2-base-en` is pretrained on the C4 dataset.
The model is further trained on Jina AI's collection of more than 400 millions of sentence pairs and hard negatives.
These pairs were obtained from various domains and were carefully selected through a thorough cleaning process.
The embedding model was trained using 512 sequence length, but extrapolates to 8k sequence length (or even longer) thanks to ALiBi.
This makes our model useful for a range of use cases, especially when processing long documents is needed, including long document retrieval, semantic textual similarity, text reranking, recommendation, RAG and LLM-based generative search, etc.
With a standard size of 137 million parameters, the model enables fast inference while delivering better performance than our small model. It is recommended to use a single GPU for inference.
Additionally, we provide the following embedding models:
**V1 (Based on T5, 512 Seq)**
- [`jina-embeddings-v1-small-en`](https://huggingface.co/jinaai/jina-embedding-s-en-v1): 35 million parameters.
- [`jina-embeddings-v1-base-en`](https://huggingface.co/jinaai/jina-embedding-b-en-v1): 110 million parameters.
- [`jina-embeddings-v1-large-en`](https://huggingface.co/jinaai/jina-embedding-l-en-v1): 330 million parameters.
**V2 (Based on JinaBert, 8k Seq)**
- [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters.
- [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters **(you are here)**.
- [`jina-embeddings-v2-large-en`](): 435 million parameters (releasing soon).
## Data & Parameters
Jina Embeddings V2 [technical report](https://arxiv.org/abs/2310.19923)
## Usage
You can use Jina Embedding models directly from transformers package:
```python
!pip install transformers
from transformers import AutoModel
from numpy.linalg import norm
cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-base-en', trust_remote_code=True) # trust_remote_code is needed to use the encode method
embeddings = model.encode(['How is the weather today?', 'What is the current weather like today?'])
print(cos_sim(embeddings[0], embeddings[1]))
```
If you only want to handle shorter sequence, such as 2k, pass the `max_length` parameter to the `encode` function:
```python
embeddings = model.encode(
['Very long ... document'],
max_length=2048
)
```
*Alternatively, you can use Jina AI's [Embedding platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models*.
## Fine-tuning
Please consider [Finetuner](https://github.com/jina-ai/finetuner).
## Plans
The development of new bilingual models is currently underway. We will be targeting mainly the German and Spanish languages.
The upcoming models will be called `jina-embeddings-v2-base-de/es`.
## Contact
Join our [Discord community](https://discord.jina.ai) and chat with other community members about ideas.
## Citation
If you find Jina Embeddings useful in your research, please cite the following paper:
```
@misc{günther2023jina,
title={Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents},
author={Michael Günther and Jackmin Ong and Isabelle Mohr and Alaeddine Abdessalem and Tanguy Abel and Mohammad Kalim Akram and Susana Guzman and Georgios Mastrapas and Saba Sturua and Bo Wang and Maximilian Werk and Nan Wang and Han Xiao},
year={2023},
eprint={2310.19923},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
``` latex
@misc{günther2023jina,
title={Beyond the 512-Token Barrier: Training General-Purpose Text
Embeddings for Large Documents},
author={Michael Günther and Jackmin Ong and Isabelle Mohr and Alaeddine Abdessalem and Tanguy Abel and Mohammad Kalim Akram and Susana Guzman and Georgios Mastrapas and Saba Sturua and Bo Wang},
year={2023},
eprint={2307.11224},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@misc{günther2023jina,
title={Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models},
author={Michael Günther and Louis Milliken and Jonathan Geuter and Georgios Mastrapas and Bo Wang and Han Xiao},
year={2023},
eprint={2307.11224},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
--> | 67,932 | [
[
-0.030792236328125,
-0.0694580078125,
0.035308837890625,
0.0291748046875,
-0.0230255126953125,
-0.03704833984375,
-0.0229339599609375,
-0.025421142578125,
0.0288543701171875,
0.01117706298828125,
-0.0199432373046875,
-0.042205810546875,
-0.044403076171875,
0.01155853271484375,
-0.0152740478515625,
0.060791015625,
-0.01145172119140625,
0.00801849365234375,
-0.0239410400390625,
-0.01078033447265625,
-0.025054931640625,
-0.029296875,
-0.0413818359375,
0.0006966590881347656,
0.0300750732421875,
0.00626373291015625,
0.0469970703125,
0.061309814453125,
0.0142364501953125,
0.023193359375,
-0.007335662841796875,
0.0180816650390625,
-0.0228424072265625,
0.004199981689453125,
-0.00370025634765625,
-0.038818359375,
-0.039337158203125,
0.00223541259765625,
0.0543212890625,
0.0294342041015625,
0.00626373291015625,
0.0201416015625,
-0.0012187957763671875,
0.0377197265625,
-0.04107666015625,
0.026885986328125,
-0.024871826171875,
-0.0034332275390625,
-0.0180206298828125,
0.0157012939453125,
-0.035919189453125,
-0.0204010009765625,
0.0173187255859375,
-0.047149658203125,
-0.0093536376953125,
0.0182037353515625,
0.10137939453125,
0.01451873779296875,
-0.035247802734375,
-0.0086669921875,
-0.0228271484375,
0.075439453125,
-0.07183837890625,
0.038299560546875,
0.0300140380859375,
-0.008636474609375,
-0.01303863525390625,
-0.048431396484375,
-0.049407958984375,
-0.00954437255859375,
0.0011920928955078125,
0.01397705078125,
-0.00687408447265625,
-0.004146575927734375,
0.0222930908203125,
0.0170745849609375,
-0.04156494140625,
0.006580352783203125,
-0.0200958251953125,
0.0003814697265625,
0.061767578125,
-0.0011167526245117188,
0.0230712890625,
-0.04443359375,
-0.023681640625,
-0.0295257568359375,
-0.024383544921875,
0.0007662773132324219,
0.038970947265625,
0.01186370849609375,
-0.035003662109375,
0.037506103515625,
-0.01081085205078125,
0.04656982421875,
0.005130767822265625,
-0.00018596649169921875,
0.0391845703125,
-0.0288238525390625,
-0.0234375,
-0.027008056640625,
0.08477783203125,
0.0159912109375,
0.0200347900390625,
0.004726409912109375,
-0.01096343994140625,
-0.02447509765625,
0.00652313232421875,
-0.06329345703125,
-0.0008554458618164062,
0.0190582275390625,
-0.04852294921875,
-0.01617431640625,
0.01507568359375,
-0.06756591796875,
-0.0171966552734375,
-0.00699615478515625,
0.049560546875,
-0.0458984375,
-0.0105133056640625,
0.0242767333984375,
-0.01210784912109375,
0.026153564453125,
0.010650634765625,
-0.05841064453125,
0.00794219970703125,
0.03424072265625,
0.0626220703125,
0.0196380615234375,
-0.0236968994140625,
-0.0172271728515625,
-0.00923919677734375,
-0.01153564453125,
0.032073974609375,
-0.032196044921875,
-0.001712799072265625,
0.015228271484375,
0.0074310302734375,
-0.0196380615234375,
-0.01033782958984375,
0.040374755859375,
-0.03900146484375,
0.0236053466796875,
-0.0030651092529296875,
-0.051727294921875,
-0.031646728515625,
0.01163482666015625,
-0.058349609375,
0.0653076171875,
0.00830078125,
-0.05792236328125,
0.00444793701171875,
-0.038909912109375,
-0.0218048095703125,
-0.03839111328125,
0.0101165771484375,
-0.061309814453125,
-0.0014801025390625,
0.041046142578125,
0.059173583984375,
-0.042755126953125,
0.01383209228515625,
-0.03179931640625,
-0.0179595947265625,
0.01021575927734375,
-0.0229339599609375,
0.07049560546875,
0.0189056396484375,
-0.0173187255859375,
-0.00914764404296875,
-0.04876708984375,
-0.004749298095703125,
0.03961181640625,
-0.0167083740234375,
-0.032012939453125,
-0.0058746337890625,
0.01513671875,
0.01544189453125,
0.04046630859375,
-0.041412353515625,
0.0260467529296875,
-0.04052734375,
0.0298919677734375,
0.051910400390625,
0.0013561248779296875,
0.030303955078125,
-0.0306243896484375,
0.028045654296875,
0.00901031494140625,
0.0159149169921875,
-0.018829345703125,
-0.050994873046875,
-0.06927490234375,
-0.01462554931640625,
0.055084228515625,
0.03228759765625,
-0.037750244140625,
0.052825927734375,
-0.033203125,
-0.046234130859375,
-0.049896240234375,
0.0128326416015625,
0.033203125,
-0.00287628173828125,
0.03961181640625,
-0.00679779052734375,
-0.049163818359375,
-0.0711669921875,
-0.004383087158203125,
-0.004489898681640625,
-0.0022335052490234375,
0.01557159423828125,
0.053192138671875,
-0.019317626953125,
0.058349609375,
-0.04022216796875,
-0.0283966064453125,
-0.01230621337890625,
-0.005107879638671875,
0.0295257568359375,
0.046844482421875,
0.05255126953125,
-0.04534912109375,
-0.054534912109375,
-0.013641357421875,
-0.06292724609375,
0.0240936279296875,
-0.0244140625,
-0.0106201171875,
0.0258636474609375,
0.026702880859375,
-0.05963134765625,
0.026031494140625,
0.040283203125,
-0.0298919677734375,
0.022003173828125,
-0.0204010009765625,
-0.003543853759765625,
-0.11981201171875,
-0.0008320808410644531,
0.018707275390625,
-0.0092010498046875,
-0.032440185546875,
0.01287078857421875,
0.0172119140625,
0.00373077392578125,
-0.0245208740234375,
0.04547119140625,
-0.04656982421875,
0.020111083984375,
0.01433563232421875,
0.0168609619140625,
0.0031909942626953125,
0.0513916015625,
-0.0199432373046875,
0.035369873046875,
0.042633056640625,
-0.031280517578125,
0.0174407958984375,
0.04400634765625,
-0.031494140625,
0.02093505859375,
-0.056304931640625,
0.0173187255859375,
-0.00626373291015625,
0.025848388671875,
-0.057708740234375,
-0.012786865234375,
0.0260162353515625,
-0.039886474609375,
0.03729248046875,
-0.01399993896484375,
-0.059112548828125,
-0.0291900634765625,
-0.0511474609375,
0.0200347900390625,
0.04443359375,
-0.037078857421875,
0.048828125,
0.02166748046875,
-0.004772186279296875,
-0.048431396484375,
-0.045135498046875,
-0.00905609130859375,
-0.00946044921875,
-0.0626220703125,
0.031585693359375,
0.00441741943359375,
0.005584716796875,
0.006519317626953125,
0.01552581787109375,
0.006809234619140625,
0.00009363889694213867,
0.021087646484375,
0.0157470703125,
-0.0157012939453125,
0.007602691650390625,
0.025604248046875,
-0.0008587837219238281,
0.00286102294921875,
-0.02069091796875,
0.06365966796875,
-0.0247039794921875,
-0.0123138427734375,
-0.047698974609375,
0.0247039794921875,
0.039276123046875,
-0.0300140380859375,
0.08251953125,
0.064453125,
-0.04345703125,
-0.00313568115234375,
-0.03912353515625,
-0.0010557174682617188,
-0.0362548828125,
0.03790283203125,
-0.0303955078125,
-0.038665771484375,
0.045654296875,
0.0133819580078125,
0.006969451904296875,
0.06494140625,
0.02581787109375,
-0.00920867919921875,
0.08544921875,
0.03173828125,
-0.020355224609375,
0.037994384765625,
-0.0599365234375,
0.00836181640625,
-0.06927490234375,
-0.0284423828125,
-0.026702880859375,
-0.0210113525390625,
-0.061492919921875,
-0.046051025390625,
0.0097503662109375,
0.0159149169921875,
-0.0238037109375,
0.04046630859375,
-0.0179595947265625,
0.007720947265625,
0.04461669921875,
0.01261138916015625,
-0.0121917724609375,
-0.003620147705078125,
-0.0128326416015625,
0.002593994140625,
-0.039093017578125,
-0.0271453857421875,
0.09405517578125,
0.0498046875,
0.052093505859375,
-0.003360748291015625,
0.06597900390625,
0.0035400390625,
-0.00958251953125,
-0.053680419921875,
0.035247802734375,
-0.018096923828125,
-0.039154052734375,
-0.02325439453125,
-0.01506805419921875,
-0.07586669921875,
0.0095367431640625,
-0.0223541259765625,
-0.050994873046875,
0.0220947265625,
-0.019287109375,
-0.031402587890625,
0.0323486328125,
-0.047088623046875,
0.05926513671875,
0.006786346435546875,
-0.025604248046875,
-0.01934814453125,
-0.04107666015625,
0.002544403076171875,
-0.0032596588134765625,
0.0022144317626953125,
-0.002643585205078125,
-0.00518798828125,
0.07427978515625,
-0.03326416015625,
0.060272216796875,
-0.0204620361328125,
-0.00684356689453125,
0.01739501953125,
-0.02154541015625,
0.060150146484375,
0.025482177734375,
-0.0157318115234375,
0.0236358642578125,
-0.00030231475830078125,
-0.04046630859375,
-0.041748046875,
0.060791015625,
-0.07244873046875,
-0.046142578125,
-0.0400390625,
-0.037445068359375,
-0.0100555419921875,
0.0164031982421875,
0.016357421875,
0.0276336669921875,
0.00042366981506347656,
0.04107666015625,
0.0455322265625,
-0.0404052734375,
0.033203125,
0.0128021240234375,
-0.004825592041015625,
-0.04376220703125,
0.07135009765625,
0.01947021484375,
-0.003978729248046875,
0.0283355712890625,
0.006916046142578125,
-0.0219268798828125,
-0.037078857421875,
-0.039276123046875,
0.0465087890625,
-0.039154052734375,
-0.02569580078125,
-0.06829833984375,
-0.0313720703125,
-0.042755126953125,
-0.0090484619140625,
-0.0401611328125,
-0.0289154052734375,
-0.047210693359375,
-0.0074005126953125,
0.03363037109375,
0.048583984375,
0.004058837890625,
0.005985260009765625,
-0.048309326171875,
0.0216217041015625,
0.01023101806640625,
0.0302886962890625,
0.01241302490234375,
-0.04974365234375,
-0.04595947265625,
0.01666259765625,
-0.0210418701171875,
-0.0614013671875,
0.03839111328125,
0.0137939453125,
0.043243408203125,
0.03436279296875,
0.00542449951171875,
0.048583984375,
-0.03680419921875,
0.06524658203125,
0.0016374588012695312,
-0.06878662109375,
0.039825439453125,
-0.025787353515625,
0.0082244873046875,
0.0272369384765625,
0.04339599609375,
-0.0241546630859375,
-0.0268402099609375,
-0.045440673828125,
-0.06982421875,
0.0574951171875,
0.0179595947265625,
0.04119873046875,
-0.011688232421875,
0.032684326171875,
-0.003173828125,
-0.01739501953125,
-0.0496826171875,
-0.037261962890625,
-0.0200042724609375,
-0.024261474609375,
0.0036029815673828125,
-0.03021240234375,
0.0066375732421875,
-0.04132080078125,
0.0594482421875,
-0.003314971923828125,
0.057891845703125,
0.0123291015625,
-0.0222930908203125,
0.018096923828125,
0.002330780029296875,
0.034423828125,
0.01922607421875,
-0.025146484375,
-0.0205078125,
0.0305023193359375,
-0.0292205810546875,
-0.0003170967102050781,
0.035858154296875,
-0.01297760009765625,
0.0010499954223632812,
0.02520751953125,
0.0704345703125,
0.0096588134765625,
-0.0306243896484375,
0.055816650390625,
-0.0042877197265625,
-0.01776123046875,
-0.037109375,
-0.002925872802734375,
0.015106201171875,
0.02569580078125,
0.026885986328125,
-0.00894927978515625,
-0.0023136138916015625,
-0.029693603515625,
0.01123809814453125,
0.0238494873046875,
-0.017547607421875,
-0.033416748046875,
0.05841064453125,
0.00867462158203125,
-0.00534820556640625,
0.05096435546875,
-0.0196075439453125,
-0.027313232421875,
0.051849365234375,
0.05499267578125,
0.07232666015625,
-0.00579833984375,
0.017486572265625,
0.054046630859375,
0.0186614990234375,
-0.00788116455078125,
0.022552490234375,
0.022216796875,
-0.0499267578125,
-0.011810302734375,
-0.059814453125,
-0.007038116455078125,
0.01303863525390625,
-0.054962158203125,
0.0251007080078125,
-0.044342041015625,
-0.01727294921875,
0.0017108917236328125,
0.0272674560546875,
-0.07379150390625,
0.0124053955078125,
0.0088653564453125,
0.07049560546875,
-0.05767822265625,
0.06689453125,
0.053955078125,
-0.0665283203125,
-0.045196533203125,
0.0172576904296875,
-0.017547607421875,
-0.046173095703125,
0.030029296875,
0.031005859375,
0.019561767578125,
0.0023365020751953125,
-0.03448486328125,
-0.081787109375,
0.096435546875,
0.0295867919921875,
-0.0284271240234375,
-0.01549530029296875,
-0.0017566680908203125,
0.040863037109375,
-0.0144805908203125,
0.0235137939453125,
0.0230255126953125,
0.045867919921875,
-0.036956787109375,
-0.056793212890625,
0.03448486328125,
-0.0439453125,
0.02435302734375,
-0.0133819580078125,
-0.07855224609375,
0.07183837890625,
-0.0213470458984375,
-0.01428985595703125,
0.0271148681640625,
0.07440185546875,
0.0023441314697265625,
0.0038604736328125,
0.031097412109375,
0.05316162109375,
0.0482177734375,
-0.007171630859375,
0.10296630859375,
-0.021881103515625,
0.03326416015625,
0.053955078125,
0.01702880859375,
0.0740966796875,
0.01959228515625,
-0.0244140625,
0.060638427734375,
0.04754638671875,
-0.017974853515625,
0.035919189453125,
0.005451202392578125,
0.00844573974609375,
-0.0131378173828125,
-0.0033817291259765625,
-0.0433349609375,
0.039154052734375,
0.0287017822265625,
-0.0447998046875,
0.0087738037109375,
0.0064239501953125,
0.0220489501953125,
-0.00797271728515625,
0.01250457763671875,
0.037017822265625,
0.0172882080078125,
-0.032562255859375,
0.0614013671875,
0.032196044921875,
0.07171630859375,
-0.037017822265625,
0.0157623291015625,
-0.0193328857421875,
0.0107879638671875,
-0.0019474029541015625,
-0.0498046875,
-0.0006422996520996094,
-0.01120758056640625,
-0.01451873779296875,
-0.0012559890747070312,
0.034210205078125,
-0.033447265625,
-0.03216552734375,
0.038177490234375,
0.024566650390625,
-0.004039764404296875,
-0.0048675537109375,
-0.06298828125,
-0.0019445419311523438,
0.000331878662109375,
-0.052154541015625,
0.018035888671875,
0.0157470703125,
0.0019359588623046875,
0.040740966796875,
0.05377197265625,
-0.01336669921875,
0.00531768798828125,
0.00531768798828125,
0.058929443359375,
-0.058685302734375,
-0.0284271240234375,
-0.060272216796875,
0.04052734375,
-0.01458740234375,
-0.03497314453125,
0.06463623046875,
0.046417236328125,
0.06085205078125,
-0.0238037109375,
0.048309326171875,
-0.01171112060546875,
0.007663726806640625,
-0.04290771484375,
0.06854248046875,
-0.066162109375,
-0.006122589111328125,
-0.0264129638671875,
-0.06976318359375,
-0.0227203369140625,
0.05242919921875,
-0.013397216796875,
0.006305694580078125,
0.045867919921875,
0.05615234375,
0.002094268798828125,
-0.01561737060546875,
0.0139923095703125,
0.029876708984375,
0.0246429443359375,
0.051116943359375,
0.03765869140625,
-0.07611083984375,
0.0321044921875,
-0.033416748046875,
0.00797271728515625,
-0.032684326171875,
-0.05010986328125,
-0.08026123046875,
-0.07440185546875,
-0.0198211669921875,
-0.0282745361328125,
0.00432586669921875,
0.0809326171875,
0.0452880859375,
-0.06536865234375,
0.0093994140625,
0.0111236572265625,
0.0123748779296875,
-0.0189666748046875,
-0.0184478759765625,
0.0540771484375,
-0.021026611328125,
-0.08929443359375,
0.0260467529296875,
-0.006938934326171875,
0.0088958740234375,
-0.0174407958984375,
-0.0165863037109375,
-0.05340576171875,
0.0300445556640625,
0.0357666015625,
0.01500701904296875,
-0.051910400390625,
-0.022003173828125,
0.0048370361328125,
-0.0194091796875,
-0.005832672119140625,
0.0009813308715820312,
-0.04144287109375,
0.036712646484375,
0.06201171875,
0.051910400390625,
0.048248291015625,
-0.01904296875,
0.044647216796875,
-0.051055908203125,
0.0154876708984375,
-0.0041046142578125,
0.049468994140625,
0.0202789306640625,
-0.0225830078125,
0.040863037109375,
0.0130462646484375,
-0.0221710205078125,
-0.05877685546875,
-0.0208587646484375,
-0.08197021484375,
-0.009674072265625,
0.093505859375,
-0.027008056640625,
-0.02001953125,
0.0113372802734375,
-0.007778167724609375,
0.04449462890625,
-0.032318115234375,
0.048309326171875,
0.047393798828125,
0.0224609375,
0.0002994537353515625,
-0.04962158203125,
0.030914306640625,
0.04583740234375,
-0.0535888671875,
-0.0253143310546875,
0.00937652587890625,
0.0283355712890625,
0.0294342041015625,
0.0200042724609375,
-0.01297760009765625,
0.0213165283203125,
0.00943756103515625,
-0.0016584396362304688,
-0.0277557373046875,
-0.0186309814453125,
-0.0215301513671875,
0.0006732940673828125,
-0.0196380615234375,
-0.030029296875
]
] |
facebook/mask2former-swin-large-coco-instance | 2023-09-11T20:35:35.000Z | [
"transformers",
"pytorch",
"safetensors",
"mask2former",
"vision",
"image-segmentation",
"dataset:coco",
"arxiv:2112.01527",
"arxiv:2107.06278",
"license:other",
"endpoints_compatible",
"region:us"
] | image-segmentation | facebook | null | null | facebook/mask2former-swin-large-coco-instance | 3 | 46,932 | transformers | 2023-01-02T12:10:40 | ---
license: other
tags:
- vision
- image-segmentation
datasets:
- coco
widget:
- src: http://images.cocodataset.org/val2017/000000039769.jpg
example_title: Cats
- src: http://images.cocodataset.org/val2017/000000039770.jpg
example_title: Castle
---
# Mask2Former
Mask2Former model trained on COCO instance segmentation (large-sized version, Swin backbone). It was introduced in the paper [Masked-attention Mask Transformer for Universal Image Segmentation
](https://arxiv.org/abs/2112.01527) and first released in [this repository](https://github.com/facebookresearch/Mask2Former/).
Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA,
[MaskFormer](https://arxiv.org/abs/2107.06278) both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without
without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.
## Intended uses & limitations
You can use this particular checkpoint for instance segmentation. See the [model hub](https://huggingface.co/models?search=mask2former) to look for other
fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model:
```python
import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation
# load Mask2Former fine-tuned on COCO instance segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-large-coco-instance")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-large-coco-instance")
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
# model predicts class_queries_logits of shape `(batch_size, num_queries)`
# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits
# you can pass them to processor for postprocessing
result = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)
predicted_instance_map = result["segmentation"]
```
For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/mask2former). | 3,193 | [
[
-0.03558349609375,
-0.053497314453125,
0.022216796875,
0.016021728515625,
-0.025115966796875,
-0.00733184814453125,
0.007053375244140625,
-0.055694580078125,
0.01006317138671875,
0.040435791015625,
-0.043670654296875,
-0.020477294921875,
-0.05615234375,
-0.027252197265625,
-0.0116729736328125,
0.060943603515625,
-0.005107879638671875,
-0.00560760498046875,
-0.029052734375,
-0.00272369384765625,
-0.023590087890625,
-0.0299224853515625,
-0.0677490234375,
-0.0257568359375,
0.01491546630859375,
0.02911376953125,
0.022674560546875,
0.040924072265625,
0.04132080078125,
0.02362060546875,
-0.00830078125,
-0.0023746490478515625,
-0.03961181640625,
-0.00653076171875,
0.00916290283203125,
-0.0384521484375,
-0.0169830322265625,
0.010650634765625,
0.037750244140625,
0.017974853515625,
0.006500244140625,
0.031494140625,
-0.00537872314453125,
0.03857421875,
-0.041717529296875,
0.0217437744140625,
-0.035369873046875,
0.0125579833984375,
-0.00684356689453125,
0.029998779296875,
-0.02520751953125,
-0.007843017578125,
0.007602691650390625,
-0.0290679931640625,
0.039703369140625,
0.0014581680297851562,
0.0771484375,
0.0184478759765625,
-0.007465362548828125,
-0.006229400634765625,
-0.03314208984375,
0.055145263671875,
-0.02886962890625,
0.0181884765625,
0.0283966064453125,
0.046630859375,
0.01515960693359375,
-0.08673095703125,
-0.0294342041015625,
0.016754150390625,
-0.0091705322265625,
0.00830078125,
-0.0233154296875,
0.002140045166015625,
0.031890869140625,
0.030059814453125,
-0.038330078125,
0.0048675537109375,
-0.0672607421875,
-0.0244598388671875,
0.05078125,
-0.0137786865234375,
0.023773193359375,
-0.016387939453125,
-0.04278564453125,
-0.02215576171875,
-0.02349853515625,
0.037322998046875,
0.01141357421875,
-0.022125244140625,
-0.0189056396484375,
0.0404052734375,
-0.006618499755859375,
0.05035400390625,
0.0246429443359375,
-0.00933837890625,
0.011474609375,
0.0161895751953125,
-0.0283966064453125,
0.00670623779296875,
0.0509033203125,
0.031280517578125,
0.002552032470703125,
0.00478363037109375,
-0.005382537841796875,
0.01416015625,
0.02239990234375,
-0.0958251953125,
-0.042999267578125,
0.0173187255859375,
-0.0265655517578125,
-0.0294647216796875,
0.0204620361328125,
-0.056060791015625,
0.0017404556274414062,
-0.0042877197265625,
0.03125,
-0.021209716796875,
-0.006488800048828125,
-0.0018491744995117188,
-0.0160980224609375,
0.033660888671875,
0.0198822021484375,
-0.073974609375,
0.031646728515625,
0.038818359375,
0.073486328125,
-0.00830841064453125,
0.00850677490234375,
-0.0183563232421875,
0.001216888427734375,
-0.019805908203125,
0.07501220703125,
-0.03094482421875,
-0.005035400390625,
-0.0229339599609375,
0.0272216796875,
-0.0198516845703125,
-0.04803466796875,
0.0298614501953125,
-0.03826904296875,
0.0294189453125,
-0.01428985595703125,
-0.0255889892578125,
-0.04852294921875,
0.0038242340087890625,
-0.037841796875,
0.09527587890625,
0.040191650390625,
-0.03851318359375,
0.01360321044921875,
-0.0428466796875,
-0.01509857177734375,
-0.004390716552734375,
-0.006343841552734375,
-0.07147216796875,
0.002155303955078125,
0.0268402099609375,
0.0369873046875,
-0.0199432373046875,
0.0008573532104492188,
-0.0233154296875,
-0.0178070068359375,
0.003955841064453125,
0.0136871337890625,
0.06640625,
0.010345458984375,
-0.04913330078125,
0.0261688232421875,
-0.03277587890625,
0.00800323486328125,
0.0297698974609375,
0.0172882080078125,
0.01200103759765625,
-0.0303802490234375,
0.02484130859375,
0.04754638671875,
-0.000044286251068115234,
-0.040924072265625,
0.0126495361328125,
-0.007472991943359375,
0.058319091796875,
0.044921875,
0.00568389892578125,
0.030975341796875,
-0.0128326416015625,
0.0298004150390625,
0.00555419921875,
0.035186767578125,
-0.00821685791015625,
-0.053253173828125,
-0.06622314453125,
-0.03070068359375,
0.0019168853759765625,
0.0194549560546875,
-0.0247344970703125,
0.0285186767578125,
0.01654052734375,
-0.05072021484375,
-0.03265380859375,
-0.0012445449829101562,
0.031890869140625,
0.04718017578125,
0.0282135009765625,
-0.0443115234375,
-0.055511474609375,
-0.080810546875,
0.020660400390625,
0.006877899169921875,
-0.006710052490234375,
0.0277557373046875,
0.04302978515625,
-0.03070068359375,
0.06719970703125,
-0.05133056640625,
-0.031463623046875,
-0.0174102783203125,
-0.002899169921875,
-0.007076263427734375,
0.05059814453125,
0.05511474609375,
-0.060943603515625,
-0.02593994140625,
-0.02593994140625,
-0.061676025390625,
0.007099151611328125,
0.00560760498046875,
-0.026702880859375,
0.0203857421875,
0.0278472900390625,
-0.0308837890625,
0.038726806640625,
0.038726806640625,
-0.0222015380859375,
0.043975830078125,
0.0062713623046875,
-0.0002503395080566406,
-0.06402587890625,
0.00982666015625,
0.0090484619140625,
-0.0256195068359375,
-0.035064697265625,
0.0087890625,
0.01145172119140625,
-0.0168914794921875,
-0.044677734375,
0.03570556640625,
-0.04705810546875,
-0.027069091796875,
-0.0208587646484375,
-0.020294189453125,
0.017486572265625,
0.05340576171875,
0.02679443359375,
0.036285400390625,
0.058746337890625,
-0.032684326171875,
0.032745361328125,
0.0206756591796875,
-0.03424072265625,
0.03179931640625,
-0.07635498046875,
0.033935546875,
-0.0019369125366210938,
0.034393310546875,
-0.0838623046875,
-0.0435791015625,
0.036529541015625,
-0.0278472900390625,
0.031005859375,
-0.023590087890625,
-0.01885986328125,
-0.061676025390625,
-0.032470703125,
0.05340576171875,
0.059967041015625,
-0.04656982421875,
0.0158843994140625,
0.037811279296875,
0.0120086669921875,
-0.0175323486328125,
-0.061767578125,
-0.0143890380859375,
-0.0167694091796875,
-0.06719970703125,
0.03448486328125,
-0.0019893646240234375,
0.004528045654296875,
-0.0010824203491210938,
-0.0191802978515625,
-0.006221771240234375,
-0.023529052734375,
0.036590576171875,
0.02777099609375,
-0.00823211669921875,
-0.0298004150390625,
0.00978851318359375,
-0.015167236328125,
0.0096893310546875,
-0.031829833984375,
0.050750732421875,
-0.01415252685546875,
-0.0181732177734375,
-0.054779052734375,
0.0019130706787109375,
0.0297088623046875,
-0.01947021484375,
0.044219970703125,
0.076416015625,
-0.052001953125,
-0.00418853759765625,
-0.067138671875,
-0.03204345703125,
-0.035491943359375,
0.022308349609375,
-0.032989501953125,
-0.06573486328125,
0.04364013671875,
0.0111236572265625,
-0.004520416259765625,
0.051971435546875,
0.040252685546875,
0.001476287841796875,
0.0782470703125,
0.048553466796875,
0.02191162109375,
0.043243408203125,
-0.069580078125,
0.01078033447265625,
-0.095458984375,
-0.053955078125,
-0.00722503662109375,
-0.03802490234375,
-0.014556884765625,
-0.05999755859375,
0.037322998046875,
0.04278564453125,
-0.01117706298828125,
0.041656494140625,
-0.076904296875,
0.0187530517578125,
0.04217529296875,
0.018707275390625,
-0.0205230712890625,
0.0258331298828125,
0.01277923583984375,
-0.0013074874877929688,
-0.04736328125,
-0.0282135009765625,
0.054779052734375,
0.0379638671875,
0.03411865234375,
-0.019744873046875,
0.0304718017578125,
-0.0009598731994628906,
0.0094451904296875,
-0.0614013671875,
0.0304718017578125,
0.009613037109375,
-0.0419921875,
-0.01194000244140625,
-0.002063751220703125,
-0.056243896484375,
0.0272979736328125,
-0.000453948974609375,
-0.085693359375,
0.03118896484375,
0.01073455810546875,
-0.0216522216796875,
0.0304718017578125,
-0.0531005859375,
0.08148193359375,
-0.004314422607421875,
-0.034423828125,
0.005584716796875,
-0.055755615234375,
0.039642333984375,
0.00611114501953125,
-0.009979248046875,
-0.0137939453125,
0.0220184326171875,
0.09088134765625,
-0.038177490234375,
0.061859130859375,
-0.0198211669921875,
0.01473236083984375,
0.055572509765625,
-0.013671875,
0.02313232421875,
0.0138702392578125,
0.004302978515625,
0.03070068359375,
0.0009255409240722656,
-0.040802001953125,
-0.042449951171875,
0.040252685546875,
-0.06243896484375,
-0.03228759765625,
-0.02496337890625,
-0.0219879150390625,
0.0149993896484375,
0.0089111328125,
0.059173583984375,
0.032501220703125,
-0.00019669532775878906,
0.00911712646484375,
0.04412841796875,
0.0003714561462402344,
0.03167724609375,
-0.006038665771484375,
-0.01232147216796875,
-0.034393310546875,
0.0498046875,
0.003208160400390625,
0.018707275390625,
0.01483917236328125,
0.01407623291015625,
-0.036346435546875,
-0.0120391845703125,
-0.05059814453125,
0.0277862548828125,
-0.034698486328125,
-0.0302886962890625,
-0.06658935546875,
-0.0343017578125,
-0.06011962890625,
-0.0286102294921875,
-0.036773681640625,
-0.03570556640625,
-0.0245361328125,
-0.0028362274169921875,
0.031341552734375,
0.03924560546875,
-0.00943756103515625,
0.03948974609375,
-0.0219879150390625,
0.023040771484375,
0.04620361328125,
0.0192718505859375,
-0.01171112060546875,
-0.04595947265625,
-0.0026149749755859375,
0.0016012191772460938,
-0.040618896484375,
-0.055938720703125,
0.0205535888671875,
0.0019102096557617188,
0.0267486572265625,
0.049041748046875,
-0.0160980224609375,
0.05133056640625,
-0.01134490966796875,
0.054412841796875,
0.0361328125,
-0.060394287109375,
0.054779052734375,
-0.004901885986328125,
0.005657196044921875,
0.01824951171875,
0.011077880859375,
-0.04608154296875,
-0.00905609130859375,
-0.05841064453125,
-0.06787109375,
0.09228515625,
0.0185546875,
-0.00782012939453125,
0.0167388916015625,
0.03564453125,
-0.0036449432373046875,
0.0032501220703125,
-0.05072021484375,
-0.0250244140625,
-0.032135009765625,
0.00896453857421875,
-0.007495880126953125,
-0.0555419921875,
-0.0034351348876953125,
-0.036102294921875,
0.052520751953125,
0.003360748291015625,
0.046295166015625,
0.02435302734375,
-0.0219268798828125,
-0.0206756591796875,
-0.0300140380859375,
0.040008544921875,
0.0380859375,
-0.019805908203125,
0.01230621337890625,
0.0023174285888671875,
-0.0382080078125,
0.0009975433349609375,
0.00849151611328125,
-0.023223876953125,
-0.01232147216796875,
0.0228729248046875,
0.08074951171875,
0.00826263427734375,
-0.0197601318359375,
0.036224365234375,
0.0087890625,
-0.0245513916015625,
-0.02734375,
0.012420654296875,
0.0011548995971679688,
0.01885986328125,
0.01346588134765625,
0.018280029296875,
0.021820068359375,
-0.0283050537109375,
0.0157928466796875,
0.0189056396484375,
-0.04486083984375,
-0.0288848876953125,
0.0699462890625,
-0.0108489990234375,
-0.0184326171875,
0.05029296875,
-0.0203704833984375,
-0.06304931640625,
0.0809326171875,
0.056121826171875,
0.059661865234375,
-0.030181884765625,
0.023590087890625,
0.058563232421875,
0.01407623291015625,
-0.01194000244140625,
-0.0086517333984375,
-0.00756072998046875,
-0.0340576171875,
-0.002079010009765625,
-0.04962158203125,
-0.004009246826171875,
0.0145263671875,
-0.051605224609375,
0.025054931640625,
-0.04632568359375,
-0.00421905517578125,
0.00876617431640625,
0.0095367431640625,
-0.057891845703125,
0.032135009765625,
0.01629638671875,
0.0465087890625,
-0.056976318359375,
0.049591064453125,
0.071044921875,
-0.0289764404296875,
-0.058929443359375,
-0.0325927734375,
0.006397247314453125,
-0.0767822265625,
0.0225677490234375,
0.055389404296875,
0.0021381378173828125,
-0.0064849853515625,
-0.042816162109375,
-0.06158447265625,
0.095458984375,
0.01378631591796875,
-0.030059814453125,
0.007152557373046875,
0.00394439697265625,
0.02117919921875,
-0.0382080078125,
0.039276123046875,
0.04022216796875,
0.0291595458984375,
0.045135498046875,
-0.03424072265625,
0.0164794921875,
-0.02447509765625,
0.02325439453125,
-0.0015401840209960938,
-0.06787109375,
0.061859130859375,
-0.032958984375,
-0.0096435546875,
-0.00286865234375,
0.059112548828125,
0.017578125,
0.03106689453125,
0.04058837890625,
0.050994873046875,
0.040863037109375,
-0.01136016845703125,
0.0723876953125,
0.0010156631469726562,
0.045806884765625,
0.0570068359375,
0.013397216796875,
0.0343017578125,
0.0187225341796875,
-0.00618743896484375,
0.041290283203125,
0.07391357421875,
-0.032318115234375,
0.0308380126953125,
0.01406097412109375,
-0.00506591796875,
-0.011199951171875,
-0.001453399658203125,
-0.03497314453125,
0.04547119140625,
0.01824951171875,
-0.0313720703125,
-0.00408935546875,
0.0093841552734375,
0.004852294921875,
-0.0264434814453125,
-0.01457977294921875,
0.050567626953125,
0.001987457275390625,
-0.0472412109375,
0.052337646484375,
0.019073486328125,
0.04705810546875,
-0.0280609130859375,
-0.0005941390991210938,
-0.0106964111328125,
0.01045989990234375,
-0.0310821533203125,
-0.046630859375,
0.037994384765625,
-0.012725830078125,
-0.012542724609375,
0.001712799072265625,
0.0621337890625,
-0.0291748046875,
-0.061859130859375,
0.0148162841796875,
0.00009381771087646484,
0.035369873046875,
-0.026702880859375,
-0.06610107421875,
0.03619384765625,
0.0013399124145507812,
-0.034210205078125,
0.0176849365234375,
0.00009918212890625,
-0.0186767578125,
0.0298309326171875,
0.0439453125,
-0.029541015625,
0.00022709369659423828,
-0.003650665283203125,
0.06756591796875,
-0.0256805419921875,
-0.030517578125,
-0.046142578125,
0.036651611328125,
-0.0214691162109375,
-0.0150909423828125,
0.036895751953125,
0.07049560546875,
0.06756591796875,
-0.01273345947265625,
0.0382080078125,
-0.0170745849609375,
-0.0009260177612304688,
-0.024810791015625,
0.043182373046875,
-0.0379638671875,
-0.0180511474609375,
-0.0234375,
-0.089111328125,
-0.019439697265625,
0.07464599609375,
-0.03314208984375,
0.0159454345703125,
0.04248046875,
0.06201171875,
-0.02777099609375,
-0.00933837890625,
0.01024627685546875,
-0.002292633056640625,
0.0261383056640625,
0.03790283203125,
0.02716064453125,
-0.05340576171875,
0.0272064208984375,
-0.06622314453125,
-0.038543701171875,
-0.030364990234375,
-0.0272064208984375,
-0.071044921875,
-0.0556640625,
-0.041168212890625,
-0.0278472900390625,
-0.00357818603515625,
0.03314208984375,
0.10321044921875,
-0.063232421875,
-0.013153076171875,
-0.006992340087890625,
0.003887176513671875,
-0.018890380859375,
-0.023529052734375,
0.051422119140625,
-0.01032257080078125,
-0.06951904296875,
-0.00606536865234375,
0.0215606689453125,
0.003101348876953125,
0.0009565353393554688,
0.0007843971252441406,
0.0085601806640625,
-0.014312744140625,
0.05682373046875,
0.0286712646484375,
-0.05572509765625,
-0.024261474609375,
-0.0099029541015625,
-0.00222015380859375,
0.0184326171875,
0.0579833984375,
-0.04681396484375,
0.034881591796875,
0.01702880859375,
0.01837158203125,
0.0867919921875,
0.006610870361328125,
0.0038909912109375,
-0.037261962890625,
0.031829833984375,
0.00841522216796875,
0.034942626953125,
0.0272064208984375,
-0.045654296875,
0.042449951171875,
0.0294647216796875,
-0.039459228515625,
-0.046630859375,
0.0186767578125,
-0.1048583984375,
-0.01473236083984375,
0.083740234375,
-0.01290130615234375,
-0.04229736328125,
0.019256591796875,
-0.03814697265625,
0.03680419921875,
-0.02105712890625,
0.0628662109375,
0.01568603515625,
-0.0265960693359375,
-0.03570556640625,
-0.01934814453125,
0.0389404296875,
0.00981903076171875,
-0.05682373046875,
-0.0322265625,
0.033203125,
0.045623779296875,
0.00930023193359375,
0.047637939453125,
-0.0280609130859375,
0.02386474609375,
0.006519317626953125,
0.0276031494140625,
-0.022491455078125,
-0.021392822265625,
-0.0117034912109375,
0.0110931396484375,
-0.024810791015625,
-0.03997802734375
]
] |
sentence-transformers/multi-qa-distilbert-cos-v1 | 2023-11-02T09:30:28.000Z | [
"sentence-transformers",
"pytorch",
"distilbert",
"feature-extraction",
"sentence-similarity",
"en",
"dataset:flax-sentence-embeddings/stackexchange_xml",
"dataset:ms_marco",
"dataset:gooaq",
"dataset:yahoo_answers_topics",
"dataset:search_qa",
"dataset:eli5",
"dataset:natural_questions",
"dataset:trivia_qa",
"dataset:embedding-data/QQP",
"dataset:embedding-data/PAQ_pairs",
"dataset:embedding-data/Amazon-QA",
"dataset:embedding-data/WikiAnswers",
"endpoints_compatible",
"has_space",
"region:us"
] | sentence-similarity | sentence-transformers | null | null | sentence-transformers/multi-qa-distilbert-cos-v1 | 14 | 46,920 | sentence-transformers | 2022-03-02T23:29:05 | ---
language:
- en
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
datasets:
- flax-sentence-embeddings/stackexchange_xml
- ms_marco
- gooaq
- yahoo_answers_topics
- search_qa
- eli5
- natural_questions
- trivia_qa
- embedding-data/QQP
- embedding-data/PAQ_pairs
- embedding-data/Amazon-QA
- embedding-data/WikiAnswers
---
# multi-qa-distilbert-cos-v1
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 215M (question, answer) pairs from diverse sources. For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/multi-qa-distilbert-cos-v1')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F
#Mean Pooling - Take average of all tokens
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
# Normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/multi-qa-distilbert-cos-v1")
model = AutoModel.from_pretrained("sentence-transformers/multi-qa-distilbert-cos-v1")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 768 |
| Produces normalized embeddings | Yes |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (`util.dot_score`), cosine-similarity (`util.cos_sim`), or euclidean distance |
Note: When loaded with `sentence-transformers`, this model produces normalized embeddings with length 1. In that case, dot-product and cosine-similarity are equivalent. dot-product is preferred as it is faster. Euclidean distance is proportional to dot-product and can also be used.
----
## Background
The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised
contrastive learning objective. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.
We developped this model during the
[Community week using JAX/Flax for NLP & CV](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104),
organized by Hugging Face. We developped this model as part of the project:
[Train the Best Sentence Embedding Model Ever with 1B Training Pairs](https://discuss.huggingface.co/t/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs/7354). We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.
## Intended uses
Our model is intented to be used for semantic search: It encodes queries / questions and text paragraphs in a dense vector space. It finds relevant documents for the given passages.
Note that there is a limit of 512 word pieces: Text longer than that will be truncated. Further note that the model was just trained on input text up to 250 word pieces. It might not work well for longer text.
## Training procedure
The full training script is accessible in this current repository: `train_script.py`.
### Pre-training
We use the pretrained [`distilbert-base-uncased`](https://huggingface.co/distilbert-base-uncased) model. Please refer to the model card for more detailed information about the pre-training procedure.
#### Training
We use the concatenation from multiple datasets to fine-tune our model. In total we have about 215M (question, answer) pairs.
We sampled each dataset given a weighted probability which configuration is detailed in the `data_config.json` file.
The model was trained with [MultipleNegativesRankingLoss](https://www.sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) using Mean-pooling, cosine-similarity as similarity function, and a scale of 20.
| Dataset | Number of training tuples |
|--------------------------------------------------------|:--------------------------:|
| [WikiAnswers](https://github.com/afader/oqa#wikianswers-corpus) Duplicate question pairs from WikiAnswers | 77,427,422 |
| [PAQ](https://github.com/facebookresearch/PAQ) Automatically generated (Question, Paragraph) pairs for each paragraph in Wikipedia | 64,371,441 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Body) pairs from all StackExchanges | 25,316,456 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) (Title, Answer) pairs from all StackExchanges | 21,396,559 |
| [MS MARCO](https://microsoft.github.io/msmarco/) Triplets (query, answer, hard_negative) for 500k queries from Bing search engine | 17,579,773 |
| [GOOAQ: Open Question Answering with Diverse Answer Types](https://github.com/allenai/gooaq) (query, answer) pairs for 3M Google queries and Google featured snippet | 3,012,496 |
| [Amazon-QA](http://jmcauley.ucsd.edu/data/amazon/qa/) (Question, Answer) pairs from Amazon product pages | 2,448,839
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Answer) pairs from Yahoo Answers | 1,198,260 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Question, Answer) pairs from Yahoo Answers | 681,164 |
| [Yahoo Answers](https://www.kaggle.com/soumikrakshit/yahoo-answers-dataset) (Title, Question) pairs from Yahoo Answers | 659,896 |
| [SearchQA](https://huggingface.co/datasets/search_qa) (Question, Answer) pairs for 140k questions, each with Top5 Google snippets on that question | 582,261 |
| [ELI5](https://huggingface.co/datasets/eli5) (Question, Answer) pairs from Reddit ELI5 (explainlikeimfive) | 325,475 |
| [Stack Exchange](https://huggingface.co/datasets/flax-sentence-embeddings/stackexchange_xml) Duplicate questions pairs (titles) | 304,525 |
| [Quora Question Triplets](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs) (Question, Duplicate_Question, Hard_Negative) triplets for Quora Questions Pairs dataset | 103,663 |
| [Natural Questions (NQ)](https://ai.google.com/research/NaturalQuestions) (Question, Paragraph) pairs for 100k real Google queries with relevant Wikipedia paragraph | 100,231 |
| [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/) (Question, Paragraph) pairs from SQuAD2.0 dataset | 87,599 |
| [TriviaQA](https://huggingface.co/datasets/trivia_qa) (Question, Evidence) pairs | 73,346 |
| **Total** | **214,988,242** | | 9,472 | [
[
-0.0302581787109375,
-0.06640625,
0.031219482421875,
0.0184478759765625,
-0.0091705322265625,
-0.018890380859375,
-0.00959014892578125,
-0.01410675048828125,
0.0188140869140625,
0.0213623046875,
-0.0382080078125,
-0.047088623046875,
-0.049041748046875,
0.01418304443359375,
-0.0306243896484375,
0.0693359375,
-0.0016870498657226562,
0.0081634521484375,
-0.026824951171875,
-0.024688720703125,
-0.0194549560546875,
-0.033843994140625,
-0.029266357421875,
-0.0030517578125,
0.0265350341796875,
0.0219573974609375,
0.0426025390625,
0.0229034423828125,
0.0300445556640625,
0.029815673828125,
0.0005087852478027344,
0.01898193359375,
-0.041107177734375,
-0.004016876220703125,
0.0006518363952636719,
-0.0328369140625,
-0.0053558349609375,
0.0249786376953125,
0.033966064453125,
0.036651611328125,
-0.004116058349609375,
0.01189422607421875,
0.00243377685546875,
0.0379638671875,
-0.029571533203125,
0.0162353515625,
-0.035491943359375,
0.007167816162109375,
0.00478363037109375,
-0.0076446533203125,
-0.02569580078125,
-0.02215576171875,
0.025238037109375,
-0.05218505859375,
0.018585205078125,
0.01336669921875,
0.083740234375,
0.0178680419921875,
-0.033782958984375,
-0.038726806640625,
-0.01314544677734375,
0.065185546875,
-0.05670166015625,
0.02734375,
0.0264892578125,
-0.00897216796875,
-0.004856109619140625,
-0.0595703125,
-0.061248779296875,
-0.01216888427734375,
-0.0266876220703125,
0.02294921875,
-0.0146942138671875,
-0.004974365234375,
0.0177459716796875,
0.03387451171875,
-0.059600830078125,
-0.0008063316345214844,
-0.03350830078125,
-0.013458251953125,
0.0552978515625,
0.0083770751953125,
0.02227783203125,
-0.043426513671875,
-0.03857421875,
-0.025543212890625,
-0.019622802734375,
0.010162353515625,
0.021148681640625,
0.0032958984375,
-0.01477813720703125,
0.05706787109375,
-0.01708984375,
0.0478515625,
0.005550384521484375,
0.00041413307189941406,
0.04150390625,
-0.04034423828125,
-0.01160430908203125,
-0.022308349609375,
0.0821533203125,
0.0308990478515625,
0.014862060546875,
-0.005817413330078125,
-0.003376007080078125,
0.0030193328857421875,
0.007656097412109375,
-0.06414794921875,
-0.02215576171875,
0.0265350341796875,
-0.02899169921875,
-0.0235137939453125,
0.0138702392578125,
-0.049102783203125,
-0.01187896728515625,
-0.0084686279296875,
0.057861328125,
-0.053497314453125,
0.0000775456428527832,
0.0325927734375,
-0.0294036865234375,
0.0253143310546875,
0.0021076202392578125,
-0.045013427734375,
0.0128173828125,
0.02691650390625,
0.061004638671875,
0.0045166015625,
-0.03125,
-0.0261383056640625,
-0.0160064697265625,
-0.0014696121215820312,
0.047027587890625,
-0.03131103515625,
-0.012298583984375,
0.0017518997192382812,
0.00833892822265625,
-0.023406982421875,
-0.0269317626953125,
0.044342041015625,
-0.03302001953125,
0.060577392578125,
-0.00984954833984375,
-0.072021484375,
-0.0133209228515625,
0.0257110595703125,
-0.043853759765625,
0.08953857421875,
0.0214996337890625,
-0.07806396484375,
0.005199432373046875,
-0.048553466796875,
-0.01525115966796875,
-0.0168609619140625,
-0.007293701171875,
-0.041259765625,
0.002166748046875,
0.033233642578125,
0.047576904296875,
-0.01081085205078125,
0.0024814605712890625,
-0.0222015380859375,
-0.03289794921875,
0.024658203125,
-0.012664794921875,
0.07830810546875,
0.0037479400634765625,
-0.02618408203125,
-0.008148193359375,
-0.05377197265625,
-0.003772735595703125,
0.0259552001953125,
-0.02215576171875,
-0.022430419921875,
-0.0192718505859375,
0.0117034912109375,
0.037567138671875,
0.02215576171875,
-0.054168701171875,
0.01788330078125,
-0.044769287109375,
0.048583984375,
0.046600341796875,
0.0004603862762451172,
0.032562255859375,
-0.031524658203125,
0.0303802490234375,
0.0196075439453125,
0.00479888916015625,
-0.00678253173828125,
-0.0347900390625,
-0.06756591796875,
-0.010040283203125,
0.026641845703125,
0.0421142578125,
-0.054443359375,
0.056976318359375,
-0.024871826171875,
-0.0386962890625,
-0.0667724609375,
0.00824737548828125,
0.0232391357421875,
0.044464111328125,
0.052001953125,
-0.005523681640625,
-0.025970458984375,
-0.06866455078125,
-0.00629425048828125,
0.0061492919921875,
-0.00231170654296875,
0.02313232421875,
0.051544189453125,
-0.01493072509765625,
0.065185546875,
-0.06463623046875,
-0.038543701171875,
-0.009674072265625,
0.00801849365234375,
0.0176849365234375,
0.036041259765625,
0.042236328125,
-0.06439208984375,
-0.03936767578125,
-0.04071044921875,
-0.055572509765625,
0.008087158203125,
-0.006511688232421875,
-0.0185699462890625,
0.01491546630859375,
0.047271728515625,
-0.05718994140625,
0.022796630859375,
0.03900146484375,
-0.04180908203125,
0.0281219482421875,
-0.02081298828125,
-0.001377105712890625,
-0.10565185546875,
0.0028057098388671875,
0.00836181640625,
-0.008026123046875,
-0.02459716796875,
0.00939178466796875,
-0.000010848045349121094,
-0.00734710693359375,
-0.032806396484375,
0.03643798828125,
-0.03900146484375,
0.01377105712890625,
0.01181793212890625,
0.042938232421875,
0.0248260498046875,
0.053802490234375,
-0.01074981689453125,
0.052215576171875,
0.0325927734375,
-0.0382080078125,
0.0297088623046875,
0.050872802734375,
-0.0296630859375,
0.032135009765625,
-0.05987548828125,
0.0066680908203125,
-0.01131439208984375,
0.0240936279296875,
-0.0867919921875,
-0.0002734661102294922,
0.0088653564453125,
-0.048095703125,
0.0123748779296875,
0.0200958251953125,
-0.0478515625,
-0.039886474609375,
-0.049163818359375,
0.0124053955078125,
0.0288543701171875,
-0.0341796875,
0.034088134765625,
0.0246429443359375,
0.002735137939453125,
-0.05023193359375,
-0.066650390625,
-0.01531219482421875,
-0.0107269287109375,
-0.0631103515625,
0.04022216796875,
-0.0161590576171875,
0.01012420654296875,
0.0193328857421875,
0.01012420654296875,
0.005458831787109375,
0.004489898681640625,
0.00531005859375,
0.01480865478515625,
-0.007110595703125,
0.03350830078125,
-0.0032806396484375,
-0.00858306884765625,
-0.00139617919921875,
-0.01849365234375,
0.0538330078125,
-0.02685546875,
-0.0125579833984375,
-0.0302886962890625,
0.030792236328125,
0.0273895263671875,
-0.0243377685546875,
0.077392578125,
0.0758056640625,
-0.0204925537109375,
-0.002803802490234375,
-0.048583984375,
-0.0152587890625,
-0.0364990234375,
0.042205810546875,
-0.0267333984375,
-0.078369140625,
0.031646728515625,
0.0181732177734375,
0.00124359130859375,
0.06201171875,
0.0323486328125,
-0.0211181640625,
0.06854248046875,
0.03179931640625,
-0.0094757080078125,
0.0305328369140625,
-0.05072021484375,
0.0191497802734375,
-0.0579833984375,
-0.01457977294921875,
-0.0291595458984375,
-0.02386474609375,
-0.07177734375,
-0.036865234375,
0.029541015625,
0.00751495361328125,
-0.01080322265625,
0.0304412841796875,
-0.0523681640625,
0.0150299072265625,
0.05242919921875,
0.022735595703125,
-0.00049591064453125,
-0.001953125,
-0.01953125,
-0.007717132568359375,
-0.057464599609375,
-0.02545166015625,
0.08953857421875,
0.02801513671875,
0.040374755859375,
-0.0015516281127929688,
0.0694580078125,
0.0070648193359375,
-0.00585174560546875,
-0.050079345703125,
0.038177490234375,
-0.02178955078125,
-0.0367431640625,
-0.02777099609375,
-0.038360595703125,
-0.0738525390625,
0.02142333984375,
-0.0302734375,
-0.0333251953125,
0.003147125244140625,
-0.01522064208984375,
-0.0298919677734375,
0.00853729248046875,
-0.06365966796875,
0.0784912109375,
-0.00485992431640625,
-0.02508544921875,
-0.018890380859375,
-0.054046630859375,
0.0108795166015625,
0.0172119140625,
0.006443023681640625,
-0.00595855712890625,
-0.004978179931640625,
0.06768798828125,
-0.0289306640625,
0.043243408203125,
-0.00896453857421875,
0.01328277587890625,
0.02386474609375,
-0.024871826171875,
0.0231475830078125,
0.0037174224853515625,
-0.0044708251953125,
-0.0017633438110351562,
0.01160430908203125,
-0.047760009765625,
-0.04095458984375,
0.057830810546875,
-0.080322265625,
-0.0361328125,
-0.041961669921875,
-0.036224365234375,
-0.01152801513671875,
0.011260986328125,
0.03070068359375,
0.039703369140625,
-0.01220703125,
0.033843994140625,
0.053466796875,
-0.037567138671875,
0.03778076171875,
0.0242767333984375,
-0.0040130615234375,
-0.03887939453125,
0.06072998046875,
0.011199951171875,
0.003894805908203125,
0.046630859375,
0.0195770263671875,
-0.040283203125,
-0.0249176025390625,
-0.01409912109375,
0.03228759765625,
-0.04803466796875,
-0.0190887451171875,
-0.07806396484375,
-0.0287628173828125,
-0.054962158203125,
-0.003574371337890625,
-0.0128173828125,
-0.037139892578125,
-0.036041259765625,
-0.021942138671875,
0.0288238525390625,
0.04595947265625,
0.00461578369140625,
0.00887298583984375,
-0.048736572265625,
0.0233001708984375,
0.027008056640625,
0.01410675048828125,
-0.012664794921875,
-0.045440673828125,
-0.0182647705078125,
0.0014896392822265625,
-0.03424072265625,
-0.06610107421875,
0.03363037109375,
0.015594482421875,
0.04071044921875,
0.01468658447265625,
0.01386260986328125,
0.046966552734375,
-0.019989013671875,
0.068115234375,
0.005382537841796875,
-0.060791015625,
0.037994384765625,
-0.010650634765625,
0.0302581787109375,
0.05352783203125,
0.045654296875,
-0.037567138671875,
-0.03076171875,
-0.057647705078125,
-0.0718994140625,
0.04693603515625,
0.025238037109375,
0.0225067138671875,
-0.0167999267578125,
0.0229644775390625,
-0.00475311279296875,
0.0109100341796875,
-0.0670166015625,
-0.0301513671875,
-0.01934814453125,
-0.03924560546875,
-0.0184326171875,
-0.0193023681640625,
0.0023479461669921875,
-0.0372314453125,
0.06243896484375,
-0.00516510009765625,
0.038604736328125,
0.038726806640625,
-0.0305328369140625,
0.031829833984375,
0.01099395751953125,
0.037322998046875,
0.0265045166015625,
-0.016387939453125,
0.0009832382202148438,
0.0173797607421875,
-0.0301055908203125,
-0.004947662353515625,
0.038482666015625,
-0.005939483642578125,
0.0058441162109375,
0.0284271240234375,
0.0567626953125,
0.0216217041015625,
-0.042633056640625,
0.06549072265625,
-0.018524169921875,
-0.0201873779296875,
-0.034759521484375,
-0.01105499267578125,
0.0227508544921875,
0.0163726806640625,
0.0193023681640625,
-0.0160980224609375,
0.01056671142578125,
-0.035308837890625,
0.0287628173828125,
0.02215576171875,
-0.028778076171875,
-0.006526947021484375,
0.04095458984375,
0.01366424560546875,
-0.004261016845703125,
0.07049560546875,
-0.0261383056640625,
-0.046600341796875,
0.035888671875,
0.0296173095703125,
0.056427001953125,
0.0030364990234375,
0.027374267578125,
0.0478515625,
0.01934814453125,
0.0096282958984375,
0.0144500732421875,
0.005847930908203125,
-0.057861328125,
-0.007495880126953125,
-0.06353759765625,
-0.0038967132568359375,
0.007465362548828125,
-0.04046630859375,
0.0231170654296875,
-0.01471710205078125,
-0.0018396377563476562,
0.0030918121337890625,
0.0311126708984375,
-0.07257080078125,
0.012939453125,
0.0009899139404296875,
0.07330322265625,
-0.0673828125,
0.05145263671875,
0.0518798828125,
-0.06964111328125,
-0.06414794921875,
-0.003543853759765625,
-0.021453857421875,
-0.061859130859375,
0.030670166015625,
0.039886474609375,
0.01386260986328125,
0.00875091552734375,
-0.034149169921875,
-0.06365966796875,
0.1048583984375,
0.01442718505859375,
-0.0287628173828125,
-0.020263671875,
0.0162200927734375,
0.04766845703125,
-0.02734375,
0.039581298828125,
0.0289764404296875,
0.02447509765625,
-0.00959014892578125,
-0.0516357421875,
0.0098724365234375,
-0.0284881591796875,
-0.0021991729736328125,
-0.00931549072265625,
-0.06341552734375,
0.0703125,
-0.00675201416015625,
-0.00933837890625,
0.0003516674041748047,
0.0501708984375,
0.021881103515625,
0.01116943359375,
0.038604736328125,
0.07373046875,
0.057525634765625,
-0.00466156005859375,
0.08447265625,
-0.0303802490234375,
0.0447998046875,
0.07177734375,
0.01351165771484375,
0.072998046875,
0.0296478271484375,
-0.016845703125,
0.055145263671875,
0.04901123046875,
-0.00983428955078125,
0.0380859375,
0.017913818359375,
-0.0005726814270019531,
-0.00972747802734375,
0.003437042236328125,
-0.0289459228515625,
0.0477294921875,
0.01305389404296875,
-0.038360595703125,
-0.007472991943359375,
0.00382232666015625,
0.007904052734375,
0.01044464111328125,
0.005168914794921875,
0.055755615234375,
0.01116180419921875,
-0.0447998046875,
0.0416259765625,
0.00518798828125,
0.072265625,
-0.03765869140625,
0.01141357421875,
-0.0184173583984375,
0.0199127197265625,
-0.0102386474609375,
-0.060791015625,
0.0182952880859375,
-0.024688720703125,
-0.0119781494140625,
-0.018585205078125,
0.04229736328125,
-0.0504150390625,
-0.0458984375,
0.038299560546875,
0.041595458984375,
0.00601959228515625,
-0.01035308837890625,
-0.08056640625,
-0.01554107666015625,
-0.0005044937133789062,
-0.0396728515625,
0.01806640625,
0.03546142578125,
0.0230712890625,
0.034027099609375,
0.039794921875,
-0.0220947265625,
0.01136016845703125,
0.00014352798461914062,
0.07061767578125,
-0.055389404296875,
-0.040191650390625,
-0.053924560546875,
0.04205322265625,
-0.02569580078125,
-0.039154052734375,
0.060791015625,
0.05255126953125,
0.07501220703125,
-0.00630950927734375,
0.043670654296875,
-0.00995635986328125,
0.030792236328125,
-0.040496826171875,
0.052093505859375,
-0.05401611328125,
-0.0015726089477539062,
-0.01666259765625,
-0.062042236328125,
-0.00731658935546875,
0.054473876953125,
-0.0264129638671875,
0.00200653076171875,
0.060394287109375,
0.0682373046875,
-0.002689361572265625,
-0.0075531005859375,
0.0109100341796875,
0.0276336669921875,
0.01361846923828125,
0.057647705078125,
0.039825439453125,
-0.06976318359375,
0.058685302734375,
-0.034576416015625,
-0.005237579345703125,
-0.01511383056640625,
-0.046875,
-0.06744384765625,
-0.06756591796875,
-0.029052734375,
-0.0377197265625,
-0.0125579833984375,
0.06744384765625,
0.043853759765625,
-0.056549072265625,
0.0016078948974609375,
-0.007740020751953125,
0.001125335693359375,
-0.0029544830322265625,
-0.024658203125,
0.044158935546875,
-0.0293121337890625,
-0.053802490234375,
0.01125335693359375,
-0.002811431884765625,
-0.004901885986328125,
-0.02593994140625,
0.0012941360473632812,
-0.05908203125,
0.00910186767578125,
0.049835205078125,
-0.0078887939453125,
-0.048095703125,
-0.0260467529296875,
0.0193023681640625,
-0.033447265625,
0.0036029815673828125,
0.022979736328125,
-0.052886962890625,
0.0291290283203125,
0.04913330078125,
0.044769287109375,
0.05853271484375,
-0.0017528533935546875,
0.027374267578125,
-0.058502197265625,
0.0071258544921875,
0.018524169921875,
0.033538818359375,
0.03729248046875,
-0.0257720947265625,
0.049957275390625,
0.026519775390625,
-0.04278564453125,
-0.041717529296875,
-0.006229400634765625,
-0.083251953125,
-0.0269775390625,
0.08905029296875,
-0.0223388671875,
-0.0172119140625,
0.00814056396484375,
-0.0192108154296875,
0.0261993408203125,
-0.0270538330078125,
0.059234619140625,
0.0633544921875,
-0.00594329833984375,
-0.0106353759765625,
-0.0262451171875,
0.029083251953125,
0.038177490234375,
-0.0516357421875,
-0.032562255859375,
0.027069091796875,
0.040771484375,
0.0296173095703125,
0.046417236328125,
-0.00894927978515625,
0.00446319580078125,
0.00360870361328125,
-0.0028896331787109375,
-0.01074981689453125,
0.006046295166015625,
-0.0246734619140625,
0.027008056640625,
-0.025054931640625,
-0.029510498046875
]
] |
sagorsarker/codeswitch-hineng-lid-lince | 2023-08-06T14:36:55.000Z | [
"transformers",
"pytorch",
"jax",
"safetensors",
"bert",
"token-classification",
"codeswitching",
"hindi-english",
"language-identification",
"hi",
"en",
"multilingual",
"dataset:lince",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | sagorsarker | null | null | sagorsarker/codeswitch-hineng-lid-lince | 0 | 46,914 | transformers | 2022-03-02T23:29:05 | ---
language:
- hi
- en
- multilingual
license: mit
tags:
- codeswitching
- hindi-english
- language-identification
datasets:
- lince
---
# codeswitch-hineng-lid-lince
This is a pretrained model for **language identification** of `hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home)
This model is trained for this below repository.
[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch)
To install codeswitch:
```
pip install codeswitch
```
## Identify Language
* **Method-1**
```py
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-lid-lince")
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-lid-lince")
lid_model = pipeline('ner', model=model, tokenizer=tokenizer)
lid_model("put any hindi english code-mixed sentence")
```
* **Method-2**
```py
from codeswitch.codeswitch import LanguageIdentification
lid = LanguageIdentification('hin-eng')
text = "" # your code-mixed sentence
result = lid.identify(text)
print(result)
```
| 1,149 | [
[
-0.0256500244140625,
-0.0186309814453125,
-0.0010042190551757812,
0.0255889892578125,
-0.0247650146484375,
0.00949859619140625,
-0.015289306640625,
-0.01016998291015625,
0.0178375244140625,
0.033172607421875,
-0.039459228515625,
-0.0222320556640625,
-0.05328369140625,
0.0079345703125,
-0.04168701171875,
0.0797119140625,
-0.017425537109375,
0.00763702392578125,
0.01763916015625,
-0.0008692741394042969,
-0.0247802734375,
-0.0275726318359375,
-0.0211181640625,
-0.021575927734375,
0.01137542724609375,
0.02935791015625,
0.036102294921875,
0.033477783203125,
0.0209197998046875,
0.0242156982421875,
0.007274627685546875,
-0.011322021484375,
-0.01450347900390625,
-0.00335693359375,
-0.00815582275390625,
-0.037322998046875,
-0.0020542144775390625,
0.002044677734375,
0.036346435546875,
0.0205535888671875,
-0.0096435546875,
0.0310821533203125,
0.0017843246459960938,
0.0186309814453125,
-0.057281494140625,
0.0179901123046875,
-0.0477294921875,
-0.0028896331787109375,
-0.0253753662109375,
-0.0132293701171875,
-0.02459716796875,
-0.02874755859375,
-0.00429534912109375,
-0.043243408203125,
0.005924224853515625,
-0.0019779205322265625,
0.10302734375,
0.027679443359375,
-0.0333251953125,
-0.030029296875,
-0.03643798828125,
0.062164306640625,
-0.06378173828125,
0.0278472900390625,
0.035125732421875,
0.0156097412109375,
0.0129241943359375,
-0.075927734375,
-0.036865234375,
-0.00464630126953125,
-0.0171051025390625,
-0.0036525726318359375,
0.0025653839111328125,
-0.016754150390625,
0.04315185546875,
0.02313232421875,
-0.047149658203125,
-0.00722503662109375,
-0.041748046875,
-0.049774169921875,
0.035186767578125,
0.00490570068359375,
0.044189453125,
-0.0216522216796875,
-0.02996826171875,
-0.007755279541015625,
-0.0233612060546875,
0.003330230712890625,
0.0306549072265625,
0.0150909423828125,
-0.035186767578125,
0.037750244140625,
-0.0308685302734375,
0.054412841796875,
-0.0029392242431640625,
-0.01334381103515625,
0.0526123046875,
-0.0253753662109375,
-0.0196533203125,
-0.00623321533203125,
0.06988525390625,
-0.005809783935546875,
0.037750244140625,
0.009185791015625,
-0.02685546875,
0.01532745361328125,
-0.0026111602783203125,
-0.055999755859375,
-0.033966064453125,
0.006076812744140625,
-0.03564453125,
-0.043426513671875,
0.0203399658203125,
-0.05096435546875,
0.003276824951171875,
-0.01432037353515625,
0.04644775390625,
-0.0201263427734375,
-0.040374755859375,
0.003925323486328125,
-0.00384521484375,
0.045257568359375,
-0.019866943359375,
-0.08477783203125,
0.0265655517578125,
0.02679443359375,
0.055145263671875,
0.004730224609375,
-0.05206298828125,
-0.017364501953125,
-0.01410675048828125,
-0.017059326171875,
0.0338134765625,
-0.0123138427734375,
0.00087738037109375,
0.00545501708984375,
0.029815673828125,
-0.024993896484375,
-0.036224365234375,
0.031341552734375,
-0.046539306640625,
0.032989501953125,
0.0105133056640625,
-0.0295867919921875,
0.00885772705078125,
0.005496978759765625,
-0.032135009765625,
0.08660888671875,
0.0261077880859375,
-0.0845947265625,
0.0200042724609375,
-0.05615234375,
-0.042083740234375,
0.0270538330078125,
-0.02020263671875,
-0.040679931640625,
-0.0140533447265625,
0.016021728515625,
0.0216064453125,
0.0033721923828125,
0.034423828125,
0.01090240478515625,
-0.0419921875,
0.0063323974609375,
-0.03338623046875,
0.102294921875,
0.040802001953125,
-0.04229736328125,
0.00885009765625,
-0.058319091796875,
0.01238250732421875,
0.0184783935546875,
-0.0213775634765625,
-0.00839996337890625,
-0.0204315185546875,
0.0305938720703125,
0.01406097412109375,
0.033935546875,
-0.036651611328125,
0.0235137939453125,
-0.03765869140625,
0.028900146484375,
0.040863037109375,
-0.0079345703125,
0.039642333984375,
-0.00554656982421875,
0.056243896484375,
0.00832366943359375,
0.0189361572265625,
-0.00830078125,
-0.035980224609375,
-0.06939697265625,
-0.018829345703125,
0.03924560546875,
0.05078125,
-0.0753173828125,
0.03759765625,
-0.01009368896484375,
-0.038055419921875,
-0.03436279296875,
-0.003383636474609375,
0.028656005859375,
0.0055389404296875,
0.013702392578125,
-0.0224151611328125,
-0.058837890625,
-0.06451416015625,
-0.0269012451171875,
0.001995086669921875,
-0.00716400146484375,
-0.003917694091796875,
0.060791015625,
-0.054718017578125,
0.06854248046875,
-0.04400634765625,
-0.0024814605712890625,
-0.0057525634765625,
0.0197601318359375,
0.0277557373046875,
0.04266357421875,
0.0322265625,
-0.042816162109375,
-0.046600341796875,
-0.01558685302734375,
-0.039337158203125,
-0.0196533203125,
-0.005344390869140625,
0.0014324188232421875,
0.01399993896484375,
0.034912109375,
-0.02410888671875,
0.035614013671875,
0.057891845703125,
-0.0262451171875,
0.06939697265625,
-0.0006785392761230469,
0.01514434814453125,
-0.09716796875,
0.010223388671875,
-0.034576416015625,
-0.0026988983154296875,
-0.0261688232421875,
0.017822265625,
0.035614013671875,
-0.0275115966796875,
-0.03729248046875,
0.057373046875,
-0.0367431640625,
0.01050567626953125,
-0.01187896728515625,
-0.03033447265625,
-0.01290130615234375,
0.036956787109375,
0.0015707015991210938,
0.06964111328125,
0.0823974609375,
-0.0447998046875,
0.040679931640625,
0.0227813720703125,
-0.042816162109375,
-0.01146697998046875,
-0.039306640625,
0.00376129150390625,
0.0226593017578125,
-0.00804901123046875,
-0.056854248046875,
-0.028594970703125,
0.036346435546875,
-0.0399169921875,
0.007015228271484375,
-0.0295867919921875,
-0.030914306640625,
-0.0304412841796875,
0.00899505615234375,
0.052337646484375,
0.0557861328125,
-0.0535888671875,
0.045318603515625,
0.0167694091796875,
-0.0095977783203125,
-0.06292724609375,
-0.059722900390625,
-0.00582122802734375,
-0.005157470703125,
-0.0242919921875,
-0.0004668235778808594,
-0.0035533905029296875,
0.0086669921875,
-0.01331329345703125,
-0.01000213623046875,
-0.035614013671875,
-0.005298614501953125,
0.006824493408203125,
0.01291656494140625,
-0.0160675048828125,
-0.0014390945434570312,
-0.00652313232421875,
-0.036285400390625,
0.00949859619140625,
-0.019866943359375,
0.059295654296875,
-0.019195556640625,
-0.0241546630859375,
-0.023712158203125,
-0.0025157928466796875,
0.039794921875,
-0.0379638671875,
0.0408935546875,
0.05975341796875,
-0.0207977294921875,
-0.02099609375,
-0.0311279296875,
-0.0190582275390625,
-0.039031982421875,
0.036895751953125,
-0.040374755859375,
-0.036102294921875,
0.045074462890625,
-0.00467681884765625,
-0.0187530517578125,
0.030029296875,
0.0355224609375,
0.00579833984375,
0.053436279296875,
0.04034423828125,
-0.0261688232421875,
0.042083740234375,
-0.01824951171875,
0.0362548828125,
-0.031463623046875,
-0.0017766952514648438,
-0.049041748046875,
0.0277252197265625,
-0.05023193359375,
-0.00021255016326904297,
-0.0037403106689453125,
0.0037689208984375,
-0.0210113525390625,
0.0589599609375,
-0.0509033203125,
0.0399169921875,
0.044036865234375,
-0.005588531494140625,
0.002323150634765625,
-0.00421142578125,
-0.0261993408203125,
0.007343292236328125,
-0.050048828125,
-0.030120849609375,
0.08160400390625,
0.03448486328125,
0.06939697265625,
-0.0086822509765625,
0.06695556640625,
-0.009857177734375,
-0.0005807876586914062,
-0.04229736328125,
0.026458740234375,
0.0084381103515625,
-0.06280517578125,
-0.007480621337890625,
-0.036895751953125,
-0.07122802734375,
-0.0016870498657226562,
-0.0015316009521484375,
-0.04290771484375,
0.0079345703125,
0.007686614990234375,
-0.0100860595703125,
0.0179290771484375,
-0.06646728515625,
0.07806396484375,
-0.027069091796875,
0.005084991455078125,
0.010345458984375,
-0.04010009765625,
0.03173828125,
-0.01461029052734375,
0.037506103515625,
0.011322021484375,
0.0190277099609375,
0.08392333984375,
-0.02899169921875,
0.056793212890625,
-0.013458251953125,
-0.00569915771484375,
0.00894927978515625,
0.0034770965576171875,
0.0211334228515625,
0.00696563720703125,
0.0084075927734375,
0.022705078125,
0.029052734375,
-0.050750732421875,
-0.0242767333984375,
0.04931640625,
-0.06597900390625,
-0.010833740234375,
-0.056121826171875,
-0.02935791015625,
0.01038360595703125,
0.034515380859375,
0.0548095703125,
0.048187255859375,
0.01525115966796875,
0.00652313232421875,
0.032928466796875,
-0.0186004638671875,
0.043060302734375,
0.031463623046875,
-0.031402587890625,
-0.0218658447265625,
0.062469482421875,
-0.00958251953125,
0.0215301513671875,
0.006191253662109375,
0.0166015625,
-0.01061248779296875,
-0.01229095458984375,
-0.02215576171875,
0.004131317138671875,
-0.057373046875,
-0.0083465576171875,
-0.030548095703125,
-0.056121826171875,
-0.037750244140625,
0.00853729248046875,
-0.0333251953125,
-0.004032135009765625,
-0.00384521484375,
0.01262664794921875,
0.02301025390625,
0.043060302734375,
-0.00830078125,
0.034210205078125,
-0.0526123046875,
0.039031982421875,
0.0272979736328125,
0.04425048828125,
-0.015350341796875,
-0.054351806640625,
-0.0428466796875,
0.006961822509765625,
-0.0006322860717773438,
-0.0714111328125,
0.0295867919921875,
-0.01385498046875,
0.04681396484375,
0.02093505859375,
-0.0012311935424804688,
0.0214080810546875,
-0.023284912109375,
0.0528564453125,
0.00923919677734375,
-0.08026123046875,
0.04107666015625,
-0.0116424560546875,
0.048309326171875,
0.045379638671875,
0.0306396484375,
-0.04071044921875,
-0.0188751220703125,
-0.046142578125,
-0.07696533203125,
0.05047607421875,
0.02655029296875,
0.018096923828125,
0.00518035888671875,
0.01210784912109375,
-0.0013227462768554688,
0.00904083251953125,
-0.10302734375,
-0.03436279296875,
-0.023529052734375,
-0.0283355712890625,
0.001194000244140625,
-0.0160064697265625,
0.0007290840148925781,
-0.035980224609375,
0.0645751953125,
0.0028553009033203125,
0.023895263671875,
-0.0038967132568359375,
-0.032623291015625,
0.001003265380859375,
0.02545166015625,
0.0316162109375,
0.046051025390625,
-0.0142669677734375,
0.00702667236328125,
0.01006317138671875,
-0.054779052734375,
0.00980377197265625,
-0.005275726318359375,
-0.0165252685546875,
0.01062774658203125,
0.046783447265625,
0.06195068359375,
0.0082855224609375,
-0.024871826171875,
0.05499267578125,
-0.0164794921875,
-0.0174713134765625,
-0.043426513671875,
0.00325775146484375,
0.002178192138671875,
0.0003113746643066406,
0.0280303955078125,
0.029754638671875,
-0.0034389495849609375,
-0.0230560302734375,
0.0244598388671875,
0.0114593505859375,
-0.0282745361328125,
0.00983428955078125,
0.033203125,
0.022796630859375,
-0.039947509765625,
0.053619384765625,
-0.0266265869140625,
-0.06829833984375,
0.06005859375,
0.036865234375,
0.07952880859375,
-0.0126190185546875,
0.00452423095703125,
0.051300048828125,
0.034027099609375,
0.0024356842041015625,
0.0256500244140625,
-0.0211944580078125,
-0.07086181640625,
-0.0266876220703125,
-0.05841064453125,
-0.0009479522705078125,
0.004486083984375,
-0.05633544921875,
0.0390625,
-0.0010995864868164062,
0.0132293701171875,
-0.01401519775390625,
0.0031223297119140625,
-0.0618896484375,
0.019805908203125,
-0.0026111602783203125,
0.06182861328125,
-0.1072998046875,
0.09832763671875,
0.02911376953125,
-0.043243408203125,
-0.0892333984375,
0.02130126953125,
-0.020050048828125,
-0.06427001953125,
0.056121826171875,
0.00934600830078125,
-0.005054473876953125,
0.026458740234375,
-0.046112060546875,
-0.072021484375,
0.05621337890625,
-0.0003991127014160156,
-0.04656982421875,
0.01552581787109375,
-0.0092926025390625,
0.020782470703125,
-0.0189971923828125,
0.04888916015625,
0.049041748046875,
0.034332275390625,
-0.0167083740234375,
-0.08984375,
-0.005023956298828125,
-0.04058837890625,
-0.006427764892578125,
0.01003265380859375,
-0.016082763671875,
0.056854248046875,
-0.00875091552734375,
-0.00637054443359375,
0.0122528076171875,
0.0159912109375,
0.027252197265625,
-0.007598876953125,
0.042388916015625,
0.0268707275390625,
0.0276031494140625,
-0.0167694091796875,
0.0526123046875,
-0.041290283203125,
0.0634765625,
0.07012939453125,
0.0010690689086914062,
0.051300048828125,
0.0404052734375,
-0.01102447509765625,
0.0574951171875,
0.046600341796875,
-0.02264404296875,
0.052093505859375,
0.01641845703125,
0.0008716583251953125,
0.00965118408203125,
0.034149169921875,
-0.047149658203125,
0.0264739990234375,
0.005168914794921875,
-0.01403045654296875,
-0.0056304931640625,
0.01450347900390625,
-0.0086822509765625,
-0.01470947265625,
0.0026531219482421875,
0.050140380859375,
-0.006938934326171875,
-0.044403076171875,
0.0687255859375,
-0.005077362060546875,
0.08160400390625,
-0.06756591796875,
0.0051116943359375,
-0.00429534912109375,
0.01202392578125,
-0.025970458984375,
-0.03973388671875,
0.018463134765625,
-0.01120758056640625,
-0.004734039306640625,
-0.0140838623046875,
0.0540771484375,
-0.05316162109375,
-0.031402587890625,
0.041595458984375,
0.0084228515625,
0.01934814453125,
0.0114898681640625,
-0.059539794921875,
0.0184783935546875,
0.0202178955078125,
-0.022979736328125,
0.0040130615234375,
0.00974273681640625,
0.01261138916015625,
0.042449951171875,
0.0340576171875,
0.011932373046875,
0.023681640625,
0.02850341796875,
0.048309326171875,
-0.03741455078125,
-0.045623779296875,
-0.0509033203125,
0.04376220703125,
-0.00044417381286621094,
-0.04254150390625,
0.054412841796875,
0.056549072265625,
0.08001708984375,
-0.047698974609375,
0.0609130859375,
-0.0252227783203125,
0.03192138671875,
-0.03839111328125,
0.06829833984375,
-0.036346435546875,
0.01522064208984375,
-0.024444580078125,
-0.06787109375,
-0.002262115478515625,
0.058502197265625,
-0.0223541259765625,
0.015380859375,
0.073486328125,
0.0888671875,
-0.037445068359375,
-0.02032470703125,
0.01470184326171875,
0.0179901123046875,
-0.005519866943359375,
0.0289306640625,
0.062255859375,
-0.06396484375,
0.042083740234375,
-0.04119873046875,
-0.0299835205078125,
-0.0035076141357421875,
-0.044464111328125,
-0.0643310546875,
-0.0570068359375,
-0.02685546875,
-0.03375244140625,
-0.01215362548828125,
0.06707763671875,
0.0694580078125,
-0.0853271484375,
-0.03851318359375,
-0.0194091796875,
-0.007419586181640625,
-0.00838470458984375,
-0.0241851806640625,
0.0211639404296875,
-0.039703369140625,
-0.04718017578125,
0.0116424560546875,
-0.008056640625,
-0.00070953369140625,
-0.0138092041015625,
-0.0165252685546875,
-0.0291595458984375,
-0.00504302978515625,
0.0021381378173828125,
0.027618408203125,
-0.05694580078125,
-0.01140594482421875,
-0.00921630859375,
-0.032501220703125,
-0.005985260009765625,
0.04718017578125,
-0.040374755859375,
0.03045654296875,
0.04693603515625,
0.0289459228515625,
0.0498046875,
-0.026641845703125,
0.039642333984375,
-0.0654296875,
0.043548583984375,
0.0083770751953125,
0.045379638671875,
0.0056915283203125,
-0.01215362548828125,
0.031768798828125,
0.02001953125,
-0.046051025390625,
-0.053375244140625,
0.026153564453125,
-0.0413818359375,
-0.0260009765625,
0.0841064453125,
-0.005252838134765625,
-0.0216217041015625,
-0.023529052734375,
-0.03045654296875,
0.0273590087890625,
0.0012044906616210938,
0.03900146484375,
0.04949951171875,
0.027679443359375,
-0.0272369384765625,
-0.021484375,
0.04022216796875,
0.03033447265625,
-0.0535888671875,
-0.0136260986328125,
-0.01428985595703125,
0.051300048828125,
0.01824951171875,
0.05377197265625,
-0.004489898681640625,
0.01558685302734375,
0.010986328125,
0.050445556640625,
0.0028438568115234375,
-0.0235443115234375,
-0.034942626953125,
-0.0188751220703125,
0.0013608932495117188,
-0.035614013671875
]
] |
sagorsarker/codeswitch-hineng-pos-lince | 2023-03-19T12:46:40.000Z | [
"transformers",
"pytorch",
"jax",
"safetensors",
"bert",
"token-classification",
"codeswitching",
"hindi-english",
"pos",
"hi",
"en",
"multilingual",
"dataset:lince",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | sagorsarker | null | null | sagorsarker/codeswitch-hineng-pos-lince | 1 | 46,897 | transformers | 2022-03-02T23:29:05 | ---
language:
- hi
- en
- multilingual
license: mit
tags:
- codeswitching
- hindi-english
- pos
datasets:
- lince
---
# codeswitch-hineng-pos-lince
This is a pretrained model for **Part of Speech Tagging** of `hindi-english` code-mixed data used from [LinCE](https://ritual.uh.edu/lince/home)
This model is trained for this below repository.
[https://github.com/sagorbrur/codeswitch](https://github.com/sagorbrur/codeswitch)
To install codeswitch:
```
pip install codeswitch
```
## Part-of-Speech Tagging of Hindi-English Mixed Data
* **Method-1**
```py
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("sagorsarker/codeswitch-hineng-pos-lince")
model = AutoModelForTokenClassification.from_pretrained("sagorsarker/codeswitch-hineng-pos-lince")
pos_model = pipeline('ner', model=model, tokenizer=tokenizer)
pos_model("put any hindi english code-mixed sentence")
```
* **Method-2**
```py
from codeswitch.codeswitch import POS
pos = POS('hin-eng')
text = "" # your mixed sentence
result = pos.tag(text)
print(result)
```
| 1,111 | [
[
-0.0186614990234375,
-0.019439697265625,
-0.00882720947265625,
0.0192108154296875,
-0.0301055908203125,
0.0014133453369140625,
-0.01140594482421875,
-0.00009369850158691406,
0.03173828125,
0.0281829833984375,
-0.042510986328125,
-0.02886962890625,
-0.053497314453125,
-0.00048661231994628906,
-0.03497314453125,
0.08563232421875,
-0.0038852691650390625,
0.0128631591796875,
0.022735595703125,
0.0026988983154296875,
-0.0265045166015625,
-0.043792724609375,
-0.021087646484375,
-0.0218505859375,
0.01288604736328125,
0.02691650390625,
0.03741455078125,
0.0301055908203125,
0.0199737548828125,
0.022216796875,
-0.00209808349609375,
-0.0032672882080078125,
-0.01134490966796875,
0.01012420654296875,
-0.0167694091796875,
-0.03814697265625,
-0.022064208984375,
0.00872802734375,
0.04241943359375,
0.0186920166015625,
-0.0214385986328125,
0.02825927734375,
-0.00437164306640625,
0.01015472412109375,
-0.04998779296875,
0.01557159423828125,
-0.052764892578125,
-0.0009164810180664062,
-0.020599365234375,
-0.006923675537109375,
-0.01995849609375,
-0.023651123046875,
0.0013818740844726562,
-0.042877197265625,
0.0019178390502929688,
-0.00524139404296875,
0.09381103515625,
0.034942626953125,
-0.0193023681640625,
-0.02593994140625,
-0.0302581787109375,
0.058441162109375,
-0.0775146484375,
0.0263824462890625,
0.04046630859375,
0.002712249755859375,
0.0133209228515625,
-0.08770751953125,
-0.042938232421875,
-0.005107879638671875,
-0.01065826416015625,
-0.0033206939697265625,
-0.00864410400390625,
-0.008636474609375,
0.042938232421875,
0.01049041748046875,
-0.045166015625,
-0.00656890869140625,
-0.0305023193359375,
-0.045135498046875,
0.03631591796875,
0.0012559890747070312,
0.033447265625,
-0.035614013671875,
-0.0305023193359375,
-0.0080413818359375,
-0.020965576171875,
-0.0018262863159179688,
0.034759521484375,
0.0175933837890625,
-0.0260009765625,
0.047027587890625,
-0.02374267578125,
0.062408447265625,
-0.00508880615234375,
-0.01369476318359375,
0.048370361328125,
-0.031005859375,
-0.0222625732421875,
-0.00397491455078125,
0.0689697265625,
-0.0012350082397460938,
0.04046630859375,
0.0146331787109375,
-0.0183258056640625,
0.030670166015625,
-0.006656646728515625,
-0.0478515625,
-0.0413818359375,
-0.00002300739288330078,
-0.0296630859375,
-0.027740478515625,
0.007389068603515625,
-0.052337646484375,
-0.004055023193359375,
-0.01074981689453125,
0.04815673828125,
-0.027191162109375,
-0.038909912109375,
0.0154571533203125,
-0.0062713623046875,
0.035247802734375,
-0.022735595703125,
-0.0755615234375,
0.0197601318359375,
0.0270233154296875,
0.05767822265625,
0.0195770263671875,
-0.053009033203125,
-0.032135009765625,
-0.0172119140625,
-0.00601959228515625,
0.043304443359375,
-0.0190277099609375,
-0.01436614990234375,
-0.0003256797790527344,
0.0081634521484375,
-0.036468505859375,
-0.027252197265625,
0.04833984375,
-0.030303955078125,
0.0301055908203125,
0.01422119140625,
-0.043060302734375,
0.0090789794921875,
0.0013217926025390625,
-0.01849365234375,
0.0848388671875,
0.010833740234375,
-0.08367919921875,
0.017822265625,
-0.058746337890625,
-0.045166015625,
0.0185089111328125,
-0.020172119140625,
-0.033935546875,
-0.0196685791015625,
0.014251708984375,
0.029388427734375,
0.0138702392578125,
0.033538818359375,
0.01534271240234375,
-0.033905029296875,
0.00746917724609375,
-0.0188446044921875,
0.0831298828125,
0.038330078125,
-0.0372314453125,
0.01467132568359375,
-0.052947998046875,
0.015777587890625,
0.01666259765625,
-0.024078369140625,
-0.002918243408203125,
-0.0010976791381835938,
0.01654052734375,
0.022918701171875,
0.019775390625,
-0.039154052734375,
0.02691650390625,
-0.048736572265625,
0.0458984375,
0.03424072265625,
-0.00910186767578125,
0.039703369140625,
-0.01471710205078125,
0.0496826171875,
0.0030689239501953125,
0.01149749755859375,
-0.0167236328125,
-0.042999267578125,
-0.0694580078125,
-0.01328277587890625,
0.046142578125,
0.047515869140625,
-0.0689697265625,
0.051116943359375,
-0.00824737548828125,
-0.045166015625,
-0.04559326171875,
-0.0123748779296875,
0.0265655517578125,
0.01605224609375,
0.018310546875,
-0.0236358642578125,
-0.06475830078125,
-0.0609130859375,
-0.032012939453125,
-0.0038776397705078125,
-0.0054931640625,
-0.012176513671875,
0.05560302734375,
-0.044219970703125,
0.07049560546875,
-0.044708251953125,
-0.00838470458984375,
-0.00930023193359375,
0.0267486572265625,
0.019989013671875,
0.04949951171875,
0.021270751953125,
-0.042388916015625,
-0.037139892578125,
-0.0296783447265625,
-0.0208740234375,
-0.01354217529296875,
0.002349853515625,
0.0020198822021484375,
0.0147552490234375,
0.0300750732421875,
-0.035888671875,
0.042938232421875,
0.0552978515625,
-0.03094482421875,
0.06927490234375,
0.004817962646484375,
0.008209228515625,
-0.0999755859375,
0.0031681060791015625,
-0.024688720703125,
-0.0130462646484375,
-0.029266357421875,
0.00569915771484375,
0.02203369140625,
-0.0307464599609375,
-0.03924560546875,
0.044525146484375,
-0.0305328369140625,
0.01183319091796875,
-0.01155853271484375,
-0.01568603515625,
-0.0105743408203125,
0.04376220703125,
-0.0022735595703125,
0.0640869140625,
0.08282470703125,
-0.044952392578125,
0.0377197265625,
0.0340576171875,
-0.035552978515625,
-0.0017194747924804688,
-0.041107177734375,
0.00970458984375,
0.0209197998046875,
0.002857208251953125,
-0.0673828125,
-0.0280914306640625,
0.041839599609375,
-0.056549072265625,
0.01000213623046875,
-0.023681640625,
-0.041748046875,
-0.025604248046875,
0.00191497802734375,
0.03955078125,
0.06005859375,
-0.040069580078125,
0.04302978515625,
0.0310211181640625,
-0.0124664306640625,
-0.0521240234375,
-0.06573486328125,
-0.003814697265625,
-0.00031876564025878906,
-0.03363037109375,
0.0034809112548828125,
-0.002628326416015625,
0.0133056640625,
-0.00849151611328125,
-0.0155181884765625,
-0.0197296142578125,
-0.0143585205078125,
0.0072174072265625,
0.00885772705078125,
-0.01338958740234375,
-0.0004131793975830078,
-0.015777587890625,
-0.030853271484375,
0.006443023681640625,
-0.0254364013671875,
0.0699462890625,
-0.01296234130859375,
-0.027130126953125,
-0.0306854248046875,
0.00432586669921875,
0.0230865478515625,
-0.043853759765625,
0.03631591796875,
0.05572509765625,
-0.0255889892578125,
-0.0234527587890625,
-0.025970458984375,
-0.01029205322265625,
-0.036468505859375,
0.0404052734375,
-0.02459716796875,
-0.0455322265625,
0.03765869140625,
-0.0055694580078125,
-0.014862060546875,
0.039337158203125,
0.031097412109375,
-0.0019989013671875,
0.066650390625,
0.031982421875,
-0.018096923828125,
0.04150390625,
-0.0245208740234375,
0.03948974609375,
-0.0399169921875,
-0.003841400146484375,
-0.05035400390625,
0.01525115966796875,
-0.046173095703125,
-0.01354217529296875,
-0.00205230712890625,
0.004886627197265625,
-0.0243072509765625,
0.046234130859375,
-0.061279296875,
0.03326416015625,
0.041259765625,
-0.01300811767578125,
-0.002094268798828125,
0.0029582977294921875,
-0.02020263671875,
0.000469207763671875,
-0.060150146484375,
-0.02880859375,
0.06689453125,
0.033905029296875,
0.07855224609375,
-0.0159912109375,
0.058929443359375,
-0.009918212890625,
-0.01336669921875,
-0.053558349609375,
0.0325927734375,
-0.004863739013671875,
-0.0582275390625,
-0.004184722900390625,
-0.02532958984375,
-0.0684814453125,
0.0031566619873046875,
-0.003566741943359375,
-0.04803466796875,
0.0032196044921875,
0.00826263427734375,
-0.021697998046875,
0.0289306640625,
-0.072021484375,
0.06646728515625,
-0.0165863037109375,
0.00791168212890625,
0.00701141357421875,
-0.051422119140625,
0.02435302734375,
0.0023136138916015625,
0.026519775390625,
0.003887176513671875,
0.0165863037109375,
0.10272216796875,
-0.02679443359375,
0.06396484375,
-0.0166168212890625,
-0.0016279220581054688,
0.017852783203125,
0.0002484321594238281,
0.02215576171875,
0.00382232666015625,
0.0097808837890625,
0.0202484130859375,
0.0211639404296875,
-0.04278564453125,
-0.0135650634765625,
0.04815673828125,
-0.058013916015625,
-0.01210784912109375,
-0.06640625,
-0.0267486572265625,
-0.0034275054931640625,
0.023284912109375,
0.05682373046875,
0.044677734375,
0.0186614990234375,
-0.005138397216796875,
0.036285400390625,
-0.01471710205078125,
0.040435791015625,
0.0241851806640625,
-0.027801513671875,
-0.031646728515625,
0.0555419921875,
0.0005669593811035156,
0.01480865478515625,
-0.0005655288696289062,
0.01043701171875,
-0.0172576904296875,
-0.012786865234375,
-0.01039886474609375,
0.0134429931640625,
-0.058319091796875,
-0.020477294921875,
-0.0384521484375,
-0.06201171875,
-0.048248291015625,
0.00807952880859375,
-0.034637451171875,
-0.010345458984375,
-0.014251708984375,
0.0089569091796875,
0.02484130859375,
0.048095703125,
-0.011505126953125,
0.04730224609375,
-0.052001953125,
0.03631591796875,
0.0232391357421875,
0.04547119140625,
-0.0160064697265625,
-0.060699462890625,
-0.039581298828125,
0.0108795166015625,
-0.00852203369140625,
-0.0755615234375,
0.036529541015625,
-0.006061553955078125,
0.045257568359375,
0.00565338134765625,
-0.01076507568359375,
0.031768798828125,
-0.0273895263671875,
0.06689453125,
0.017578125,
-0.0853271484375,
0.051177978515625,
-0.0159912109375,
0.04998779296875,
0.0340576171875,
0.0282745361328125,
-0.052947998046875,
-0.01093292236328125,
-0.054168701171875,
-0.0784912109375,
0.060699462890625,
0.0279083251953125,
0.0189361572265625,
0.0012674331665039062,
0.0070343017578125,
-0.004665374755859375,
0.0094757080078125,
-0.0888671875,
-0.035491943359375,
-0.033172607421875,
-0.02166748046875,
-0.003082275390625,
-0.0237884521484375,
0.0010652542114257812,
-0.04632568359375,
0.06939697265625,
0.0099029541015625,
0.0306243896484375,
0.01506805419921875,
-0.0244598388671875,
0.0001652240753173828,
0.03204345703125,
0.037445068359375,
0.041168212890625,
-0.01396942138671875,
0.007457733154296875,
0.003856658935546875,
-0.04931640625,
0.004833221435546875,
0.012298583984375,
-0.007259368896484375,
0.02008056640625,
0.0382080078125,
0.0716552734375,
0.0182342529296875,
-0.022796630859375,
0.0452880859375,
-0.016021728515625,
-0.0247344970703125,
-0.03277587890625,
0.0048828125,
0.01611328125,
-0.00286102294921875,
0.025299072265625,
0.039154052734375,
-0.0085601806640625,
-0.01483917236328125,
0.0217742919921875,
0.0036830902099609375,
-0.0172119140625,
-0.0014638900756835938,
0.038116455078125,
0.021270751953125,
-0.04766845703125,
0.039794921875,
-0.03033447265625,
-0.06866455078125,
0.04473876953125,
0.035308837890625,
0.0675048828125,
-0.019866943359375,
0.003398895263671875,
0.0482177734375,
0.0260162353515625,
0.00102996826171875,
0.0362548828125,
-0.0159912109375,
-0.05865478515625,
-0.036407470703125,
-0.0618896484375,
-0.004734039306640625,
0.0064697265625,
-0.04571533203125,
0.037017822265625,
-0.00432586669921875,
-0.004581451416015625,
-0.0027065277099609375,
0.002307891845703125,
-0.0535888671875,
0.020172119140625,
0.006771087646484375,
0.0687255859375,
-0.08392333984375,
0.09515380859375,
0.04632568359375,
-0.039794921875,
-0.0963134765625,
0.0189361572265625,
-0.030029296875,
-0.06280517578125,
0.04949951171875,
-0.0001291036605834961,
-0.00527191162109375,
0.033905029296875,
-0.050201416015625,
-0.07733154296875,
0.047271728515625,
-0.0010099411010742188,
-0.0516357421875,
0.005794525146484375,
-0.0107574462890625,
0.0216522216796875,
-0.01806640625,
0.0303955078125,
0.04974365234375,
0.0254058837890625,
-0.0084075927734375,
-0.0953369140625,
-0.020263671875,
-0.037811279296875,
-0.0114593505859375,
0.0109405517578125,
-0.0185546875,
0.068115234375,
-0.0024814605712890625,
-0.0093536376953125,
0.00865936279296875,
0.0244903564453125,
0.0245513916015625,
-0.000056743621826171875,
0.043792724609375,
0.037078857421875,
0.034576416015625,
-0.0143585205078125,
0.051910400390625,
-0.0292205810546875,
0.0618896484375,
0.08160400390625,
-0.0124053955078125,
0.056427001953125,
0.03125,
-0.0176544189453125,
0.051910400390625,
0.045318603515625,
-0.0147552490234375,
0.048370361328125,
0.022216796875,
-0.002216339111328125,
0.004329681396484375,
0.0202484130859375,
-0.047607421875,
0.038909912109375,
0.007343292236328125,
-0.0105133056640625,
-0.01511383056640625,
0.00988006591796875,
0.00453948974609375,
-0.005321502685546875,
-0.006488800048828125,
0.04730224609375,
-0.005123138427734375,
-0.0523681640625,
0.06756591796875,
0.0016012191772460938,
0.09832763671875,
-0.0726318359375,
0.0071258544921875,
0.0007724761962890625,
0.003849029541015625,
-0.026885986328125,
-0.0479736328125,
0.018585205078125,
0.004489898681640625,
0.0013217926025390625,
-0.01113128662109375,
0.0667724609375,
-0.052703857421875,
-0.0256805419921875,
0.031524658203125,
0.014434814453125,
0.02020263671875,
0.012359619140625,
-0.0626220703125,
0.01149749755859375,
0.0200347900390625,
-0.0244293212890625,
0.0009608268737792969,
0.0026149749755859375,
0.021820068359375,
0.034698486328125,
0.0328369140625,
0.020782470703125,
0.0321044921875,
0.0262298583984375,
0.057830810546875,
-0.043060302734375,
-0.056732177734375,
-0.055145263671875,
0.050994873046875,
0.0017404556274414062,
-0.040252685546875,
0.056884765625,
0.05035400390625,
0.07562255859375,
-0.02972412109375,
0.0650634765625,
-0.0232391357421875,
0.043487548828125,
-0.03485107421875,
0.06951904296875,
-0.029144287109375,
0.007404327392578125,
-0.0135345458984375,
-0.05902099609375,
-0.0035762786865234375,
0.0667724609375,
-0.0264739990234375,
0.0121917724609375,
0.0687255859375,
0.07672119140625,
-0.0220489501953125,
-0.00836181640625,
0.01526641845703125,
0.0205535888671875,
-0.003551483154296875,
0.023468017578125,
0.06927490234375,
-0.05462646484375,
0.0384521484375,
-0.035675048828125,
-0.021087646484375,
0.00476837158203125,
-0.046722412109375,
-0.059661865234375,
-0.059356689453125,
-0.0285491943359375,
-0.03411865234375,
-0.01062774658203125,
0.0712890625,
0.07452392578125,
-0.0716552734375,
-0.031402587890625,
-0.007808685302734375,
-0.012664794921875,
0.01212310791015625,
-0.0217437744140625,
0.0190277099609375,
-0.0406494140625,
-0.04119873046875,
0.01534271240234375,
-0.00994873046875,
-0.0021820068359375,
-0.007122039794921875,
-0.01035308837890625,
-0.052764892578125,
0.003753662109375,
0.006195068359375,
0.01953125,
-0.04931640625,
-0.004116058349609375,
-0.0117034912109375,
-0.0252227783203125,
-0.0001780986785888672,
0.04931640625,
-0.045654296875,
0.0259552001953125,
0.04339599609375,
0.019439697265625,
0.0487060546875,
-0.019866943359375,
0.0272979736328125,
-0.0809326171875,
0.038604736328125,
0.022125244140625,
0.04669189453125,
0.0173492431640625,
-0.01020050048828125,
0.0287322998046875,
0.021331787109375,
-0.054595947265625,
-0.05853271484375,
0.021759033203125,
-0.049072265625,
-0.027191162109375,
0.094970703125,
-0.004734039306640625,
-0.018890380859375,
-0.0081939697265625,
-0.04180908203125,
0.05035400390625,
-0.00496673583984375,
0.0272369384765625,
0.05023193359375,
0.0101165771484375,
-0.00384521484375,
-0.0180206298828125,
0.04339599609375,
0.0411376953125,
-0.045379638671875,
-0.012359619140625,
-0.003093719482421875,
0.04583740234375,
0.01788330078125,
0.0606689453125,
0.0030231475830078125,
0.01189422607421875,
0.01255035400390625,
0.0491943359375,
-0.0009355545043945312,
-0.01451873779296875,
-0.04205322265625,
-0.0147857666015625,
-0.002407073974609375,
-0.04608154296875
]
] |
Gryphe/MythoMax-L2-13b | 2023-09-04T18:58:36.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"en",
"license:other",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | Gryphe | null | null | Gryphe/MythoMax-L2-13b | 133 | 46,849 | transformers | 2023-08-10T20:35:34 | ---
license: other
language:
- en
---
An improved, potentially even perfected variant of MythoMix, my [MythoLogic-L2](https://huggingface.co/Gryphe/MythoLogic-L2-13b) and [Huginn](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model, resulting in increased coherency across the entire structure.
The script and the acccompanying templates I used to produce both can [be found here](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML).
This model is proficient at both roleplaying and storywriting due to its unique nature.
Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoMax-L2-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ) (You're the best!)
## Model details
The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time)
This type of merge is incapable of being illustrated, as each of its 363 tensors had an unique ratio applied to it. As with my prior merges, gradients were part of these ratios to further finetune its behaviour.
## Prompt Format
This model primarily uses Alpaca formatting, so for optimal model performance, use:
```
<System prompt/Character Card>
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
---
license: other
--- | 1,929 | [
[
-0.033447265625,
-0.04376220703125,
0.018157958984375,
-0.000911712646484375,
-0.02197265625,
0.012420654296875,
-0.007354736328125,
-0.0556640625,
0.03204345703125,
0.0311279296875,
-0.0347900390625,
-0.0223236083984375,
-0.037841796875,
-0.0081939697265625,
-0.02301025390625,
0.09619140625,
-0.01873779296875,
0.0082855224609375,
-0.01018524169921875,
-0.0249481201171875,
-0.01502227783203125,
-0.0268707275390625,
-0.07318115234375,
-0.038787841796875,
0.04693603515625,
-0.01070404052734375,
0.0655517578125,
0.05718994140625,
0.04656982421875,
0.023895263671875,
-0.017669677734375,
0.0364990234375,
-0.060638427734375,
0.0034084320068359375,
0.006679534912109375,
-0.039886474609375,
-0.05914306640625,
0.020599365234375,
0.05767822265625,
0.040374755859375,
-0.02783203125,
0.0135040283203125,
0.005859375,
0.0306549072265625,
-0.0214385986328125,
-0.00983428955078125,
0.0058135986328125,
0.029571533203125,
-0.005138397216796875,
0.0012502670288085938,
-0.004100799560546875,
-0.0579833984375,
0.00627899169921875,
-0.06500244140625,
0.011993408203125,
0.01641845703125,
0.065673828125,
0.019561767578125,
-0.0200347900390625,
-0.00711822509765625,
-0.04425048828125,
0.04656982421875,
-0.052642822265625,
0.021514892578125,
0.0211181640625,
0.0273590087890625,
0.007595062255859375,
-0.06488037109375,
-0.0303955078125,
-0.01525115966796875,
-0.024169921875,
0.0184173583984375,
-0.04833984375,
-0.0073089599609375,
0.036590576171875,
0.05316162109375,
-0.048095703125,
0.0162506103515625,
-0.0574951171875,
-0.0243988037109375,
0.038970947265625,
0.0257110595703125,
0.01312255859375,
-0.014678955078125,
-0.04888916015625,
-0.022979736328125,
-0.03594970703125,
-0.005462646484375,
0.05718994140625,
-0.00482940673828125,
-0.024169921875,
0.06256103515625,
0.009765625,
0.05487060546875,
0.026336669921875,
-0.016387939453125,
0.007770538330078125,
-0.0311737060546875,
-0.0240478515625,
-0.0128326416015625,
0.057891845703125,
0.045074462890625,
-0.00502777099609375,
0.00048160552978515625,
-0.0157470703125,
0.0157318115234375,
0.01947021484375,
-0.06707763671875,
-0.0120697021484375,
0.0306549072265625,
-0.040618896484375,
-0.05712890625,
-0.02899169921875,
-0.031890869140625,
-0.0294647216796875,
-0.030120849609375,
0.038818359375,
-0.05877685546875,
-0.0372314453125,
0.01025390625,
-0.024261474609375,
0.0212249755859375,
0.0288238525390625,
-0.0374755859375,
0.026092529296875,
0.0496826171875,
0.0645751953125,
-0.0113677978515625,
-0.0134735107421875,
-0.040069580078125,
-0.0201873779296875,
-0.06329345703125,
0.029205322265625,
-0.019439697265625,
-0.0197601318359375,
-0.006103515625,
-0.035369873046875,
0.011993408203125,
-0.040618896484375,
0.049896240234375,
-0.04046630859375,
0.06231689453125,
-0.0181884765625,
-0.05682373046875,
-0.010711669921875,
0.00910186767578125,
-0.061370849609375,
0.057281494140625,
0.03790283203125,
-0.060455322265625,
0.0137176513671875,
-0.034149169921875,
-0.004619598388671875,
0.01468658447265625,
0.010650634765625,
-0.0270843505859375,
0.01015472412109375,
-0.0110931396484375,
0.0232696533203125,
-0.03515625,
0.0250244140625,
-0.0361328125,
-0.0233306884765625,
0.0184783935546875,
-0.009368896484375,
0.0528564453125,
0.03607177734375,
-0.0092315673828125,
-0.0014362335205078125,
-0.053741455078125,
0.0024204254150390625,
-0.004100799560546875,
-0.00540924072265625,
-0.020477294921875,
-0.055511474609375,
0.0229949951171875,
0.0058746337890625,
0.0199127197265625,
-0.0102996826171875,
0.037994384765625,
0.0115509033203125,
0.02557373046875,
0.034332275390625,
-0.0160064697265625,
0.053558349609375,
-0.052642822265625,
0.0430908203125,
-0.0012731552124023438,
0.01038360595703125,
-0.001369476318359375,
-0.0255279541015625,
-0.06243896484375,
-0.05633544921875,
0.040802001953125,
0.0288238525390625,
-0.051483154296875,
0.0146026611328125,
0.00537872314453125,
-0.0574951171875,
-0.0552978515625,
-0.0178680419921875,
0.054534912109375,
0.050445556640625,
0.02923583984375,
-0.037200927734375,
-0.040191650390625,
-0.07525634765625,
-0.01371002197265625,
-0.03057861328125,
-0.00899505615234375,
0.0257720947265625,
-0.01081085205078125,
-0.02435302734375,
0.048614501953125,
-0.056793212890625,
-0.0200042724609375,
-0.006137847900390625,
0.031890869140625,
0.0275726318359375,
0.05523681640625,
0.060028076171875,
-0.036102294921875,
-0.0207672119140625,
0.01151275634765625,
-0.0726318359375,
0.0000022649765014648438,
0.0053558349609375,
-0.025848388671875,
0.0091705322265625,
0.0150604248046875,
-0.0716552734375,
0.022918701171875,
0.029266357421875,
-0.034515380859375,
0.044647216796875,
-0.019744873046875,
0.040069580078125,
-0.0966796875,
0.025848388671875,
0.01470947265625,
-0.0283660888671875,
-0.0697021484375,
0.040191650390625,
0.0036830902099609375,
-0.00664520263671875,
-0.016204833984375,
0.04345703125,
-0.033447265625,
0.01163482666015625,
-0.0020656585693359375,
-0.02886962890625,
-0.0210418701171875,
0.0254974365234375,
-0.0042724609375,
0.03814697265625,
0.05255126953125,
-0.0321044921875,
0.047882080078125,
0.0302276611328125,
-0.0104827880859375,
0.052490234375,
-0.053955078125,
0.00891876220703125,
-0.02349853515625,
0.032745361328125,
-0.06597900390625,
-0.034332275390625,
0.03692626953125,
-0.017822265625,
0.038330078125,
-0.016693115234375,
-0.019134521484375,
-0.036956787109375,
-0.03912353515625,
0.045928955078125,
0.07537841796875,
-0.04302978515625,
0.06201171875,
-0.006008148193359375,
0.0020275115966796875,
-0.04833984375,
-0.0506591796875,
-0.0060882568359375,
-0.0423583984375,
-0.047119140625,
0.027252197265625,
-0.0271148681640625,
-0.00728607177734375,
0.01012420654296875,
-0.003871917724609375,
-0.01285552978515625,
-0.0275115966796875,
0.00630950927734375,
0.0638427734375,
-0.03326416015625,
-0.0263519287109375,
0.015594482421875,
0.0013628005981445312,
-0.0271148681640625,
-0.0162200927734375,
0.042083740234375,
-0.006847381591796875,
0.0178375244140625,
-0.041717529296875,
0.0225372314453125,
0.06439208984375,
-0.0036869049072265625,
0.040802001953125,
0.0703125,
-0.037689208984375,
0.01157379150390625,
-0.06500244140625,
-0.0111846923828125,
-0.03167724609375,
-0.00023853778839111328,
-0.0213623046875,
-0.0889892578125,
0.053375244140625,
0.01244354248046875,
0.01256561279296875,
0.032379150390625,
0.0164031982421875,
-0.0161590576171875,
0.046417236328125,
0.048980712890625,
-0.0006608963012695312,
0.02227783203125,
-0.0340576171875,
0.02398681640625,
-0.06390380859375,
-0.0210723876953125,
-0.00927734375,
-0.0281219482421875,
-0.0556640625,
-0.05181884765625,
0.030975341796875,
0.0212554931640625,
0.0019550323486328125,
0.05242919921875,
-0.0184326171875,
0.0234527587890625,
0.035919189453125,
0.01436614990234375,
0.0241851806640625,
0.030731201171875,
0.00785064697265625,
-0.00959014892578125,
-0.056060791015625,
-0.018798828125,
0.0770263671875,
0.040283203125,
0.06719970703125,
0.01523590087890625,
0.06884765625,
0.01001739501953125,
0.0202484130859375,
-0.044647216796875,
0.030792236328125,
-0.01094818115234375,
-0.034271240234375,
-0.0142822265625,
-0.042510986328125,
-0.040802001953125,
0.0251312255859375,
-0.0430908203125,
-0.0280609130859375,
0.023712158203125,
0.038330078125,
-0.04974365234375,
0.01308441162109375,
-0.055816650390625,
0.04022216796875,
0.018524169921875,
-0.038421630859375,
-0.0362548828125,
-0.037445068359375,
0.06866455078125,
-0.0179901123046875,
-0.0107421875,
0.0263519287109375,
0.00278472900390625,
0.04254150390625,
-0.035125732421875,
0.037841796875,
0.01727294921875,
-0.0172119140625,
0.0228729248046875,
0.026947021484375,
0.0247802734375,
-0.0009226799011230469,
0.0180816650390625,
0.0150604248046875,
-0.004024505615234375,
-0.0204620361328125,
-0.0565185546875,
0.05804443359375,
-0.0723876953125,
-0.03961181640625,
-0.032501220703125,
-0.042449951171875,
-0.00122833251953125,
-0.0015897750854492188,
0.02935791015625,
0.0709228515625,
-0.0223541259765625,
-0.007595062255859375,
0.0565185546875,
0.006488800048828125,
0.02484130859375,
0.03192138671875,
-0.033905029296875,
-0.052154541015625,
0.049530029296875,
-0.009002685546875,
0.0155792236328125,
0.021820068359375,
0.00862884521484375,
-0.02825927734375,
-0.0028705596923828125,
-0.0259552001953125,
0.049072265625,
-0.03448486328125,
-0.033538818359375,
-0.050628662109375,
-0.03326416015625,
-0.0272369384765625,
-0.005535125732421875,
-0.019775390625,
-0.061767578125,
-0.01168060302734375,
-0.005336761474609375,
0.033355712890625,
0.059326171875,
-0.037109375,
0.011444091796875,
-0.04302978515625,
0.026824951171875,
0.02532958984375,
0.0287628173828125,
-0.007472991943359375,
-0.0469970703125,
0.0098419189453125,
-0.0202789306640625,
0.003406524658203125,
-0.055023193359375,
0.0265045166015625,
-0.00720977783203125,
0.01039886474609375,
0.033172607421875,
-0.0175323486328125,
0.0618896484375,
-0.033111572265625,
0.044830322265625,
0.061248779296875,
-0.051666259765625,
0.01123046875,
-0.03155517578125,
-0.0004973411560058594,
0.01776123046875,
0.05267333984375,
-0.044189453125,
-0.03662109375,
-0.064697265625,
-0.043701171875,
0.06085205078125,
0.035736083984375,
-0.0175323486328125,
0.029296875,
0.033416748046875,
0.021240234375,
0.0202484130859375,
-0.029327392578125,
-0.0418701171875,
-0.019439697265625,
-0.0032291412353515625,
-0.0169525146484375,
-0.028564453125,
-0.0477294921875,
-0.0233917236328125,
0.04241943359375,
0.00586700439453125,
0.0223236083984375,
0.0008335113525390625,
0.0138092041015625,
-0.0218048095703125,
-0.01129913330078125,
0.04388427734375,
0.03924560546875,
-0.0186309814453125,
0.0163726806640625,
0.003612518310546875,
-0.037445068359375,
-0.00679779052734375,
0.027618408203125,
-0.0016679763793945312,
0.00470733642578125,
0.042999267578125,
0.08172607421875,
0.001926422119140625,
-0.01509857177734375,
0.012664794921875,
-0.02117919921875,
-0.0291290283203125,
0.01251220703125,
0.01381683349609375,
-0.00033211708068847656,
0.036865234375,
0.00789642333984375,
0.04376220703125,
0.01454925537109375,
-0.040191650390625,
0.01018524169921875,
0.023529052734375,
-0.01227569580078125,
-0.0098724365234375,
0.05047607421875,
0.00736236572265625,
-0.013641357421875,
0.040130615234375,
-0.010162353515625,
-0.0325927734375,
0.033935546875,
0.039154052734375,
0.056549072265625,
-0.0300750732421875,
0.034881591796875,
0.055694580078125,
0.0132904052734375,
-0.0163726806640625,
0.0017232894897460938,
-0.0019702911376953125,
-0.03411865234375,
-0.0255279541015625,
-0.03656005859375,
-0.02032470703125,
0.0164642333984375,
-0.05755615234375,
0.031097412109375,
-0.0382080078125,
-0.0175323486328125,
0.004329681396484375,
-0.00319671630859375,
-0.05291748046875,
0.0223388671875,
0.005817413330078125,
0.06390380859375,
-0.07147216796875,
0.03790283203125,
0.0579833984375,
-0.0213470458984375,
-0.082275390625,
-0.0165252685546875,
-0.0160980224609375,
-0.058929443359375,
0.0161590576171875,
-0.01995849609375,
0.0123138427734375,
-0.01187896728515625,
-0.04022216796875,
-0.07867431640625,
0.10272216796875,
0.035186767578125,
-0.048431396484375,
0.000812530517578125,
-0.005107879638671875,
0.060150146484375,
-0.0296478271484375,
0.046295166015625,
0.052642822265625,
0.016998291015625,
0.03118896484375,
-0.08026123046875,
0.01403045654296875,
-0.0206146240234375,
0.017120361328125,
0.01219940185546875,
-0.0657958984375,
0.061431884765625,
-0.0135345458984375,
-0.001804351806640625,
0.0305328369140625,
0.06353759765625,
0.0277252197265625,
0.00814056396484375,
0.043731689453125,
0.0762939453125,
0.07110595703125,
-0.00870513916015625,
0.086669921875,
-0.0248870849609375,
0.03985595703125,
0.047332763671875,
0.0022640228271484375,
0.03167724609375,
0.0234527587890625,
-0.005558013916015625,
0.01074981689453125,
0.05328369140625,
0.0018606185913085938,
0.035736083984375,
0.0002522468566894531,
-0.01934814453125,
-0.02679443359375,
-0.01317596435546875,
-0.056427001953125,
0.01416015625,
-0.01256561279296875,
-0.003475189208984375,
-0.00891876220703125,
-0.018951416015625,
0.0255279541015625,
-0.01245880126953125,
-0.01218414306640625,
0.02801513671875,
0.005199432373046875,
-0.06829833984375,
0.050994873046875,
0.006832122802734375,
0.0634765625,
-0.06280517578125,
0.0013513565063476562,
-0.053558349609375,
-0.00005841255187988281,
-0.0148773193359375,
-0.056610107421875,
0.0003864765167236328,
-0.00733184814453125,
-0.0122528076171875,
-0.01340484619140625,
0.055023193359375,
-0.07891845703125,
-0.0213623046875,
0.006816864013671875,
0.033782958984375,
0.00826263427734375,
0.04327392578125,
-0.035552978515625,
0.0347900390625,
-0.005596160888671875,
0.006778717041015625,
0.0177764892578125,
0.00858306884765625,
0.003696441650390625,
0.042816162109375,
0.0374755859375,
0.0019989013671875,
-0.01113128662109375,
0.002964019775390625,
0.07781982421875,
-0.01532745361328125,
-0.039337158203125,
-0.036285400390625,
0.0277557373046875,
-0.01544952392578125,
-0.04400634765625,
0.0280914306640625,
0.0611572265625,
0.038543701171875,
-0.0294189453125,
0.048095703125,
-0.0096435546875,
0.01149749755859375,
-0.037872314453125,
0.059967041015625,
-0.057281494140625,
-0.0135040283203125,
-0.0156402587890625,
-0.09100341796875,
-0.00469207763671875,
0.032806396484375,
0.01611328125,
-0.00909423828125,
0.069580078125,
0.052001953125,
-0.0247955322265625,
-0.00286102294921875,
0.033447265625,
0.01995849609375,
0.006374359130859375,
0.0406494140625,
0.071533203125,
-0.04730224609375,
0.0151519775390625,
-0.01366424560546875,
-0.04083251953125,
-0.00551605224609375,
-0.05816650390625,
-0.072021484375,
-0.0469970703125,
-0.046295166015625,
-0.05181884765625,
0.01406097412109375,
0.0654296875,
0.05303955078125,
-0.034637451171875,
-0.01959228515625,
0.0180816650390625,
-0.011810302734375,
-0.0127105712890625,
-0.014190673828125,
0.00798797607421875,
-0.002536773681640625,
-0.06610107421875,
0.01348876953125,
0.01116943359375,
0.0202178955078125,
-0.003734588623046875,
-0.01224517822265625,
0.03594970703125,
0.012237548828125,
0.0303955078125,
0.0263214111328125,
-0.047515869140625,
-0.01187896728515625,
-0.002017974853515625,
-0.01219940185546875,
-0.0189361572265625,
0.072265625,
-0.041046142578125,
0.01361846923828125,
0.0253143310546875,
0.039764404296875,
0.05364990234375,
-0.0060272216796875,
0.05767822265625,
-0.0281219482421875,
-0.0035839080810546875,
0.00215911865234375,
0.0252532958984375,
0.033172607421875,
-0.040252685546875,
0.051300048828125,
0.027008056640625,
-0.01418304443359375,
-0.067138671875,
0.0164337158203125,
-0.1094970703125,
0.0098419189453125,
0.09027099609375,
0.005802154541015625,
0.00017952919006347656,
0.05401611328125,
-0.032440185546875,
0.0286865234375,
-0.01678466796875,
0.042449951171875,
0.051971435546875,
-0.006183624267578125,
-0.00418853759765625,
0.00547027587890625,
0.054779052734375,
0.0421142578125,
-0.046417236328125,
-0.01334381103515625,
0.040435791015625,
0.0254974365234375,
0.01326751708984375,
0.04229736328125,
-0.017425537109375,
0.037109375,
-0.01190948486328125,
0.0018558502197265625,
-0.0106353759765625,
-0.013641357421875,
-0.036712646484375,
0.00815582275390625,
-0.015289306640625,
-0.004375457763671875
]
] |
BAAI/bge-reranker-base | 2023-10-12T03:38:37.000Z | [
"transformers",
"pytorch",
"xlm-roberta",
"text-classification",
"arxiv:2310.07554",
"arxiv:2309.07597",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-classification | BAAI | null | null | BAAI/bge-reranker-base | 14 | 46,790 | transformers | 2023-09-11T12:30:04 | ---
license: mit
---
<h1 align="center">FlagEmbedding</h1>
<h4 align="center">
<p>
<a href=#model-list>Model List</a> |
<a href=#frequently-asked-questions>FAQ</a> |
<a href=#usage>Usage</a> |
<a href="#evaluation">Evaluation</a> |
<a href="#train">Train</a> |
<a href="#contact">Contact</a> |
<a href="#citation">Citation</a> |
<a href="#license">License</a>
<p>
</h4>
More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
[English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
And it also can be used in vector databases for LLMs.
************* 🌟**Updates**🌟 *************
- 10/12/2023: Release [LLM-Embedder](./FlagEmbedding/llm_embedder/README.md), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Paper](https://arxiv.org/pdf/2310.07554.pdf) :fire:
- 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released
- 09/15/2023: The [masive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released
- 09/12/2023: New models:
- **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.
- **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
<details>
<summary>More</summary>
<!-- ### More -->
- 09/07/2023: Update [fine-tune code](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md): Add script to mine hard negatives and support adding instruction during fine-tuning.
- 08/09/2023: BGE Models are integrated into **Langchain**, you can use it like [this](#using-langchain); C-MTEB **leaderboard** is [available](https://huggingface.co/spaces/mteb/leaderboard).
- 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗**
- 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!** :tada: :tada:
- 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (**C-MTEB**), consisting of 31 test dataset.
</details>
## Model List
`bge` is short for `BAAI general embedding`.
| Model | Language | | Description | query instruction for retrieval [1] |
|:-------------------------------|:--------:| :--------:| :--------:|:--------:|
| [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) |
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-en` | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) |a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：` |
[1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, **no instruction** needs to be added to passages.
[2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models.
For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results.
All models have been uploaded to Huggingface Hub, and you can see them at https://huggingface.co/BAAI.
If you cannot open the Huggingface Hub, you also can download the models at https://model.baai.ac.cn/models .
## Frequently asked questions
<details>
<summary>1. How to fine-tune bge embedding model?</summary>
<!-- ### How to fine-tune bge embedding model? -->
Following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) to prepare data and fine-tune your model.
Some suggestions:
- Mine hard negatives following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune#hard-negatives), which can improve the retrieval performance.
- If you pre-train bge on your data, the pre-trained model cannot be directly used to calculate similarity, and it must be fine-tuned with contrastive learning before computing similarity.
- If the accuracy of the fine-tuned model is still not high, it is recommended to use/fine-tune the cross-encoder model (bge-reranker) to re-rank top-k results. Hard negatives also are needed to fine-tune reranker.
</details>
<details>
<summary>2. The similarity score between two dissimilar sentences is higher than 0.5</summary>
<!-- ### The similarity score between two dissimilar sentences is higher than 0.5 -->
**Suggest to use bge v1.5, which alleviates the issue of the similarity distribution.**
Since we finetune the models by contrastive learning with a temperature of 0.01,
the similarity distribution of the current BGE model is about in the interval \[0.6, 1\].
So a similarity score greater than 0.5 does not indicate that the two sentences are similar.
For downstream tasks, such as passage retrieval or semantic similarity,
**what matters is the relative order of the scores, not the absolute value.**
If you need to filter similar sentences based on a similarity threshold,
please select an appropriate similarity threshold based on the similarity distribution on your data (such as 0.8, 0.85, or even 0.9).
</details>
<details>
<summary>3. When does the query instruction need to be used</summary>
<!-- ### When does the query instruction need to be used -->
For the `bge-*-v1.5`, we improve its retrieval ability when not using instruction.
No instruction only has a slight degradation in retrieval performance compared with using instruction.
So you can generate embedding without instruction in all cases for convenience.
For a retrieval task that uses short queries to find long related documents,
it is recommended to add instructions for these short queries.
**The best method to decide whether to add instructions for queries is choosing the setting that achieves better performance on your task.**
In all cases, the documents/passages do not need to add the instruction.
</details>
## Usage
### Usage for Embedding Model
Here are some examples for using `bge` models with
[FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers).
#### Using FlagEmbedding
```
pip install -U FlagEmbedding
```
If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding.
```python
from FlagEmbedding import FlagModel
sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-4"]
model = FlagModel('BAAI/bge-large-zh-v1.5',
query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章：",
use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
embeddings_1 = model.encode(sentences_1)
embeddings_2 = model.encode(sentences_2)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
# for s2p(short query to long passage) retrieval task, suggest to use encode_queries() which will automatically add the instruction to each query
# corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction
queries = ['query_1', 'query_2']
passages = ["样例文档-1", "样例文档-2"]
q_embeddings = model.encode_queries(queries)
p_embeddings = model.encode(passages)
scores = q_embeddings @ p_embeddings.T
```
For the value of the argument `query_instruction_for_retrieval`, see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list).
By default, FlagModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs.
You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable.
#### Using Sentence-Transformers
You can also use the `bge` models with [sentence-transformers](https://www.SBERT.net):
```
pip install -U sentence-transformers
```
```python
from sentence_transformers import SentenceTransformer
sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-4"]
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
```
For s2p(short query to long passage) retrieval task,
each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)).
But the instruction is not needed for passages.
```python
from sentence_transformers import SentenceTransformer
queries = ['query_1', 'query_2']
passages = ["样例文档-1", "样例文档-2"]
instruction = "为这个句子生成表示以用于检索相关文章："
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)
scores = q_embeddings @ p_embeddings.T
```
#### Using Langchain
You can use `bge` in langchain like this:
```python
from langchain.embeddings import HuggingFaceBgeEmbeddings
model_name = "BAAI/bge-large-en-v1.5"
model_kwargs = {'device': 'cuda'}
encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
model = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs,
query_instruction="为这个句子生成表示以用于检索相关文章："
)
model.query_instruction = "为这个句子生成表示以用于检索相关文章："
```
#### Using HuggingFace Transformers
With the transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of the first token (i.e., [CLS]) as the sentence embedding.
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Sentences we want sentence embeddings for
sentences = ["样例数据-1", "样例数据-2"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh-v1.5')
model = AutoModel.from_pretrained('BAAI/bge-large-zh-v1.5')
model.eval()
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages)
# encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, cls pooling.
sentence_embeddings = model_output[0][:, 0]
# normalize embeddings
sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:", sentence_embeddings)
```
### Usage for Reranker
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding.
You can get a relevance score by inputting query and passage to the reranker.
The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range.
#### Using FlagEmbedding
```
pip install -U FlagEmbedding
```
Get relevance scores (higher scores indicate more relevance):
```python
from FlagEmbedding import FlagReranker
reranker = FlagReranker('BAAI/bge-reranker-large', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'])
print(score)
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
print(scores)
```
#### Using Huggingface transformers
```python
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large')
model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-large')
model.eval()
pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
with torch.no_grad():
inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
print(scores)
```
## Evaluation
`baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!**
For more details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md).
- **MTEB**:
| Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) |
|:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | **64.23** | **54.29** | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | 63.55 | 53.25 | 45.77 | 86.55 | 58.86 | 82.4 | 31.07 | 75.53 |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | 62.17 |51.68 | 43.82 | 84.92 | 58.36 | 81.59 | 30.12 | 74.14 |
| [bge-large-en](https://huggingface.co/BAAI/bge-large-en) | 1024 | 512 | 63.98 | 53.9 | 46.98 | 85.8 | 59.48 | 81.56 | 32.06 | 76.21 |
| [bge-base-en](https://huggingface.co/BAAI/bge-base-en) | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 |
| [gte-large](https://huggingface.co/thenlper/gte-large) | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 |
| [gte-base](https://huggingface.co/thenlper/gte-base) | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 |
| [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 |
| [bge-small-en](https://huggingface.co/BAAI/bge-small-en) | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 |
| [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 |
| [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 |
| [gte-small](https://huggingface.co/thenlper/gte-small) | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 |
| [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 |
| [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 |
| [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 |
| [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 |
| [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 |
- **C-MTEB**:
We create the benchmark C-MTEB for Chinese text embedding which consists of 31 datasets from 6 tasks.
Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction.
| Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering |
|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| [**BAAI/bge-large-zh-v1.5**](https://huggingface.co/BAAI/bge-large-zh-v1.5) | 1024 | **64.53** | 70.46 | 56.25 | 81.6 | 69.13 | 65.84 | 48.99 |
| [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | 768 | 63.13 | 69.49 | 53.72 | 79.75 | 68.07 | 65.39 | 47.53 |
| [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | 512 | 57.82 | 61.77 | 49.11 | 70.41 | 63.96 | 60.92 | 44.18 |
| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | 1024 | 64.20 | 71.53 | 54.98 | 78.94 | 68.32 | 65.11 | 48.39 |
| [bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | 1024 | 63.53 | 70.55 | 53 | 76.77 | 68.58 | 64.91 | 50.01 |
| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | 768 | 62.96 | 69.53 | 54.12 | 77.5 | 67.07 | 64.91 | 47.63 |
| [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 1024 | 58.79 | 63.66 | 48.44 | 69.89 | 67.34 | 56.00 | 48.23 |
| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | 512 | 58.27 | 63.07 | 49.45 | 70.35 | 63.64 | 61.48 | 45.09 |
| [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 | 56.91 | 50.47 | 63.99 | 67.52 | 59.34 | 47.68 |
| [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 | 57.05 | 54.75 | 50.42 | 64.3 | 68.2 | 59.66 | 48.88 |
| [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 768 | 55.48 | 61.63 | 46.49 | 67.07 | 65.35 | 54.35 | 40.68 |
| [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) | 384 | 55.38 | 59.95 | 45.27 | 66.45 | 65.85 | 53.86 | 45.26 |
| [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) | 1536 | 53.02 | 52.0 | 43.35 | 69.56 | 64.31 | 54.28 | 45.68 |
| [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 | 44.4 | 42.78 | 66.62 | 61 | 49.25 | 44.39 |
| [text2vec-base](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 | 47.63 | 38.79 | 43.41 | 67.41 | 62.19 | 49.45 | 37.66 |
| [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 44.97 | 70.86 | 60.66 | 49.16 | 30.02 |
- **Reranking**:
See [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/) for evaluation script.
| Model | T2Reranking | T2RerankingZh2En\* | T2RerankingEn2Zh\* | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg |
|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| text2vec-base-multilingual | 64.66 | 62.94 | 62.51 | 14.37 | 48.46 | 48.6 | 50.26 |
| multilingual-e5-small | 65.62 | 60.94 | 56.41 | 29.91 | 67.26 | 66.54 | 57.78 |
| multilingual-e5-large | 64.55 | 61.61 | 54.28 | 28.6 | 67.42 | 67.92 | 57.4 |
| multilingual-e5-base | 64.21 | 62.13 | 54.68 | 29.5 | 66.23 | 66.98 | 57.29 |
| m3e-base | 66.03 | 62.74 | 56.07 | 17.51 | 77.05 | 76.76 | 59.36 |
| m3e-large | 66.13 | 62.72 | 56.1 | 16.46 | 77.76 | 78.27 | 59.57 |
| bge-base-zh-v1.5 | 66.49 | 63.25 | 57.02 | 29.74 | 80.47 | 84.88 | 63.64 |
| bge-large-zh-v1.5 | 65.74 | 63.39 | 57.03 | 28.74 | 83.45 | 85.44 | 63.97 |
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | 67.28 | 63.95 | 60.45 | 35.46 | 81.26 | 84.1 | 65.42 |
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | 67.6 | 64.03 | 61.44 | 37.16 | 82.15 | 84.18 | 66.09 |
\* : T2RerankingZh2En and T2RerankingEn2Zh are cross-language retrieval tasks
## Train
### BAAI Embedding
We pre-train the models using [retromae](https://github.com/staoxiao/RetroMAE) and train them on large-scale pairs data using contrastive learning.
**You can fine-tune the embedding model on your data following our [examples](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune).**
We also provide a [pre-train example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain).
Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned.
More training details for bge see [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md).
### BGE Reranker
Cross-encoder will perform full-attention over the input pair,
which is more accurate than embedding model (i.e., bi-encoder) but more time-consuming than embedding model.
Therefore, it can be used to re-rank the top-k documents returned by embedding model.
We train the cross-encoder on a multilingual pair data,
The data format is the same as embedding model, so you can fine-tune it easily following our [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker).
More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
## Contact
If you have any question or suggestion related to this project, feel free to open an issue or pull request.
You also can email Shitao Xiao(stxiao@baai.ac.cn) and Zheng Liu(liuzheng@baai.ac.cn).
## Citation
If you find this repository useful, please consider giving a star :star: and citation
```
@misc{bge_embedding,
title={C-Pack: Packaged Resources To Advance General Chinese Embedding},
author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
year={2023},
eprint={2309.07597},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## License
FlagEmbedding is licensed under the [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.
| 27,150 | [
[
-0.036651611328125,
-0.06793212890625,
0.029296875,
0.0118865966796875,
-0.02716064453125,
-0.02056884765625,
-0.0237579345703125,
-0.0189666748046875,
0.0300445556640625,
0.0283966064453125,
-0.0260467529296875,
-0.06549072265625,
-0.036102294921875,
-0.004604339599609375,
-0.006374359130859375,
0.041473388671875,
-0.0037555694580078125,
0.010711669921875,
0.003925323486328125,
-0.0186767578125,
-0.0283966064453125,
-0.01904296875,
-0.049224853515625,
-0.0192108154296875,
0.025726318359375,
0.017059326171875,
0.042205810546875,
0.056365966796875,
0.0222930908203125,
0.02020263671875,
-0.0175933837890625,
0.01165771484375,
-0.0357666015625,
-0.005153656005859375,
-0.01552581787109375,
-0.024871826171875,
-0.03143310546875,
0.01317596435546875,
0.050994873046875,
0.0335693359375,
-0.007740020751953125,
0.00778961181640625,
0.0004954338073730469,
0.053192138671875,
-0.034515380859375,
0.020751953125,
-0.042724609375,
0.0027294158935546875,
-0.0180511474609375,
0.01128387451171875,
-0.03863525390625,
-0.0287017822265625,
0.0119476318359375,
-0.0458984375,
0.00617218017578125,
0.0216064453125,
0.097412109375,
0.01541900634765625,
-0.033935546875,
-0.01239013671875,
-0.009063720703125,
0.0740966796875,
-0.07525634765625,
0.051177978515625,
0.037933349609375,
0.0190277099609375,
-0.005809783935546875,
-0.0609130859375,
-0.0269622802734375,
-0.0124053955078125,
-0.0151519775390625,
0.03155517578125,
0.001903533935546875,
0.0014982223510742188,
0.0236358642578125,
0.044586181640625,
-0.041412353515625,
0.007049560546875,
-0.00511932373046875,
-0.011871337890625,
0.0570068359375,
-0.01230621337890625,
0.034210205078125,
-0.041595458984375,
-0.0223541259765625,
-0.027435302734375,
-0.0596923828125,
0.0034122467041015625,
0.0273284912109375,
0.0102386474609375,
-0.02935791015625,
0.0423583984375,
-0.017120361328125,
0.045501708984375,
0.003787994384765625,
0.00383758544921875,
0.03924560546875,
-0.0278472900390625,
-0.0154876708984375,
-0.0109405517578125,
0.069580078125,
0.029449462890625,
-0.004314422607421875,
0.003849029541015625,
-0.024139404296875,
-0.007076263427734375,
-0.006961822509765625,
-0.06695556640625,
-0.018157958984375,
0.0148162841796875,
-0.05712890625,
-0.0135498046875,
0.0177459716796875,
-0.05816650390625,
0.00774383544921875,
0.00010311603546142578,
0.043670654296875,
-0.055755615234375,
-0.005519866943359375,
0.02337646484375,
-0.015777587890625,
0.029998779296875,
-0.00024437904357910156,
-0.046844482421875,
-0.018524169921875,
0.039764404296875,
0.0640869140625,
0.0124969482421875,
-0.005706787109375,
-0.0279541015625,
0.00283050537109375,
-0.010650634765625,
0.0244598388671875,
-0.03887939453125,
-0.01331329345703125,
0.015777587890625,
0.0289764404296875,
-0.00771331787109375,
-0.0216827392578125,
0.06597900390625,
-0.040130615234375,
0.02691650390625,
-0.0283050537109375,
-0.0615234375,
-0.037506103515625,
0.0069122314453125,
-0.060089111328125,
0.08270263671875,
-0.00733184814453125,
-0.06341552734375,
0.006229400634765625,
-0.048248291015625,
-0.0161895751953125,
-0.01910400390625,
-0.0024871826171875,
-0.044769287109375,
-0.00879669189453125,
0.0284423828125,
0.043701171875,
-0.017120361328125,
0.002605438232421875,
-0.025970458984375,
-0.042755126953125,
-0.0005397796630859375,
-0.017303466796875,
0.0819091796875,
0.0191497802734375,
-0.025115966796875,
-0.0164794921875,
-0.032806396484375,
0.00899505615234375,
0.022705078125,
-0.02337646484375,
-0.025787353515625,
0.0165557861328125,
0.0176849365234375,
0.0038814544677734375,
0.039642333984375,
-0.05279541015625,
0.01369476318359375,
-0.043792724609375,
0.044464111328125,
0.04180908203125,
0.012939453125,
0.0179290771484375,
-0.035491943359375,
0.021514892578125,
-0.0017499923706054688,
-0.0028553009033203125,
-0.0166168212890625,
-0.039703369140625,
-0.046966552734375,
-0.0226287841796875,
0.055419921875,
0.04937744140625,
-0.0653076171875,
0.049774169921875,
-0.034210205078125,
-0.04632568359375,
-0.07049560546875,
0.0100555419921875,
0.039947509765625,
0.00016045570373535156,
0.05377197265625,
-0.01035308837890625,
-0.035858154296875,
-0.0699462890625,
-0.0046234130859375,
0.005855560302734375,
-0.00679779052734375,
0.040191650390625,
0.0460205078125,
-0.023895263671875,
0.0305023193359375,
-0.05487060546875,
-0.026153564453125,
-0.0172119140625,
-0.0054779052734375,
0.0253753662109375,
0.036773681640625,
0.0478515625,
-0.07537841796875,
-0.043701171875,
-0.000606536865234375,
-0.058319091796875,
0.00571441650390625,
0.0027141571044921875,
-0.0224151611328125,
0.01305389404296875,
0.045654296875,
-0.0307769775390625,
0.017791748046875,
0.035675048828125,
-0.019317626953125,
0.0210418701171875,
-0.0015697479248046875,
0.010986328125,
-0.09912109375,
0.00164031982421875,
0.022613525390625,
-0.008575439453125,
-0.020477294921875,
0.0389404296875,
0.012725830078125,
0.0154266357421875,
-0.025909423828125,
0.0439453125,
-0.0394287109375,
0.0187530517578125,
0.009674072265625,
0.0460205078125,
-0.0067138671875,
0.038330078125,
-0.0034999847412109375,
0.0537109375,
0.02783203125,
-0.0299072265625,
0.00928497314453125,
0.03955078125,
-0.0333251953125,
0.0060882568359375,
-0.04937744140625,
-0.005687713623046875,
-0.00554656982421875,
0.0125579833984375,
-0.06207275390625,
-0.005462646484375,
0.0198516845703125,
-0.042999267578125,
0.03955078125,
-0.0224456787109375,
-0.037261962890625,
-0.027587890625,
-0.06829833984375,
0.010986328125,
0.04376220703125,
-0.048553466796875,
0.0164794921875,
0.022125244140625,
0.006961822509765625,
-0.0579833984375,
-0.061309814453125,
-0.01165771484375,
-0.00017368793487548828,
-0.03955078125,
0.0408935546875,
-0.002140045166015625,
0.0191650390625,
0.0141754150390625,
-0.005359649658203125,
0.0112762451171875,
0.00865936279296875,
-0.00020933151245117188,
0.0184326171875,
-0.035797119140625,
0.0035400390625,
0.02056884765625,
0.0098114013671875,
-0.0148773193359375,
-0.01212310791015625,
0.033111572265625,
-0.01291656494140625,
-0.02679443359375,
-0.017791748046875,
0.0255584716796875,
0.0192413330078125,
-0.0303955078125,
0.0445556640625,
0.07452392578125,
-0.0281829833984375,
-0.0062713623046875,
-0.0496826171875,
-0.00923919677734375,
-0.036224365234375,
0.034149169921875,
-0.02435302734375,
-0.07379150390625,
0.02972412109375,
-0.0015201568603515625,
0.0162506103515625,
0.050872802734375,
0.0252532958984375,
-0.01061248779296875,
0.08099365234375,
0.0281524658203125,
-0.020294189453125,
0.049835205078125,
-0.049774169921875,
0.0133209228515625,
-0.0882568359375,
-0.00335693359375,
-0.0297088623046875,
-0.0297088623046875,
-0.099853515625,
-0.03802490234375,
0.00463104248046875,
0.021026611328125,
-0.02862548828125,
0.0323486328125,
-0.04302978515625,
0.01145172119140625,
0.036407470703125,
0.0222930908203125,
-0.00138092041015625,
0.00933837890625,
-0.0325927734375,
-0.0203704833984375,
-0.04583740234375,
-0.038238525390625,
0.07513427734375,
0.036407470703125,
0.046051025390625,
0.027374267578125,
0.061981201171875,
0.01422119140625,
0.007293701171875,
-0.058197021484375,
0.042999267578125,
-0.03936767578125,
-0.04296875,
-0.0269927978515625,
-0.036712646484375,
-0.083984375,
0.02984619140625,
-0.0206146240234375,
-0.058319091796875,
0.00806427001953125,
-0.0148773193359375,
-0.0022869110107421875,
0.03515625,
-0.050872802734375,
0.07720947265625,
-0.00811004638671875,
-0.0231781005859375,
-0.0058746337890625,
-0.03155517578125,
0.0245208740234375,
0.01497650146484375,
0.00620269775390625,
0.00556182861328125,
-0.01953125,
0.05718994140625,
-0.01416015625,
0.04803466796875,
-0.01220703125,
0.01123809814453125,
0.03240966796875,
-0.01386260986328125,
0.04168701171875,
0.006061553955078125,
-0.0135498046875,
0.0226898193359375,
0.0067291259765625,
-0.036376953125,
-0.037384033203125,
0.06634521484375,
-0.05072021484375,
-0.05328369140625,
-0.0282440185546875,
-0.0188751220703125,
0.01348114013671875,
0.032989501953125,
0.0265960693359375,
0.0165252685546875,
-0.0077667236328125,
0.048736572265625,
0.06982421875,
-0.0411376953125,
0.028900146484375,
0.0261077880859375,
-0.0206146240234375,
-0.044647216796875,
0.0845947265625,
0.019805908203125,
-0.003963470458984375,
0.05078125,
0.0010051727294921875,
-0.021087646484375,
-0.0400390625,
-0.034393310546875,
0.047943115234375,
-0.04473876953125,
-0.01264190673828125,
-0.048309326171875,
-0.0322265625,
-0.0325927734375,
0.0016393661499023438,
-0.020416259765625,
-0.021331787109375,
-0.013427734375,
-0.021209716796875,
0.0177764892578125,
0.0357666015625,
0.00916290283203125,
0.00669097900390625,
-0.0535888671875,
0.015899658203125,
-0.00736236572265625,
0.033172607421875,
0.005413055419921875,
-0.04071044921875,
-0.046844482421875,
0.013153076171875,
-0.03692626953125,
-0.081787109375,
0.0262908935546875,
0.005680084228515625,
0.06317138671875,
0.02484130859375,
-0.000843048095703125,
0.0309600830078125,
-0.03955078125,
0.08062744140625,
-0.008148193359375,
-0.05926513671875,
0.0384521484375,
-0.02117919921875,
0.012420654296875,
0.042205810546875,
0.049285888671875,
-0.03497314453125,
-0.0206451416015625,
-0.03704833984375,
-0.07275390625,
0.036712646484375,
0.01372528076171875,
0.003223419189453125,
-0.022369384765625,
0.0247802734375,
-0.01372528076171875,
-0.0001710653305053711,
-0.060302734375,
-0.05621337890625,
-0.0251922607421875,
-0.02655029296875,
-0.0073089599609375,
-0.0208892822265625,
0.01558685302734375,
-0.021881103515625,
0.075439453125,
0.0003371238708496094,
0.041412353515625,
0.0270233154296875,
-0.024688720703125,
0.0180511474609375,
0.019073486328125,
0.0224609375,
0.01412200927734375,
-0.0291595458984375,
-0.01093292236328125,
0.0237579345703125,
-0.0416259765625,
-0.004810333251953125,
0.0233612060546875,
-0.035308837890625,
0.01459503173828125,
0.023040771484375,
0.05328369140625,
0.033843994140625,
-0.03338623046875,
0.042633056640625,
0.00862884521484375,
-0.01419830322265625,
-0.02252197265625,
-0.005405426025390625,
0.02301025390625,
0.0189666748046875,
0.00879669189453125,
-0.034393310546875,
0.0199737548828125,
-0.039947509765625,
0.0255584716796875,
0.033843994140625,
-0.028656005859375,
-0.005062103271484375,
0.05279541015625,
0.0026149749755859375,
-0.0016050338745117188,
0.03607177734375,
-0.037841796875,
-0.055450439453125,
0.031982421875,
0.028289794921875,
0.06329345703125,
-0.010986328125,
0.016876220703125,
0.06500244140625,
0.04010009765625,
-0.02410888671875,
0.026885986328125,
0.0058441162109375,
-0.04400634765625,
-0.033447265625,
-0.0408935546875,
-0.004383087158203125,
0.0200958251953125,
-0.043548583984375,
0.0264434814453125,
-0.031402587890625,
-0.01113128662109375,
0.0023651123046875,
0.033111572265625,
-0.05609130859375,
0.00955963134765625,
0.0034236907958984375,
0.08477783203125,
-0.04400634765625,
0.06292724609375,
0.07476806640625,
-0.07232666015625,
-0.058197021484375,
0.0059814453125,
-0.0098419189453125,
-0.045867919921875,
0.0283050537109375,
0.0198822021484375,
0.0133209228515625,
0.004669189453125,
-0.03594970703125,
-0.06890869140625,
0.11822509765625,
0.002880096435546875,
-0.0399169921875,
-0.00466156005859375,
-0.021240234375,
0.034454345703125,
-0.02850341796875,
0.033599853515625,
0.0310516357421875,
0.0460205078125,
-0.0139617919921875,
-0.04852294921875,
0.040863037109375,
-0.023834228515625,
0.0176849365234375,
0.0036907196044921875,
-0.0733642578125,
0.0623779296875,
0.0034465789794921875,
-0.0249786376953125,
0.014678955078125,
0.05450439453125,
0.0173187255859375,
0.031585693359375,
0.0181732177734375,
0.07000732421875,
0.049652099609375,
-0.01678466796875,
0.08709716796875,
-0.019439697265625,
0.04736328125,
0.06549072265625,
0.01274871826171875,
0.0843505859375,
0.006679534912109375,
-0.0177459716796875,
0.05059814453125,
0.0596923828125,
-0.024078369140625,
0.035064697265625,
0.0014257431030273438,
0.004581451416015625,
-0.0240631103515625,
0.004016876220703125,
-0.04034423828125,
0.021697998046875,
0.0245513916015625,
-0.038970947265625,
0.0033702850341796875,
-0.0220489501953125,
0.0089874267578125,
0.00799560546875,
-0.0017108917236328125,
0.04339599609375,
0.0235137939453125,
-0.035064697265625,
0.050079345703125,
0.0177459716796875,
0.07611083984375,
-0.0305023193359375,
-0.0114898681640625,
-0.0212860107421875,
-0.0085906982421875,
-0.01708984375,
-0.05889892578125,
-0.006099700927734375,
-0.019378662109375,
-0.0155487060546875,
0.00634765625,
0.0406494140625,
-0.046966552734375,
-0.0306549072265625,
0.0426025390625,
0.038818359375,
0.0182647705078125,
0.01349639892578125,
-0.08270263671875,
0.0023555755615234375,
0.0288238525390625,
-0.040130615234375,
0.0231170654296875,
0.035552978515625,
-0.004669189453125,
0.04437255859375,
0.043975830078125,
0.00484466552734375,
-0.0014820098876953125,
0.0030384063720703125,
0.0386962890625,
-0.07037353515625,
-0.022979736328125,
-0.047607421875,
0.02716064453125,
-0.0246124267578125,
0.0016565322875976562,
0.060791015625,
0.053009033203125,
0.08074951171875,
-0.00397491455078125,
0.061309814453125,
-0.008636474609375,
0.03070068359375,
-0.045379638671875,
0.067138671875,
-0.0772705078125,
0.0194244384765625,
-0.0266265869140625,
-0.07049560546875,
-0.0118408203125,
0.052703857421875,
-0.0252838134765625,
0.0174102783203125,
0.051177978515625,
0.0736083984375,
-0.019256591796875,
-0.01438140869140625,
0.023193359375,
0.0328369140625,
0.01187896728515625,
0.0596923828125,
0.0259857177734375,
-0.0736083984375,
0.0482177734375,
-0.017852783203125,
0.00962066650390625,
-0.039154052734375,
-0.04791259765625,
-0.06939697265625,
-0.055145263671875,
-0.031707763671875,
-0.022979736328125,
-0.0034198760986328125,
0.06927490234375,
0.0257568359375,
-0.056304931640625,
-0.0052032470703125,
0.02081298828125,
0.03643798828125,
-0.0200958251953125,
-0.0207061767578125,
0.0496826171875,
-0.005706787109375,
-0.07037353515625,
0.02471923828125,
-0.006282806396484375,
-0.005138397216796875,
-0.0039825439453125,
-0.0184326171875,
-0.06640625,
0.0089569091796875,
0.044952392578125,
0.0191650390625,
-0.06866455078125,
-0.031585693359375,
0.00634765625,
-0.0196075439453125,
-0.01158905029296875,
0.01271820068359375,
-0.0309906005859375,
0.0269927978515625,
0.046600341796875,
0.05792236328125,
0.0496826171875,
-0.0035190582275390625,
0.01529693603515625,
-0.04608154296875,
-0.006397247314453125,
-0.003162384033203125,
0.053375244140625,
0.0273895263671875,
-0.02264404296875,
0.06781005859375,
0.016082763671875,
-0.03045654296875,
-0.056610107421875,
0.002437591552734375,
-0.07928466796875,
-0.0247344970703125,
0.08404541015625,
-0.031982421875,
-0.0188140869140625,
0.0205535888671875,
-0.01439666748046875,
0.041259765625,
-0.036956787109375,
0.035369873046875,
0.05999755859375,
0.03271484375,
-0.0117034912109375,
-0.0684814453125,
0.0235137939453125,
0.046722412109375,
-0.0206756591796875,
-0.0255126953125,
0.025390625,
0.036346435546875,
0.0179595947265625,
0.00876617431640625,
-0.0185699462890625,
0.024017333984375,
-0.005641937255859375,
-0.0006580352783203125,
-0.010406494140625,
0.018524169921875,
-0.01372528076171875,
0.001949310302734375,
-0.0125579833984375,
-0.0232086181640625
]
] |
Linaqruf/anything-v3.0 | 2023-03-28T03:19:30.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"en",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Linaqruf | null | null | Linaqruf/anything-v3.0 | 669 | 46,283 | diffusers | 2023-01-25T23:30:53 | ---
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# Anything V5 (https://civitai.com/models/9409)
# Uploaded by the Real Anything V3 Author
# Please try it | 259 | [
[
-0.014404296875,
-0.028106689453125,
0.05169677734375,
0.042327880859375,
-0.0265655517578125,
-0.034576416015625,
0.033721923828125,
-0.029083251953125,
0.04058837890625,
0.039642333984375,
-0.054107666015625,
-0.0229034423828125,
-0.0157012939453125,
0.003887176513671875,
-0.060638427734375,
0.01959228515625,
0.00925445556640625,
0.0273895263671875,
0.0018472671508789062,
0.007419586181640625,
-0.046051025390625,
-0.017913818359375,
-0.042938232421875,
0.00484466552734375,
0.050445556640625,
0.05572509765625,
0.0265350341796875,
0.03387451171875,
0.0257720947265625,
0.014068603515625,
0.01197052001953125,
-0.0169830322265625,
-0.037384033203125,
-0.0202789306640625,
-0.012847900390625,
-0.03558349609375,
-0.06317138671875,
0.00376129150390625,
0.03839111328125,
-0.00859832763671875,
-0.0213623046875,
0.029266357421875,
-0.03936767578125,
0.021148681640625,
-0.047210693359375,
-0.01378631591796875,
-0.0218505859375,
0.0116424560546875,
-0.028411865234375,
-0.0193328857421875,
-0.021484375,
-0.0469970703125,
-0.022125244140625,
-0.08270263671875,
0.018829345703125,
0.0048370361328125,
0.089599609375,
0.0054779052734375,
-0.0243988037109375,
-0.006679534912109375,
-0.06854248046875,
0.0328369140625,
-0.04498291015625,
0.040618896484375,
0.0135650634765625,
0.06756591796875,
-0.01433563232421875,
-0.08367919921875,
-0.057708740234375,
0.01439666748046875,
0.022430419921875,
0.0176239013671875,
-0.0191802978515625,
-0.0174407958984375,
0.029632568359375,
0.029144287109375,
-0.045196533203125,
-0.019500732421875,
-0.07501220703125,
0.00423431396484375,
0.034912109375,
-0.00522613525390625,
0.06744384765625,
0.00390625,
-0.0203094482421875,
-0.0164031982421875,
-0.06939697265625,
-0.00540924072265625,
0.02642822265625,
-0.0011014938354492188,
-0.023162841796875,
0.055267333984375,
-0.0065460205078125,
0.053314208984375,
0.01288604736328125,
-0.0042266845703125,
0.0229339599609375,
-0.017578125,
-0.049163818359375,
0.0075225830078125,
0.02252197265625,
0.051025390625,
0.004688262939453125,
0.024749755859375,
0.0103302001953125,
-0.048736572265625,
0.04296875,
-0.07537841796875,
-0.035308837890625,
0.03509521484375,
-0.028656005859375,
-0.0391845703125,
0.035552978515625,
-0.03045654296875,
-0.035369873046875,
-0.00015866756439208984,
0.0191802978515625,
-0.061676025390625,
-0.041015625,
0.0184783935546875,
-0.00946044921875,
0.03912353515625,
0.01181793212890625,
-0.048675537109375,
0.012054443359375,
0.0214691162109375,
0.022186279296875,
0.061676025390625,
-0.025787353515625,
-0.046356201171875,
0.01824951171875,
-0.02886962890625,
0.04412841796875,
0.0094451904296875,
-0.032867431640625,
0.027191162109375,
0.0286712646484375,
0.0172271728515625,
-0.0186614990234375,
0.07275390625,
-0.0623779296875,
-0.01024627685546875,
-0.040618896484375,
-0.032470703125,
-0.03887939453125,
0.0018329620361328125,
-0.061859130859375,
0.033721923828125,
0.00264739990234375,
-0.02703857421875,
0.033905029296875,
-0.0670166015625,
-0.00444793701171875,
0.008148193359375,
0.00434112548828125,
-0.06085205078125,
0.0290679931640625,
-0.01459503173828125,
0.0203399658203125,
-0.0033245086669921875,
-0.0020294189453125,
-0.058441162109375,
-0.0165557861328125,
0.020294189453125,
-0.0230712890625,
0.08013916015625,
0.0187225341796875,
-0.0087127685546875,
0.0028781890869140625,
-0.08026123046875,
0.004638671875,
0.044525146484375,
0.03497314453125,
0.005641937255859375,
-0.01416778564453125,
0.0114288330078125,
0.002933502197265625,
0.0213775634765625,
-0.055694580078125,
0.039337158203125,
0.007579803466796875,
0.0150299072265625,
0.03466796875,
0.01157379150390625,
-0.0006232261657714844,
-0.04632568359375,
0.043670654296875,
-0.0173797607421875,
0.048431396484375,
0.0131072998046875,
-0.0197906494140625,
-0.07623291015625,
-0.0255889892578125,
0.04534912109375,
0.02203369140625,
-0.047637939453125,
0.00604248046875,
-0.00739288330078125,
-0.06622314453125,
-0.0308380126953125,
0.0007195472717285156,
0.003173828125,
0.0014801025390625,
0.0124969482421875,
-0.01111602783203125,
-0.06048583984375,
-0.07763671875,
0.0194091796875,
-0.02545166015625,
-0.0297088623046875,
0.031402587890625,
0.036651611328125,
0.00505828857421875,
0.051239013671875,
-0.029083251953125,
-0.021514892578125,
-0.01020050048828125,
-0.00916290283203125,
0.016876220703125,
0.0272064208984375,
0.093994140625,
-0.05889892578125,
-0.0219573974609375,
-0.01354217529296875,
-0.0435791015625,
-0.020538330078125,
0.0118560791015625,
-0.012786865234375,
-0.0236968994140625,
0.0166168212890625,
-0.03240966796875,
0.039276123046875,
0.0211334228515625,
-0.024627685546875,
0.0293121337890625,
-0.0270538330078125,
0.03643798828125,
-0.0828857421875,
0.0110931396484375,
-0.0097503662109375,
-0.039520263671875,
-0.013092041015625,
0.0293121337890625,
0.0233917236328125,
0.002300262451171875,
-0.086669921875,
0.0253753662109375,
-0.041748046875,
-0.011260986328125,
-0.00353240966796875,
0.007251739501953125,
0.001171112060546875,
-0.01418304443359375,
-0.0172882080078125,
0.03741455078125,
0.038055419921875,
-0.03448486328125,
0.0555419921875,
0.031646728515625,
-0.022369384765625,
0.047149658203125,
-0.08349609375,
-0.00012576580047607422,
-0.013336181640625,
0.0166778564453125,
-0.0631103515625,
-0.06146240234375,
0.0157012939453125,
-0.0479736328125,
-0.00731658935546875,
-0.006603240966796875,
-0.0482177734375,
-0.0184783935546875,
-0.0268402099609375,
0.0215911865234375,
0.05706787109375,
-0.05548095703125,
0.03497314453125,
0.020263671875,
0.019866943359375,
0.002857208251953125,
-0.038818359375,
-0.0100860595703125,
-0.0209503173828125,
-0.0299835205078125,
0.036041259765625,
-0.0062103271484375,
-0.0137786865234375,
-0.0192718505859375,
-0.0013837814331054688,
-0.0270233154296875,
-0.013671875,
0.029266357421875,
0.0297088623046875,
-0.0279541015625,
-0.035308837890625,
-0.0191802978515625,
0.005481719970703125,
-0.004383087158203125,
-0.004337310791015625,
0.020111083984375,
-0.01491546630859375,
-0.016143798828125,
-0.051361083984375,
0.0214080810546875,
0.053680419921875,
-0.0008068084716796875,
0.0265655517578125,
0.0582275390625,
-0.047271728515625,
-0.0103912353515625,
-0.03961181640625,
0.005756378173828125,
-0.03387451171875,
-0.0029659271240234375,
-0.04925537109375,
-0.03643798828125,
0.0070343017578125,
0.0143280029296875,
0.0005135536193847656,
0.03900146484375,
0.022125244140625,
-0.017425537109375,
0.064208984375,
0.061309814453125,
0.01158905029296875,
0.0203704833984375,
-0.0494384765625,
0.002971649169921875,
-0.036895751953125,
-0.02587890625,
-0.0293121337890625,
-0.00170135498046875,
-0.0229339599609375,
-0.03253173828125,
0.01119232177734375,
0.0268402099609375,
-0.01377105712890625,
0.0704345703125,
-0.02264404296875,
0.042938232421875,
0.027862548828125,
0.0174102783203125,
0.025177001953125,
-0.027496337890625,
0.009552001953125,
-0.01222991943359375,
-0.040802001953125,
-0.017547607421875,
0.053558349609375,
0.025115966796875,
0.0236358642578125,
0.03765869140625,
0.0372314453125,
0.0176239013671875,
0.016265869140625,
-0.0270843505859375,
0.031402587890625,
0.0121002197265625,
-0.08221435546875,
-0.000011861324310302734,
0.025909423828125,
-0.0638427734375,
0.01338958740234375,
-0.0283203125,
-0.01934814453125,
0.018890380859375,
0.03155517578125,
-0.0430908203125,
0.039215087890625,
-0.05755615234375,
0.0657958984375,
-0.0279998779296875,
-0.004222869873046875,
0.0196685791015625,
-0.047332763671875,
0.0391845703125,
0.01532745361328125,
0.0263214111328125,
0.01495361328125,
-0.01190185546875,
0.0308380126953125,
-0.051483154296875,
0.054962158203125,
0.004779815673828125,
-0.019744873046875,
0.0235748291015625,
0.01090240478515625,
0.01474761962890625,
0.03228759765625,
0.0092010498046875,
-0.0160064697265625,
0.004245758056640625,
-0.06085205078125,
-0.047821044921875,
0.0621337890625,
-0.054931640625,
-0.0279541015625,
-0.04498291015625,
0.0261993408203125,
0.0162811279296875,
0.038604736328125,
0.042449951171875,
0.029693603515625,
-0.03375244140625,
0.0185089111328125,
0.048065185546875,
0.02227783203125,
0.0469970703125,
0.0491943359375,
-0.030364990234375,
-0.0489501953125,
0.08978271484375,
0.0190887451171875,
-0.006439208984375,
0.006015777587890625,
0.001033782958984375,
-0.0027313232421875,
-0.0469970703125,
-0.0299072265625,
0.0322265625,
-0.01097869873046875,
-0.007213592529296875,
-0.02178955078125,
-0.027679443359375,
-0.032989501953125,
-0.043243408203125,
-0.0504150390625,
-0.026763916015625,
-0.039581298828125,
-0.0281219482421875,
0.044525146484375,
0.0587158203125,
-0.018829345703125,
0.0190887451171875,
-0.055084228515625,
0.0435791015625,
0.029052734375,
0.018768310546875,
-0.030364990234375,
-0.031585693359375,
0.005039215087890625,
0.0081634521484375,
-0.0494384765625,
-0.0419921875,
0.046356201171875,
-0.004528045654296875,
0.0182952880859375,
0.0288848876953125,
-0.002323150634765625,
0.07196044921875,
-0.03656005859375,
0.059661865234375,
0.0181732177734375,
-0.0601806640625,
0.041839599609375,
-0.040313720703125,
0.0185546875,
0.06817626953125,
0.04400634765625,
-0.01078033447265625,
0.01284027099609375,
-0.08837890625,
-0.059814453125,
0.01435089111328125,
0.04461669921875,
-0.007755279541015625,
0.034576416015625,
0.031890869140625,
0.0031528472900390625,
0.0247802734375,
-0.06353759765625,
-0.0228118896484375,
-0.047271728515625,
-0.0091705322265625,
-0.000873565673828125,
-0.01465606689453125,
0.0070037841796875,
-0.026763916015625,
0.05853271484375,
0.0159454345703125,
0.0283355712890625,
0.0430908203125,
0.0014495849609375,
-0.0025653839111328125,
-0.0018854141235351562,
0.05828857421875,
0.05316162109375,
-0.049102783203125,
-0.0073394775390625,
-0.0070343017578125,
-0.0281219482421875,
0.017822265625,
-0.01006317138671875,
-0.01229095458984375,
0.01751708984375,
0.006500244140625,
0.04901123046875,
0.006893157958984375,
-0.02484130859375,
0.0545654296875,
-0.029144287109375,
-0.0183258056640625,
-0.07806396484375,
0.0260009765625,
-0.0017232894897460938,
0.01436614990234375,
-0.002857208251953125,
0.00730133056640625,
0.0283050537109375,
-0.047882080078125,
0.015869140625,
-0.01131439208984375,
-0.0596923828125,
-0.0469970703125,
0.08978271484375,
0.02020263671875,
-0.057342529296875,
0.0220184326171875,
-0.0104522705078125,
-0.00644683837890625,
0.038177490234375,
0.053680419921875,
0.0689697265625,
-0.021881103515625,
0.035552978515625,
0.033111572265625,
0.013336181640625,
-0.0032138824462890625,
0.05120849609375,
0.0008516311645507812,
-0.033050537109375,
-0.00916290283203125,
-0.006633758544921875,
-0.05169677734375,
0.04937744140625,
-0.04498291015625,
0.05364990234375,
-0.05364990234375,
0.01525115966796875,
0.023406982421875,
-0.008514404296875,
-0.0186920166015625,
0.060394287109375,
0.009796142578125,
0.1007080078125,
-0.048858642578125,
0.07037353515625,
0.04132080078125,
-0.054443359375,
-0.04302978515625,
-0.004543304443359375,
0.0242462158203125,
-0.044586181640625,
0.008087158203125,
-0.006237030029296875,
-0.00164031982421875,
0.026824951171875,
-0.08697509765625,
-0.0537109375,
0.09918212890625,
0.016815185546875,
-0.0303192138671875,
0.004283905029296875,
-0.03125,
0.030426025390625,
-0.049835205078125,
0.0272216796875,
0.0199432373046875,
0.047698974609375,
0.0225372314453125,
-0.042327880859375,
-0.0080718994140625,
-0.045074462890625,
0.0215911865234375,
-0.007755279541015625,
-0.07061767578125,
0.03253173828125,
-0.013031005859375,
0.0164642333984375,
0.048126220703125,
0.0626220703125,
0.03973388671875,
0.00632476806640625,
0.038238525390625,
0.026611328125,
0.032073974609375,
0.00627899169921875,
0.09478759765625,
0.0016393661499023438,
0.02471923828125,
0.07208251953125,
-0.04205322265625,
0.043548583984375,
0.02142333984375,
0.001796722412109375,
0.025543212890625,
0.055755615234375,
-0.0276947021484375,
0.0299835205078125,
0.00966644287109375,
-0.040252685546875,
-0.0024204254150390625,
-0.006500244140625,
-0.02825927734375,
0.01271820068359375,
-0.00502777099609375,
-0.00681304931640625,
0.0241851806640625,
-0.0057373046875,
0.01317596435546875,
-0.00537872314453125,
-0.006595611572265625,
0.031524658203125,
-0.016876220703125,
-0.0188446044921875,
0.046173095703125,
0.00015115737915039062,
0.0195770263671875,
-0.0269927978515625,
-0.0158538818359375,
0.008056640625,
-0.0095672607421875,
-0.027557373046875,
-0.033203125,
0.0208892822265625,
-0.0049285888671875,
0.0024585723876953125,
-0.0178985595703125,
0.05682373046875,
-0.025299072265625,
-0.053375244140625,
0.0008916854858398438,
-0.005397796630859375,
0.0192718505859375,
0.0183258056640625,
-0.031768798828125,
0.030364990234375,
0.0096893310546875,
0.0031719207763671875,
-0.003246307373046875,
0.003582000732421875,
0.03228759765625,
0.04400634765625,
0.047210693359375,
0.0203399658203125,
0.00702667236328125,
-0.01123809814453125,
0.039215087890625,
-0.060638427734375,
-0.0057525634765625,
-0.0364990234375,
0.06072998046875,
-0.04046630859375,
-0.047027587890625,
0.06298828125,
0.0732421875,
0.0794677734375,
-0.056304931640625,
0.046051025390625,
-0.031707763671875,
0.028167724609375,
-0.033111572265625,
0.051788330078125,
-0.0545654296875,
-0.017822265625,
-0.012939453125,
-0.043243408203125,
-0.031646728515625,
0.04736328125,
0.02838134765625,
-0.008392333984375,
0.0421142578125,
0.044403076171875,
-0.0285797119140625,
0.00785064697265625,
0.0496826171875,
0.0265655517578125,
0.022064208984375,
0.0127716064453125,
0.0252532958984375,
-0.08514404296875,
0.022735595703125,
-0.037017822265625,
-0.00980377197265625,
-0.034576416015625,
-0.0704345703125,
-0.035919189453125,
-0.03594970703125,
-0.023284912109375,
-0.04296875,
0.006114959716796875,
0.058135986328125,
0.061676025390625,
-0.044525146484375,
-0.0172882080078125,
-0.0219268798828125,
0.020843505859375,
0.013397216796875,
-0.01342010498046875,
-0.009429931640625,
0.039764404296875,
-0.0736083984375,
0.036224365234375,
0.011016845703125,
0.04962158203125,
-0.01300811767578125,
0.029205322265625,
-0.0180206298828125,
0.0219573974609375,
0.02703857421875,
0.06402587890625,
-0.0282135009765625,
-0.032989501953125,
-0.0065460205078125,
0.00592041015625,
-0.0024051666259765625,
0.0731201171875,
-0.0097503662109375,
0.01006317138671875,
0.04107666015625,
0.0126953125,
0.0474853515625,
-0.0053863525390625,
0.057098388671875,
-0.0308837890625,
0.01236724853515625,
-0.0130767822265625,
0.03253173828125,
0.004215240478515625,
-0.00943756103515625,
0.050689697265625,
0.032073974609375,
-0.031494140625,
-0.05560302734375,
-0.006214141845703125,
-0.11090087890625,
0.0056304931640625,
0.060638427734375,
0.00539398193359375,
-0.0623779296875,
0.0149688720703125,
-0.055267333984375,
0.0145263671875,
-0.016357421875,
0.04620361328125,
0.0343017578125,
-0.008148193359375,
-0.03265380859375,
-0.06121826171875,
0.026092529296875,
-0.00513458251953125,
-0.051422119140625,
-0.04339599609375,
0.032073974609375,
0.0252227783203125,
0.0188751220703125,
0.04498291015625,
-0.03607177734375,
0.053619384765625,
0.0153656005859375,
0.0443115234375,
-0.012725830078125,
-0.02471923828125,
-0.0230560302734375,
0.036163330078125,
-0.00908660888671875,
-0.044708251953125
]
] |
codellama/CodeLlama-7b-Instruct-hf | 2023-10-27T18:11:26.000Z | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"llama-2",
"code",
"arxiv:2308.12950",
"license:llama2",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | codellama | null | null | codellama/CodeLlama-7b-Instruct-hf | 88 | 46,269 | transformers | 2023-08-24T16:33:37 | ---
language:
- code
pipeline_tag: text-generation
tags:
- llama-2
license: llama2
---
# **Code Llama**
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 7B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
| | Base Model | Python | Instruct |
| --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
## Model Use
To use this model, please make sure to install transformers from `main` until the next version is released:
```bash
pip install git+https://github.com/huggingface/transformers.git@main accelerate
```
Model capabilities:
- [x] Code completion.
- [x] Infilling.
- [x] Instructions / chat.
- [ ] Python specialist.
## Model Details
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
**Model Developers** Meta
**Variations** Code Llama comes in three model sizes, and three variants:
* Code Llama: base models designed for general code synthesis and understanding
* Code Llama - Python: designed specifically for Python
* Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B and 34B parameters.
**This repository contains the Instruct version of the 7B parameters model.**
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
**Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## Intended Use
**Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
**Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
## Hardware and Software
**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
**Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
## Training Data
All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
## Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
## Ethical Considerations and Limitations
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide). | 6,160 | [
[
-0.028289794921875,
-0.04705810546875,
0.0223388671875,
0.040130615234375,
-0.0186920166015625,
0.0117645263671875,
-0.006084442138671875,
-0.0477294921875,
0.017913818359375,
0.039154052734375,
-0.02862548828125,
-0.041961669921875,
-0.0438232421875,
0.0245361328125,
-0.037139892578125,
0.08953857421875,
-0.00348663330078125,
-0.0231475830078125,
-0.0209808349609375,
-0.0003094673156738281,
-0.01873779296875,
-0.047271728515625,
-0.01308441162109375,
-0.033294677734375,
0.02532958984375,
0.0211334228515625,
0.055023193359375,
0.046966552734375,
0.0379638671875,
0.0238494873046875,
-0.0243988037109375,
0.0005459785461425781,
-0.0230255126953125,
-0.0272216796875,
0.0171051025390625,
-0.044525146484375,
-0.0576171875,
-0.0021514892578125,
0.0264129638671875,
0.0259246826171875,
-0.02239990234375,
0.033233642578125,
-0.01415252685546875,
0.03643798828125,
-0.0249481201171875,
0.01561737060546875,
-0.047271728515625,
-0.00545501708984375,
0.0030727386474609375,
-0.006542205810546875,
-0.00849151611328125,
-0.04248046875,
-0.01033782958984375,
-0.032196044921875,
-0.00661468505859375,
-0.0027599334716796875,
0.0806884765625,
0.04168701171875,
-0.024017333984375,
-0.0185394287109375,
-0.021514892578125,
0.05889892578125,
-0.07342529296875,
0.00153350830078125,
0.0289306640625,
-0.00251007080078125,
-0.01336669921875,
-0.062225341796875,
-0.056243896484375,
-0.0283355712890625,
-0.00882720947265625,
-0.003231048583984375,
-0.033721923828125,
0.00592803955078125,
0.032867431640625,
0.038360595703125,
-0.033172607421875,
0.01203155517578125,
-0.033599853515625,
-0.0167694091796875,
0.0673828125,
0.0073394775390625,
0.032012939453125,
-0.0188751220703125,
-0.024566650390625,
-0.0016880035400390625,
-0.06463623046875,
0.002544403076171875,
0.036651611328125,
-0.01039886474609375,
-0.057586669921875,
0.054962158203125,
-0.0137939453125,
0.043212890625,
0.00455474853515625,
-0.04278564453125,
0.039520263671875,
-0.022674560546875,
-0.0224761962890625,
-0.0090789794921875,
0.06463623046875,
0.037200927734375,
0.026458740234375,
0.0032196044921875,
-0.0189056396484375,
0.025726318359375,
0.01084136962890625,
-0.060577392578125,
-0.003948211669921875,
0.022918701171875,
-0.04583740234375,
-0.05078125,
-0.0215301513671875,
-0.060333251953125,
-0.00916290283203125,
-0.005157470703125,
0.009124755859375,
-0.01245880126953125,
-0.0301666259765625,
0.01611328125,
0.0072784423828125,
0.034393310546875,
0.007511138916015625,
-0.06494140625,
0.0020847320556640625,
0.03631591796875,
0.055938720703125,
0.0029449462890625,
-0.035308837890625,
0.0014495849609375,
-0.00910186767578125,
-0.02630615234375,
0.05029296875,
-0.036712646484375,
-0.038116455078125,
-0.0069580078125,
0.00746917724609375,
-0.000014662742614746094,
-0.039398193359375,
0.0171356201171875,
-0.0271148681640625,
-0.0022678375244140625,
0.01041412353515625,
-0.0205230712890625,
-0.034912109375,
0.003505706787109375,
-0.042938232421875,
0.08538818359375,
0.0211181640625,
-0.04840087890625,
-0.002689361572265625,
-0.041961669921875,
-0.0287017822265625,
-0.0198822021484375,
-0.002117156982421875,
-0.048675537109375,
-0.0027923583984375,
0.01401519775390625,
0.037841796875,
-0.031402587890625,
0.03387451171875,
-0.01007843017578125,
-0.031158447265625,
0.01611328125,
-0.0120849609375,
0.07330322265625,
0.0260009765625,
-0.034332275390625,
0.0175933837890625,
-0.0706787109375,
-0.00986480712890625,
0.03570556640625,
-0.040985107421875,
0.00986480712890625,
-0.01018524169921875,
-0.0023746490478515625,
-0.0036945343017578125,
0.041259765625,
-0.019683837890625,
0.04205322265625,
-0.0301361083984375,
0.0557861328125,
0.04852294921875,
-0.001495361328125,
0.02972412109375,
-0.04364013671875,
0.05914306640625,
-0.01190185546875,
0.0157623291015625,
-0.0208282470703125,
-0.055328369140625,
-0.07586669921875,
-0.0211181640625,
0.00136566162109375,
0.05120849609375,
-0.037994384765625,
0.046630859375,
0.0001455545425415039,
-0.056610107421875,
-0.0394287109375,
0.01593017578125,
0.040924072265625,
0.020721435546875,
0.0249786376953125,
-0.006500244140625,
-0.058441162109375,
-0.063720703125,
0.005474090576171875,
-0.03125,
0.0078277587890625,
0.0140838623046875,
0.06341552734375,
-0.04901123046875,
0.056488037109375,
-0.0311737060546875,
0.00012934207916259766,
-0.0284576416015625,
-0.0224761962890625,
0.038482666015625,
0.040283203125,
0.05657958984375,
-0.044036865234375,
-0.01763916015625,
0.005035400390625,
-0.06365966796875,
-0.00899505615234375,
-0.0147857666015625,
-0.0037212371826171875,
0.03131103515625,
0.023681640625,
-0.04827880859375,
0.0386962890625,
0.06768798828125,
-0.0164337158203125,
0.043975830078125,
-0.0104827880859375,
-0.01084136962890625,
-0.07940673828125,
0.01531219482421875,
-0.0117034912109375,
-0.0014410018920898438,
-0.03729248046875,
0.0273284912109375,
0.007472991943359375,
0.0077667236328125,
-0.03985595703125,
0.0261383056640625,
-0.0296173095703125,
-0.0029697418212890625,
-0.0095672607421875,
-0.016937255859375,
-0.0033283233642578125,
0.056976318359375,
-0.005413055419921875,
0.07403564453125,
0.039093017578125,
-0.049041748046875,
0.0230560302734375,
0.0244598388671875,
-0.0301666259765625,
0.01418304443359375,
-0.07080078125,
0.0278472900390625,
0.008544921875,
0.02545166015625,
-0.056671142578125,
-0.0202789306640625,
0.0258636474609375,
-0.033203125,
0.007572174072265625,
-0.0034198760986328125,
-0.037322998046875,
-0.035003662109375,
-0.018585205078125,
0.0333251953125,
0.0648193359375,
-0.047576904296875,
0.031494140625,
0.0306854248046875,
0.00917816162109375,
-0.05426025390625,
-0.052215576171875,
0.00812530517578125,
-0.035888671875,
-0.0469970703125,
0.0308380126953125,
-0.0236053466796875,
-0.01561737060546875,
-0.0132904052734375,
0.0031757354736328125,
-0.0002474784851074219,
0.0231781005859375,
0.035491943359375,
0.030548095703125,
-0.00868988037109375,
-0.016448974609375,
0.002391815185546875,
-0.007335662841796875,
0.0028820037841796875,
0.0128326416015625,
0.05657958984375,
-0.029296875,
-0.01666259765625,
-0.040985107421875,
0.0139007568359375,
0.0443115234375,
-0.01983642578125,
0.04351806640625,
0.0276031494140625,
-0.027801513671875,
-0.0024261474609375,
-0.049835205078125,
0.0114593505859375,
-0.040985107421875,
0.0220184326171875,
-0.018951416015625,
-0.06439208984375,
0.050079345703125,
0.005268096923828125,
0.01532745361328125,
0.035858154296875,
0.06103515625,
0.0091400146484375,
0.05621337890625,
0.07269287109375,
-0.031494140625,
0.0303802490234375,
-0.039764404296875,
0.007358551025390625,
-0.060699462890625,
-0.03460693359375,
-0.04779052734375,
-0.002716064453125,
-0.05133056640625,
-0.0333251953125,
0.025054931640625,
0.016021728515625,
-0.037628173828125,
0.05499267578125,
-0.059539794921875,
0.0328369140625,
0.033416748046875,
0.0018892288208007812,
0.02960205078125,
0.0024566650390625,
-0.0013179779052734375,
0.0247039794921875,
-0.032958984375,
-0.05450439453125,
0.09033203125,
0.032867431640625,
0.063720703125,
-0.0010232925415039062,
0.0634765625,
0.005184173583984375,
0.0262603759765625,
-0.051605224609375,
0.045074462890625,
0.0208587646484375,
-0.036529541015625,
0.0008902549743652344,
-0.0165863037109375,
-0.069091796875,
0.01212310791015625,
0.0049591064453125,
-0.060028076171875,
0.005939483642578125,
-0.0006461143493652344,
-0.0173187255859375,
0.022735595703125,
-0.05059814453125,
0.044921875,
-0.01666259765625,
0.003490447998046875,
-0.01418304443359375,
-0.0396728515625,
0.04498291015625,
-0.009521484375,
0.0168609619140625,
-0.01111602783203125,
-0.01457977294921875,
0.0489501953125,
-0.038482666015625,
0.0810546875,
0.01047515869140625,
-0.03460693359375,
0.04498291015625,
-0.0012216567993164062,
0.035308837890625,
0.0008578300476074219,
-0.017059326171875,
0.052764892578125,
0.001071929931640625,
-0.014678955078125,
-0.0101318359375,
0.047821044921875,
-0.079345703125,
-0.057373046875,
-0.030517578125,
-0.034820556640625,
0.019989013671875,
0.01235198974609375,
0.028839111328125,
0.0037860870361328125,
0.01442718505859375,
0.01097869873046875,
0.029632568359375,
-0.051849365234375,
0.047119140625,
0.027008056640625,
-0.0206146240234375,
-0.036834716796875,
0.061004638671875,
-0.01093292236328125,
0.016845703125,
0.0203094482421875,
0.0033702850341796875,
-0.01036834716796875,
-0.035675048828125,
-0.0316162109375,
0.03338623046875,
-0.04852294921875,
-0.042327880859375,
-0.04541015625,
-0.025665283203125,
-0.026702880859375,
-0.024078369140625,
-0.0201568603515625,
-0.019866943359375,
-0.049591064453125,
-0.01320648193359375,
0.057403564453125,
0.06121826171875,
0.0048675537109375,
0.03515625,
-0.0474853515625,
0.03436279296875,
0.006267547607421875,
0.02923583984375,
0.0015087127685546875,
-0.03656005859375,
-0.01032257080078125,
-0.0019102096557617188,
-0.039825439453125,
-0.06524658203125,
0.046142578125,
0.00843048095703125,
0.047943115234375,
0.0093536376953125,
-0.003627777099609375,
0.05047607421875,
-0.0322265625,
0.06982421875,
0.0258331298828125,
-0.0819091796875,
0.046478271484375,
-0.0188140869140625,
0.00354766845703125,
0.0070953369140625,
0.0254669189453125,
-0.03082275390625,
-0.0193634033203125,
-0.04840087890625,
-0.055938720703125,
0.044952392578125,
0.0128021240234375,
0.0211334228515625,
0.00193023681640625,
0.034423828125,
-0.00080108642578125,
0.0246734619140625,
-0.0794677734375,
-0.024139404296875,
-0.0244598388671875,
-0.0185699462890625,
-0.00693511962890625,
-0.0223846435546875,
-0.005687713623046875,
-0.021270751953125,
0.033172607421875,
-0.0143890380859375,
0.03924560546875,
0.01007080078125,
-0.01300811767578125,
-0.0189056396484375,
0.0044708251953125,
0.051483154296875,
0.043853759765625,
-0.0008902549743652344,
-0.01067352294921875,
0.02899169921875,
-0.040802001953125,
0.017425537109375,
-0.0097503662109375,
-0.006931304931640625,
-0.022796630859375,
0.041748046875,
0.049346923828125,
0.01110076904296875,
-0.0626220703125,
0.035858154296875,
0.01235198974609375,
-0.0207672119140625,
-0.037811279296875,
0.0217437744140625,
0.021026611328125,
0.027130126953125,
0.0179443359375,
0.0011615753173828125,
-0.007293701171875,
-0.03277587890625,
-0.002315521240234375,
0.0256805419921875,
0.01366424560546875,
-0.02703857421875,
0.06854248046875,
0.00865936279296875,
-0.02703857421875,
0.035064697265625,
0.005542755126953125,
-0.043365478515625,
0.08782958984375,
0.052001953125,
0.056793212890625,
-0.01517486572265625,
0.00740814208984375,
0.03460693359375,
0.041259765625,
-0.00139617919921875,
0.031982421875,
0.0014934539794921875,
-0.039520263671875,
-0.025482177734375,
-0.06591796875,
-0.0290374755859375,
0.007747650146484375,
-0.0343017578125,
0.0229339599609375,
-0.04803466796875,
-0.0034313201904296875,
-0.0276336669921875,
0.006778717041015625,
-0.047271728515625,
-0.0009284019470214844,
0.0081939697265625,
0.0701904296875,
-0.046112060546875,
0.06927490234375,
0.044158935546875,
-0.054168701171875,
-0.068603515625,
-0.0159912109375,
-0.005641937255859375,
-0.09210205078125,
0.0357666015625,
0.0208740234375,
0.0039043426513671875,
0.005786895751953125,
-0.07110595703125,
-0.08172607421875,
0.09619140625,
0.036224365234375,
-0.039642333984375,
-0.001049041748046875,
0.01464080810546875,
0.04193115234375,
-0.0261383056640625,
0.0291595458984375,
0.049591064453125,
0.03277587890625,
-0.0070648193359375,
-0.0906982421875,
0.024078369140625,
-0.029876708984375,
0.016845703125,
-0.0201416015625,
-0.0787353515625,
0.07745361328125,
-0.0416259765625,
-0.00977325439453125,
0.034942626953125,
0.048919677734375,
0.040191650390625,
0.015289306640625,
0.026702880859375,
0.041412353515625,
0.04815673828125,
0.002288818359375,
0.08880615234375,
-0.03411865234375,
0.0299835205078125,
0.03851318359375,
-0.0088043212890625,
0.054168701171875,
0.0304107666015625,
-0.04278564453125,
0.0550537109375,
0.057586669921875,
-0.016357421875,
0.020294189453125,
0.024078369140625,
-0.0050201416015625,
-0.0028591156005859375,
-0.00719451904296875,
-0.05609130859375,
0.02825927734375,
0.0242919921875,
-0.025604248046875,
0.00586700439453125,
-0.0166778564453125,
0.0218963623046875,
-0.0094757080078125,
-0.006542205810546875,
0.04827880859375,
0.01776123046875,
-0.040557861328125,
0.08746337890625,
0.00839996337890625,
0.07330322265625,
-0.039703369140625,
-0.01031494140625,
-0.033599853515625,
0.0038604736328125,
-0.04248046875,
-0.038482666015625,
0.01313018798828125,
0.0215301513671875,
0.000007033348083496094,
-0.0086822509765625,
0.035614013671875,
-0.0053558349609375,
-0.037994384765625,
0.02862548828125,
0.0126190185546875,
0.0206756591796875,
0.01041412353515625,
-0.048675537109375,
0.0345458984375,
0.01491546630859375,
-0.034271240234375,
0.0275115966796875,
0.00833892822265625,
0.0026702880859375,
0.07080078125,
0.0587158203125,
-0.009857177734375,
0.0139007568359375,
-0.00843048095703125,
0.0845947265625,
-0.0531005859375,
-0.025848388671875,
-0.05865478515625,
0.048126220703125,
0.02301025390625,
-0.033203125,
0.045379638671875,
0.02618408203125,
0.06182861328125,
-0.01023101806640625,
0.06109619140625,
-0.013519287109375,
0.0066680908203125,
-0.03662109375,
0.048095703125,
-0.057586669921875,
0.0293426513671875,
-0.036712646484375,
-0.07025146484375,
-0.0233154296875,
0.064208984375,
-0.0033416748046875,
0.0050048828125,
0.039398193359375,
0.074462890625,
0.02301025390625,
-0.0087738037109375,
0.0175018310546875,
0.01549530029296875,
0.0303192138671875,
0.058319091796875,
0.07318115234375,
-0.04278564453125,
0.054107666015625,
-0.04296875,
-0.0174560546875,
-0.021484375,
-0.07373046875,
-0.074462890625,
-0.0372314453125,
-0.024200439453125,
-0.02862548828125,
-0.020416259765625,
0.06829833984375,
0.0404052734375,
-0.043609619140625,
-0.035064697265625,
-0.00923919677734375,
0.03143310546875,
-0.00791168212890625,
-0.01497650146484375,
0.021697998046875,
-0.00931549072265625,
-0.0634765625,
0.029632568359375,
-0.001983642578125,
0.01296234130859375,
-0.0253448486328125,
-0.018035888671875,
-0.0089263916015625,
0.0003566741943359375,
0.036651611328125,
0.02606201171875,
-0.06378173828125,
-0.01557159423828125,
0.005794525146484375,
-0.01293182373046875,
0.00847625732421875,
0.032012939453125,
-0.0474853515625,
-0.005199432373046875,
0.0249481201171875,
0.033599853515625,
0.024200439453125,
-0.0170440673828125,
0.0171966552734375,
-0.0270843505859375,
0.03277587890625,
-0.0003147125244140625,
0.03790283203125,
0.0079193115234375,
-0.04498291015625,
0.052490234375,
0.01934814453125,
-0.050537109375,
-0.0679931640625,
0.01102447509765625,
-0.08526611328125,
-0.0153045654296875,
0.09832763671875,
-0.007083892822265625,
-0.0257568359375,
0.01380157470703125,
-0.0290374755859375,
0.0197296142578125,
-0.030242919921875,
0.054168701171875,
0.0217437744140625,
-0.00585174560546875,
-0.0108642578125,
-0.031341552734375,
0.0205230712890625,
0.0182952880859375,
-0.07147216796875,
-0.01287841796875,
0.0292816162109375,
0.029510498046875,
0.014862060546875,
0.05078125,
-0.00921630859375,
0.01248931884765625,
0.0039825439453125,
0.034210205078125,
-0.007297515869140625,
-0.017242431640625,
-0.028564453125,
-0.004627227783203125,
-0.005847930908203125,
-0.0025768280029296875
]
] |
finiteautomata/bertweet-base-emotion-analysis | 2023-03-20T14:47:04.000Z | [
"transformers",
"pytorch",
"safetensors",
"roberta",
"text-classification",
"emotion-analysis",
"en",
"arxiv:2106.09462",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | finiteautomata | null | null | finiteautomata/bertweet-base-emotion-analysis | 11 | 46,262 | transformers | 2022-03-02T23:29:05 | ---
language:
- en
tags:
- emotion-analysis
---
# Emotion Analysis in English
## bertweet-base-emotion-analysis
Repository: [https://github.com/finiteautomata/pysentimiento/](https://github.com/finiteautomata/pysentimiento/)
Model trained with EmoEvent corpus for Emotion detection in English. Base model is [BerTweet](https://huggingface.co/vinai/bertweet-base).
## License
`pysentimiento` is an open-source library for non-commercial use and scientific research purposes only. Please be aware that models are trained with third-party datasets and are subject to their respective licenses.
1. [TASS Dataset license](http://tass.sepln.org/tass_data/download.php)
2. [SEMEval 2017 Dataset license]()
## Citation
If you use `pysentimiento` in your work, please cite [this paper](https://arxiv.org/abs/2106.09462)
```
@misc{perez2021pysentimiento,
title={pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks},
author={Juan Manuel Pérez and Juan Carlos Giudici and Franco Luque},
year={2021},
eprint={2106.09462},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
and also the dataset related paper
```
@inproceedings{del2020emoevent,
title={EmoEvent: A multilingual emotion corpus based on different events},
author={del Arco, Flor Miriam Plaza and Strapparava, Carlo and Lopez, L Alfonso Urena and Mart{\'\i}n-Valdivia, M Teresa},
booktitle={Proceedings of the 12th Language Resources and Evaluation Conference},
pages={1492--1498},
year={2020}
}
```
Enjoy! 🤗
| 1,547 | [
[
-0.01483154296875,
-0.0528564453125,
0.0194244384765625,
0.0538330078125,
-0.032470703125,
-0.01174163818359375,
-0.040252685546875,
-0.032196044921875,
0.04351806640625,
-0.0173797607421875,
-0.03558349609375,
-0.06256103515625,
-0.039703369140625,
0.0141754150390625,
0.00023543834686279297,
0.055419921875,
-0.024444580078125,
0.016998291015625,
-0.003917694091796875,
-0.023468017578125,
0.024322509765625,
-0.03948974609375,
-0.057952880859375,
-0.002445220947265625,
0.050384521484375,
0.02154541015625,
0.0113067626953125,
-0.0220947265625,
0.01373291015625,
0.0213775634765625,
-0.0087738037109375,
-0.003917694091796875,
-0.0220794677734375,
0.0234832763671875,
-0.0027408599853515625,
-0.0161590576171875,
-0.0311279296875,
-0.0224609375,
0.033416748046875,
0.006092071533203125,
-0.00458526611328125,
0.0004646778106689453,
-0.00543212890625,
0.049041748046875,
-0.050048828125,
0.0304718017578125,
-0.02764892578125,
0.01470947265625,
-0.017120361328125,
-0.003917694091796875,
-0.018341064453125,
-0.059906005859375,
0.003803253173828125,
-0.0057830810546875,
-0.006542205810546875,
0.0004189014434814453,
0.0791015625,
0.00461578369140625,
-0.017333984375,
-0.0242919921875,
-0.009368896484375,
0.061553955078125,
-0.06365966796875,
0.0350341796875,
0.0090789794921875,
-0.0027713775634765625,
0.005741119384765625,
-0.0276947021484375,
-0.043975830078125,
-0.0010347366333007812,
0.0307769775390625,
0.0250244140625,
-0.04522705078125,
-0.01148223876953125,
-0.0017175674438476562,
0.01039886474609375,
-0.034698486328125,
0.0011577606201171875,
-0.021636962890625,
-0.01151275634765625,
0.0443115234375,
0.0010728836059570312,
0.0211029052734375,
-0.0202484130859375,
-0.00788116455078125,
-0.01849365234375,
-0.0309295654296875,
0.014923095703125,
0.04071044921875,
0.005764007568359375,
-0.0489501953125,
0.0299072265625,
-0.0019378662109375,
0.006298065185546875,
-0.014434814453125,
0.0195770263671875,
0.065673828125,
0.007099151611328125,
-0.0212860107421875,
-0.00933074951171875,
0.08966064453125,
0.031097412109375,
0.039306640625,
0.00519561767578125,
-0.002857208251953125,
-0.00390625,
-0.00530242919921875,
-0.05450439453125,
-0.00905609130859375,
0.0537109375,
-0.0404052734375,
-0.0213775634765625,
-0.0018024444580078125,
-0.09906005859375,
-0.027801513671875,
0.0088653564453125,
0.0211029052734375,
-0.0355224609375,
-0.0552978515625,
0.001544952392578125,
0.0037555694580078125,
0.016937255859375,
0.00507354736328125,
-0.042327880859375,
-0.0064849853515625,
0.0308990478515625,
0.0665283203125,
-0.0016021728515625,
-0.0291290283203125,
0.002414703369140625,
-0.0274505615234375,
-0.00927734375,
0.053070068359375,
-0.0145111083984375,
-0.0167999267578125,
0.0382080078125,
0.028717041015625,
-0.016448974609375,
-0.0119476318359375,
0.0665283203125,
-0.01428985595703125,
0.021636962890625,
-0.01172637939453125,
-0.026458740234375,
-0.016571044921875,
0.0079193115234375,
-0.048004150390625,
0.08807373046875,
-0.0009822845458984375,
-0.07568359375,
-0.00853729248046875,
-0.056671142578125,
-0.031646728515625,
-0.0199127197265625,
0.00511932373046875,
-0.0399169921875,
0.01404571533203125,
0.01169586181640625,
0.048004150390625,
-0.010772705078125,
0.0139923095703125,
-0.044525146484375,
0.0085296630859375,
0.02618408203125,
-0.0028667449951171875,
0.07379150390625,
0.0245513916015625,
-0.0322265625,
0.0031795501708984375,
-0.0521240234375,
-0.0113677978515625,
0.0219268798828125,
-0.00937652587890625,
-0.0267333984375,
0.006649017333984375,
0.0234832763671875,
0.0176544189453125,
0.035430908203125,
-0.0794677734375,
-0.006694793701171875,
-0.032073974609375,
0.003658294677734375,
0.044464111328125,
0.0039520263671875,
0.0142059326171875,
0.00399017333984375,
0.052703857421875,
0.0022983551025390625,
0.01111602783203125,
-0.00197601318359375,
-0.038360595703125,
-0.047088623046875,
-0.020477294921875,
0.004154205322265625,
0.052581787109375,
-0.049163818359375,
0.043975830078125,
0.00449371337890625,
-0.04559326171875,
-0.047332763671875,
-0.0255126953125,
0.017120361328125,
0.0275421142578125,
0.0207977294921875,
0.012451171875,
-0.06884765625,
-0.039642333984375,
-0.0243988037109375,
-0.010223388671875,
0.01312255859375,
0.0257415771484375,
0.049530029296875,
-0.01338958740234375,
0.043975830078125,
-0.029815673828125,
-0.007595062255859375,
-0.009674072265625,
0.01416015625,
0.0246124267578125,
0.0272216796875,
0.052978515625,
-0.056060791015625,
-0.0562744140625,
0.01065826416015625,
-0.0655517578125,
-0.0291290283203125,
0.0127105712890625,
-0.0113372802734375,
0.057525634765625,
0.007694244384765625,
-0.014495849609375,
0.038726806640625,
0.042877197265625,
-0.039215087890625,
0.0225372314453125,
-0.007656097412109375,
0.0294952392578125,
-0.08868408203125,
-0.0002655982971191406,
0.0287933349609375,
0.0001506805419921875,
-0.031494140625,
-0.00930023193359375,
0.0122528076171875,
0.00437164306640625,
-0.06536865234375,
0.04974365234375,
-0.0208282470703125,
0.0143585205078125,
0.00310516357421875,
-0.0059814453125,
-0.0118560791015625,
0.041595458984375,
0.01311492919921875,
0.015106201171875,
0.04766845703125,
-0.0196075439453125,
0.048309326171875,
0.032623291015625,
-0.0293121337890625,
0.050140380859375,
-0.055755615234375,
0.0003070831298828125,
-0.0101776123046875,
-0.00928497314453125,
-0.07684326171875,
-0.0162506103515625,
0.0288848876953125,
-0.056732177734375,
0.01021575927734375,
-0.00428009033203125,
-0.03802490234375,
-0.0200042724609375,
-0.048736572265625,
-0.0037078857421875,
0.046661376953125,
-0.0487060546875,
0.053863525390625,
0.0208740234375,
-0.0257110595703125,
-0.042816162109375,
-0.0665283203125,
-0.0084228515625,
-0.0364990234375,
-0.06951904296875,
-0.0014657974243164062,
-0.002468109130859375,
-0.022735595703125,
0.006649017333984375,
0.0198822021484375,
-0.032867431640625,
-0.004199981689453125,
0.0202178955078125,
0.0097198486328125,
-0.00540924072265625,
0.0251312255859375,
0.0222320556640625,
0.018951416015625,
0.007678985595703125,
0.012359619140625,
0.04290771484375,
-0.0243682861328125,
-0.003887176513671875,
-0.043609619140625,
0.035400390625,
0.0494384765625,
-0.01120758056640625,
0.06817626953125,
0.07354736328125,
-0.043731689453125,
-0.00568389892578125,
-0.03631591796875,
0.01317596435546875,
-0.0279693603515625,
0.0335693359375,
-0.025665283203125,
-0.05340576171875,
0.06396484375,
0.017303466796875,
-0.0103759765625,
0.045013427734375,
0.07305908203125,
-0.0271148681640625,
0.048004150390625,
0.03326416015625,
-0.01367950439453125,
0.058624267578125,
-0.0109710693359375,
0.005329132080078125,
-0.05908203125,
-0.0308074951171875,
-0.0594482421875,
-0.019927978515625,
-0.04925537109375,
-0.00476837158203125,
0.0126495361328125,
-0.0252227783203125,
-0.03411865234375,
0.00804901123046875,
-0.0222625732421875,
0.019561767578125,
0.02392578125,
0.00666046142578125,
-0.0125579833984375,
0.01151275634765625,
-0.0106964111328125,
-0.032684326171875,
-0.032135009765625,
-0.026641845703125,
0.0699462890625,
0.044921875,
0.06341552734375,
0.01380157470703125,
0.0748291015625,
0.0057220458984375,
-0.00144195556640625,
-0.0604248046875,
0.0169525146484375,
-0.01488494873046875,
-0.027862548828125,
-0.0184478759765625,
-0.0229644775390625,
-0.084228515625,
0.01291656494140625,
-0.004383087158203125,
-0.084716796875,
0.049285888671875,
-0.01287078857421875,
-0.0099945068359375,
0.0269317626953125,
-0.05694580078125,
0.07452392578125,
-0.018829345703125,
-0.0240325927734375,
-0.0139617919921875,
-0.0293426513671875,
0.00463104248046875,
-0.0029506683349609375,
0.026702880859375,
-0.021087646484375,
-0.00937652587890625,
0.062408447265625,
-0.0232086181640625,
0.0733642578125,
-0.0262451171875,
-0.01082611083984375,
0.0209503173828125,
0.007694244384765625,
0.0316162109375,
0.006031036376953125,
-0.0257720947265625,
0.0189208984375,
0.01404571533203125,
-0.017852783203125,
-0.0159912109375,
0.06805419921875,
-0.067626953125,
0.006542205810546875,
-0.043426513671875,
-0.0246124267578125,
0.0049896240234375,
-0.0122528076171875,
0.03338623046875,
0.0222625732421875,
-0.02630615234375,
0.025909423828125,
0.041229248046875,
-0.039642333984375,
0.047149658203125,
0.046051025390625,
0.0071868896484375,
-0.042755126953125,
0.059326171875,
0.00958251953125,
-0.0095672607421875,
0.0198211669921875,
0.024200439453125,
-0.032867431640625,
-0.007160186767578125,
-0.004016876220703125,
0.0274810791015625,
-0.045684814453125,
-0.005115509033203125,
-0.06671142578125,
0.0226898193359375,
-0.046051025390625,
-0.01081085205078125,
-0.0289154052734375,
-0.0236358642578125,
-0.029541015625,
-0.01309967041015625,
0.04290771484375,
0.0261383056640625,
-0.031280517578125,
0.016265869140625,
-0.052581787109375,
0.003131866455078125,
-0.01396942138671875,
0.0200042724609375,
0.002552032470703125,
-0.035491943359375,
-0.0252685546875,
-0.00850677490234375,
-0.02392578125,
-0.09918212890625,
0.07781982421875,
0.0181884765625,
0.032073974609375,
0.0296630859375,
0.01241302490234375,
0.016510009765625,
-0.01012420654296875,
0.054901123046875,
0.01093292236328125,
-0.078857421875,
0.055572509765625,
-0.0260467529296875,
-0.00028777122497558594,
0.039764404296875,
0.057281494140625,
-0.052032470703125,
-0.0257568359375,
-0.0714111328125,
-0.080078125,
0.05657958984375,
0.011688232421875,
0.00608062744140625,
-0.006458282470703125,
0.00444793701171875,
-0.013031005859375,
0.020477294921875,
-0.07110595703125,
-0.01447296142578125,
-0.01259613037109375,
-0.0504150390625,
0.0189208984375,
-0.029754638671875,
0.0037174224853515625,
-0.0272216796875,
0.064453125,
0.01480865478515625,
0.044830322265625,
0.032745361328125,
-0.016265869140625,
-0.009674072265625,
0.01461029052734375,
0.036407470703125,
0.0173187255859375,
-0.040496826171875,
-0.005634307861328125,
0.0145111083984375,
-0.0233306884765625,
-0.00885772705078125,
0.0004978179931640625,
0.00814056396484375,
0.02703857421875,
0.0236358642578125,
0.06170654296875,
0.0224151611328125,
-0.035980224609375,
0.050384521484375,
-0.002887725830078125,
-0.00994873046875,
-0.043731689453125,
-0.0372314453125,
0.004856109619140625,
0.04364013671875,
0.0297698974609375,
-0.023468017578125,
0.00453948974609375,
-0.0280303955078125,
0.004108428955078125,
0.002269744873046875,
-0.0308380126953125,
-0.04217529296875,
0.02886962890625,
0.0303802490234375,
-0.01464080810546875,
0.0234527587890625,
-0.040435791015625,
-0.06396484375,
0.0723876953125,
0.02728271484375,
0.09429931640625,
-0.018585205078125,
0.0157470703125,
0.05126953125,
0.0274810791015625,
0.001697540283203125,
0.07672119140625,
0.02191162109375,
-0.07586669921875,
-0.02374267578125,
-0.037506103515625,
-0.0369873046875,
0.00681304931640625,
-0.0513916015625,
0.0209808349609375,
-0.018280029296875,
0.0088958740234375,
-0.0170135498046875,
-0.00038743019104003906,
-0.04058837890625,
0.0121002197265625,
0.022064208984375,
0.06756591796875,
-0.0882568359375,
0.06561279296875,
0.0711669921875,
-0.042633056640625,
-0.04730224609375,
-0.004184722900390625,
0.005584716796875,
-0.04254150390625,
0.039520263671875,
-0.004791259765625,
0.01007080078125,
-0.006702423095703125,
-0.041351318359375,
-0.033538818359375,
0.0599365234375,
0.0177001953125,
-0.0260772705078125,
0.025848388671875,
-0.033935546875,
0.054656982421875,
-0.031829833984375,
0.031829833984375,
0.037872314453125,
0.043731689453125,
0.007049560546875,
-0.051910400390625,
-0.0273590087890625,
-0.02728271484375,
-0.0275726318359375,
0.01171112060546875,
-0.052581787109375,
0.07623291015625,
0.0004329681396484375,
-0.00823211669921875,
-0.0084991455078125,
0.04840087890625,
0.00565338134765625,
0.042083740234375,
0.018035888671875,
0.043731689453125,
0.06396484375,
-0.0303802490234375,
0.076416015625,
-0.0214385986328125,
0.06256103515625,
0.061614990234375,
-0.0159759521484375,
0.07623291015625,
0.0281219482421875,
-0.03863525390625,
0.057891845703125,
0.0618896484375,
-0.000016391277313232422,
0.033050537109375,
-0.007320404052734375,
-0.020416259765625,
0.00933837890625,
-0.003673553466796875,
-0.0298614501953125,
0.020111083984375,
0.0267333984375,
-0.02130126953125,
-0.00713348388671875,
0.0127105712890625,
0.0291900634765625,
-0.0017948150634765625,
-0.0228118896484375,
0.0264129638671875,
0.0033168792724609375,
-0.004993438720703125,
0.041290283203125,
-0.0196075439453125,
0.0771484375,
-0.039703369140625,
0.03131103515625,
-0.0290679931640625,
0.00960540771484375,
-0.039154052734375,
-0.067626953125,
0.02886962890625,
0.027587890625,
0.00124359130859375,
-0.00392913818359375,
0.049468994140625,
-0.03961181640625,
-0.041595458984375,
0.039520263671875,
0.03582763671875,
0.03741455078125,
-0.00859832763671875,
-0.058837890625,
0.0199737548828125,
0.0190277099609375,
-0.04888916015625,
0.002552032470703125,
0.0577392578125,
0.0020809173583984375,
0.03668212890625,
0.0211944580078125,
0.02313232421875,
0.004062652587890625,
0.021484375,
0.045013427734375,
-0.052276611328125,
-0.042236328125,
-0.07135009765625,
0.050872802734375,
-0.016876220703125,
-0.02996826171875,
0.049285888671875,
0.038543701171875,
0.045166015625,
-0.030303955078125,
0.0640869140625,
-0.0308380126953125,
0.042083740234375,
-0.010955810546875,
0.046295166015625,
-0.04742431640625,
-0.031829833984375,
-0.04046630859375,
-0.0478515625,
-0.026031494140625,
0.06475830078125,
-0.023651123046875,
-0.0213165283203125,
0.0679931640625,
0.05206298828125,
0.0250244140625,
-0.01263427734375,
0.0207977294921875,
0.043731689453125,
0.0024318695068359375,
0.05926513671875,
0.0570068359375,
-0.0306396484375,
0.0171661376953125,
-0.0239715576171875,
-0.0244598388671875,
-0.0281982421875,
-0.08087158203125,
-0.0537109375,
-0.0498046875,
-0.04571533203125,
-0.04388427734375,
-0.0125579833984375,
0.091796875,
0.0029163360595703125,
-0.08575439453125,
-0.022064208984375,
0.0229644775390625,
0.0202178955078125,
0.01137542724609375,
-0.016387939453125,
0.03668212890625,
-0.0245208740234375,
-0.083740234375,
0.006885528564453125,
0.00791168212890625,
0.005596160888671875,
0.009674072265625,
-0.008758544921875,
-0.0301971435546875,
-0.00449371337890625,
0.037353515625,
0.042694091796875,
-0.036407470703125,
-0.011566162109375,
-0.0014371871948242188,
-0.00634765625,
0.007678985595703125,
0.02203369140625,
-0.0167388916015625,
0.031158447265625,
0.0643310546875,
0.035980224609375,
0.0293426513671875,
-0.019561767578125,
0.0233306884765625,
-0.056182861328125,
0.05126953125,
0.01910400390625,
0.0577392578125,
0.02374267578125,
-0.03607177734375,
0.049530029296875,
0.01495361328125,
-0.0390625,
-0.056640625,
-0.00991058349609375,
-0.08489990234375,
0.0015287399291992188,
0.101318359375,
-0.026641845703125,
-0.032806396484375,
0.01546478271484375,
-0.0284576416015625,
0.0380859375,
-0.060577392578125,
0.041900634765625,
0.05877685546875,
-0.01117706298828125,
-0.0181884765625,
-0.03265380859375,
0.023284912109375,
0.0220947265625,
-0.06396484375,
-0.01177215576171875,
0.023834228515625,
0.00809478759765625,
0.00118255615234375,
0.038970947265625,
-0.01226043701171875,
0.026641845703125,
-0.0233612060546875,
0.0638427734375,
0.0139312744140625,
0.0015544891357421875,
-0.060943603515625,
0.0027942657470703125,
-0.0179901123046875,
-0.0292205810546875
]
] |
sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens | 2022-06-15T20:39:21.000Z | [
"sentence-transformers",
"pytorch",
"tf",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"arxiv:1908.10084",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | sentence-similarity | sentence-transformers | null | null | sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens | 4 | 46,045 | sentence-transformers | 2022-03-02T23:29:05 | ---
pipeline_tag: sentence-similarity
license: apache-2.0
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
# sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/xlm-r-100langs-bert-base-nli-stsb-mean-tokens)
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` | 4,055 | [
[
-0.0181427001953125,
-0.057830810546875,
0.02142333984375,
0.02960205078125,
-0.0301971435546875,
-0.02923583984375,
-0.0236358642578125,
-0.0051116943359375,
0.0137939453125,
0.032745361328125,
-0.040252685546875,
-0.033935546875,
-0.05487060546875,
0.00768280029296875,
-0.032745361328125,
0.059600830078125,
-0.016632080078125,
0.00716400146484375,
-0.0189361572265625,
-0.01328277587890625,
-0.0244903564453125,
-0.03814697265625,
-0.026275634765625,
-0.01898193359375,
0.01354217529296875,
0.00977325439453125,
0.0355224609375,
0.0304412841796875,
0.0180511474609375,
0.032867431640625,
-0.006580352783203125,
0.0147857666015625,
-0.02825927734375,
-0.0106048583984375,
0.00858306884765625,
-0.0240631103515625,
-0.0078277587890625,
0.0225677490234375,
0.045257568359375,
0.0394287109375,
-0.01043701171875,
0.0016298294067382812,
-0.0008382797241210938,
0.0226898193359375,
-0.03082275390625,
0.032318115234375,
-0.041839599609375,
0.016632080078125,
0.01166534423828125,
0.004547119140625,
-0.050445556640625,
-0.0123138427734375,
0.021820068359375,
-0.0294647216796875,
-0.00022745132446289062,
0.01727294921875,
0.0853271484375,
0.0216064453125,
-0.0207672119140625,
-0.026519775390625,
-0.021759033203125,
0.06829833984375,
-0.07244873046875,
0.023101806640625,
0.0175933837890625,
-0.0070343017578125,
0.002201080322265625,
-0.07879638671875,
-0.05230712890625,
-0.01085662841796875,
-0.03350830078125,
0.01727294921875,
-0.032806396484375,
-0.0008921623229980469,
0.00971221923828125,
0.014556884765625,
-0.050140380859375,
-0.00820159912109375,
-0.0306396484375,
-0.00821685791015625,
0.037139892578125,
0.000446319580078125,
0.0295562744140625,
-0.0438232421875,
-0.035430908203125,
-0.0223846435546875,
-0.0181121826171875,
-0.0062255859375,
0.00818634033203125,
0.0164337158203125,
-0.023284912109375,
0.0567626953125,
0.00800323486328125,
0.040069580078125,
-0.0012254714965820312,
0.0229644775390625,
0.05133056640625,
-0.0256195068359375,
-0.0262298583984375,
-0.0035228729248046875,
0.08331298828125,
0.0265350341796875,
0.0281219482421875,
-0.00699615478515625,
-0.0157470703125,
-0.00234222412109375,
0.0194244384765625,
-0.0623779296875,
-0.0228424072265625,
0.01318359375,
-0.0296783447265625,
-0.02044677734375,
0.01406097412109375,
-0.04071044921875,
0.005924224853515625,
0.0009474754333496094,
0.057373046875,
-0.052764892578125,
0.00492095947265625,
0.021331787109375,
-0.01479339599609375,
0.011566162109375,
-0.02069091796875,
-0.05181884765625,
0.01837158203125,
0.0210723876953125,
0.07080078125,
0.01064300537109375,
-0.03350830078125,
-0.0228118896484375,
-0.01204681396484375,
-0.007587432861328125,
0.04638671875,
-0.023651123046875,
-0.01021575927734375,
0.0142822265625,
0.020538330078125,
-0.0413818359375,
-0.027679443359375,
0.044342041015625,
-0.0265045166015625,
0.049530029296875,
0.0076751708984375,
-0.06756591796875,
-0.01387786865234375,
0.00789642333984375,
-0.0369873046875,
0.07696533203125,
0.01605224609375,
-0.0697021484375,
0.00879669189453125,
-0.06024169921875,
-0.02264404296875,
-0.0108184814453125,
0.0060577392578125,
-0.0555419921875,
0.009002685546875,
0.034423828125,
0.05059814453125,
0.0181121826171875,
0.034027099609375,
-0.01500701904296875,
-0.03582763671875,
0.031036376953125,
-0.0256195068359375,
0.0870361328125,
0.013916015625,
-0.025604248046875,
0.01043701171875,
-0.03570556640625,
-0.003025054931640625,
0.019073486328125,
-0.0108795166015625,
-0.015167236328125,
0.00153350830078125,
0.0246734619140625,
0.019683837890625,
0.01383209228515625,
-0.054412841796875,
0.006195068359375,
-0.048431396484375,
0.07025146484375,
0.046173095703125,
-0.0023899078369140625,
0.03814697265625,
-0.018798828125,
0.00916290283203125,
0.03021240234375,
-0.0012598037719726562,
-0.0201416015625,
-0.03167724609375,
-0.07366943359375,
-0.021514892578125,
0.0268096923828125,
0.04290771484375,
-0.052734375,
0.0849609375,
-0.03472900390625,
-0.03265380859375,
-0.051513671875,
0.0000015497207641601562,
0.008392333984375,
0.0259246826171875,
0.04766845703125,
-0.00835418701171875,
-0.050994873046875,
-0.07061767578125,
-0.00052642822265625,
-0.00032806396484375,
0.00615692138671875,
0.022064208984375,
0.0570068359375,
-0.03936767578125,
0.08050537109375,
-0.047637939453125,
-0.032562255859375,
-0.04248046875,
0.0250701904296875,
0.019805908203125,
0.050140380859375,
0.044036865234375,
-0.045928955078125,
-0.0305328369140625,
-0.04425048828125,
-0.05029296875,
0.00110626220703125,
-0.0167236328125,
-0.01271820068359375,
0.022613525390625,
0.03790283203125,
-0.060455322265625,
0.027587890625,
0.048065185546875,
-0.039794921875,
0.0221710205078125,
-0.0256195068359375,
-0.01702880859375,
-0.1038818359375,
0.003406524658203125,
0.005847930908203125,
-0.0213623046875,
-0.034820556640625,
-0.00039696693420410156,
0.0160064697265625,
-0.01132965087890625,
-0.03826904296875,
0.034637451171875,
-0.02880859375,
0.01194000244140625,
-0.00045752525329589844,
0.034881591796875,
0.0019321441650390625,
0.054229736328125,
-0.002544403076171875,
0.050506591796875,
0.03741455078125,
-0.03955078125,
0.0198974609375,
0.051605224609375,
-0.041107177734375,
0.00620269775390625,
-0.0625,
-0.0009045600891113281,
-0.0017004013061523438,
0.03375244140625,
-0.07952880859375,
0.003993988037109375,
0.02569580078125,
-0.0428466796875,
0.01861572265625,
0.0265045166015625,
-0.0499267578125,
-0.043487548828125,
-0.028533935546875,
0.01015472412109375,
0.044952392578125,
-0.0428466796875,
0.04388427734375,
0.018768310546875,
-0.00528717041015625,
-0.045379638671875,
-0.08740234375,
0.005130767822265625,
-0.0073089599609375,
-0.052490234375,
0.042724609375,
-0.007076263427734375,
0.01369476318359375,
0.0272979736328125,
0.01971435546875,
0.0009360313415527344,
-0.002414703369140625,
0.0020904541015625,
0.0187530517578125,
-0.0061187744140625,
0.01568603515625,
0.01348876953125,
-0.0093841552734375,
0.004474639892578125,
-0.0185089111328125,
0.054168701171875,
-0.0122833251953125,
-0.0079803466796875,
-0.033935546875,
0.0155487060546875,
0.0244293212890625,
-0.0193939208984375,
0.08514404296875,
0.0780029296875,
-0.03350830078125,
-0.00649261474609375,
-0.038787841796875,
-0.0205841064453125,
-0.03424072265625,
0.05413818359375,
-0.00788116455078125,
-0.0758056640625,
0.0273895263671875,
0.0152587890625,
0.0032196044921875,
0.04449462890625,
0.03851318359375,
-0.00563812255859375,
0.06396484375,
0.045379638671875,
-0.01678466796875,
0.037933349609375,
-0.050140380859375,
0.028961181640625,
-0.07110595703125,
-0.0010528564453125,
-0.0180511474609375,
-0.0182952880859375,
-0.052154541015625,
-0.033599853515625,
0.0095367431640625,
-0.00933074951171875,
-0.024017333984375,
0.0452880859375,
-0.03350830078125,
0.007770538330078125,
0.045257568359375,
0.01442718505859375,
-0.0128936767578125,
0.0024013519287109375,
-0.03558349609375,
-0.00565338134765625,
-0.051177978515625,
-0.044586181640625,
0.0631103515625,
0.036102294921875,
0.036407470703125,
-0.0126495361328125,
0.05126953125,
0.00279998779296875,
0.007419586181640625,
-0.05181884765625,
0.043304443359375,
-0.03204345703125,
-0.0338134765625,
-0.0226593017578125,
-0.03192138671875,
-0.0640869140625,
0.0249481201171875,
-0.01187896728515625,
-0.060455322265625,
0.007213592529296875,
-0.0183563232421875,
-0.0230865478515625,
0.025177001953125,
-0.06396484375,
0.0806884765625,
-0.000152587890625,
-0.0046234130859375,
-0.0088653564453125,
-0.050506591796875,
0.01064300537109375,
0.0137176513671875,
0.00862884521484375,
0.0026264190673828125,
-0.0024547576904296875,
0.0662841796875,
-0.0240631103515625,
0.07611083984375,
-0.01457977294921875,
0.015777587890625,
0.0288543701171875,
-0.028076171875,
0.0229644775390625,
-0.004241943359375,
-0.004856109619140625,
0.010955810546875,
-0.0142974853515625,
-0.025665283203125,
-0.035247802734375,
0.05377197265625,
-0.0787353515625,
-0.0294952392578125,
-0.035247802734375,
-0.045928955078125,
-0.00421905517578125,
0.01337432861328125,
0.0270538330078125,
0.035430908203125,
-0.0143890380859375,
0.03521728515625,
0.03680419921875,
-0.034942626953125,
0.057525634765625,
0.0094146728515625,
-0.0022525787353515625,
-0.04412841796875,
0.044586181640625,
0.01041412353515625,
0.0017175674438476562,
0.037384033203125,
0.0122528076171875,
-0.03399658203125,
-0.0161285400390625,
-0.0266265869140625,
0.031341552734375,
-0.045318603515625,
-0.01490020751953125,
-0.0823974609375,
-0.043975830078125,
-0.050140380859375,
-0.004039764404296875,
-0.0175628662109375,
-0.031829833984375,
-0.042755126953125,
-0.024444580078125,
0.025299072265625,
0.038482666015625,
-0.006561279296875,
0.0284423828125,
-0.058624267578125,
0.007160186767578125,
0.01198577880859375,
0.01424407958984375,
-0.004489898681640625,
-0.055999755859375,
-0.03424072265625,
0.0041656494140625,
-0.0323486328125,
-0.0611572265625,
0.058746337890625,
0.0164947509765625,
0.046966552734375,
0.016632080078125,
0.01128387451171875,
0.04608154296875,
-0.043853759765625,
0.07073974609375,
0.00273895263671875,
-0.08441162109375,
0.032318115234375,
0.003627777099609375,
0.028228759765625,
0.02716064453125,
0.0254974365234375,
-0.03759765625,
-0.035400390625,
-0.05023193359375,
-0.08282470703125,
0.058990478515625,
0.036102294921875,
0.04840087890625,
-0.02825927734375,
0.0219879150390625,
-0.0174713134765625,
0.0128021240234375,
-0.0897216796875,
-0.031402587890625,
-0.034515380859375,
-0.044677734375,
-0.0266876220703125,
-0.0283966064453125,
0.016998291015625,
-0.02642822265625,
0.06146240234375,
0.006557464599609375,
0.059844970703125,
0.0284576416015625,
-0.040802001953125,
0.005741119384765625,
0.0186920166015625,
0.040985107421875,
0.0178985595703125,
-0.01824951171875,
0.0109710693359375,
0.0221099853515625,
-0.0265655517578125,
-0.0021953582763671875,
0.0386962890625,
-0.0081329345703125,
0.0190277099609375,
0.02801513671875,
0.07806396484375,
0.043426513671875,
-0.039093017578125,
0.055694580078125,
-0.00679779052734375,
-0.023040771484375,
-0.03436279296875,
-0.0098876953125,
0.0237274169921875,
0.0174407958984375,
0.0264434814453125,
-0.0014905929565429688,
-0.005596160888671875,
-0.027587890625,
0.028717041015625,
0.0203399658203125,
-0.03936767578125,
-0.006256103515625,
0.051422119140625,
0.0072784423828125,
-0.01180267333984375,
0.07464599609375,
-0.02117919921875,
-0.0572509765625,
0.030426025390625,
0.05010986328125,
0.07513427734375,
0.0037078857421875,
0.022491455078125,
0.041046142578125,
0.0283966064453125,
-0.0008378028869628906,
-0.0015935897827148438,
0.01262664794921875,
-0.07147216796875,
-0.0235137939453125,
-0.042144775390625,
0.0029201507568359375,
0.0019683837890625,
-0.040679931640625,
0.019500732421875,
-0.0028743743896484375,
-0.01031494140625,
-0.0175933837890625,
0.0036773681640625,
-0.0450439453125,
0.0078277587890625,
0.008819580078125,
0.0665283203125,
-0.07421875,
0.057952880859375,
0.0517578125,
-0.04925537109375,
-0.05474853515625,
-0.005985260009765625,
-0.0298309326171875,
-0.05828857421875,
0.046112060546875,
0.040863037109375,
0.020050048828125,
0.01678466796875,
-0.04620361328125,
-0.059356689453125,
0.0992431640625,
0.02008056640625,
-0.0305938720703125,
-0.0125885009765625,
0.01284027099609375,
0.03472900390625,
-0.043975830078125,
0.030426025390625,
0.0225677490234375,
0.0263671875,
-0.006649017333984375,
-0.045989990234375,
0.0160675048828125,
-0.022735595703125,
0.0176544189453125,
-0.014007568359375,
-0.039794921875,
0.0736083984375,
-0.008636474609375,
-0.0175323486328125,
0.016876220703125,
0.06500244140625,
0.0206298828125,
-0.004848480224609375,
0.035369873046875,
0.06536865234375,
0.036407470703125,
-0.01108551025390625,
0.069091796875,
-0.02874755859375,
0.0545654296875,
0.07012939453125,
0.0005788803100585938,
0.08270263671875,
0.032073974609375,
-0.0023193359375,
0.06195068359375,
0.040374755859375,
-0.0231475830078125,
0.048614501953125,
0.0150604248046875,
0.00879669189453125,
-0.002246856689453125,
0.01148223876953125,
-0.01457977294921875,
0.03179931640625,
0.01342010498046875,
-0.058013916015625,
-0.0027065277099609375,
0.0115509033203125,
0.0101318359375,
-0.0009188652038574219,
0.00717926025390625,
0.0419921875,
0.016204833984375,
-0.031585693359375,
0.0290679931640625,
0.01558685302734375,
0.073974609375,
-0.030120849609375,
0.0131683349609375,
-0.005321502685546875,
0.0250701904296875,
0.0027980804443359375,
-0.04364013671875,
0.024810791015625,
-0.00691986083984375,
0.0038967132568359375,
-0.02191162109375,
0.041290283203125,
-0.047027587890625,
-0.04931640625,
0.03057861328125,
0.041290283203125,
-0.0008296966552734375,
0.007694244384765625,
-0.076416015625,
-0.0007081031799316406,
-0.0011186599731445312,
-0.041961669921875,
0.01311492919921875,
0.0278472900390625,
0.030120849609375,
0.045440673828125,
0.025299072265625,
-0.01139068603515625,
0.004467010498046875,
0.014373779296875,
0.0653076171875,
-0.050262451171875,
-0.042022705078125,
-0.07049560546875,
0.054779052734375,
-0.01291656494140625,
-0.0179443359375,
0.047576904296875,
0.04290771484375,
0.0650634765625,
-0.0239410400390625,
0.04266357421875,
-0.01033782958984375,
0.01763916015625,
-0.041473388671875,
0.06732177734375,
-0.03570556640625,
-0.0021877288818359375,
-0.022430419921875,
-0.066650390625,
-0.0236358642578125,
0.08221435546875,
-0.02557373046875,
0.016448974609375,
0.07073974609375,
0.05767822265625,
-0.003551483154296875,
-0.00611114501953125,
0.0163726806640625,
0.036407470703125,
0.016998291015625,
0.03680419921875,
0.036102294921875,
-0.0621337890625,
0.052886962890625,
-0.03936767578125,
-0.002620697021484375,
-0.0118408203125,
-0.06475830078125,
-0.0723876953125,
-0.05865478515625,
-0.035919189453125,
-0.0164337158203125,
-0.0039043426513671875,
0.08514404296875,
0.050689697265625,
-0.056915283203125,
-0.01207733154296875,
-0.018585205078125,
-0.01544952392578125,
-0.0107421875,
-0.023681640625,
0.03961181640625,
-0.046478271484375,
-0.06280517578125,
0.00788116455078125,
-0.004032135009765625,
0.0098419189453125,
-0.0279388427734375,
0.005893707275390625,
-0.047637939453125,
0.0174102783203125,
0.046478271484375,
-0.0261383056640625,
-0.05706787109375,
-0.024566650390625,
0.00824737548828125,
-0.025909423828125,
-0.00377655029296875,
0.0238800048828125,
-0.051513671875,
0.0180206298828125,
0.022613525390625,
0.039093017578125,
0.0450439453125,
-0.016326904296875,
0.037933349609375,
-0.0611572265625,
0.01479339599609375,
0.005924224853515625,
0.056610107421875,
0.03375244140625,
-0.01690673828125,
0.03924560546875,
0.01406097412109375,
-0.03704833984375,
-0.05120849609375,
-0.0160675048828125,
-0.07928466796875,
-0.024810791015625,
0.08221435546875,
-0.0372314453125,
-0.0269775390625,
0.01531982421875,
-0.0173492431640625,
0.03741455078125,
-0.0272064208984375,
0.054290771484375,
0.06292724609375,
0.004673004150390625,
-0.0254974365234375,
-0.022735595703125,
0.01026153564453125,
0.0297088623046875,
-0.04296875,
-0.01103973388671875,
0.016448974609375,
0.0191650390625,
0.0220184326171875,
0.0267181396484375,
-0.0098114013671875,
-0.0018568038940429688,
0.0001634359359741211,
0.01207733154296875,
-0.01343536376953125,
0.0090484619140625,
-0.022247314453125,
0.0028324127197265625,
-0.027679443359375,
-0.02557373046875
]
] |
valhalla/distilbart-mnli-12-1 | 2021-06-14T10:27:55.000Z | [
"transformers",
"pytorch",
"jax",
"bart",
"text-classification",
"distilbart",
"distilbart-mnli",
"zero-shot-classification",
"dataset:mnli",
"endpoints_compatible",
"has_space",
"region:us"
] | zero-shot-classification | valhalla | null | null | valhalla/distilbart-mnli-12-1 | 40 | 45,720 | transformers | 2022-03-02T23:29:05 | ---
datasets:
- mnli
tags:
- distilbart
- distilbart-mnli
pipeline_tag: zero-shot-classification
---
# DistilBart-MNLI
distilbart-mnli is the distilled version of bart-large-mnli created using the **No Teacher Distillation** technique proposed for BART summarisation by Huggingface, [here](https://github.com/huggingface/transformers/tree/master/examples/seq2seq#distilbart).
We just copy alternating layers from `bart-large-mnli` and finetune more on the same data.
| | matched acc | mismatched acc |
| ------------------------------------------------------------------------------------ | ----------- | -------------- |
| [bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) (baseline, 12-12) | 89.9 | 90.01 |
| [distilbart-mnli-12-1](https://huggingface.co/valhalla/distilbart-mnli-12-1) | 87.08 | 87.5 |
| [distilbart-mnli-12-3](https://huggingface.co/valhalla/distilbart-mnli-12-3) | 88.1 | 88.19 |
| [distilbart-mnli-12-6](https://huggingface.co/valhalla/distilbart-mnli-12-6) | 89.19 | 89.01 |
| [distilbart-mnli-12-9](https://huggingface.co/valhalla/distilbart-mnli-12-9) | 89.56 | 89.52 |
This is a very simple and effective technique, as we can see the performance drop is very little.
Detailed performace trade-offs will be posted in this [sheet](https://docs.google.com/spreadsheets/d/1dQeUvAKpScLuhDV1afaPJRRAE55s2LpIzDVA5xfqxvk/edit?usp=sharing).
## Fine-tuning
If you want to train these models yourself, clone the [distillbart-mnli repo](https://github.com/patil-suraj/distillbart-mnli) and follow the steps below
Clone and install transformers from source
```bash
git clone https://github.com/huggingface/transformers.git
pip install -qqq -U ./transformers
```
Download MNLI data
```bash
python transformers/utils/download_glue_data.py --data_dir glue_data --tasks MNLI
```
Create student model
```bash
python create_student.py \
--teacher_model_name_or_path facebook/bart-large-mnli \
--student_encoder_layers 12 \
--student_decoder_layers 6 \
--save_path student-bart-mnli-12-6 \
```
Start fine-tuning
```bash
python run_glue.py args.json
```
You can find the logs of these trained models in this [wandb project](https://wandb.ai/psuraj/distilbart-mnli). | 2,406 | [
[
-0.044891357421875,
-0.052337646484375,
0.017852783203125,
0.020416259765625,
-0.0157928466796875,
0.01392364501953125,
-0.00244140625,
-0.0168609619140625,
0.0245819091796875,
0.031341552734375,
-0.04290771484375,
-0.0119171142578125,
-0.0447998046875,
0.0102386474609375,
-0.0250244140625,
0.0947265625,
-0.00392913818359375,
0.00525665283203125,
-0.00897979736328125,
-0.01898193359375,
-0.017486572265625,
-0.030609130859375,
-0.043731689453125,
-0.02667236328125,
0.0277252197265625,
0.0251617431640625,
0.05206298828125,
0.0140228271484375,
0.04205322265625,
0.031585693359375,
-0.0389404296875,
0.0182342529296875,
-0.044281005859375,
0.007656097412109375,
0.0010881423950195312,
-0.03948974609375,
-0.047943115234375,
-0.000045239925384521484,
0.053314208984375,
0.039093017578125,
-0.006679534912109375,
0.035797119140625,
0.01641845703125,
0.08660888671875,
-0.041229248046875,
0.0015001296997070312,
-0.0294342041015625,
0.00646209716796875,
-0.0106048583984375,
0.002719879150390625,
-0.0290679931640625,
-0.025177001953125,
0.00197601318359375,
-0.03863525390625,
0.02337646484375,
-0.002536773681640625,
0.0814208984375,
0.03472900390625,
-0.0237884521484375,
-0.0096435546875,
-0.05645751953125,
0.06597900390625,
-0.057281494140625,
0.00959014892578125,
0.017486572265625,
0.045745849609375,
-0.0050201416015625,
-0.069580078125,
-0.0440673828125,
-0.004215240478515625,
-0.0309295654296875,
0.0168304443359375,
-0.007526397705078125,
-0.015716552734375,
0.05609130859375,
0.049530029296875,
-0.035430908203125,
-0.016204833984375,
-0.048553466796875,
0.00824737548828125,
0.0653076171875,
0.02294921875,
0.0034942626953125,
-0.0110321044921875,
-0.03985595703125,
-0.028411865234375,
-0.0229034423828125,
0.0078887939453125,
0.018798828125,
0.00988006591796875,
-0.0201263427734375,
0.048675537109375,
-0.0149078369140625,
0.0245361328125,
0.03570556640625,
-0.03106689453125,
0.053466796875,
-0.033111572265625,
-0.0257720947265625,
0.0111236572265625,
0.067626953125,
0.020843505859375,
0.02447509765625,
0.029632568359375,
-0.020416259765625,
-0.011383056640625,
0.001983642578125,
-0.09271240234375,
-0.03643798828125,
0.016204833984375,
-0.037750244140625,
-0.038330078125,
0.005329132080078125,
-0.049530029296875,
-0.00592041015625,
-0.03173828125,
0.03570556640625,
-0.041748046875,
-0.03167724609375,
-0.0155029296875,
-0.03271484375,
0.00447845458984375,
0.00872039794921875,
-0.07171630859375,
0.0176849365234375,
0.038116455078125,
0.058135986328125,
0.006015777587890625,
-0.01201629638671875,
-0.029541015625,
-0.004791259765625,
-0.0226593017578125,
0.0200042724609375,
-0.01317596435546875,
-0.030609130859375,
-0.035064697265625,
0.0130462646484375,
0.002323150634765625,
-0.04339599609375,
0.045013427734375,
-0.0172271728515625,
0.027557373046875,
-0.0234222412109375,
-0.034332275390625,
-0.0247650146484375,
0.00274658203125,
-0.0587158203125,
0.09515380859375,
0.02801513671875,
-0.08367919921875,
0.0220947265625,
-0.047576904296875,
-0.03179931640625,
-0.013336181640625,
0.012908935546875,
-0.07232666015625,
0.011566162109375,
0.0278472900390625,
0.042388916015625,
-0.006244659423828125,
0.03173828125,
-0.030853271484375,
-0.0361328125,
0.016815185546875,
-0.03778076171875,
0.09124755859375,
0.032501220703125,
-0.0304107666015625,
-0.00113677978515625,
-0.0726318359375,
0.00008153915405273438,
0.025054931640625,
-0.018524169921875,
-0.029022216796875,
-0.031890869140625,
0.0136566162109375,
0.006072998046875,
0.0233917236328125,
-0.0200653076171875,
0.021453857421875,
-0.018402099609375,
0.035491943359375,
0.050079345703125,
-0.0050811767578125,
0.028045654296875,
-0.041656494140625,
0.021026611328125,
0.0169525146484375,
0.034149169921875,
-0.002185821533203125,
-0.036712646484375,
-0.061248779296875,
-0.041473388671875,
0.03302001953125,
0.031219482421875,
-0.0640869140625,
0.029815673828125,
-0.01432037353515625,
-0.057708740234375,
-0.049652099609375,
0.0004892349243164062,
0.024749755859375,
0.042144775390625,
0.032501220703125,
0.0030918121337890625,
-0.04937744140625,
-0.08782958984375,
0.01073455810546875,
-0.006740570068359375,
-0.0070343017578125,
0.00489044189453125,
0.047943115234375,
-0.0092315673828125,
0.06524658203125,
-0.04998779296875,
-0.01532745361328125,
-0.0098114013671875,
0.0037250518798828125,
0.05914306640625,
0.03912353515625,
0.07781982421875,
-0.06524658203125,
-0.075439453125,
-0.004779815673828125,
-0.055938720703125,
-0.0014467239379882812,
0.0029926300048828125,
-0.014129638671875,
0.0182342529296875,
0.01319122314453125,
-0.05218505859375,
0.033233642578125,
0.03863525390625,
-0.02813720703125,
0.05328369140625,
-0.00991058349609375,
0.0231475830078125,
-0.1123046875,
0.0333251953125,
-0.01279449462890625,
-0.032196044921875,
-0.044342041015625,
0.0030918121337890625,
0.00847625732421875,
0.0008702278137207031,
-0.035614013671875,
0.029754638671875,
-0.03619384765625,
0.005626678466796875,
-0.00775909423828125,
-0.0206756591796875,
0.0158538818359375,
0.0501708984375,
-0.0241546630859375,
0.061614990234375,
0.042724609375,
-0.033233642578125,
0.030487060546875,
0.0308990478515625,
-0.0175628662109375,
0.043121337890625,
-0.05535888671875,
-0.00897979736328125,
-0.01105499267578125,
0.018402099609375,
-0.070068359375,
-0.002044677734375,
0.0242767333984375,
-0.033050537109375,
0.0440673828125,
-0.014923095703125,
-0.0279083251953125,
-0.03924560546875,
-0.04052734375,
0.026123046875,
0.066650390625,
-0.05084228515625,
0.047943115234375,
0.0119476318359375,
-0.00789642333984375,
-0.05914306640625,
-0.06005859375,
-0.0226898193359375,
-0.043975830078125,
-0.03863525390625,
0.031280517578125,
-0.01380157470703125,
-0.0163726806640625,
0.0080413818359375,
-0.004741668701171875,
-0.01203155517578125,
0.0080718994140625,
0.0269317626953125,
0.03875732421875,
-0.0143585205078125,
-0.0164947509765625,
0.01605224609375,
-0.01465606689453125,
-0.004726409912109375,
0.0133209228515625,
0.02813720703125,
-0.01415252685546875,
-0.00506591796875,
-0.056854248046875,
0.00958251953125,
0.0626220703125,
0.0036563873291015625,
0.046478271484375,
0.06787109375,
-0.006900787353515625,
-0.0012569427490234375,
-0.042022705078125,
-0.0194549560546875,
-0.040130615234375,
0.01197052001953125,
-0.0445556640625,
-0.04736328125,
0.042938232421875,
-0.00634765625,
0.023651123046875,
0.05767822265625,
0.039215087890625,
-0.0172119140625,
0.07861328125,
0.0272674560546875,
-0.0247039794921875,
0.0386962890625,
-0.047332763671875,
0.0021514892578125,
-0.058929443359375,
-0.011932373046875,
-0.03271484375,
-0.043975830078125,
-0.051361083984375,
-0.0233917236328125,
0.035430908203125,
0.02972412109375,
-0.0255279541015625,
0.04132080078125,
-0.05908203125,
0.0277557373046875,
0.042724609375,
-0.0028476715087890625,
0.033447265625,
0.009033203125,
-0.01093292236328125,
0.0026950836181640625,
-0.03839111328125,
-0.0225982666015625,
0.09063720703125,
0.0284423828125,
0.05029296875,
0.0077362060546875,
0.06610107421875,
0.01099395751953125,
0.0192108154296875,
-0.038665771484375,
0.02734375,
-0.00780487060546875,
-0.05950927734375,
-0.0233154296875,
-0.050628662109375,
-0.057342529296875,
0.027740478515625,
-0.023681640625,
-0.034423828125,
0.004878997802734375,
0.00921630859375,
-0.0206451416015625,
0.0284271240234375,
-0.060821533203125,
0.047210693359375,
-0.00579833984375,
-0.022003173828125,
-0.006328582763671875,
-0.0416259765625,
0.042816162109375,
-0.01363372802734375,
0.006557464599609375,
-0.00908660888671875,
0.030487060546875,
0.041748046875,
-0.058441162109375,
0.043701171875,
-0.029022216796875,
-0.0042266845703125,
0.042327880859375,
-0.00460052490234375,
0.03759765625,
0.0155487060546875,
-0.00829315185546875,
0.017120361328125,
0.0226898193359375,
-0.033111572265625,
-0.0546875,
0.0533447265625,
-0.054412841796875,
-0.03204345703125,
-0.0296478271484375,
-0.0264129638671875,
0.01213836669921875,
0.01045989990234375,
0.0217437744140625,
0.03350830078125,
-0.00383758544921875,
0.02142333984375,
0.04229736328125,
-0.004791259765625,
0.04541015625,
0.015655517578125,
-0.0343017578125,
-0.033294677734375,
0.06207275390625,
0.0024261474609375,
0.0178375244140625,
0.021820068359375,
0.025543212890625,
-0.030517578125,
-0.014801025390625,
-0.04541015625,
0.016357421875,
-0.0279388427734375,
-0.0226898193359375,
-0.035552978515625,
-0.035919189453125,
-0.02203369140625,
0.00312042236328125,
-0.046539306640625,
-0.0560302734375,
-0.019073486328125,
0.0079345703125,
0.05413818359375,
0.04449462890625,
-0.00850677490234375,
0.00445556640625,
-0.061676025390625,
0.0217132568359375,
0.0252685546875,
0.0137176513671875,
0.00390625,
-0.048095703125,
-0.009368896484375,
0.0221710205078125,
-0.0406494140625,
-0.042205810546875,
0.0279083251953125,
0.018402099609375,
0.0269927978515625,
0.033935546875,
0.017852783203125,
0.0634765625,
-0.034912109375,
0.0501708984375,
0.029754638671875,
-0.057708740234375,
0.037506103515625,
-0.009033203125,
0.008544921875,
0.05078125,
0.043304443359375,
-0.00899505615234375,
-0.025543212890625,
-0.052764892578125,
-0.0584716796875,
0.054443359375,
0.039703369140625,
-0.003719329833984375,
0.022918701171875,
0.003963470458984375,
0.0155792236328125,
0.00823974609375,
-0.044219970703125,
-0.052459716796875,
-0.0195770263671875,
-0.0148162841796875,
-0.01387786865234375,
-0.0208892822265625,
-0.0116424560546875,
-0.050872802734375,
0.060211181640625,
0.0045318603515625,
0.0027065277099609375,
0.0219573974609375,
0.007472991943359375,
0.004161834716796875,
-0.004619598388671875,
0.03399658203125,
0.035797119140625,
-0.03863525390625,
-0.002696990966796875,
0.02545166015625,
-0.04168701171875,
0.0105438232421875,
0.0045928955078125,
-0.0132293701171875,
0.02569580078125,
0.0182952880859375,
0.07208251953125,
0.0085601806640625,
-0.033721923828125,
0.03082275390625,
-0.005157470703125,
-0.0394287109375,
-0.04296875,
0.006649017333984375,
0.019012451171875,
0.040313720703125,
0.0269317626953125,
0.00969696044921875,
0.0210723876953125,
-0.037322998046875,
0.018585205078125,
0.0186614990234375,
-0.01251983642578125,
-0.0218658447265625,
0.04779052734375,
-0.006778717041015625,
-0.01003265380859375,
0.055511474609375,
-0.0140838623046875,
-0.0276336669921875,
0.04718017578125,
0.0255584716796875,
0.0543212890625,
-0.0245513916015625,
0.011138916015625,
0.057098388671875,
-0.007328033447265625,
-0.00708770751953125,
0.017791748046875,
-0.0010833740234375,
-0.026885986328125,
-0.02813720703125,
-0.06109619140625,
-0.01271820068359375,
0.01110076904296875,
-0.058624267578125,
0.03338623046875,
-0.03265380859375,
-0.0243072509765625,
0.023284912109375,
0.006343841552734375,
-0.053253173828125,
-0.005771636962890625,
-0.0035190582275390625,
0.050506591796875,
-0.064208984375,
0.06689453125,
0.040740966796875,
-0.03173828125,
-0.06500244140625,
-0.025146484375,
-0.0027980804443359375,
-0.040496826171875,
0.04779052734375,
0.00785064697265625,
0.01824951171875,
-0.0125732421875,
-0.0229034423828125,
-0.06964111328125,
0.10595703125,
0.0188751220703125,
-0.0635986328125,
0.0021266937255859375,
0.0079345703125,
0.046173095703125,
-0.0042572021484375,
0.042755126953125,
0.049774169921875,
0.034423828125,
0.03558349609375,
-0.08642578125,
0.00988006591796875,
-0.034149169921875,
0.005764007568359375,
0.0254669189453125,
-0.061065673828125,
0.0843505859375,
-0.0084686279296875,
-0.0180816650390625,
0.005100250244140625,
0.0352783203125,
0.02972412109375,
0.0302734375,
0.03741455078125,
0.06719970703125,
0.04693603515625,
-0.00096893310546875,
0.064453125,
-0.0109100341796875,
0.0592041015625,
0.0732421875,
-0.00524139404296875,
0.049957275390625,
0.0391845703125,
-0.04296875,
0.031341552734375,
0.03558349609375,
-0.021087646484375,
0.046844482421875,
0.01082611083984375,
-0.006076812744140625,
0.00406646728515625,
0.0151519775390625,
-0.05108642578125,
0.02655029296875,
0.00921630859375,
-0.0309600830078125,
-0.0090179443359375,
-0.006275177001953125,
0.00279998779296875,
-0.00885772705078125,
-0.0033893585205078125,
0.050201416015625,
0.01263427734375,
-0.039703369140625,
0.08709716796875,
-0.0177154541015625,
0.06103515625,
-0.029022216796875,
-0.00469207763671875,
-0.0192108154296875,
0.01540374755859375,
-0.021575927734375,
-0.05047607421875,
0.035125732421875,
-0.003986358642578125,
-0.01465606689453125,
-0.00704193115234375,
0.039520263671875,
-0.028167724609375,
-0.05841064453125,
0.01363372802734375,
0.023040771484375,
0.021148681640625,
0.002689361572265625,
-0.061920166015625,
-0.0009860992431640625,
0.01311492919921875,
-0.04168701171875,
0.022308349609375,
0.0288543701171875,
0.009521484375,
0.040557861328125,
0.052886962890625,
-0.01654052734375,
-0.00507354736328125,
0.0016078948974609375,
0.08221435546875,
-0.02972412109375,
-0.01629638671875,
-0.07916259765625,
0.05755615234375,
-0.0323486328125,
-0.025360107421875,
0.050506591796875,
0.05810546875,
0.060394287109375,
-0.0219573974609375,
0.0426025390625,
-0.0095062255859375,
0.03533935546875,
-0.037994384765625,
0.0718994140625,
-0.06427001953125,
-0.00798797607421875,
-0.04071044921875,
-0.0947265625,
0.002410888671875,
0.0487060546875,
0.0025501251220703125,
0.0017423629760742188,
0.04132080078125,
0.058502197265625,
-0.02032470703125,
0.0020580291748046875,
0.01438140869140625,
0.01462554931640625,
0.0137786865234375,
0.042816162109375,
0.056732177734375,
-0.055511474609375,
0.0338134765625,
-0.048004150390625,
-0.0155792236328125,
-0.02557373046875,
-0.051055908203125,
-0.0845947265625,
-0.051544189453125,
-0.027862548828125,
-0.0190582275390625,
-0.02069091796875,
0.055938720703125,
0.052703857421875,
-0.0628662109375,
0.00212860107421875,
0.007221221923828125,
0.002986907958984375,
-0.021575927734375,
-0.023101806640625,
0.0361328125,
-0.011749267578125,
-0.08026123046875,
0.0159454345703125,
-0.0021457672119140625,
0.0177154541015625,
-0.01232147216796875,
-0.00618743896484375,
-0.005489349365234375,
-0.0126800537109375,
0.04730224609375,
0.0015478134155273438,
-0.039886474609375,
-0.005702972412109375,
-0.0180206298828125,
-0.00044727325439453125,
0.00823974609375,
0.034423828125,
-0.0311279296875,
0.01410675048828125,
0.050201416015625,
0.02667236328125,
0.069580078125,
0.006927490234375,
0.0101470947265625,
-0.054290771484375,
0.0253143310546875,
0.006458282470703125,
0.031341552734375,
0.0093994140625,
-0.0293426513671875,
0.05169677734375,
0.01898193359375,
-0.044830322265625,
-0.06781005859375,
-0.00307464599609375,
-0.0872802734375,
-0.0258636474609375,
0.0665283203125,
-0.0111541748046875,
-0.0226593017578125,
0.0259857177734375,
-0.0306243896484375,
0.0251312255859375,
-0.032958984375,
0.057891845703125,
0.034759521484375,
0.00327301025390625,
0.0062713623046875,
-0.04058837890625,
0.034942626953125,
0.03369140625,
-0.030517578125,
-0.00884246826171875,
0.0200653076171875,
0.038787841796875,
0.0286407470703125,
0.039703369140625,
-0.02056884765625,
-0.005916595458984375,
0.01140594482421875,
0.005161285400390625,
-0.03179931640625,
-0.016265869140625,
-0.0025997161865234375,
0.00469207763671875,
-0.01242828369140625,
-0.0267486572265625
]
] |
guillaumekln/faster-whisper-small.en | 2023-05-12T18:57:44.000Z | [
"ctranslate2",
"audio",
"automatic-speech-recognition",
"en",
"license:mit",
"region:us"
] | automatic-speech-recognition | guillaumekln | null | null | guillaumekln/faster-whisper-small.en | 1 | 45,559 | ctranslate2 | 2023-03-23T10:20:17 | ---
language:
- en
tags:
- audio
- automatic-speech-recognition
license: mit
library_name: ctranslate2
---
# Whisper small.en model for CTranslate2
This repository contains the conversion of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) to the [CTranslate2](https://github.com/OpenNMT/CTranslate2) model format.
This model can be used in CTranslate2 or projects based on CTranslate2 such as [faster-whisper](https://github.com/guillaumekln/faster-whisper).
## Example
```python
from faster_whisper import WhisperModel
model = WhisperModel("small.en")
segments, info = model.transcribe("audio.mp3")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
```
## Conversion details
The original model was converted with the following command:
```
ct2-transformers-converter --model openai/whisper-small.en --output_dir faster-whisper-small.en \
--copy_files tokenizer.json --quantization float16
```
Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the [`compute_type` option in CTranslate2](https://opennmt.net/CTranslate2/quantization.html).
## More information
**For more information about the original model, see its [model card](https://huggingface.co/openai/whisper-small.en).**
| 1,335 | [
[
0.002422332763671875,
-0.0279541015625,
0.020843505859375,
0.032379150390625,
-0.03509521484375,
-0.029449462890625,
-0.0389404296875,
-0.03338623046875,
0.004932403564453125,
0.0521240234375,
-0.03607177734375,
-0.0400390625,
-0.041748046875,
-0.01515960693359375,
-0.02081298828125,
0.06463623046875,
-0.0176544189453125,
0.0210418701171875,
0.02874755859375,
-0.005680084228515625,
-0.0257568359375,
-0.01279449462890625,
-0.060302734375,
-0.0204925537109375,
0.01345062255859375,
0.022796630859375,
0.042449951171875,
0.026580810546875,
0.034912109375,
0.0204620361328125,
-0.02154541015625,
-0.005023956298828125,
-0.0214996337890625,
-0.014373779296875,
0.01641845703125,
-0.052642822265625,
-0.045806884765625,
0.0094451904296875,
0.04937744140625,
0.00881195068359375,
-0.0218048095703125,
0.036041259765625,
-0.0133819580078125,
0.0247344970703125,
-0.03302001953125,
0.023193359375,
-0.041412353515625,
-0.0001995563507080078,
-0.01236724853515625,
-0.01279449462890625,
-0.0423583984375,
-0.028076171875,
0.035430908203125,
-0.0616455078125,
0.01268768310546875,
0.0009202957153320312,
0.06402587890625,
0.0186767578125,
-0.034210205078125,
-0.028228759765625,
-0.06536865234375,
0.0701904296875,
-0.059173583984375,
0.0163116455078125,
0.0197601318359375,
0.0416259765625,
0.0156707763671875,
-0.0804443359375,
-0.019805908203125,
-0.005664825439453125,
0.0032806396484375,
0.0205841064453125,
-0.028839111328125,
0.02142333984375,
0.01104736328125,
0.034576416015625,
-0.048492431640625,
-0.006683349609375,
-0.058135986328125,
-0.032989501953125,
0.0411376953125,
0.009613037109375,
0.0183258056640625,
-0.0218505859375,
-0.020599365234375,
-0.04559326171875,
-0.040008544921875,
0.001873016357421875,
0.03607177734375,
0.0255126953125,
-0.054046630859375,
0.050048828125,
0.003360748291015625,
0.0284271240234375,
0.00617218017578125,
-0.0240020751953125,
0.024322509765625,
-0.0206451416015625,
-0.01470184326171875,
0.0347900390625,
0.050933837890625,
0.0352783203125,
0.006488800048828125,
0.022216796875,
-0.0195465087890625,
-0.005096435546875,
0.0005545616149902344,
-0.08489990234375,
-0.031219482421875,
0.01953125,
-0.0693359375,
-0.0161285400390625,
0.003757476806640625,
-0.0256805419921875,
0.00728607177734375,
-0.01381683349609375,
0.04644775390625,
-0.03314208984375,
-0.034881591796875,
0.031036376953125,
-0.037872314453125,
0.00936126708984375,
0.032684326171875,
-0.055694580078125,
0.03216552734375,
0.0389404296875,
0.08343505859375,
0.006580352783203125,
-0.0034503936767578125,
-0.0157928466796875,
0.0170440673828125,
-0.004947662353515625,
0.03936767578125,
-0.001583099365234375,
-0.037933349609375,
-0.004062652587890625,
0.0013608932495117188,
-0.01087188720703125,
-0.041290283203125,
0.04547119140625,
-0.0143280029296875,
0.0299224853515625,
0.0224609375,
-0.01209259033203125,
-0.015777587890625,
-0.00014913082122802734,
-0.050872802734375,
0.073486328125,
0.032867431640625,
-0.058807373046875,
-0.013092041015625,
-0.061309814453125,
-0.011566162109375,
-0.0175933837890625,
0.033721923828125,
-0.03173828125,
0.02166748046875,
-0.003215789794921875,
-0.0032958984375,
-0.036590576171875,
0.01812744140625,
-0.0091094970703125,
-0.0288848876953125,
0.019500732421875,
-0.035064697265625,
0.07379150390625,
0.029632568359375,
0.00719451904296875,
0.0193023681640625,
-0.045318603515625,
0.0024871826171875,
0.00007963180541992188,
-0.029449462890625,
-0.0248870849609375,
-0.0134429931640625,
0.039886474609375,
0.0033016204833984375,
0.0263214111328125,
-0.04852294921875,
0.0218505859375,
-0.048248291015625,
0.064208984375,
0.028167724609375,
0.0021209716796875,
0.0335693359375,
-0.0311737060546875,
0.00849151611328125,
0.017120361328125,
0.03131103515625,
0.0106658935546875,
-0.04290771484375,
-0.057159423828125,
-0.01055908203125,
0.033966064453125,
0.03204345703125,
-0.047576904296875,
0.01422882080078125,
-0.026885986328125,
-0.069091796875,
-0.07415771484375,
-0.033233642578125,
0.0164947509765625,
0.01554107666015625,
0.039947509765625,
-0.00453948974609375,
-0.0616455078125,
-0.0693359375,
-0.008819580078125,
-0.0287017822265625,
-0.021026611328125,
0.0152587890625,
0.04815673828125,
-0.01320648193359375,
0.048431396484375,
-0.045501708984375,
-0.03790283203125,
-0.0172271728515625,
0.0274658203125,
0.0212860107421875,
0.06256103515625,
0.04534912109375,
-0.055633544921875,
-0.0235595703125,
-0.012237548828125,
-0.0211029052734375,
0.0021228790283203125,
-0.00888824462890625,
-0.003406524658203125,
0.0006470680236816406,
0.0066986083984375,
-0.056121826171875,
0.037017822265625,
0.052490234375,
-0.02655029296875,
0.03436279296875,
-0.0033664703369140625,
-0.0010852813720703125,
-0.09112548828125,
0.00797271728515625,
0.0010004043579101562,
-0.01104736328125,
-0.042205810546875,
0.00262451171875,
0.0154571533203125,
0.004222869873046875,
-0.0638427734375,
0.052764892578125,
-0.0112762451171875,
-0.00243377685546875,
-0.006183624267578125,
-0.01171112060546875,
-0.005687713623046875,
0.0211181640625,
0.03131103515625,
0.05926513671875,
0.0290679931640625,
-0.0298309326171875,
0.00838470458984375,
0.0469970703125,
-0.021270751953125,
0.009307861328125,
-0.074462890625,
0.0110015869140625,
0.0175323486328125,
0.0308685302734375,
-0.04022216796875,
-0.0035839080810546875,
0.0203857421875,
-0.050628662109375,
0.01346588134765625,
-0.04541015625,
-0.0433349609375,
-0.0220947265625,
-0.036468505859375,
0.03839111328125,
0.04913330078125,
-0.030853271484375,
0.05059814453125,
0.0187530517578125,
0.005741119384765625,
0.0008492469787597656,
-0.0811767578125,
-0.01023101806640625,
-0.0152740478515625,
-0.060699462890625,
0.051483154296875,
-0.0193939208984375,
-0.01251983642578125,
-0.00963592529296875,
-0.001163482666015625,
-0.0194244384765625,
-0.0132293701171875,
0.0294952392578125,
0.019805908203125,
-0.032135009765625,
-0.0191650390625,
0.0302886962890625,
-0.0246734619140625,
0.00540924072265625,
-0.03778076171875,
0.04864501953125,
-0.012481689453125,
0.004680633544921875,
-0.0543212890625,
0.00725555419921875,
0.03692626953125,
-0.0139312744140625,
0.037933349609375,
0.053070068359375,
-0.029571533203125,
-0.01453399658203125,
-0.0261688232421875,
-0.0195770263671875,
-0.036102294921875,
0.0152130126953125,
-0.02874755859375,
-0.0577392578125,
0.035797119140625,
0.00780487060546875,
-0.0013399124145507812,
0.0631103515625,
0.0406494140625,
0.0035724639892578125,
0.0831298828125,
0.03594970703125,
0.0224456787109375,
0.030517578125,
-0.053375244140625,
-0.010833740234375,
-0.085693359375,
-0.021453857421875,
-0.05413818359375,
-0.0162811279296875,
-0.033233642578125,
-0.0250396728515625,
0.040069580078125,
0.01284027099609375,
-0.034881591796875,
0.051513671875,
-0.054046630859375,
0.0008187294006347656,
0.034881591796875,
0.01447296142578125,
0.0205230712890625,
-0.0013418197631835938,
0.01416015625,
-0.01505279541015625,
-0.0305023193359375,
-0.030426025390625,
0.07965087890625,
0.044891357421875,
0.053924560546875,
0.0284271240234375,
0.050323486328125,
0.009735107421875,
0.0107879638671875,
-0.06549072265625,
0.01910400390625,
-0.0192413330078125,
-0.04071044921875,
-0.006412506103515625,
-0.02325439453125,
-0.050933837890625,
0.0043487548828125,
0.0037059783935546875,
-0.05218505859375,
0.007228851318359375,
-0.00202178955078125,
-0.01213836669921875,
0.0257568359375,
-0.040924072265625,
0.059539794921875,
0.00899505615234375,
0.0225677490234375,
-0.016754150390625,
-0.02972412109375,
0.037139892578125,
0.00789642333984375,
-0.0167694091796875,
0.005710601806640625,
-0.005374908447265625,
0.08197021484375,
-0.052642822265625,
0.06353759765625,
-0.032623291015625,
-0.01103973388671875,
0.054595947265625,
0.0143280029296875,
0.035003662109375,
0.01496124267578125,
-0.0141143798828125,
0.038543701171875,
0.034820556640625,
-0.0006656646728515625,
-0.0234527587890625,
0.0406494140625,
-0.09344482421875,
-0.00835418701171875,
-0.0184478759765625,
-0.03839111328125,
0.0279541015625,
0.01023101806640625,
0.039642333984375,
0.04217529296875,
-0.0032806396484375,
0.0165863037109375,
0.0433349609375,
0.0024967193603515625,
0.034454345703125,
0.05364990234375,
-0.004604339599609375,
-0.052520751953125,
0.054718017578125,
0.0159912109375,
0.0198822021484375,
0.033233642578125,
0.027252197265625,
-0.037872314453125,
-0.069091796875,
-0.031219482421875,
0.00916290283203125,
-0.047515869140625,
-0.030517578125,
-0.043731689453125,
-0.038787841796875,
-0.037261962890625,
0.00835418701171875,
-0.050506591796875,
-0.056732177734375,
-0.041351318359375,
0.0209808349609375,
0.05023193359375,
0.03570556640625,
-0.00830841064453125,
0.05206298828125,
-0.07818603515625,
0.0185394287109375,
-0.0008401870727539062,
0.00983428955078125,
0.0084686279296875,
-0.07476806640625,
-0.01201629638671875,
0.013153076171875,
-0.02130126953125,
-0.0576171875,
0.0382080078125,
0.0078277587890625,
0.0090789794921875,
0.01297760009765625,
0.01122283935546875,
0.054046630859375,
-0.01346588134765625,
0.074462890625,
0.021881103515625,
-0.08447265625,
0.053466796875,
-0.033905029296875,
0.010955810546875,
0.03887939453125,
0.004917144775390625,
-0.04498291015625,
-0.005828857421875,
-0.048370361328125,
-0.054718017578125,
0.06805419921875,
0.033782958984375,
-0.00896453857421875,
0.013397216796875,
0.0121002197265625,
0.01067352294921875,
0.0113983154296875,
-0.05767822265625,
-0.0216064453125,
-0.041046142578125,
-0.034912109375,
0.0147705078125,
-0.01922607421875,
-0.006954193115234375,
-0.0204925537109375,
0.05828857421875,
-0.0185089111328125,
0.0374755859375,
0.036529541015625,
-0.016265869140625,
-0.007350921630859375,
0.0028228759765625,
0.05499267578125,
0.00396728515625,
-0.038543701171875,
-0.006610870361328125,
0.0134429931640625,
-0.058319091796875,
-0.0052642822265625,
0.0003566741943359375,
-0.0295867919921875,
0.01523590087890625,
0.028289794921875,
0.057037353515625,
0.02935791015625,
-0.0206146240234375,
0.049774169921875,
-0.014984130859375,
-0.029022216796875,
-0.05889892578125,
0.002410888671875,
0.01282501220703125,
0.0165863037109375,
0.02105712890625,
0.0205078125,
0.01763916015625,
-0.026092529296875,
-0.0157012939453125,
0.007572174072265625,
-0.03680419921875,
-0.039093017578125,
0.058990478515625,
0.012908935546875,
-0.026031494140625,
0.045196533203125,
-0.0001800060272216797,
-0.01125335693359375,
0.04498291015625,
0.057586669921875,
0.08941650390625,
-0.003131866455078125,
0.008544921875,
0.050872802734375,
0.02899169921875,
-0.01904296875,
0.05169677734375,
-0.00966644287109375,
-0.0287933349609375,
-0.0216064453125,
-0.05853271484375,
-0.02239990234375,
0.00543975830078125,
-0.07086181640625,
0.02655029296875,
-0.037353515625,
-0.01390838623046875,
0.004611968994140625,
0.006683349609375,
-0.05145263671875,
0.00020885467529296875,
0.0120391845703125,
0.10858154296875,
-0.048919677734375,
0.0892333984375,
0.03680419921875,
-0.034210205078125,
-0.0699462890625,
-0.0227813720703125,
-0.0003902912139892578,
-0.052459716796875,
0.04180908203125,
0.011993408203125,
0.002490997314453125,
0.0023517608642578125,
-0.056427001953125,
-0.0736083984375,
0.1033935546875,
0.0026454925537109375,
-0.04608154296875,
-0.0137176513671875,
0.01323699951171875,
0.037445068359375,
-0.044158935546875,
0.047332763671875,
0.035308837890625,
0.0633544921875,
-0.0011186599731445312,
-0.09136962890625,
0.000614166259765625,
-0.010955810546875,
0.0206756591796875,
0.007762908935546875,
-0.0665283203125,
0.08807373046875,
-0.01110076904296875,
-0.01154327392578125,
0.061981201171875,
0.049774169921875,
0.0192413330078125,
0.02203369140625,
0.02899169921875,
0.032623291015625,
0.0296173095703125,
-0.026580810546875,
0.046844482421875,
-0.0172882080078125,
0.0408935546875,
0.07073974609375,
-0.01358795166015625,
0.07684326171875,
0.031402587890625,
-0.00460052490234375,
0.052032470703125,
0.038818359375,
-0.0221099853515625,
0.046630859375,
-0.0016880035400390625,
0.0035266876220703125,
-0.001094818115234375,
-0.0022068023681640625,
-0.033447265625,
0.054595947265625,
0.03546142578125,
-0.0275726318359375,
-0.00942230224609375,
-0.0021610260009765625,
0.0008177757263183594,
-0.016082763671875,
-0.033843994140625,
0.051025390625,
-0.0004177093505859375,
-0.0310821533203125,
0.04864501953125,
0.033660888671875,
0.0654296875,
-0.06573486328125,
-0.007411956787109375,
0.0182647705078125,
0.013824462890625,
-0.0157012939453125,
-0.052398681640625,
0.035247802734375,
-0.0147705078125,
-0.0223388671875,
-0.002147674560546875,
0.046844482421875,
-0.0469970703125,
-0.030548095703125,
0.0247039794921875,
0.01299285888671875,
0.02532958984375,
-0.0162811279296875,
-0.056488037109375,
0.0282440185546875,
0.01861572265625,
-0.0226287841796875,
0.020294189453125,
-0.0003113746643066406,
-0.00010973215103149414,
0.031280517578125,
0.05889892578125,
0.01198577880859375,
-0.00238037109375,
0.0045928955078125,
0.04754638671875,
-0.047943115234375,
-0.053070068359375,
-0.0272979736328125,
0.044403076171875,
-0.0008549690246582031,
-0.051055908203125,
0.04071044921875,
0.06256103515625,
0.046173095703125,
-0.0262298583984375,
0.04541015625,
-0.0017061233520507812,
0.0257568359375,
-0.060211181640625,
0.060394287109375,
-0.02874755859375,
-0.00756072998046875,
0.00304412841796875,
-0.057281494140625,
0.004451751708984375,
0.02972412109375,
-0.004756927490234375,
-0.017730712890625,
0.05078125,
0.06646728515625,
-0.009735107421875,
0.021148681640625,
-0.00010687112808227539,
0.033782958984375,
0.0211944580078125,
0.046844482421875,
0.043701171875,
-0.07598876953125,
0.052520751953125,
-0.028594970703125,
0.0027523040771484375,
-0.005481719970703125,
-0.047149658203125,
-0.06756591796875,
-0.045501708984375,
-0.033660888671875,
-0.045013427734375,
-0.01107025146484375,
0.069580078125,
0.06549072265625,
-0.052398681640625,
-0.0249786376953125,
0.005588531494140625,
-0.00732421875,
-0.0006937980651855469,
-0.0211639404296875,
0.0379638671875,
0.02923583984375,
-0.05731201171875,
0.0408935546875,
0.0065460205078125,
0.037628173828125,
-0.020843505859375,
-0.0333251953125,
0.02130126953125,
0.00542449951171875,
0.027069091796875,
0.009002685546875,
-0.06597900390625,
-0.018951416015625,
-0.0228271484375,
-0.0033931732177734375,
0.012908935546875,
0.053924560546875,
-0.052490234375,
0.0101165771484375,
0.044952392578125,
-0.020050048828125,
0.057159423828125,
-0.029022216796875,
0.015838623046875,
-0.045166015625,
0.041473388671875,
0.018829345703125,
0.03033447265625,
0.01128387451171875,
-0.006404876708984375,
0.031890869140625,
0.01233673095703125,
-0.0232086181640625,
-0.0694580078125,
-0.0037860870361328125,
-0.098388671875,
-0.005649566650390625,
0.08111572265625,
0.00238800048828125,
-0.03070068359375,
0.01505279541015625,
-0.04339599609375,
0.02532958984375,
-0.047119140625,
0.0169677734375,
0.01013946533203125,
0.02899169921875,
-0.0022945404052734375,
-0.035247802734375,
0.03521728515625,
-0.00966644287109375,
-0.029449462890625,
0.0013875961303710938,
0.004932403564453125,
0.033966064453125,
0.030853271484375,
0.04034423828125,
-0.03326416015625,
0.031646728515625,
0.023773193359375,
0.029754638671875,
-0.0244598388671875,
-0.0301971435546875,
-0.0269317626953125,
-0.00041675567626953125,
-0.0022335052490234375,
-0.0196533203125
]
] |
stabilityai/stable-diffusion-xl-base-0.9 | 2023-07-12T13:55:37.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"arxiv:2108.01073",
"arxiv:2112.10752",
"arxiv:2307.01952",
"license:other",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | stabilityai | null | null | stabilityai/stable-diffusion-xl-base-0.9 | 1,339 | 45,524 | diffusers | 2023-06-19T15:30:11 | ---
license: other
extra_gated_prompt: >-
Copyright (c) Stability AI Ltd.
This License Agreement (as may be amended in accordance with this License
Agreement, “License”), between you, or your employer or other entity (if you
are entering into this agreement on behalf of your employer or other entity)
(“Licensee” or “you”) and Stability AI Ltd. (“Stability AI” or “we”) applies
to your use of any computer program, algorithm, source code, object code,
software, models, or model weights that is made available by Stability AI
under this License (“Software”) and any specifications, manuals,
documentation, and other written information provided by Stability AI related
to the Software (“Documentation”). By using the Software, you agree to the
terms of this License. If you do not agree to this License, then you do not
have any rights to use the Software or Documentation (collectively, the
“Software Products”), and you must immediately cease using the Software
Products. If you are agreeing to be bound by the terms of this License on
behalf of your employer or other entity, you represent and warrant to
Stability AI that you have full legal authority to bind your employer or such
entity to this License. If you do not have the requisite authority, you may
not accept the License or access the Software Products on behalf of your
employer or other entity.
1. LICENSE GRANT
a. Subject to your compliance with the Documentation and Sections 2, 3, and 5,
Stability AI grants you a non-exclusive, worldwide, non-transferable,
non-sublicensable, revocable, royalty free and limited license under Stability
AI’s copyright interests to use, reproduce, and create derivative works of the
Software solely for your non-commercial research purposes. The foregoing
license is personal to you, and you may not assign, sublicense, distribute,
publish, host, or otherwise make available this Software, derivative works of
the Software, models or model weights associated with the Software, this
License, or any other rights or obligations under this License without
Stability AI’s prior written consent; any such assignment or sublicense
without Stability AI’s prior written consent will be void and will
automatically and immediately terminate this License. For sake of clarity,
this License does not grant to you the right or ability to extend any license
to the Software, derivative works of the Software, or associated models or
model weights to a non-Licensee, nor does this License permit you to create a
new Licensee, such as by making available a copy of this License. If you
would like rights not granted by this License, you may seek permission by
sending an email to legal@stability.ai.
b. You may make a reasonable number of copies of the Documentation solely for
your use in connection with the license to the Software granted above.
c. The grant of rights expressly set forth in this Section 1 (License Grant)
are the complete grant of rights to you in the Software Products, and no other
licenses are granted, whether by waiver, estoppel, implication, equity or
otherwise. Stability AI and its licensors reserve all rights not expressly
granted by this License.
2. RESTRICTIONS
You will not, and will not permit, assist or cause any third party to:
a. use, modify, copy, reproduce, create derivative works of, or distribute the
Software Products (or any derivative works thereof, works incorporating the
Software Products, or any data produced by the Software), in whole or in part,
for (i) any commercial or production purposes, (ii) military purposes or in
the service of nuclear technology, (iii) purposes of surveillance, including
any research or development relating to surveillance, (iv) biometric
processing, (v) in any manner that infringes, misappropriates, or otherwise
violates any third-party rights, or (vi) in any manner that violates any
applicable law and violating any privacy or security laws, rules, regulations,
directives, or governmental requirements (including the General Data Privacy
Regulation (Regulation (EU) 2016/679), the California Consumer Privacy Act,
and any and all laws governing the processing of biometric information), as
well as all amendments and successor laws to any of the foregoing;
b. alter or remove copyright and other proprietary notices which appear on or
in the Software Products;
c. utilize any equipment, device, software, or other means to circumvent or
remove any security or protection used by Stability AI in connection with the
Software, or to circumvent or remove any usage restrictions, or to enable
functionality disabled by Stability AI; or
d. offer or impose any terms on the Software Products that alter, restrict, or
are inconsistent with the terms of this License.
e. 1) violate any applicable U.S. and non-U.S. export control and trade
sanctions laws (“Export Laws”); 2) directly or indirectly export, re-export,
provide, or otherwise transfer Software Products: (a) to any individual,
entity, or country prohibited by Export Laws; (b) to anyone on U.S. or
non-U.S. government restricted parties lists; or (c) for any purpose
prohibited by Export Laws, including nuclear, chemical or biological weapons,
or missile technology applications; 3) use or download Software Products if
you or they are: (a) located in a comprehensively sanctioned jurisdiction, (b)
currently listed on any U.S. or non-U.S. restricted parties list, or (c) for
any purpose prohibited by Export Laws; and (4) will not disguise your location
through IP proxying or other methods.
3. ATTRIBUTION
Together with any copies of the Software Products (as well as derivative works
thereof or works incorporating the Software Products) that you distribute, you
must provide (i) a copy of this License, and (ii) the following attribution
notice: “SDXL 0.9 is licensed under the SDXL Research License, Copyright (c)
Stability AI Ltd. All Rights Reserved.”
4. DISCLAIMERS
THE SOFTWARE PRODUCTS ARE PROVIDED “AS IS” AND “WITH ALL FAULTS” WITH NO
WARRANTY OF ANY KIND, EXPRESS OR IMPLIED. STABILITY AI EXPRESSLY DISCLAIMS ALL
REPRESENTATIONS AND WARRANTIES, EXPRESS OR IMPLIED, WHETHER BY STATUTE,
CUSTOM, USAGE OR OTHERWISE AS TO ANY MATTERS RELATED TO THE SOFTWARE PRODUCTS,
INCLUDING BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE, SATISFACTORY QUALITY, OR
NON-INFRINGEMENT. STABILITY AI MAKES NO WARRANTIES OR REPRESENTATIONS THAT THE
SOFTWARE PRODUCTS WILL BE ERROR FREE OR FREE OF VIRUSES OR OTHER HARMFUL
COMPONENTS, OR PRODUCE ANY PARTICULAR RESULTS.
5. LIMITATION OF LIABILITY
TO THE FULLEST EXTENT PERMITTED BY LAW, IN NO EVENT WILL STABILITY AI BE
LIABLE TO YOU (A) UNDER ANY THEORY OF LIABILITY, WHETHER BASED IN CONTRACT,
TORT, NEGLIGENCE, STRICT LIABILITY, WARRANTY, OR OTHERWISE UNDER THIS LICENSE,
OR (B) FOR ANY INDIRECT, CONSEQUENTIAL, EXEMPLARY, INCIDENTAL, PUNITIVE OR
SPECIAL DAMAGES OR LOST PROFITS, EVEN IF STABILITY AI HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES. THE SOFTWARE PRODUCTS, THEIR CONSTITUENT
COMPONENTS, AND ANY OUTPUT (COLLECTIVELY, “SOFTWARE MATERIALS”) ARE NOT
DESIGNED OR INTENDED FOR USE IN ANY APPLICATION OR SITUATION WHERE FAILURE OR
FAULT OF THE SOFTWARE MATERIALS COULD REASONABLY BE ANTICIPATED TO LEAD TO
SERIOUS INJURY OF ANY PERSON, INCLUDING POTENTIAL DISCRIMINATION OR VIOLATION
OF AN INDIVIDUAL’S PRIVACY RIGHTS, OR TO SEVERE PHYSICAL, PROPERTY, OR
ENVIRONMENTAL DAMAGE (EACH, A “HIGH-RISK USE”). IF YOU ELECT TO USE ANY OF THE
SOFTWARE MATERIALS FOR A HIGH-RISK USE, YOU DO SO AT YOUR OWN RISK. YOU AGREE
TO DESIGN AND IMPLEMENT APPROPRIATE DECISION-MAKING AND RISK-MITIGATION
PROCEDURES AND POLICIES IN CONNECTION WITH A HIGH-RISK USE SUCH THAT EVEN IF
THERE IS A FAILURE OR FAULT IN ANY OF THE SOFTWARE MATERIALS, THE SAFETY OF
PERSONS OR PROPERTY AFFECTED BY THE ACTIVITY STAYS AT A LEVEL THAT IS
REASONABLE, APPROPRIATE, AND LAWFUL FOR THE FIELD OF THE HIGH-RISK USE.
6. INDEMNIFICATION
You will indemnify, defend and hold harmless Stability AI and our subsidiaries
and affiliates, and each of our respective shareholders, directors, officers,
employees, agents, successors, and assigns (collectively, the “Stability AI
Parties”) from and against any losses, liabilities, damages, fines, penalties,
and expenses (including reasonable attorneys’ fees) incurred by any Stability
AI Party in connection with any claim, demand, allegation, lawsuit,
proceeding, or investigation (collectively, “Claims”) arising out of or
related to: (a) your access to or use of the Software Products (as well as any
results or data generated from such access or use), including any High-Risk
Use (defined below); (b) your violation of this License; or (c) your
violation, misappropriation or infringement of any rights of another
(including intellectual property or other proprietary rights and privacy
rights). You will promptly notify the Stability AI Parties of any such Claims,
and cooperate with Stability AI Parties in defending such Claims. You will
also grant the Stability AI Parties sole control of the defense or settlement,
at Stability AI’s sole option, of any Claims. This indemnity is in addition
to, and not in lieu of, any other indemnities or remedies set forth in a
written agreement between you and Stability AI or the other Stability AI
Parties.
7. TERMINATION; SURVIVAL
a. This License will automatically terminate upon any breach by you of the
terms of this License.
b. We may terminate this License, in whole or in part, at any time upon notice
(including electronic) to you.
c. The following sections survive termination of this License: 2
(Restrictions), 3 (Attribution), 4 (Disclaimers), 5 (Limitation on Liability),
6 (Indemnification) 7 (Termination; Survival), 8 (Third Party Materials), 9
(Trademarks), 10 (Applicable Law; Dispute Resolution), and 11 (Miscellaneous).
8. THIRD PARTY MATERIALS
The Software Products may contain third-party software or other components
(including free and open source software) (all of the foregoing, “Third Party
Materials”), which are subject to the license terms of the respective
third-party licensors. Your dealings or correspondence with third parties and
your use of or interaction with any Third Party Materials are solely between
you and the third party. Stability AI does not control or endorse, and makes
no representations or warranties regarding, any Third Party Materials, and
your access to and use of such Third Party Materials are at your own risk.
9. TRADEMARKS
Licensee has not been granted any trademark license as part of this License
and may not use any name or mark associated with Stability AI without the
prior written permission of Stability AI, except to the extent necessary to
make the reference required by the “ATTRIBUTION” section of this Agreement.
10. APPLICABLE LAW; DISPUTE RESOLUTION
This License will be governed and construed under the laws of the State of
California without regard to conflicts of law provisions. Any suit or
proceeding arising out of or relating to this License will be brought in the
federal or state courts, as applicable, in San Mateo County, California, and
each party irrevocably submits to the jurisdiction and venue of such courts.
11. MISCELLANEOUS
If any provision or part of a provision of this License is unlawful, void or
unenforceable, that provision or part of the provision is deemed severed from
this License, and will not affect the validity and enforceability of any
remaining provisions. The failure of Stability AI to exercise or enforce any
right or provision of this License will not operate as a waiver of such right
or provision. This License does not confer any third-party beneficiary rights
upon any other person or entity. This License, together with the
Documentation, contains the entire understanding between you and Stability AI
regarding the subject matter of this License, and supersedes all other written
or oral agreements and understandings between you and Stability AI regarding
such subject matter. No change or addition to any provision of this License
will be binding unless it is in writing and signed by an authorized
representative of both you and Stability AI.
extra_gated_heading: Researcher Early Access
extra_gated_description: SDXL 0.9 Research License Agreement
extra_gated_button_content: Submit application
extra_gated_fields:
Organization: text
Nature of research: text
Personal researcher link (CV, website, github): text
Other Comments: text
I accept the above license agreement, and will use the Software non-commercially and for research purposes only: checkbox
tags:
- text-to-image
- stable-diffusion
---
# SD-XL 0.9-base Model Card
## Model
SDXL consists of a two-step pipeline for latent diffusion:
First, we use a base model to generate latents of the desired output size.
In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img")
to the latents generated in the first step, using the same prompt.
### Model Description
- **Developed by:** Stability AI
- **Model type:** Diffusion-based text-to-image generative model
- **License:** [SDXL 0.9 Research License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9/blob/main/LICENSE.md)
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses two fixed, pretrained text encoders ([OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip) and [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main)).
- **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/generative-models) [SDXL paper on arXiv](https://arxiv.org/abs/2307.01952).
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/Stability-AI/generative-models
- **Demo [optional]:** https://clipdrop.co/stable-diffusion
### 🧨 Diffusers
Make sure to upgrade diffusers to >= 0.18.0:
```
pip install diffusers --upgrade
```
In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```
You can use the model then as follows
```py
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")
# if using torch < 2.0
# pipe.enable_xformers_memory_efficient_attention()
prompt = "An astronaut riding a green horse"
images = pipe(prompt=prompt).images[0]
```
When using `torch >= 2.0`, you can improve the inference speed by 20-30% with torch.compile. Simple wrap the unet with torch compile before running the pipeline:
```py
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
```
If you are limited by GPU VRAM, you can enable *cpu offloading* by calling `pipe.enable_model_cpu_offload`
instead of `.to("cuda")`:
```diff
- pipe.to("cuda")
+ pipe.enable_model_cpu_offload()
```
## Uses
### Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
Excluded uses are described below.
### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The autoencoding part of the model is lossy.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
## Evaluation
The chart above evaluates user preference for SDXL (with and without refinement) over Stable Diffusion 1.5 and 2.1.
The SDXL base model performs significantly better than the previous variants, and the model combined with the refinement module achieves the best overall performance. | 17,152 | [
[
-0.02960205078125,
-0.060760498046875,
0.0443115234375,
0.00742340087890625,
-0.0174407958984375,
-0.011749267578125,
0.0011339187622070312,
-0.01727294921875,
-0.005435943603515625,
0.04083251953125,
-0.03759765625,
-0.043426513671875,
-0.053070068359375,
-0.01361846923828125,
-0.033233642578125,
0.07275390625,
-0.013427734375,
-0.0019893646240234375,
-0.01142120361328125,
-0.005558013916015625,
-0.00862884521484375,
-0.005298614501953125,
-0.07623291015625,
-0.01432037353515625,
0.0233154296875,
-0.00891876220703125,
0.05450439453125,
0.039337158203125,
0.018280029296875,
0.0239410400390625,
-0.0278167724609375,
-0.004608154296875,
-0.034912109375,
0.0035877227783203125,
0.00385284423828125,
-0.035247802734375,
-0.0262298583984375,
0.006557464599609375,
0.050628662109375,
0.03375244140625,
-0.00536346435546875,
0.001651763916015625,
-0.00047469139099121094,
0.04071044921875,
-0.04583740234375,
0.0023441314697265625,
-0.0209197998046875,
0.01137542724609375,
-0.006763458251953125,
0.0205230712890625,
-0.026824951171875,
-0.0220794677734375,
0.001007080078125,
-0.05938720703125,
0.038116455078125,
-0.012786865234375,
0.07177734375,
0.03680419921875,
-0.0187530517578125,
-0.01161956787109375,
-0.0535888671875,
0.051483154296875,
-0.058349609375,
0.0241546630859375,
0.01480865478515625,
0.000774383544921875,
0.017974853515625,
-0.08209228515625,
-0.047210693359375,
-0.0097198486328125,
0.01421356201171875,
0.0308990478515625,
-0.018402099609375,
0.006465911865234375,
0.03961181640625,
0.0259552001953125,
-0.044281005859375,
-0.0001691579818725586,
-0.047576904296875,
-0.0012664794921875,
0.052734375,
0.0204925537109375,
0.028167724609375,
0.001651763916015625,
-0.029205322265625,
-0.01287078857421875,
-0.048309326171875,
-0.00649261474609375,
0.0266265869140625,
-0.012786865234375,
-0.033935546875,
0.051361083984375,
0.0178985595703125,
0.0377197265625,
0.019561767578125,
-0.0023822784423828125,
0.0208740234375,
-0.0248565673828125,
-0.021820068359375,
-0.0233001708984375,
0.068359375,
0.037445068359375,
-0.01294708251953125,
0.00785064697265625,
-0.01641845703125,
0.0165557861328125,
0.00829315185546875,
-0.080078125,
-0.027923583984375,
0.033935546875,
-0.04876708984375,
-0.0277862548828125,
-0.01259613037109375,
-0.06561279296875,
-0.0168609619140625,
-0.006259918212890625,
0.0367431640625,
-0.0247955322265625,
-0.03955078125,
-0.001796722412109375,
-0.02557373046875,
0.0030364990234375,
0.034820556640625,
-0.05401611328125,
0.007686614990234375,
0.01035308837890625,
0.08648681640625,
-0.0283203125,
-0.004730224609375,
-0.015594482421875,
-0.00106048583984375,
-0.03424072265625,
0.044158935546875,
-0.0259552001953125,
-0.046112060546875,
-0.01450347900390625,
0.014373779296875,
0.0019054412841796875,
-0.0391845703125,
0.048980712890625,
-0.040130615234375,
0.0190887451171875,
-0.00475311279296875,
-0.04852294921875,
-0.007007598876953125,
-0.01983642578125,
-0.054107666015625,
0.0838623046875,
0.0247955322265625,
-0.069580078125,
0.00957489013671875,
-0.06646728515625,
-0.01103973388671875,
0.0033111572265625,
-0.00879669189453125,
-0.050201416015625,
-0.0005636215209960938,
-0.00010514259338378906,
0.033599853515625,
-0.00940704345703125,
0.0135955810546875,
-0.01548004150390625,
-0.015838623046875,
-0.0025196075439453125,
-0.03289794921875,
0.099853515625,
0.037567138671875,
-0.0280303955078125,
0.029205322265625,
-0.06256103515625,
-0.00696563720703125,
0.018280029296875,
-0.0215301513671875,
-0.006748199462890625,
-0.0126953125,
0.02777099609375,
0.0127716064453125,
0.005001068115234375,
-0.04443359375,
0.003757476806640625,
-0.0175628662109375,
0.04620361328125,
0.060821533203125,
-0.0011816024780273438,
0.043426513671875,
-0.0107879638671875,
0.039520263671875,
0.0266265869140625,
0.005168914794921875,
-0.0163116455078125,
-0.06219482421875,
-0.061920166015625,
-0.0168914794921875,
0.01214599609375,
0.03594970703125,
-0.07086181640625,
0.029998779296875,
0.008056640625,
-0.047393798828125,
-0.039215087890625,
0.0031223297119140625,
0.01282501220703125,
0.043121337890625,
0.01885986328125,
-0.0297088623046875,
-0.02716064453125,
-0.041839599609375,
0.044769287109375,
-0.00634765625,
-0.00031948089599609375,
0.014617919921875,
0.050445556640625,
-0.029022216796875,
0.05584716796875,
-0.06787109375,
-0.005710601806640625,
-0.0068817138671875,
0.0228424072265625,
0.0103302001953125,
0.041229248046875,
0.05279541015625,
-0.065185546875,
-0.051666259765625,
-0.00836944580078125,
-0.061248779296875,
-0.0024871826171875,
-0.005462646484375,
-0.00858306884765625,
0.0280303955078125,
0.028717041015625,
-0.07110595703125,
0.047027587890625,
0.043304443359375,
-0.0386962890625,
0.062225341796875,
-0.034332275390625,
-0.004093170166015625,
-0.0780029296875,
0.01328277587890625,
0.0184326171875,
-0.01529693603515625,
-0.0439453125,
0.0162811279296875,
0.01006317138671875,
-0.0233154296875,
-0.044158935546875,
0.0565185546875,
-0.02130126953125,
0.0243682861328125,
-0.031524658203125,
-0.013427734375,
0.010009765625,
0.027740478515625,
0.0262451171875,
0.06671142578125,
0.07061767578125,
-0.052276611328125,
0.030914306640625,
0.01409149169921875,
-0.028594970703125,
0.0301971435546875,
-0.06903076171875,
0.0028820037841796875,
-0.031768798828125,
0.01220703125,
-0.07769775390625,
0.001605987548828125,
0.0289459228515625,
-0.0259552001953125,
0.02960205078125,
-0.00572967529296875,
-0.0262298583984375,
-0.032958984375,
-0.01319122314453125,
0.0271453857421875,
0.0682373046875,
-0.033935546875,
0.039520263671875,
0.0189056396484375,
0.0022220611572265625,
-0.034912109375,
-0.044647216796875,
-0.01105499267578125,
-0.015777587890625,
-0.057373046875,
0.04046630859375,
-0.04364013671875,
-0.02288818359375,
0.01137542724609375,
0.021575927734375,
-0.00690460205078125,
-0.0112762451171875,
0.02935791015625,
0.0296478271484375,
-0.020782470703125,
-0.0162811279296875,
0.01369476318359375,
-0.016937255859375,
0.003650665283203125,
-0.00858306884765625,
0.0290069580078125,
0.0183563232421875,
-0.0137176513671875,
-0.0439453125,
0.037322998046875,
0.045318603515625,
0.0030117034912109375,
0.061309814453125,
0.0704345703125,
-0.025177001953125,
-0.0083160400390625,
-0.0290985107421875,
-0.00821685791015625,
-0.035797119140625,
0.036285400390625,
-0.01088714599609375,
-0.03778076171875,
0.041595458984375,
0.00466156005859375,
0.0146331787109375,
0.048858642578125,
0.06256103515625,
-0.0126495361328125,
0.0908203125,
0.045989990234375,
0.0247802734375,
0.03680419921875,
-0.07025146484375,
-0.00830841064453125,
-0.07421875,
-0.0034770965576171875,
-0.0221710205078125,
0.0033016204833984375,
-0.01259613037109375,
-0.050445556640625,
0.024261474609375,
0.0101165771484375,
-0.0247039794921875,
0.0162506103515625,
-0.040008544921875,
0.021820068359375,
0.0299835205078125,
0.0107269287109375,
0.004730224609375,
0.00004696846008300781,
-0.01264190673828125,
-0.0089874267578125,
-0.037109375,
-0.040252685546875,
0.08001708984375,
0.0311737060546875,
0.07440185546875,
0.0022144317626953125,
0.033721923828125,
0.0270233154296875,
0.026336669921875,
-0.034454345703125,
0.033660888671875,
-0.0218963623046875,
-0.04681396484375,
-0.01309967041015625,
-0.01885986328125,
-0.06292724609375,
0.01427459716796875,
-0.0106353759765625,
-0.036163330078125,
0.028289794921875,
0.006134033203125,
-0.035308837890625,
0.037109375,
-0.06414794921875,
0.06048583984375,
-0.010650634765625,
-0.05535888671875,
0.00435638427734375,
-0.03900146484375,
0.0260772705078125,
0.005157470703125,
-0.001983642578125,
0.0040740966796875,
-0.01122283935546875,
0.050384521484375,
-0.03021240234375,
0.07421875,
-0.0220794677734375,
-0.01348114013671875,
0.0316162109375,
-0.0224761962890625,
0.028167724609375,
-0.00007921457290649414,
-0.021087646484375,
0.0216522216796875,
0.01116943359375,
-0.0216827392578125,
-0.035125732421875,
0.0552978515625,
-0.080078125,
-0.0396728515625,
-0.0239410400390625,
-0.0350341796875,
0.04290771484375,
0.0163421630859375,
0.060333251953125,
0.0184326171875,
-0.00672149658203125,
-0.0036334991455078125,
0.07342529296875,
-0.0262298583984375,
0.039276123046875,
0.01021575927734375,
-0.025634765625,
-0.033172607421875,
0.062286376953125,
0.020111083984375,
0.03631591796875,
0.00946807861328125,
0.00505828857421875,
-0.032562255859375,
-0.04107666015625,
-0.0555419921875,
0.01111602783203125,
-0.07012939453125,
-0.010223388671875,
-0.05975341796875,
-0.041229248046875,
-0.032318115234375,
-0.01142120361328125,
-0.030426025390625,
-0.024932861328125,
-0.07012939453125,
0.0033664703369140625,
0.014312744140625,
0.055206298828125,
-0.008697509765625,
0.0262603759765625,
-0.0263671875,
0.02825927734375,
0.0185394287109375,
0.02032470703125,
0.0167999267578125,
-0.0330810546875,
-0.0079498291015625,
-0.0012941360473632812,
-0.057769775390625,
-0.06744384765625,
0.0389404296875,
0.0028076171875,
0.0428466796875,
0.0504150390625,
0.003765106201171875,
0.037841796875,
-0.0296173095703125,
0.0753173828125,
0.030059814453125,
-0.05743408203125,
0.04754638671875,
-0.01593017578125,
0.0102996826171875,
-0.006259918212890625,
0.04150390625,
-0.0157012939453125,
-0.022216796875,
-0.053192138671875,
-0.06494140625,
0.04534912109375,
0.03216552734375,
0.01558685302734375,
-0.0025081634521484375,
0.04339599609375,
0.00780487060546875,
-0.0111083984375,
-0.07244873046875,
-0.04840087890625,
-0.0296630859375,
-0.0055999755859375,
-0.00214385986328125,
-0.0193939208984375,
-0.008148193359375,
-0.0333251953125,
0.06268310546875,
0.003955841064453125,
0.030731201171875,
0.0191802978515625,
0.005023956298828125,
-0.0240936279296875,
-0.01111602783203125,
0.042083740234375,
0.04443359375,
-0.0176849365234375,
0.0028972625732421875,
-0.00266265869140625,
-0.04473876953125,
0.024871826171875,
0.01055145263671875,
-0.0509033203125,
0.00005412101745605469,
0.002285003662109375,
0.07867431640625,
-0.021270751953125,
-0.04193115234375,
0.03277587890625,
-0.014678955078125,
-0.02008056640625,
-0.03167724609375,
0.0255584716796875,
0.0227508544921875,
0.0187225341796875,
0.0160369873046875,
0.03582763671875,
0.00711822509765625,
-0.020111083984375,
-0.005046844482421875,
0.0390625,
-0.0228424072265625,
-0.021728515625,
0.09808349609375,
0.013916015625,
-0.022491455078125,
0.0428466796875,
-0.0236663818359375,
-0.0112457275390625,
0.062286376953125,
0.0555419921875,
0.06231689453125,
-0.00807952880859375,
0.031463623046875,
0.05010986328125,
0.005489349365234375,
-0.0179290771484375,
0.0129852294921875,
0.0030307769775390625,
-0.056304931640625,
-0.0149078369140625,
-0.036834716796875,
-0.00611114501953125,
0.011627197265625,
-0.031646728515625,
0.0350341796875,
-0.0311126708984375,
-0.0265655517578125,
0.01116943359375,
-0.0036296844482421875,
-0.04547119140625,
0.01251983642578125,
0.0128936767578125,
0.067138671875,
-0.07470703125,
0.0692138671875,
0.050872802734375,
-0.0576171875,
-0.0290374755859375,
-0.01210784912109375,
-0.0163421630859375,
-0.039794921875,
0.05364990234375,
0.0003948211669921875,
0.007663726806640625,
0.0178070068359375,
-0.064697265625,
-0.0645751953125,
0.10076904296875,
0.0290679931640625,
-0.0269012451171875,
-0.000453948974609375,
-0.01233673095703125,
0.038299560546875,
-0.035614013671875,
0.031463623046875,
0.01751708984375,
0.0192718505859375,
0.037200927734375,
-0.032745361328125,
0.007495880126953125,
-0.02667236328125,
0.0267486572265625,
-0.00597381591796875,
-0.050689697265625,
0.087646484375,
-0.04364013671875,
-0.0266571044921875,
0.03717041015625,
0.051055908203125,
0.0289459228515625,
0.025787353515625,
0.02569580078125,
0.07623291015625,
0.042877197265625,
-0.007595062255859375,
0.08062744140625,
-0.0114593505859375,
0.0439453125,
0.05181884765625,
-0.0170440673828125,
0.05194091796875,
0.01922607421875,
-0.03314208984375,
0.033294677734375,
0.0552978515625,
-0.0211334228515625,
0.046722412109375,
0.00347137451171875,
-0.032318115234375,
-0.00179290771484375,
0.00591278076171875,
-0.0399169921875,
-0.009521484375,
0.034271240234375,
-0.053802490234375,
-0.01248931884765625,
0.01508331298828125,
-0.0007367134094238281,
-0.015869140625,
-0.0157318115234375,
0.034454345703125,
-0.0037384033203125,
-0.0390625,
0.041839599609375,
0.0056610107421875,
0.06292724609375,
-0.047149658203125,
-0.014373779296875,
-0.006618499755859375,
0.0211334228515625,
-0.0205841064453125,
-0.073974609375,
0.0294342041015625,
-0.01103973388671875,
-0.02783203125,
-0.0091705322265625,
0.049072265625,
-0.024017333984375,
-0.06024169921875,
0.0240631103515625,
0.0174560546875,
0.020965576171875,
0.00702667236328125,
-0.07232666015625,
0.031768798828125,
0.0037250518798828125,
-0.0139923095703125,
0.0134124755859375,
0.0109405517578125,
0.01514434814453125,
0.04925537109375,
0.04083251953125,
0.0077667236328125,
0.01190948486328125,
-0.002178192138671875,
0.062103271484375,
-0.030487060546875,
-0.018280029296875,
-0.05462646484375,
0.05859375,
-0.006793975830078125,
-0.01934814453125,
0.04376220703125,
0.047210693359375,
0.04779052734375,
-0.0220489501953125,
0.06982421875,
-0.0231781005859375,
0.003997802734375,
-0.045074462890625,
0.07415771484375,
-0.047149658203125,
0.0159454345703125,
-0.0242462158203125,
-0.059295654296875,
-0.0123138427734375,
0.059051513671875,
-0.005710601806640625,
0.0181732177734375,
0.035430908203125,
0.0733642578125,
-0.0152587890625,
-0.0089874267578125,
0.032073974609375,
0.0282135009765625,
0.0294647216796875,
0.01947021484375,
0.0469970703125,
-0.044281005859375,
0.0269012451171875,
-0.042266845703125,
-0.0236663818359375,
0.016754150390625,
-0.06280517578125,
-0.06341552734375,
-0.06964111328125,
-0.06353759765625,
-0.04949951171875,
-0.0091400146484375,
0.044891357421875,
0.077880859375,
-0.04949951171875,
-0.01213836669921875,
-0.0177001953125,
0.011993408203125,
-0.0143890380859375,
-0.0233917236328125,
0.04034423828125,
-0.00678253173828125,
-0.0709228515625,
-0.0074462890625,
0.0241851806640625,
0.03375244140625,
-0.04864501953125,
-0.0190887451171875,
-0.0195770263671875,
-0.0083160400390625,
0.05035400390625,
0.017822265625,
-0.059051513671875,
0.00992584228515625,
-0.01390838623046875,
0.005603790283203125,
0.0155792236328125,
0.03485107421875,
-0.050201416015625,
0.039520263671875,
0.037811279296875,
0.0140838623046875,
0.055999755859375,
-0.0135955810546875,
0.0189971923828125,
-0.044769287109375,
0.0108642578125,
0.00421142578125,
0.033416748046875,
0.0242156982421875,
-0.04315185546875,
0.03961181640625,
0.03460693359375,
-0.050811767578125,
-0.04730224609375,
0.01177978515625,
-0.08148193359375,
-0.0271759033203125,
0.08966064453125,
-0.02435302734375,
-0.0185546875,
-0.0079498291015625,
-0.04364013671875,
0.019805908203125,
-0.02435302734375,
0.04669189453125,
0.040496826171875,
-0.0217437744140625,
-0.052093505859375,
-0.04425048828125,
0.027252197265625,
-0.005153656005859375,
-0.052276611328125,
-0.00485992431640625,
0.0309906005859375,
0.046142578125,
0.0335693359375,
0.06182861328125,
-0.01434326171875,
0.0117645263671875,
0.01265716552734375,
0.006359100341796875,
0.0108642578125,
0.0013132095336914062,
-0.018463134765625,
0.009246826171875,
-0.009429931640625,
-0.003849029541015625
]
] |
nlpaueb/legal-bert-small-uncased | 2022-04-28T14:43:32.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"bert",
"legal",
"fill-mask",
"en",
"license:cc-by-sa-4.0",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | nlpaueb | null | null | nlpaueb/legal-bert-small-uncased | 19 | 45,383 | transformers | 2022-03-02T23:29:05 | ---
language: en
pipeline_tag: fill-mask
license: cc-by-sa-4.0
thumbnail: https://i.ibb.co/p3kQ7Rw/Screenshot-2020-10-06-at-12-16-36-PM.png
tags:
- legal
widget:
- text: "The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of police."
---
# LEGAL-BERT: The Muppets straight out of Law School
<img align="left" src="https://i.ibb.co/p3kQ7Rw/Screenshot-2020-10-06-at-12-16-36-PM.png" width="100"/>
LEGAL-BERT is a family of BERT models for the legal domain, intended to assist legal NLP research, computational law, and legal technology applications. To pre-train the different variations of LEGAL-BERT, we collected 12 GB of diverse English legal text from several fields (e.g., legislation, court cases, contracts) scraped from publicly available resources. Sub-domain variants (CONTRACTS-, EURLEX-, ECHR-) and/or general LEGAL-BERT perform better than using BERT out of the box for domain-specific tasks.<br>
This is the light-weight version of BERT-BASE (33% the size of BERT-BASE) pre-trained from scratch on legal data, which achieves comparable performance to larger models, while being much more efficient (approximately 4 times faster) with a smaller environmental footprint.
<br/><br/>
---
I. Chalkidis, M. Fergadiotis, P. Malakasiotis, N. Aletras and I. Androutsopoulos. "LEGAL-BERT: The Muppets straight out of Law School". In Findings of Empirical Methods in Natural Language Processing (EMNLP 2020) (Short Papers), to be held online, 2020. (https://aclanthology.org/2020.findings-emnlp.261)
---
## Pre-training corpora
The pre-training corpora of LEGAL-BERT include:
* 116,062 documents of EU legislation, publicly available from EURLEX (http://eur-lex.europa.eu), the repository of EU Law running under the EU Publication Office.
* 61,826 documents of UK legislation, publicly available from the UK legislation portal (http://www.legislation.gov.uk).
* 19,867 cases from the European Court of Justice (ECJ), also available from EURLEX.
* 12,554 cases from HUDOC, the repository of the European Court of Human Rights (ECHR) (http://hudoc.echr.coe.int/eng).
* 164,141 cases from various courts across the USA, hosted in the Case Law Access Project portal (https://case.law).
* 76,366 US contracts from EDGAR, the database of US Securities and Exchange Commission (SECOM) (https://www.sec.gov/edgar.shtml).
## Pre-training details
* We trained BERT using the official code provided in Google BERT's GitHub repository (https://github.com/google-research/bert).
* We released a model similar to the English BERT-BASE model (12-layer, 768-hidden, 12-heads, 110M parameters).
* We chose to follow the same training set-up: 1 million training steps with batches of 256 sequences of length 512 with an initial learning rate 1e-4.
* We were able to use a single Google Cloud TPU v3-8 provided for free from [TensorFlow Research Cloud (TFRC)](https://www.tensorflow.org/tfrc), while also utilizing [GCP research credits](https://edu.google.com/programs/credits/research). Huge thanks to both Google programs for supporting us!
## Models list
| Model name | Model Path | Training corpora |
| ------------------- | ------------------------------------ | ------------------- |
| CONTRACTS-BERT-BASE | `nlpaueb/bert-base-uncased-contracts` | US contracts |
| EURLEX-BERT-BASE | `nlpaueb/bert-base-uncased-eurlex` | EU legislation |
| ECHR-BERT-BASE | `nlpaueb/bert-base-uncased-echr` | ECHR cases |
| LEGAL-BERT-BASE * | `nlpaueb/legal-bert-base-uncased` | All |
| LEGAL-BERT-SMALL | `nlpaueb/legal-bert-small-uncased` | All |
\* LEGAL-BERT-BASE is the model referred to as LEGAL-BERT-SC in Chalkidis et al. (2020); a model trained from scratch in the legal corpora mentioned below using a newly created vocabulary by a sentence-piece tokenizer trained on the very same corpora.
\*\* As many of you expressed interest in the LEGAL-BERT-FP models (those relying on the original BERT-BASE checkpoint), they have been released in Archive.org (https://archive.org/details/legal_bert_fp), as these models are secondary and possibly only interesting for those who aim to dig deeper in the open questions of Chalkidis et al. (2020).
## Load Pretrained Model
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("nlpaueb/legal-bert-small-uncased")
model = AutoModel.from_pretrained("nlpaueb/legal-bert-small-uncased")
```
## Use LEGAL-BERT variants as Language Models
| Corpus | Model | Masked token | Predictions |
| --------------------------------- | ---------------------------------- | ------------ | ------------ |
| | **BERT-BASE-UNCASED** |
| (Contracts) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('new', '0.09'), ('current', '0.04'), ('proposed', '0.03'), ('marketing', '0.03'), ('joint', '0.02')
| (ECHR) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.32'), ('rape', '0.22'), ('abuse', '0.14'), ('death', '0.04'), ('violence', '0.03')
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('farm', '0.25'), ('livestock', '0.08'), ('draft', '0.06'), ('domestic', '0.05'), ('wild', '0.05')
| | **CONTRACTS-BERT-BASE** |
| (Contracts) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('letter', '0.38'), ('dealer', '0.04'), ('employment', '0.03'), ('award', '0.03'), ('contribution', '0.02')
| (ECHR) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('death', '0.39'), ('imprisonment', '0.07'), ('contempt', '0.05'), ('being', '0.03'), ('crime', '0.02')
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | (('domestic', '0.18'), ('laboratory', '0.07'), ('household', '0.06'), ('personal', '0.06'), ('the', '0.04')
| | **EURLEX-BERT-BASE** |
| (Contracts) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('supply', '0.11'), ('cooperation', '0.08'), ('service', '0.07'), ('licence', '0.07'), ('distribution', '0.05')
| (ECHR) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.66'), ('death', '0.07'), ('imprisonment', '0.07'), ('murder', '0.04'), ('rape', '0.02')
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('live', '0.43'), ('pet', '0.28'), ('certain', '0.05'), ('fur', '0.03'), ('the', '0.02')
| | **ECHR-BERT-BASE** |
| (Contracts) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('second', '0.24'), ('latter', '0.10'), ('draft', '0.05'), ('bilateral', '0.05'), ('arbitration', '0.04')
| (ECHR) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.99'), ('death', '0.01'), ('inhuman', '0.00'), ('beating', '0.00'), ('rape', '0.00')
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('pet', '0.17'), ('all', '0.12'), ('slaughtered', '0.10'), ('domestic', '0.07'), ('individual', '0.05')
| | **LEGAL-BERT-BASE** |
| (Contracts) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('settlement', '0.26'), ('letter', '0.23'), ('dealer', '0.04'), ('master', '0.02'), ('supplemental', '0.02')
| (ECHR) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '1.00'), ('detention', '0.00'), ('arrest', '0.00'), ('rape', '0.00'), ('death', '0.00')
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('live', '0.67'), ('beef', '0.17'), ('farm', '0.03'), ('pet', '0.02'), ('dairy', '0.01')
| | **LEGAL-BERT-SMALL** |
| (Contracts) | This [MASK] Agreement is between General Motors and John Murray . | employment | ('license', '0.09'), ('transition', '0.08'), ('settlement', '0.04'), ('consent', '0.03'), ('letter', '0.03')
| (ECHR) | The applicant submitted that her husband was subjected to treatment amounting to [MASK] whilst in the custody of Adana Security Directorate | torture | ('torture', '0.59'), ('pain', '0.05'), ('ptsd', '0.05'), ('death', '0.02'), ('tuberculosis', '0.02')
| (EURLEX) | Establishing a system for the identification and registration of [MASK] animals and regarding the labelling of beef and beef products . | bovine | ('all', '0.08'), ('live', '0.07'), ('certain', '0.07'), ('the', '0.07'), ('farm', '0.05')
## Evaluation on downstream tasks
Consider the experiments in the article "LEGAL-BERT: The Muppets straight out of Law School". Chalkidis et al., 2020, (https://aclanthology.org/2020.findings-emnlp.261)
## Author - Publication
```
@inproceedings{chalkidis-etal-2020-legal,
title = "{LEGAL}-{BERT}: The Muppets straight out of Law School",
author = "Chalkidis, Ilias and
Fergadiotis, Manos and
Malakasiotis, Prodromos and
Aletras, Nikolaos and
Androutsopoulos, Ion",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
doi = "10.18653/v1/2020.findings-emnlp.261",
pages = "2898--2904"
}
```
## About Us
[AUEB's Natural Language Processing Group](http://nlp.cs.aueb.gr) develops algorithms, models, and systems that allow computers to process and generate natural language texts.
The group's current research interests include:
* question answering systems for databases, ontologies, document collections, and the Web, especially biomedical question answering,
* natural language generation from databases and ontologies, especially Semantic Web ontologies,
text classification, including filtering spam and abusive content,
* information extraction and opinion mining, including legal text analytics and sentiment analysis,
* natural language processing tools for Greek, for example parsers and named-entity recognizers,
machine learning in natural language processing, especially deep learning.
The group is part of the Information Processing Laboratory of the Department of Informatics of the Athens University of Economics and Business.
[Ilias Chalkidis](https://iliaschalkidis.github.io) on behalf of [AUEB's Natural Language Processing Group](http://nlp.cs.aueb.gr)
| Github: [@ilias.chalkidis](https://github.com/iliaschalkidis) | Twitter: [@KiddoThe2B](https://twitter.com/KiddoThe2B) |
| 11,464 | [
[
-0.0207061767578125,
-0.043701171875,
0.032867431640625,
0.005977630615234375,
-0.0298004150390625,
-0.01349639892578125,
-0.0087890625,
-0.04461669921875,
0.033782958984375,
0.048858642578125,
-0.0188751220703125,
-0.03997802734375,
-0.0390625,
-0.007183074951171875,
-0.023712158203125,
0.091064453125,
0.01335906982421875,
0.0091705322265625,
0.0162506103515625,
-0.02142333984375,
-0.0232696533203125,
-0.059814453125,
-0.0262298583984375,
0.001010894775390625,
0.040740966796875,
0.00865936279296875,
0.040283203125,
0.038543701171875,
0.029815673828125,
0.0186004638671875,
-0.0149993896484375,
-0.01442718505859375,
-0.0245361328125,
-0.01202392578125,
-0.01251983642578125,
-0.021026611328125,
-0.052825927734375,
0.015899658203125,
0.0201416015625,
0.043853759765625,
-0.036895751953125,
0.016937255859375,
-0.017791748046875,
0.055267333984375,
-0.04217529296875,
-0.0053558349609375,
-0.048370361328125,
0.007312774658203125,
-0.01238250732421875,
0.00832366943359375,
-0.0202789306640625,
-0.0228118896484375,
0.005725860595703125,
-0.05126953125,
0.01291656494140625,
0.0218353271484375,
0.09228515625,
0.0064849853515625,
-0.0277099609375,
-0.0421142578125,
-0.0269927978515625,
0.044769287109375,
-0.06640625,
0.026214599609375,
0.0306396484375,
0.0038967132568359375,
-0.0205078125,
-0.0703125,
-0.05096435546875,
-0.033477783203125,
-0.01317596435546875,
0.0243682861328125,
-0.0291900634765625,
0.0019092559814453125,
0.034454345703125,
0.03204345703125,
-0.0535888671875,
0.00251007080078125,
-0.04779052734375,
-0.038543701171875,
0.060516357421875,
0.0005316734313964844,
0.0159454345703125,
-0.0185394287109375,
-0.0312347412109375,
-0.0001367330551147461,
-0.053802490234375,
0.0273895263671875,
0.05389404296875,
0.0172882080078125,
-0.02020263671875,
0.053192138671875,
-0.00261688232421875,
0.03485107421875,
-0.0029163360595703125,
-0.0004584789276123047,
0.029754638671875,
-0.039642333984375,
-0.0254364013671875,
-0.00023055076599121094,
0.07177734375,
0.0244598388671875,
-0.0010957717895507812,
-0.0028400421142578125,
-0.0183563232421875,
-0.005840301513671875,
0.0177459716796875,
-0.045379638671875,
-0.007572174072265625,
0.032379150390625,
-0.05096435546875,
-0.0252838134765625,
0.01153564453125,
-0.049072265625,
-0.011138916015625,
-0.00957489013671875,
0.031585693359375,
-0.041534423828125,
-0.005825042724609375,
0.009796142578125,
-0.0237884521484375,
0.04803466796875,
0.005035400390625,
-0.0601806640625,
0.00962066650390625,
0.036773681640625,
0.035308837890625,
0.022735595703125,
-0.0033779144287109375,
-0.045745849609375,
0.01258087158203125,
-0.022216796875,
0.037689208984375,
-0.036529541015625,
-0.01947021484375,
0.007808685302734375,
0.0145263671875,
-0.0007371902465820312,
-0.0261688232421875,
0.046600341796875,
-0.045623779296875,
0.02008056640625,
-0.02154541015625,
-0.037078857421875,
-0.0163421630859375,
0.0179443359375,
-0.042633056640625,
0.057769775390625,
-0.004150390625,
-0.053863525390625,
0.049896240234375,
-0.0738525390625,
-0.032073974609375,
-0.00030159950256347656,
-0.0094451904296875,
-0.034759521484375,
-0.027923583984375,
0.0013322830200195312,
0.0310211181640625,
-0.01216888427734375,
0.034149169921875,
-0.027435302734375,
-0.0084991455078125,
0.0129852294921875,
-0.005916595458984375,
0.1080322265625,
0.039337158203125,
-0.027008056640625,
0.01149749755859375,
-0.06524658203125,
-0.01187896728515625,
0.0156402587890625,
-0.044677734375,
-0.00789642333984375,
-0.017120361328125,
-0.00650787353515625,
0.017852783203125,
0.0223388671875,
-0.05224609375,
0.00917816162109375,
-0.03973388671875,
0.05224609375,
0.040130615234375,
0.0029926300048828125,
0.016510009765625,
-0.0282745361328125,
0.047210693359375,
0.003185272216796875,
0.00844573974609375,
-0.0017271041870117188,
-0.049530029296875,
-0.05487060546875,
-0.0135650634765625,
0.060394287109375,
0.060699462890625,
-0.0213165283203125,
0.04827880859375,
-0.01177978515625,
-0.041412353515625,
-0.043304443359375,
-0.0147552490234375,
0.0238494873046875,
0.0285797119140625,
0.0201416015625,
-0.0279693603515625,
-0.06396484375,
-0.08648681640625,
-0.0246429443359375,
-0.0163726806640625,
0.003631591796875,
0.00968170166015625,
0.07330322265625,
-0.007808685302734375,
0.0633544921875,
-0.01493072509765625,
-0.0238800048828125,
-0.0169219970703125,
0.02593994140625,
0.0369873046875,
0.04779052734375,
0.06317138671875,
-0.04437255859375,
-0.0384521484375,
0.00926971435546875,
-0.0589599609375,
0.0237884521484375,
-0.0023956298828125,
-0.018157958984375,
0.0200653076171875,
0.0218963623046875,
-0.04229736328125,
0.037567138671875,
0.01016998291015625,
-0.033447265625,
0.056549072265625,
-0.038330078125,
-0.001285552978515625,
-0.07281494140625,
0.0172576904296875,
-0.012054443359375,
-0.019561767578125,
-0.047515869140625,
0.010009765625,
0.002956390380859375,
-0.012481689453125,
-0.0496826171875,
0.0237579345703125,
-0.035247802734375,
-0.009735107421875,
0.0198516845703125,
-0.0037021636962890625,
-0.0084228515625,
0.042633056640625,
-0.01812744140625,
0.058746337890625,
0.050872802734375,
-0.053009033203125,
0.034576416015625,
0.031646728515625,
-0.0144500732421875,
0.027435302734375,
-0.03778076171875,
0.0017099380493164062,
-0.01180267333984375,
0.0078277587890625,
-0.042266845703125,
-0.01335906982421875,
0.036895751953125,
-0.034637451171875,
0.0159912109375,
-0.0159454345703125,
-0.035552978515625,
-0.037261962890625,
-0.0306854248046875,
-0.0148773193359375,
0.048431396484375,
-0.01399993896484375,
0.0482177734375,
0.045623779296875,
-0.01210784912109375,
-0.06805419921875,
-0.06573486328125,
0.01311492919921875,
-0.0183563232421875,
-0.04302978515625,
0.0281219482421875,
0.0028209686279296875,
-0.01092529296875,
0.0238800048828125,
0.01114654541015625,
-0.02459716796875,
0.0036487579345703125,
0.009765625,
0.003650665283203125,
-0.0172119140625,
-0.01488494873046875,
-0.0017242431640625,
0.01007843017578125,
0.0221405029296875,
-0.0030574798583984375,
0.037353515625,
-0.005645751953125,
-0.014984130859375,
-0.0233306884765625,
0.044189453125,
0.02850341796875,
-0.019073486328125,
0.04913330078125,
0.037933349609375,
-0.029510498046875,
0.01198577880859375,
-0.034149169921875,
0.00414276123046875,
-0.0300445556640625,
0.005741119384765625,
-0.0228729248046875,
-0.041717529296875,
0.056793212890625,
0.01354217529296875,
0.014404296875,
0.07159423828125,
0.049346923828125,
-0.016082763671875,
0.039520263671875,
0.0491943359375,
-0.0033931732177734375,
0.0305938720703125,
-0.031890869140625,
0.0167388916015625,
-0.047027587890625,
-0.026641845703125,
-0.037506103515625,
-0.01043701171875,
-0.06396484375,
-0.007171630859375,
0.011383056640625,
-0.006290435791015625,
-0.0177459716796875,
0.053680419921875,
-0.0264434814453125,
0.0198211669921875,
0.061767578125,
0.002651214599609375,
0.005847930908203125,
-0.0014019012451171875,
-0.05755615234375,
0.002727508544921875,
-0.06475830078125,
-0.057647705078125,
0.0970458984375,
0.03607177734375,
0.03466796875,
0.01288604736328125,
0.05499267578125,
0.04119873046875,
0.0109405517578125,
-0.042999267578125,
0.047119140625,
-0.01493072509765625,
-0.0751953125,
-0.025421142578125,
-0.02850341796875,
-0.09063720703125,
0.011260986328125,
-0.021148681640625,
-0.061767578125,
0.03692626953125,
-0.0139617919921875,
-0.049896240234375,
0.022003173828125,
-0.054656982421875,
0.05950927734375,
-0.024566650390625,
-0.0225677490234375,
-0.022918701171875,
-0.0657958984375,
0.03265380859375,
-0.0025653839111328125,
0.02606201171875,
-0.01203155517578125,
0.01522064208984375,
0.0841064453125,
-0.072021484375,
0.056243896484375,
-0.0238494873046875,
-0.00337982177734375,
0.0271453857421875,
-0.0229644775390625,
0.0374755859375,
0.0157318115234375,
-0.017547607421875,
0.00485992431640625,
0.017974853515625,
-0.018890380859375,
-0.007549285888671875,
0.025543212890625,
-0.05029296875,
-0.0390625,
-0.062255859375,
-0.041595458984375,
0.01099395751953125,
0.027191162109375,
0.0276336669921875,
0.0265960693359375,
-0.004940032958984375,
0.0233306884765625,
0.027923583984375,
-0.030731201171875,
0.033294677734375,
0.049072265625,
-0.00473785400390625,
-0.037384033203125,
0.051727294921875,
0.02508544921875,
-0.01160430908203125,
0.01238250732421875,
-0.00029730796813964844,
-0.04754638671875,
-0.03790283203125,
-0.0233306884765625,
0.025970458984375,
-0.058807373046875,
-0.0180511474609375,
-0.05499267578125,
-0.022491455078125,
-0.05499267578125,
0.00891876220703125,
-0.012908935546875,
-0.0235595703125,
-0.0230865478515625,
0.0005202293395996094,
0.024078369140625,
0.054595947265625,
-0.020355224609375,
-0.00820159912109375,
-0.047393798828125,
0.03662109375,
0.0299072265625,
0.0253143310546875,
-0.03729248046875,
-0.064697265625,
-0.00206756591796875,
0.0208282470703125,
-0.0391845703125,
-0.0682373046875,
0.03424072265625,
0.01116180419921875,
0.0589599609375,
0.035614013671875,
0.01236724853515625,
0.07000732421875,
-0.045166015625,
0.0758056640625,
0.0216217041015625,
-0.07342529296875,
0.05047607421875,
-0.021026611328125,
-0.031890869140625,
0.0296173095703125,
0.041748046875,
-0.0222015380859375,
-0.04718017578125,
-0.070068359375,
-0.059814453125,
0.0643310546875,
0.0390625,
0.0122528076171875,
0.016845703125,
0.0305938720703125,
0.004913330078125,
0.027587890625,
-0.06884765625,
-0.0244598388671875,
-0.001392364501953125,
0.008758544921875,
0.035186767578125,
-0.024169921875,
-0.028564453125,
-0.034332275390625,
0.0679931640625,
0.029571533203125,
0.038482666015625,
0.0272216796875,
-0.01959228515625,
0.0079498291015625,
0.03570556640625,
0.07440185546875,
0.0743408203125,
-0.027099609375,
-0.0048980712890625,
0.017669677734375,
-0.0390625,
0.020233154296875,
0.0289764404296875,
-0.01021575927734375,
0.01538848876953125,
0.0160675048828125,
0.057342529296875,
-0.0003898143768310547,
-0.04815673828125,
0.040618896484375,
0.0034923553466796875,
-0.060760498046875,
-0.04754638671875,
-0.0099945068359375,
-0.007755279541015625,
0.0279693603515625,
0.024017333984375,
0.0011453628540039062,
0.0211639404296875,
-0.057464599609375,
0.022979736328125,
0.0278167724609375,
-0.01111602783203125,
-0.0008101463317871094,
0.061737060546875,
0.004955291748046875,
-0.0025177001953125,
0.0252227783203125,
-0.049774169921875,
-0.0389404296875,
0.05804443359375,
0.0282440185546875,
0.042022705078125,
-0.0002034902572631836,
0.01483917236328125,
0.031402587890625,
0.0401611328125,
-0.0014810562133789062,
0.04388427734375,
0.0194244384765625,
-0.038055419921875,
-0.0153656005859375,
-0.039459228515625,
-0.019989013671875,
0.023162841796875,
-0.048095703125,
0.0178375244140625,
-0.032501220703125,
-0.026611328125,
0.00446319580078125,
0.007659912109375,
-0.051544189453125,
0.0089111328125,
0.01229095458984375,
0.06256103515625,
-0.049407958984375,
0.07415771484375,
0.0643310546875,
-0.062255859375,
-0.061553955078125,
-0.0206756591796875,
-0.024169921875,
-0.05816650390625,
0.05303955078125,
-0.0007228851318359375,
0.0111846923828125,
-0.0197601318359375,
-0.043212890625,
-0.05242919921875,
0.08416748046875,
0.038055419921875,
-0.051513671875,
0.002971649169921875,
0.0199432373046875,
0.03424072265625,
-0.01351165771484375,
0.00864410400390625,
0.051422119140625,
0.034637451171875,
0.0025386810302734375,
-0.072509765625,
0.01434326171875,
-0.023895263671875,
-0.01247406005859375,
-0.00969696044921875,
-0.043792724609375,
0.07000732421875,
0.0001690387725830078,
-0.007144927978515625,
-0.0038547515869140625,
0.0390625,
0.0205078125,
0.016510009765625,
0.03924560546875,
0.061920166015625,
0.0762939453125,
-0.011383056640625,
0.076416015625,
-0.034515380859375,
0.039031982421875,
0.058013916015625,
-0.02587890625,
0.05963134765625,
0.032806396484375,
-0.03485107421875,
0.038909912109375,
0.044677734375,
-0.0298614501953125,
0.036773681640625,
0.0203094482421875,
0.00815582275390625,
-0.006000518798828125,
-0.0095672607421875,
-0.044281005859375,
0.0216522216796875,
0.023101806640625,
-0.03448486328125,
-0.0109710693359375,
-0.0023632049560546875,
0.002269744873046875,
-0.0159454345703125,
-0.01322174072265625,
0.05499267578125,
0.0013685226440429688,
-0.035003662109375,
0.03460693359375,
0.01406097412109375,
0.04833984375,
-0.048797607421875,
-0.0013427734375,
-0.005359649658203125,
-0.00788116455078125,
-0.00958251953125,
-0.060516357421875,
0.02630615234375,
0.0286102294921875,
-0.00624847412109375,
-0.0222930908203125,
0.049407958984375,
-0.0223388671875,
-0.033355712890625,
0.0126190185546875,
0.0213470458984375,
0.03692626953125,
0.004688262939453125,
-0.076904296875,
-0.01204681396484375,
-0.0171661376953125,
-0.01183319091796875,
0.007030487060546875,
0.040283203125,
0.00823974609375,
0.033172607421875,
0.05133056640625,
0.0177001953125,
0.0225372314453125,
-0.0079498291015625,
0.06671142578125,
-0.0736083984375,
-0.05133056640625,
-0.053131103515625,
0.04681396484375,
-0.01522064208984375,
-0.029510498046875,
0.030181884765625,
0.062347412109375,
0.050750732421875,
-0.0079498291015625,
0.0682373046875,
-0.04119873046875,
0.0350341796875,
-0.057769775390625,
0.0677490234375,
-0.045745849609375,
0.01064300537109375,
-0.005924224853515625,
-0.0550537109375,
-0.016204833984375,
0.043487548828125,
-0.028106689453125,
0.007595062255859375,
0.0589599609375,
0.048675537109375,
-0.004772186279296875,
-0.01291656494140625,
0.0341796875,
0.0206146240234375,
0.015167236328125,
0.036712646484375,
0.056488037109375,
-0.047607421875,
0.06585693359375,
-0.03302001953125,
0.00930023193359375,
-0.031585693359375,
-0.06512451171875,
-0.05535888671875,
-0.0287017822265625,
-0.0177001953125,
-0.025543212890625,
0.0008015632629394531,
0.06982421875,
0.057403564453125,
-0.0789794921875,
-0.027801513671875,
-0.01410675048828125,
-0.0102691650390625,
-0.0120391845703125,
-0.0133514404296875,
0.017425537109375,
-0.0270538330078125,
-0.03179931640625,
0.0174102783203125,
0.0017786026000976562,
-0.001094818115234375,
-0.0067138671875,
-0.01172637939453125,
-0.04010009765625,
0.00423431396484375,
0.04803466796875,
0.033294677734375,
-0.07403564453125,
-0.0250396728515625,
-0.0123291015625,
-0.025909423828125,
0.01108551025390625,
0.04632568359375,
-0.02325439453125,
0.0221405029296875,
0.02410888671875,
0.0360107421875,
0.04327392578125,
-0.00186920166015625,
0.035888671875,
-0.05340576171875,
0.029449462890625,
0.01898193359375,
0.05145263671875,
-0.0079803466796875,
-0.024566650390625,
0.046539306640625,
0.01412200927734375,
-0.034149169921875,
-0.052734375,
-0.000705718994140625,
-0.08917236328125,
-0.007549285888671875,
0.0653076171875,
-0.0290679931640625,
-0.028594970703125,
-0.02093505859375,
-0.01031494140625,
0.0345458984375,
-0.04144287109375,
0.0416259765625,
0.0592041015625,
0.00511932373046875,
0.0190277099609375,
-0.068359375,
0.031585693359375,
0.034271240234375,
-0.055145263671875,
-0.0166473388671875,
0.027618408203125,
0.020050048828125,
0.0180511474609375,
0.0599365234375,
-0.009857177734375,
0.0251617431640625,
0.0059051513671875,
0.015899658203125,
0.0030689239501953125,
0.0011396408081054688,
-0.031768798828125,
0.015655517578125,
-0.0147857666015625,
-0.02728271484375
]
] |
sonoisa/sentence-luke-japanese-base-lite | 2023-03-20T01:32:34.000Z | [
"sentence-transformers",
"pytorch",
"luke",
"sentence-bert",
"sentence-luke",
"feature-extraction",
"sentence-similarity",
"ja",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | feature-extraction | sonoisa | null | null | sonoisa/sentence-luke-japanese-base-lite | 7 | 45,252 | sentence-transformers | 2023-03-19T14:44:42 | ---
language: ja
license: apache-2.0
tags:
- sentence-transformers
- sentence-bert
- sentence-luke
- feature-extraction
- sentence-similarity
---
This is a Japanese sentence-LUKE model.
日本語用Sentence-LUKEモデルです。
[日本語Sentence-BERTモデル](https://huggingface.co/sonoisa/sentence-bert-base-ja-mean-tokens-v2)と同一のデータセットと設定で学習しました。
手元の非公開データセットでは、[日本語Sentence-BERTモデル](https://huggingface.co/sonoisa/sentence-bert-base-ja-mean-tokens-v2)と比べて定量的な精度が同等〜0.5pt程度高く、定性的な精度は本モデルの方が高い結果でした。
事前学習済みモデルとして[studio-ousia/luke-japanese-base-lite](https://huggingface.co/studio-ousia/luke-japanese-base-lite)を利用させていただきました。
推論の実行にはSentencePieceが必要です（pip install sentencepiece）。
# 使い方
```python
from transformers import MLukeTokenizer, LukeModel
import torch
class SentenceLukeJapanese:
def __init__(self, model_name_or_path, device=None):
self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
self.model = LukeModel.from_pretrained(model_name_or_path)
self.model.eval()
if device is None:
device = "cuda" if torch.cuda.is_available() else "cpu"
self.device = torch.device(device)
self.model.to(device)
def _mean_pooling(self, model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
@torch.no_grad()
def encode(self, sentences, batch_size=8):
all_embeddings = []
iterator = range(0, len(sentences), batch_size)
for batch_idx in iterator:
batch = sentences[batch_idx:batch_idx + batch_size]
encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest",
truncation=True, return_tensors="pt").to(self.device)
model_output = self.model(**encoded_input)
sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')
all_embeddings.extend(sentence_embeddings)
return torch.stack(all_embeddings)
MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)
sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)
print("Sentence embeddings:", sentence_embeddings)
```
| 2,509 | [
[
-0.01335906982421875,
-0.076171875,
0.0242919921875,
0.01531219482421875,
-0.032196044921875,
-0.0267181396484375,
-0.02703857421875,
-0.010101318359375,
0.02838134765625,
0.033172607421875,
-0.049468994140625,
-0.038421630859375,
-0.054931640625,
-0.0020294189453125,
-0.00800323486328125,
0.061614990234375,
-0.0269775390625,
0.00885772705078125,
0.0063323974609375,
-0.0037784576416015625,
-0.04638671875,
-0.019439697265625,
-0.042877197265625,
-0.0242767333984375,
0.0147857666015625,
0.0184783935546875,
0.03192138671875,
0.038604736328125,
0.02728271484375,
0.029571533203125,
0.009552001953125,
0.00307464599609375,
-0.02276611328125,
-0.0005850791931152344,
0.0095977783203125,
-0.046722412109375,
-0.0134429931640625,
0.005580902099609375,
0.0458984375,
0.03717041015625,
0.00954437255859375,
0.0143890380859375,
-0.0006585121154785156,
0.033935546875,
-0.0357666015625,
0.031280517578125,
-0.0307159423828125,
0.00017189979553222656,
-0.003360748291015625,
-0.008544921875,
-0.0416259765625,
-0.011993408203125,
-0.01253509521484375,
-0.0419921875,
0.0177459716796875,
-0.00960540771484375,
0.09613037109375,
0.01107025146484375,
-0.01447296142578125,
-0.02105712890625,
-0.01702880859375,
0.0675048828125,
-0.06915283203125,
0.0248565673828125,
0.0243682861328125,
-0.0037784576416015625,
-0.006938934326171875,
-0.06585693359375,
-0.0482177734375,
-0.00672149658203125,
-0.0223236083984375,
0.0193023681640625,
-0.003337860107421875,
0.0020427703857421875,
0.0240325927734375,
0.01070404052734375,
-0.049163818359375,
-0.007289886474609375,
-0.03448486328125,
-0.00927734375,
0.046539306640625,
0.0060272216796875,
0.036041259765625,
-0.040557861328125,
-0.0284271240234375,
-0.022216796875,
-0.0284881591796875,
0.0160980224609375,
0.0175628662109375,
0.0261383056640625,
-0.032196044921875,
0.058746337890625,
-0.01253509521484375,
0.041595458984375,
0.0078887939453125,
-0.0178375244140625,
0.038909912109375,
-0.0234527587890625,
-0.0262603759765625,
0.006206512451171875,
0.07861328125,
0.039093017578125,
0.0328369140625,
0.0016307830810546875,
-0.0028591156005859375,
0.01556396484375,
-0.00897216796875,
-0.07110595703125,
-0.00791168212890625,
0.015960693359375,
-0.044464111328125,
-0.014892578125,
0.01629638671875,
-0.052703857421875,
-0.0002493858337402344,
0.01078033447265625,
0.0455322265625,
-0.04302978515625,
-0.0118408203125,
0.02374267578125,
-0.0143890380859375,
0.006961822509765625,
-0.0157928466796875,
-0.0760498046875,
0.006500244140625,
0.028472900390625,
0.062255859375,
0.02532958984375,
-0.0391845703125,
-0.01495361328125,
0.00724029541015625,
-0.01172637939453125,
0.01335906982421875,
-0.027679443359375,
-0.03863525390625,
-0.01708984375,
0.01538848876953125,
-0.04833984375,
-0.02191162109375,
0.044647216796875,
-0.020355224609375,
0.04864501953125,
-0.01184844970703125,
-0.06298828125,
-0.02008056640625,
0.010467529296875,
-0.035888671875,
0.06005859375,
0.01904296875,
-0.071533203125,
0.016021728515625,
-0.048828125,
-0.0266265869140625,
-0.009521484375,
-0.017822265625,
-0.046478271484375,
0.00006633996963500977,
0.036529541015625,
0.052764892578125,
-0.006595611572265625,
0.01837158203125,
-0.01274871826171875,
-0.0291595458984375,
0.026214599609375,
-0.02520751953125,
0.09393310546875,
0.0170440673828125,
-0.042755126953125,
0.006134033203125,
-0.044952392578125,
0.001117706298828125,
0.0325927734375,
-0.0177001953125,
-0.0081329345703125,
-0.0127410888671875,
0.0203399658203125,
0.00943756103515625,
0.0234527587890625,
-0.0567626953125,
0.012115478515625,
-0.03558349609375,
0.052703857421875,
0.053466796875,
0.0220489501953125,
0.02276611328125,
-0.030731201171875,
0.017547607421875,
0.0183258056640625,
0.001705169677734375,
-0.0218048095703125,
-0.04052734375,
-0.08087158203125,
-0.02392578125,
0.007511138916015625,
0.03271484375,
-0.059814453125,
0.050567626953125,
-0.0277252197265625,
-0.0361328125,
-0.048583984375,
0.005828857421875,
0.02252197265625,
0.03973388671875,
0.028656005859375,
-0.00868988037109375,
-0.0479736328125,
-0.0684814453125,
-0.01422119140625,
-0.0200958251953125,
0.01134490966796875,
0.017486572265625,
0.04327392578125,
-0.0188140869140625,
0.04888916015625,
-0.03472900390625,
-0.0180816650390625,
-0.0305328369140625,
0.0089263916015625,
0.04931640625,
0.0567626953125,
0.03436279296875,
-0.049285888671875,
-0.0367431640625,
-0.01373291015625,
-0.0704345703125,
0.005580902099609375,
-0.03326416015625,
-0.0157623291015625,
0.0173187255859375,
0.0288543701171875,
-0.0740966796875,
0.02587890625,
0.0140228271484375,
-0.052581787109375,
0.0256805419921875,
-0.00865936279296875,
0.0236968994140625,
-0.1055908203125,
0.0052947998046875,
0.00214385986328125,
-0.00514984130859375,
-0.038238525390625,
0.027435302734375,
0.0089111328125,
0.01035308837890625,
-0.0364990234375,
0.044891357421875,
-0.04180908203125,
0.0161895751953125,
-0.00177001953125,
0.0145263671875,
0.009857177734375,
0.05194091796875,
-0.0005583763122558594,
0.052947998046875,
0.04229736328125,
-0.038177490234375,
0.0435791015625,
0.0176544189453125,
-0.0267181396484375,
0.01190185546875,
-0.057342529296875,
-0.01434326171875,
0.0003178119659423828,
0.006771087646484375,
-0.07183837890625,
-0.0146942138671875,
0.031402587890625,
-0.05279541015625,
0.0235748291015625,
0.01007080078125,
-0.050262451171875,
-0.042266845703125,
-0.0289459228515625,
0.0160369873046875,
0.04571533203125,
-0.0352783203125,
0.03582763671875,
0.00952911376953125,
0.0016622543334960938,
-0.047821044921875,
-0.0748291015625,
-0.006778717041015625,
-0.01837158203125,
-0.054931640625,
0.0225372314453125,
-0.0025348663330078125,
0.004486083984375,
0.0038204193115234375,
0.0106658935546875,
0.0034008026123046875,
0.008056640625,
0.00616455078125,
0.0386962890625,
-0.0333251953125,
-0.007213592529296875,
0.0011110305786132812,
-0.00414276123046875,
0.01416015625,
0.0019588470458984375,
0.06329345703125,
-0.0090484619140625,
-0.0218963623046875,
-0.0450439453125,
0.0141754150390625,
0.029693603515625,
-0.0001888275146484375,
0.0638427734375,
0.072265625,
-0.035308837890625,
0.001312255859375,
-0.0391845703125,
-0.0186920166015625,
-0.038818359375,
0.049896240234375,
-0.0447998046875,
-0.046112060546875,
0.044219970703125,
0.03509521484375,
0.004627227783203125,
0.05230712890625,
0.06024169921875,
-0.00028228759765625,
0.07330322265625,
0.0286712646484375,
-0.008087158203125,
0.044403076171875,
-0.054168701171875,
0.0208892822265625,
-0.061004638671875,
-0.01474761962890625,
-0.0089569091796875,
-0.0217742919921875,
-0.05194091796875,
-0.022125244140625,
0.0191192626953125,
0.00867462158203125,
-0.02618408203125,
0.03961181640625,
-0.044830322265625,
0.026947021484375,
0.0457763671875,
0.025970458984375,
-0.0005011558532714844,
-0.00921630859375,
-0.016326904296875,
-0.0123291015625,
-0.0440673828125,
-0.037994384765625,
0.07305908203125,
0.034271240234375,
0.046356201171875,
0.0024967193603515625,
0.06427001953125,
-0.0157928466796875,
-0.00186920166015625,
-0.050018310546875,
0.05303955078125,
-0.008087158203125,
-0.052520751953125,
-0.0151214599609375,
-0.03265380859375,
-0.0762939453125,
0.0236968994140625,
-0.0057373046875,
-0.07489013671875,
-0.000980377197265625,
-0.033966064453125,
-0.0148468017578125,
0.0318603515625,
-0.06903076171875,
0.07928466796875,
-0.0012683868408203125,
-0.026947021484375,
-0.00867462158203125,
-0.04302978515625,
0.0304412841796875,
0.026458740234375,
0.00688934326171875,
-0.012420654296875,
0.004039764404296875,
0.08306884765625,
-0.0233154296875,
0.062347412109375,
-0.0203857421875,
0.02276611328125,
0.03155517578125,
-0.0100860595703125,
0.0162506103515625,
0.00925445556640625,
0.00334930419921875,
-0.0102691650390625,
0.003871917724609375,
-0.03857421875,
-0.035980224609375,
0.060028076171875,
-0.0826416015625,
-0.041839599609375,
-0.02630615234375,
-0.043365478515625,
-0.004932403564453125,
0.034271240234375,
0.05084228515625,
0.0307159423828125,
-0.00325775146484375,
0.022125244140625,
0.036712646484375,
-0.01442718505859375,
0.0654296875,
0.0091552734375,
-0.0177001953125,
-0.0299072265625,
0.05633544921875,
0.01509857177734375,
0.01094818115234375,
0.030242919921875,
0.009307861328125,
-0.0201873779296875,
-0.01308441162109375,
-0.044036865234375,
0.041900634765625,
-0.052581787109375,
-0.007297515869140625,
-0.061737060546875,
-0.03424072265625,
-0.047576904296875,
-0.0225677490234375,
-0.0212554931640625,
-0.026214599609375,
-0.03863525390625,
-0.0142364501953125,
0.0280609130859375,
0.025421142578125,
0.0092010498046875,
0.02734375,
-0.054779052734375,
0.02801513671875,
0.00962066650390625,
0.0099639892578125,
-0.000690460205078125,
-0.04736328125,
-0.032745361328125,
0.0121612548828125,
-0.0300445556640625,
-0.06842041015625,
0.0435791015625,
-0.0019140243530273438,
0.048736572265625,
0.02490234375,
-0.0031795501708984375,
0.050262451171875,
-0.019866943359375,
0.07080078125,
0.032073974609375,
-0.0738525390625,
0.04296875,
-0.017303466796875,
0.027740478515625,
0.02630615234375,
0.0132598876953125,
-0.044708251953125,
-0.03302001953125,
-0.06396484375,
-0.06451416015625,
0.057952880859375,
0.0179595947265625,
0.036956787109375,
-0.0119781494140625,
0.01387786865234375,
-0.00418853759765625,
0.0021953582763671875,
-0.07647705078125,
-0.0384521484375,
-0.0245208740234375,
-0.0462646484375,
-0.01314544677734375,
-0.01251983642578125,
0.002872467041015625,
-0.02386474609375,
0.0743408203125,
0.015625,
0.04638671875,
0.020538330078125,
-0.02069091796875,
-0.00794219970703125,
0.01015472412109375,
0.0394287109375,
0.02386474609375,
-0.0228424072265625,
0.0013370513916015625,
0.00897216796875,
-0.03961181640625,
0.00690460205078125,
0.01094818115234375,
-0.0157928466796875,
0.027862548828125,
0.0482177734375,
0.0821533203125,
0.01253509521484375,
-0.032806396484375,
0.0511474609375,
-0.003345489501953125,
-0.0127716064453125,
-0.0183258056640625,
0.01178741455078125,
0.0189971923828125,
0.01314544677734375,
0.01611328125,
-0.01434326171875,
-0.0008535385131835938,
-0.03814697265625,
0.01320648193359375,
0.018524169921875,
-0.0041656494140625,
-0.002796173095703125,
0.059051513671875,
-0.0018482208251953125,
-0.007083892822265625,
0.045379638671875,
0.0028018951416015625,
-0.043060302734375,
0.057373046875,
0.046905517578125,
0.07427978515625,
-0.0013170242309570312,
0.00917816162109375,
0.0576171875,
0.0225677490234375,
0.0047454833984375,
0.0234832763671875,
0.007602691650390625,
-0.062408447265625,
-0.00959014892578125,
-0.03363037109375,
0.0027904510498046875,
0.00250244140625,
-0.0545654296875,
0.03228759765625,
-0.038177490234375,
-0.01482391357421875,
0.003360748291015625,
0.0189666748046875,
-0.043792724609375,
0.02117919921875,
0.00783538818359375,
0.053314208984375,
-0.07080078125,
0.0679931640625,
0.04327392578125,
-0.05621337890625,
-0.074951171875,
-0.0171051025390625,
-0.02740478515625,
-0.0784912109375,
0.039642333984375,
0.03277587890625,
0.01287841796875,
0.0090484619140625,
-0.034881591796875,
-0.06280517578125,
0.0855712890625,
0.02117919921875,
-0.0247344970703125,
-0.00930023193359375,
0.0002923011779785156,
0.0307464599609375,
-0.0294647216796875,
0.0294036865234375,
0.03814697265625,
0.0290679931640625,
-0.005741119384765625,
-0.057464599609375,
0.018951416015625,
-0.037994384765625,
0.004268646240234375,
-0.0018157958984375,
-0.05718994140625,
0.09033203125,
-0.0177001953125,
-0.0169830322265625,
0.0092010498046875,
0.05694580078125,
0.03363037109375,
0.0087738037109375,
0.02001953125,
0.048614501953125,
0.035430908203125,
-0.01007843017578125,
0.07232666015625,
-0.0249176025390625,
0.055694580078125,
0.06231689453125,
0.017791748046875,
0.0631103515625,
0.04180908203125,
-0.02203369140625,
0.0517578125,
0.05194091796875,
-0.01538848876953125,
0.048126220703125,
-0.0023975372314453125,
-0.00830841064453125,
0.002101898193359375,
0.005340576171875,
-0.03857421875,
0.035003662109375,
0.016448974609375,
-0.0498046875,
-0.0004062652587890625,
0.0095672607421875,
0.02838134765625,
-0.004596710205078125,
-0.0167388916015625,
0.04595947265625,
0.00765228271484375,
-0.049713134765625,
0.061279296875,
0.02374267578125,
0.0704345703125,
-0.035308837890625,
0.0216064453125,
-0.00873565673828125,
0.0247039794921875,
-0.01110076904296875,
-0.058868408203125,
0.01092529296875,
0.0006785392761230469,
-0.01568603515625,
-0.00675201416015625,
0.032806396484375,
-0.044403076171875,
-0.0638427734375,
0.020660400390625,
0.0307769775390625,
0.00980377197265625,
0.0293121337890625,
-0.06793212890625,
0.00916290283203125,
0.0127410888671875,
-0.050567626953125,
0.0029315948486328125,
0.016937255859375,
0.025604248046875,
0.036956787109375,
0.0290985107421875,
-0.0023403167724609375,
0.0229949951171875,
0.01088714599609375,
0.056915283203125,
-0.049407958984375,
-0.049407958984375,
-0.08819580078125,
0.042144775390625,
-0.006565093994140625,
-0.03271484375,
0.060791015625,
0.04345703125,
0.0692138671875,
-0.0142974853515625,
0.050018310546875,
-0.017333984375,
0.023193359375,
-0.06072998046875,
0.052734375,
-0.040374755859375,
-0.00225830078125,
-0.0181427001953125,
-0.06396484375,
-0.0139617919921875,
0.07232666015625,
-0.0200958251953125,
0.0221405029296875,
0.06951904296875,
0.06182861328125,
-0.0036830902099609375,
-0.0023651123046875,
0.015960693359375,
0.025787353515625,
0.01526641845703125,
0.0679931640625,
0.0276031494140625,
-0.06622314453125,
0.018798828125,
-0.0482177734375,
0.005222320556640625,
-0.0141448974609375,
-0.03729248046875,
-0.0736083984375,
-0.0565185546875,
-0.028594970703125,
-0.042022705078125,
-0.0157318115234375,
0.08428955078125,
0.04833984375,
-0.068115234375,
-0.02130126953125,
-0.015625,
0.00395965576171875,
-0.00865936279296875,
-0.0250091552734375,
0.0421142578125,
-0.02783203125,
-0.0704345703125,
0.006198883056640625,
-0.01201629638671875,
0.00827789306640625,
-0.005584716796875,
-0.005947113037109375,
-0.03271484375,
0.005558013916015625,
0.0213165283203125,
-0.0082550048828125,
-0.06268310546875,
-0.0159454345703125,
0.0007076263427734375,
-0.03753662109375,
0.004772186279296875,
0.029510498046875,
-0.039642333984375,
0.03973388671875,
0.038604736328125,
0.0311279296875,
0.056671142578125,
-0.022979736328125,
0.02386474609375,
-0.060638427734375,
0.0276031494140625,
0.005046844482421875,
0.06280517578125,
0.02679443359375,
-0.03564453125,
0.04193115234375,
0.037017822265625,
-0.0214385986328125,
-0.059478759765625,
-0.006175994873046875,
-0.07843017578125,
-0.029083251953125,
0.08892822265625,
-0.0181121826171875,
-0.030059814453125,
0.027496337890625,
-0.0234832763671875,
0.05419921875,
-0.0160675048828125,
0.045684814453125,
0.0625,
-0.00041675567626953125,
-0.0292816162109375,
-0.032379150390625,
-0.002964019775390625,
0.03436279296875,
-0.035980224609375,
-0.007762908935546875,
0.01158905029296875,
0.0304412841796875,
0.0162811279296875,
0.05029296875,
0.0010538101196289062,
0.023590087890625,
0.026702880859375,
0.01474761962890625,
-0.0144195556640625,
0.0095367431640625,
-0.01476287841796875,
-0.003631591796875,
-0.00894927978515625,
-0.047149658203125
]
] |
Helsinki-NLP/opus-mt-tr-en | 2023-08-16T12:07:23.000Z | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"tr",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-tr-en | 24 | 45,218 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-tr-en
* source languages: tr
* target languages: en
* OPUS readme: [tr-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/tr-en/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-16.zip](https://object.pouta.csc.fi/OPUS-MT-models/tr-en/opus-2020-01-16.zip)
* test set translations: [opus-2020-01-16.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/tr-en/opus-2020-01-16.test.txt)
* test set scores: [opus-2020-01-16.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/tr-en/opus-2020-01-16.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| newsdev2016-entr.tr.en | 27.6 | 0.548 |
| newstest2016-entr.tr.en | 25.2 | 0.532 |
| newstest2017-entr.tr.en | 24.7 | 0.530 |
| newstest2018-entr.tr.en | 27.0 | 0.547 |
| Tatoeba.tr.en | 63.5 | 0.760 |
| 997 | [
[
-0.0205841064453125,
-0.0279998779296875,
0.020050048828125,
0.0230560302734375,
-0.031951904296875,
-0.022247314453125,
-0.02557373046875,
-0.007167816162109375,
0.00611114501953125,
0.033599853515625,
-0.055023193359375,
-0.046051025390625,
-0.042724609375,
0.01445770263671875,
-0.0107269287109375,
0.0621337890625,
-0.01221466064453125,
0.032012939453125,
0.0235443115234375,
-0.036163330078125,
-0.0278472900390625,
-0.0254058837890625,
-0.03643798828125,
-0.0213165283203125,
0.0286407470703125,
0.034454345703125,
0.0283203125,
0.03192138671875,
0.06793212890625,
0.01654052734375,
-0.008087158203125,
0.0007028579711914062,
-0.032379150390625,
-0.0099029541015625,
0.0125885009765625,
-0.04241943359375,
-0.060546875,
-0.0072174072265625,
0.074462890625,
0.029144287109375,
-0.002742767333984375,
0.0361328125,
-0.002285003662109375,
0.06396484375,
-0.02081298828125,
0.0037899017333984375,
-0.04510498046875,
0.0095062255859375,
-0.0275726318359375,
-0.021820068359375,
-0.048370361328125,
-0.0204315185546875,
0.01061248779296875,
-0.046051025390625,
0.00222015380859375,
0.0148468017578125,
0.103515625,
0.0176849365234375,
-0.0285491943359375,
-0.0088653564453125,
-0.0401611328125,
0.0780029296875,
-0.0628662109375,
0.04498291015625,
0.02587890625,
0.019287109375,
0.017608642578125,
-0.046600341796875,
-0.026519775390625,
0.00983428955078125,
-0.020751953125,
0.0185394287109375,
-0.01078033447265625,
-0.0182342529296875,
0.022308349609375,
0.052947998046875,
-0.06298828125,
-0.0025577545166015625,
-0.042236328125,
-0.0005931854248046875,
0.046722412109375,
0.0125274658203125,
0.01364898681640625,
-0.01177215576171875,
-0.0309906005859375,
-0.041046142578125,
-0.052459716796875,
0.00839996337890625,
0.0234222412109375,
0.0228729248046875,
-0.03448486328125,
0.049713134765625,
-0.01123809814453125,
0.048553466796875,
-0.00423431396484375,
-0.0033016204833984375,
0.073974609375,
-0.028717041015625,
-0.0278472900390625,
-0.0092315673828125,
0.09033203125,
0.0273284912109375,
-0.0008039474487304688,
0.0070037841796875,
-0.0196380615234375,
-0.0167236328125,
0.00626373291015625,
-0.0628662109375,
-0.0014896392822265625,
0.01090240478515625,
-0.0300445556640625,
-0.01055145263671875,
0.006587982177734375,
-0.051910400390625,
0.0203094482421875,
-0.02545166015625,
0.04315185546875,
-0.042236328125,
-0.019775390625,
0.026214599609375,
0.002964019775390625,
0.0308837890625,
-0.0017805099487304688,
-0.040679931640625,
0.0182952880859375,
0.0254058837890625,
0.058868408203125,
-0.029693603515625,
-0.01849365234375,
-0.034942626953125,
-0.01152801513671875,
-0.00513458251953125,
0.0478515625,
-0.0054779052734375,
-0.027618408203125,
-0.00687408447265625,
0.03753662109375,
-0.0237274169921875,
-0.0188751220703125,
0.09674072265625,
-0.020050048828125,
0.05548095703125,
-0.035858154296875,
-0.0306549072265625,
-0.0223846435546875,
0.0386962890625,
-0.047821044921875,
0.093994140625,
0.00719451904296875,
-0.06805419921875,
0.0171356201171875,
-0.06182861328125,
-0.01092529296875,
-0.005374908447265625,
0.0093841552734375,
-0.05438232421875,
0.00241851806640625,
0.01186370849609375,
0.0258026123046875,
-0.026123046875,
0.023773193359375,
0.0021343231201171875,
-0.024932861328125,
0.001651763916015625,
-0.023895263671875,
0.07696533203125,
0.0240631103515625,
-0.0260162353515625,
0.017578125,
-0.0712890625,
0.002300262451171875,
0.0030117034912109375,
-0.031494140625,
-0.01000213623046875,
0.00323486328125,
0.0212860107421875,
0.00908660888671875,
0.0203399658203125,
-0.0458984375,
0.0184478759765625,
-0.0452880859375,
0.020477294921875,
0.04803466796875,
-0.0194854736328125,
0.0245513916015625,
-0.0350341796875,
0.0281982421875,
0.0129241943359375,
0.01111602783203125,
0.008453369140625,
-0.033782958984375,
-0.06640625,
-0.0083465576171875,
0.0396728515625,
0.07574462890625,
-0.05340576171875,
0.061859130859375,
-0.05279541015625,
-0.060455322265625,
-0.05078125,
-0.017364501953125,
0.0313720703125,
0.03497314453125,
0.039794921875,
-0.01495361328125,
-0.039154052734375,
-0.080322265625,
-0.01181793212890625,
-0.012847900390625,
-0.010467529296875,
0.0092010498046875,
0.050750732421875,
-0.00882720947265625,
0.041107177734375,
-0.040924072265625,
-0.0322265625,
-0.01708984375,
0.0131988525390625,
0.03912353515625,
0.0487060546875,
0.036376953125,
-0.059783935546875,
-0.04461669921875,
0.0007257461547851562,
-0.04632568359375,
-0.011016845703125,
0.00536346435546875,
-0.020263671875,
0.0027923583984375,
0.002407073974609375,
-0.0253753662109375,
0.00951385498046875,
0.047210693359375,
-0.047271728515625,
0.04400634765625,
-0.003421783447265625,
0.0189666748046875,
-0.09881591796875,
0.0095062255859375,
-0.009857177734375,
-0.0082244873046875,
-0.035430908203125,
-0.001644134521484375,
0.0174407958984375,
0.0095062255859375,
-0.057098388671875,
0.04107666015625,
-0.021942138671875,
-0.00850677490234375,
0.026702880859375,
0.00197601318359375,
0.009368896484375,
0.05419921875,
-0.006439208984375,
0.0628662109375,
0.049530029296875,
-0.0343017578125,
0.01274871826171875,
0.0401611328125,
-0.03485107421875,
0.0247955322265625,
-0.060546875,
-0.0180816650390625,
0.0214691162109375,
-0.004299163818359375,
-0.049591064453125,
0.005489349365234375,
0.02435302734375,
-0.0457763671875,
0.025543212890625,
-0.005222320556640625,
-0.0528564453125,
-0.00940704345703125,
-0.0218353271484375,
0.03460693359375,
0.046173095703125,
-0.00833892822265625,
0.04217529296875,
0.007801055908203125,
0.0025691986083984375,
-0.033416748046875,
-0.0743408203125,
-0.0100860595703125,
-0.034454345703125,
-0.05377197265625,
0.0208892822265625,
-0.0268096923828125,
-0.0014944076538085938,
0.0010519027709960938,
0.0225677490234375,
-0.0081939697265625,
-0.0013628005981445312,
0.00013399124145507812,
0.0174102783203125,
-0.033416748046875,
0.00792694091796875,
-0.003917694091796875,
-0.01090240478515625,
-0.00804901123046875,
-0.0164031982421875,
0.048858642578125,
-0.0304412841796875,
-0.0193939208984375,
-0.043243408203125,
-0.0008244514465332031,
0.0440673828125,
-0.035858154296875,
0.059112548828125,
0.048095703125,
-0.00815582275390625,
0.01898193359375,
-0.0303192138671875,
0.005847930908203125,
-0.032073974609375,
0.01511383056640625,
-0.0338134765625,
-0.056884765625,
0.045196533203125,
0.01580810546875,
0.03656005859375,
0.066162109375,
0.045745849609375,
0.00835418701171875,
0.056732177734375,
0.0178375244140625,
0.005977630615234375,
0.033538818359375,
-0.04052734375,
-0.01309967041015625,
-0.083251953125,
0.00003731250762939453,
-0.050994873046875,
-0.03375244140625,
-0.06671142578125,
-0.0173492431640625,
0.027374267578125,
-0.0089263916015625,
-0.0284881591796875,
0.053375244140625,
-0.0465087890625,
0.01511383056640625,
0.048858642578125,
-0.004421234130859375,
0.024383544921875,
0.001888275146484375,
-0.040924072265625,
-0.0218658447265625,
-0.032135009765625,
-0.033935546875,
0.09332275390625,
0.025177001953125,
0.0210113525390625,
0.0202789306640625,
0.038970947265625,
0.0020351409912109375,
0.017242431640625,
-0.041839599609375,
0.03564453125,
-0.0172271728515625,
-0.055877685546875,
-0.0222015380859375,
-0.04241943359375,
-0.05877685546875,
0.032562255859375,
-0.0170135498046875,
-0.04241943359375,
0.0120849609375,
-0.0032558441162109375,
-0.00876617431640625,
0.036895751953125,
-0.048553466796875,
0.08489990234375,
-0.00836944580078125,
-0.00994873046875,
0.022705078125,
-0.0386962890625,
0.02398681640625,
0.0038356781005859375,
0.019805908203125,
-0.01593017578125,
0.0121917724609375,
0.056549072265625,
-0.01165008544921875,
0.029998779296875,
-0.003299713134765625,
-0.002262115478515625,
0.005817413330078125,
0.0044708251953125,
0.03448486328125,
-0.007720947265625,
-0.028839111328125,
0.02239990234375,
0.00551605224609375,
-0.032470703125,
-0.00983428955078125,
0.03875732421875,
-0.057098388671875,
-0.00807952880859375,
-0.0394287109375,
-0.04925537109375,
0.0017604827880859375,
0.02740478515625,
0.050994873046875,
0.050018310546875,
-0.01605224609375,
0.04052734375,
0.057891845703125,
-0.022796630859375,
0.028289794921875,
0.053314208984375,
-0.0152740478515625,
-0.046478271484375,
0.06201171875,
0.00872039794921875,
0.024993896484375,
0.04412841796875,
0.01169586181640625,
-0.0148162841796875,
-0.052276611328125,
-0.04644775390625,
0.0182037353515625,
-0.0185394287109375,
-0.017303466796875,
-0.043182373046875,
-0.0087127685546875,
-0.0220184326171875,
0.017242431640625,
-0.036712646484375,
-0.043731689453125,
-0.0160980224609375,
-0.0184478759765625,
0.0192108154296875,
0.01934814453125,
-0.0020809173583984375,
0.040557861328125,
-0.0740966796875,
0.00719451904296875,
-0.007259368896484375,
0.0255584716796875,
-0.031341552734375,
-0.062408447265625,
-0.03546142578125,
0.00638580322265625,
-0.052154541015625,
-0.05389404296875,
0.04644775390625,
0.0102691650390625,
0.0168304443359375,
0.02679443359375,
0.0111846923828125,
0.0355224609375,
-0.051513671875,
0.07330322265625,
0.0038776397705078125,
-0.055206298828125,
0.039825439453125,
-0.0333251953125,
0.03582763671875,
0.06353759765625,
0.01432037353515625,
-0.029144287109375,
-0.04461669921875,
-0.056793212890625,
-0.0626220703125,
0.0634765625,
0.053985595703125,
-0.01308441162109375,
0.0178375244140625,
-0.00931549072265625,
-0.004062652587890625,
0.00940704345703125,
-0.09228515625,
-0.029571533203125,
0.0035800933837890625,
-0.0283660888671875,
-0.0093231201171875,
-0.020172119140625,
-0.0194091796875,
-0.020751953125,
0.07684326171875,
0.01238250732421875,
0.018646240234375,
0.029052734375,
-0.00719451904296875,
-0.0134735107421875,
0.0286865234375,
0.0731201171875,
0.040618896484375,
-0.04180908203125,
-0.00629425048828125,
0.02734375,
-0.034454345703125,
-0.006561279296875,
0.00567626953125,
-0.03125,
0.02166748046875,
0.033843994140625,
0.0791015625,
0.0136871337890625,
-0.043182373046875,
0.0298004150390625,
-0.027923583984375,
-0.032806396484375,
-0.05157470703125,
-0.0119171142578125,
0.0030612945556640625,
0.0021076202392578125,
0.020355224609375,
0.00943756103515625,
0.01373291015625,
-0.016632080078125,
0.0123748779296875,
0.0103912353515625,
-0.048614501953125,
-0.042236328125,
0.042388916015625,
0.004180908203125,
-0.019805908203125,
0.0362548828125,
-0.0286712646484375,
-0.04571533203125,
0.032562255859375,
0.01168060302734375,
0.07867431640625,
-0.015106201171875,
-0.0139617919921875,
0.057098388671875,
0.04632568359375,
-0.0160675048828125,
0.034912109375,
0.01555633544921875,
-0.050750732421875,
-0.035858154296875,
-0.059539794921875,
-0.009674072265625,
0.01137542724609375,
-0.06939697265625,
0.0309600830078125,
0.0241851806640625,
-0.00616455078125,
-0.028778076171875,
0.0246429443359375,
-0.044952392578125,
0.01239776611328125,
-0.0248565673828125,
0.076171875,
-0.0704345703125,
0.067626953125,
0.036895751953125,
-0.02044677734375,
-0.06317138671875,
-0.0188140869140625,
-0.0145263671875,
-0.037384033203125,
0.046630859375,
0.01348876953125,
0.0264892578125,
-0.005096435546875,
-0.0195770263671875,
-0.068603515625,
0.0899658203125,
0.01396942138671875,
-0.043182373046875,
-0.0035800933837890625,
0.01508331298828125,
0.03607177734375,
-0.0247344970703125,
0.017181396484375,
0.037200927734375,
0.05767822265625,
0.008575439453125,
-0.07843017578125,
-0.015594482421875,
-0.040283203125,
-0.0248565673828125,
0.04083251953125,
-0.0487060546875,
0.0770263671875,
0.0316162109375,
-0.0089874267578125,
0.0014352798461914062,
0.04486083984375,
0.025054931640625,
0.02166748046875,
0.042205810546875,
0.0872802734375,
0.0286865234375,
-0.04156494140625,
0.06671142578125,
-0.024749755859375,
0.04290771484375,
0.0877685546875,
-0.003162384033203125,
0.062744140625,
0.0221099853515625,
-0.01490020751953125,
0.043060302734375,
0.04925537109375,
-0.0228729248046875,
0.036590576171875,
-0.0011148452758789062,
0.0110015869140625,
-0.009033203125,
0.013519287109375,
-0.0535888671875,
0.018218994140625,
0.01611328125,
-0.01715087890625,
-0.00002181529998779297,
-0.00910186767578125,
0.00726318359375,
-0.01324462890625,
-0.007328033447265625,
0.0401611328125,
-0.0036907196044921875,
-0.04034423828125,
0.05267333984375,
-0.004299163818359375,
0.042388916015625,
-0.050994873046875,
0.011810302734375,
-0.006786346435546875,
0.0169219970703125,
-0.0001251697540283203,
-0.046142578125,
0.038482666015625,
0.00247955322265625,
-0.0167694091796875,
-0.034210205078125,
0.01100921630859375,
-0.040618896484375,
-0.069580078125,
0.0260467529296875,
0.03338623046875,
0.0215301513671875,
0.007770538330078125,
-0.064453125,
0.004055023193359375,
0.01385498046875,
-0.047760009765625,
0.002788543701171875,
0.055267333984375,
0.023040771484375,
0.036285400390625,
0.044586181640625,
0.0200347900390625,
0.018341064453125,
-0.004486083984375,
0.053741455078125,
-0.037872314453125,
-0.031890869140625,
-0.058929443359375,
0.06268310546875,
-0.00878143310546875,
-0.051849365234375,
0.051177978515625,
0.07574462890625,
0.07025146484375,
-0.005252838134765625,
0.0192413330078125,
-0.00960540771484375,
0.053192138671875,
-0.0477294921875,
0.04510498046875,
-0.07257080078125,
0.0194091796875,
-0.0088653564453125,
-0.06640625,
-0.020477294921875,
0.0225067138671875,
-0.018218994140625,
-0.0242767333984375,
0.05767822265625,
0.046112060546875,
-0.009552001953125,
-0.01270294189453125,
0.0189056396484375,
0.02752685546875,
0.01953125,
0.048614501953125,
0.02899169921875,
-0.07470703125,
0.04486083984375,
-0.0242767333984375,
-0.0034275054931640625,
-0.0028247833251953125,
-0.05145263671875,
-0.05938720703125,
-0.046630859375,
-0.01154327392578125,
-0.017852783203125,
-0.0203399658203125,
0.062744140625,
0.03692626953125,
-0.07171630859375,
-0.041259765625,
-0.0025081634521484375,
0.01090240478515625,
-0.01480865478515625,
-0.0217437744140625,
0.0479736328125,
-0.0195465087890625,
-0.0731201171875,
0.0256500244140625,
0.0006737709045410156,
-0.0025634765625,
-0.004764556884765625,
-0.0195159912109375,
-0.0374755859375,
-0.01053619384765625,
0.0215301513671875,
-0.0017442703247070312,
-0.041412353515625,
0.0029735565185546875,
0.01334381103515625,
-0.00513458251953125,
0.03240966796875,
0.023406982421875,
-0.0205230712890625,
0.01552581787109375,
0.059722900390625,
0.0126953125,
0.03521728515625,
-0.00978851318359375,
0.037017822265625,
-0.05828857421875,
0.026611328125,
0.018402099609375,
0.044219970703125,
0.0215301513671875,
0.00014281272888183594,
0.059478759765625,
0.0168914794921875,
-0.048553466796875,
-0.08282470703125,
0.0036945343017578125,
-0.09033203125,
0.00885772705078125,
0.0682373046875,
-0.0179901123046875,
-0.020843505859375,
0.0245819091796875,
-0.00553131103515625,
0.0150299072265625,
-0.026824951171875,
0.033477783203125,
0.0648193359375,
0.0251617431640625,
0.0005035400390625,
-0.05755615234375,
0.024627685546875,
0.03155517578125,
-0.05474853515625,
-0.0167083740234375,
0.00984954833984375,
0.0070037841796875,
0.0275115966796875,
0.03399658203125,
-0.0204315185546875,
0.001964569091796875,
-0.022125244140625,
0.029296875,
-0.0012187957763671875,
-0.01204681396484375,
-0.01470184326171875,
-0.0027408599853515625,
-0.005908966064453125,
-0.0216827392578125
]
] |
Rostlab/prot_t5_xl_half_uniref50-enc | 2023-01-31T21:04:38.000Z | [
"transformers",
"pytorch",
"t5",
"protein language model",
"dataset:UniRef50",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | null | Rostlab | null | null | Rostlab/prot_t5_xl_half_uniref50-enc | 12 | 45,060 | transformers | 2022-05-20T09:58:28 | ---
tags:
- protein language model
datasets:
- UniRef50
---
# Encoder only ProtT5-XL-UniRef50, half-precision model
An encoder-only, half-precision version of the [ProtT5-XL-UniRef50](https://huggingface.co/Rostlab/prot_t5_xl_uniref50) model. The original model and it's pretraining were introduced in
[this paper](https://doi.org/10.1101/2020.07.12.199554) and first released in
[this repository](https://github.com/agemagician/ProtTrans). This model is trained on uppercase amino acids: it only works with capital letter amino acids.
## Model description
ProtT5-XL-UniRef50 is based on the `t5-3b` model and was pretrained on a large corpus of protein sequences in a self-supervised fashion.
This means it was pretrained on the raw protein sequences only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those protein sequences.
One important difference between this T5 model and the original T5 version is the denoising objective.
The original T5-3B model was pretrained using a span denoising objective, while this model was pretrained with a Bart-like MLM denoising objective.
The masking probability is consistent with the original T5 training by randomly masking 15% of the amino acids in the input.
This model only contains the encoder portion of the original ProtT5-XL-UniRef50 model using half precision (float16).
As such, this model can efficiently be used to create protein/ amino acid representations. When used for training downstream networks/ feature extraction, these embeddings produced the same performance (established empirically by comparing on several downstream tasks).
## Intended uses & limitations
This version of the original ProtT5-XL-UniRef50 is mostly meant for conveniently creating amino-acid or protein embeddings with a low GPU-memory footprint without any measurable performance-decrease in our experiments. This model is fully usable on 8 GB of video RAM.
### How to use
An extensive, interactive example on how to use this model for common tasks can be found [on Google Colab](https://colab.research.google.com/drive/1TUj-ayG3WO52n5N50S7KH9vtt6zRkdmj?usp=sharing#scrollTo=ET2v51slC5ui)
Here is how to use this model to extract the features of a given protein sequence in PyTorch:
```python
sequence_examples = ["PRTEINO", "SEQWENCE"]
# this will replace all rare/ambiguous amino acids by X and introduce white-space between all amino acids
sequence_examples = [" ".join(list(re.sub(r"[UZOB]", "X", sequence))) for sequence in sequence_examples]
# tokenize sequences and pad up to the longest sequence in the batch
ids = tokenizer.batch_encode_plus(sequence_examples, add_special_tokens=True, padding="longest")
input_ids = torch.tensor(ids['input_ids']).to(device)
attention_mask = torch.tensor(ids['attention_mask']).to(device)
# generate embeddings
with torch.no_grad():
embedding_repr = model(input_ids=input_ids,attention_mask=attention_mask)
# extract embeddings for the first ([0,:]) sequence in the batch while removing padded & special tokens ([0,:7])
emb_0 = embedding_repr.last_hidden_state[0,:7] # shape (7 x 1024)
print(f"Shape of per-residue embedding of first sequences: {emb_0.shape}")
# do the same for the second ([1,:]) sequence in the batch while taking into account different sequence lengths ([1,:8])
emb_1 = embedding_repr.last_hidden_state[1,:8] # shape (8 x 1024)
# if you want to derive a single representation (per-protein embedding) for the whole protein
emb_0_per_protein = emb_0.mean(dim=0) # shape (1024)
print(f"Shape of per-protein embedding of first sequences: {emb_0_per_protein.shape}")
```
**NOTE**: Please make sure to explicitly set the model to `float16` (`T5EncoderModel.from_pretrained('Rostlab/prot_t5_xl_half_uniref50-enc', torch_dtype=torch.float16)`) otherwise, the generated embeddings will be full precision.
**NOTE**: Currently (06/2022) half-precision models cannot be used on CPU. If you want to use the encoder only version on CPU, you need to cast it to its full-precision version (`model=model.float()`).
### BibTeX entry and citation info
```bibtex
@article {Elnaggar2020.07.12.199554,
author = {Elnaggar, Ahmed and Heinzinger, Michael and Dallago, Christian and Rehawi, Ghalia and Wang, Yu and Jones, Llion and Gibbs, Tom and Feher, Tamas and Angerer, Christoph and Steinegger, Martin and BHOWMIK, DEBSINDHU and Rost, Burkhard},
title = {ProtTrans: Towards Cracking the Language of Life{\textquoteright}s Code Through Self-Supervised Deep Learning and High Performance Computing},
elocation-id = {2020.07.12.199554},
year = {2020},
doi = {10.1101/2020.07.12.199554},
publisher = {Cold Spring Harbor Laboratory},
abstract = {Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive language models (Transformer-XL, XLNet) and two auto-encoder models (Bert, Albert) on data from UniRef and BFD containing up to 393 billion amino acids (words) from 2.1 billion protein sequences (22- and 112 times the entire English Wikipedia). The LMs were trained on the Summit supercomputer at Oak Ridge National Laboratory (ORNL), using 936 nodes (total 5616 GPUs) and one TPU Pod (V3-512 or V3-1024). We validated the advantage of up-scaling LMs to larger models supported by bigger data by predicting secondary structure (3-states: Q3=76-84, 8 states: Q8=65-73), sub-cellular localization for 10 cellular compartments (Q10=74) and whether a protein is membrane-bound or water-soluble (Q2=89). Dimensionality reduction revealed that the LM-embeddings from unlabeled data (only protein sequences) captured important biophysical properties governing protein shape. This implied learning some of the grammar of the language of life realized in protein sequences. The successful up-scaling of protein LMs through HPC to larger data sets slightly reduced the gap between models trained on evolutionary information and LMs. Availability ProtTrans: \<a href="https://github.com/agemagician/ProtTrans"\>https://github.com/agemagician/ProtTrans\</a\>Competing Interest StatementThe authors have declared no competing interest.},
URL = {https://www.biorxiv.org/content/early/2020/07/21/2020.07.12.199554},
eprint = {https://www.biorxiv.org/content/early/2020/07/21/2020.07.12.199554.full.pdf},
journal = {bioRxiv}
}
```
| 6,578 | [
[
-0.0167999267578125,
-0.042938232421875,
0.0157470703125,
-0.01200103759765625,
-0.0167388916015625,
0.0018138885498046875,
0.001369476318359375,
-0.0252838134765625,
0.02496337890625,
0.022552490234375,
-0.0303192138671875,
-0.039764404296875,
-0.053375244140625,
0.0254974365234375,
-0.02197265625,
0.058319091796875,
0.01100921630859375,
0.0098876953125,
-0.005405426025390625,
-0.004817962646484375,
0.01157379150390625,
-0.037078857421875,
-0.02166748046875,
-0.03509521484375,
0.032440185546875,
0.01502227783203125,
0.0360107421875,
0.06317138671875,
0.0391845703125,
0.019866943359375,
-0.01055908203125,
0.0088043212890625,
-0.03460693359375,
-0.0193939208984375,
0.013763427734375,
-0.0293121337890625,
-0.04766845703125,
-0.0014715194702148438,
0.04656982421875,
0.051300048828125,
0.0032634735107421875,
0.0212554931640625,
0.006801605224609375,
0.0504150390625,
-0.041473388671875,
0.0169525146484375,
-0.021484375,
0.0181427001953125,
-0.0145111083984375,
0.00466156005859375,
-0.03662109375,
-0.0165557861328125,
0.0127716064453125,
-0.037384033203125,
0.0227813720703125,
0.00702667236328125,
0.07708740234375,
0.016082763671875,
-0.0145111083984375,
-0.0048980712890625,
-0.0343017578125,
0.047943115234375,
-0.0740966796875,
0.046295166015625,
0.017822265625,
-0.00008606910705566406,
-0.035247802734375,
-0.082763671875,
-0.04254150390625,
-0.01396942138671875,
-0.004131317138671875,
0.01141357421875,
-0.00980377197265625,
0.0198211669921875,
0.0208740234375,
0.035125732421875,
-0.0673828125,
-0.01117706298828125,
-0.049560546875,
-0.00962066650390625,
0.04803466796875,
-0.02618408203125,
0.0229949951171875,
-0.029754638671875,
-0.00981903076171875,
-0.0300445556640625,
-0.04998779296875,
0.002716064453125,
0.01617431640625,
0.00640106201171875,
-0.00653839111328125,
0.042449951171875,
0.0014896392822265625,
0.041015625,
0.003887176513671875,
0.007465362548828125,
0.035980224609375,
0.005268096923828125,
-0.038604736328125,
0.008087158203125,
0.0849609375,
0.00417327880859375,
0.02996826171875,
-0.01081085205078125,
0.0097808837890625,
-0.0236968994140625,
0.00936126708984375,
-0.06396484375,
-0.044708251953125,
0.046722412109375,
-0.039306640625,
-0.00936126708984375,
0.0228271484375,
-0.057373046875,
-0.0168609619140625,
0.002925872802734375,
0.061370849609375,
-0.049713134765625,
-0.001682281494140625,
0.027984619140625,
-0.0143280029296875,
0.01157379150390625,
-0.0103759765625,
-0.055450439453125,
0.0088348388671875,
0.00981903076171875,
0.06854248046875,
-0.006439208984375,
-0.01544952392578125,
-0.0206146240234375,
0.01207733154296875,
0.00140380859375,
0.037506103515625,
-0.03302001953125,
-0.0166473388671875,
-0.0226287841796875,
0.0206146240234375,
-0.000762939453125,
-0.04254150390625,
0.0272674560546875,
-0.03729248046875,
-0.0033969879150390625,
-0.011016845703125,
-0.0562744140625,
-0.029266357421875,
-0.0139617919921875,
-0.05615234375,
0.0721435546875,
0.01218414306640625,
-0.061065673828125,
0.00783538818359375,
-0.055206298828125,
-0.0162506103515625,
0.007244110107421875,
-0.00719451904296875,
-0.0504150390625,
-0.00036454200744628906,
0.024627685546875,
0.026611328125,
-0.01273345947265625,
0.0194854736328125,
-0.039337158203125,
-0.017791748046875,
0.0301055908203125,
-0.0013856887817382812,
0.0594482421875,
0.02117919921875,
-0.033477783203125,
-0.0008153915405273438,
-0.056793212890625,
0.0243682861328125,
0.0140533447265625,
-0.024566650390625,
0.0220947265625,
-0.0145721435546875,
-0.01479339599609375,
0.01352691650390625,
0.010223388671875,
-0.0472412109375,
0.032318115234375,
-0.035064697265625,
0.05975341796875,
0.0445556640625,
0.002811431884765625,
0.0304412841796875,
-0.01348114013671875,
0.0206756591796875,
0.00783538818359375,
0.0181427001953125,
0.001956939697265625,
-0.03948974609375,
-0.05572509765625,
-0.0294952392578125,
0.046295166015625,
0.0311737060546875,
-0.028778076171875,
0.03765869140625,
-0.024444580078125,
-0.038360595703125,
-0.05615234375,
0.0042266845703125,
0.029998779296875,
0.0107269287109375,
0.060455322265625,
-0.027191162109375,
-0.066650390625,
-0.06646728515625,
-0.0115203857421875,
0.006412506103515625,
-0.0159912109375,
0.002040863037109375,
0.05389404296875,
-0.0112762451171875,
0.0704345703125,
-0.03155517578125,
-0.0166168212890625,
-0.03204345703125,
-0.0004062652587890625,
0.03143310546875,
0.05230712890625,
0.01505279541015625,
-0.046722412109375,
-0.043243408203125,
-0.0159454345703125,
-0.06903076171875,
0.007686614990234375,
0.01300048828125,
0.00142669677734375,
0.006809234619140625,
0.020904541015625,
-0.054107666015625,
0.03717041015625,
0.02880859375,
-0.009765625,
0.0285186767578125,
-0.031951904296875,
-0.00839996337890625,
-0.0821533203125,
0.023681640625,
0.00409698486328125,
-0.0202178955078125,
-0.062042236328125,
-0.01200103759765625,
0.00824737548828125,
0.0006351470947265625,
-0.04541015625,
0.038177490234375,
-0.052825927734375,
-0.014007568359375,
-0.00457000732421875,
-0.01128387451171875,
0.01108551025390625,
0.0462646484375,
0.0036182403564453125,
0.042083740234375,
0.0287933349609375,
-0.042510986328125,
0.0029354095458984375,
0.028106689453125,
-0.016326904296875,
-0.0227508544921875,
-0.07220458984375,
0.0160675048828125,
-0.00891876220703125,
0.0267791748046875,
-0.053955078125,
-0.012939453125,
0.0269775390625,
-0.05511474609375,
0.0352783203125,
-0.014923095703125,
-0.0234375,
-0.0384521484375,
-0.033294677734375,
0.0178680419921875,
0.057769775390625,
-0.02001953125,
0.04193115234375,
0.0298919677734375,
0.01033782958984375,
-0.048614501953125,
-0.06353759765625,
-0.02166748046875,
-0.0027790069580078125,
-0.03973388671875,
0.04656982421875,
0.005706787109375,
0.00946044921875,
-0.0087738037109375,
-0.024078369140625,
0.02044677734375,
-0.0249481201171875,
0.0263214111328125,
0.00318145751953125,
0.0024318695068359375,
-0.0049896240234375,
-0.008514404296875,
-0.0101776123046875,
-0.0123138427734375,
-0.052459716796875,
0.05426025390625,
-0.0172576904296875,
-0.00640106201171875,
-0.04296875,
0.0210418701171875,
0.03997802734375,
-0.0232086181640625,
0.060638427734375,
0.058441162109375,
-0.04156494140625,
0.00024008750915527344,
-0.032684326171875,
-0.034332275390625,
-0.038299560546875,
0.040802001953125,
-0.02313232421875,
-0.04571533203125,
0.04180908203125,
0.005306243896484375,
-0.006542205810546875,
0.043243408203125,
0.028106689453125,
-0.0218353271484375,
0.06640625,
0.05487060546875,
0.02587890625,
0.0283966064453125,
-0.0718994140625,
0.0313720703125,
-0.07220458984375,
-0.03680419921875,
-0.028076171875,
-0.03692626953125,
-0.046417236328125,
-0.039154052734375,
0.03961181640625,
0.0335693359375,
-0.0322265625,
0.03924560546875,
-0.0384521484375,
0.022247314453125,
0.054962158203125,
0.03607177734375,
-0.002899169921875,
0.0242919921875,
-0.023651123046875,
-0.003078460693359375,
-0.07135009765625,
-0.04412841796875,
0.0970458984375,
0.0362548828125,
0.0484619140625,
0.0013418197631835938,
0.054046630859375,
0.026702880859375,
0.00778961181640625,
-0.042724609375,
0.0288848876953125,
-0.0377197265625,
-0.0330810546875,
-0.0167083740234375,
-0.0274810791015625,
-0.06854248046875,
-0.0011320114135742188,
-0.01458740234375,
-0.06646728515625,
0.04364013671875,
0.01265716552734375,
-0.0413818359375,
0.033721923828125,
-0.05712890625,
0.07952880859375,
-0.005344390869140625,
-0.029083251953125,
0.01200103759765625,
-0.066162109375,
-0.0021953582763671875,
0.01068115234375,
0.01322174072265625,
0.006328582763671875,
0.0208587646484375,
0.08642578125,
-0.04217529296875,
0.0711669921875,
-0.01556396484375,
0.01435089111328125,
0.02789306640625,
0.010009765625,
0.036102294921875,
0.0021190643310546875,
-0.006175994873046875,
0.02581787109375,
0.0157012939453125,
-0.041748046875,
-0.0258636474609375,
0.0266571044921875,
-0.07867431640625,
-0.028564453125,
-0.0293121337890625,
-0.029022216796875,
0.00798797607421875,
0.022247314453125,
0.050994873046875,
0.034698486328125,
0.018768310546875,
0.0269775390625,
0.061676025390625,
-0.025909423828125,
0.04229736328125,
0.0170135498046875,
-0.00862884521484375,
-0.04949951171875,
0.052886962890625,
0.024566650390625,
0.0192108154296875,
0.03961181640625,
0.00820159912109375,
-0.03936767578125,
-0.04498291015625,
-0.022491455078125,
0.0308074951171875,
-0.051239013671875,
-0.0258941650390625,
-0.07635498046875,
-0.0258636474609375,
-0.046295166015625,
-0.0021820068359375,
-0.047454833984375,
-0.03497314453125,
-0.0205230712890625,
-0.0087738037109375,
0.02435302734375,
0.043975830078125,
-0.02392578125,
0.01386260986328125,
-0.07073974609375,
0.01442718505859375,
0.00909423828125,
-0.0026721954345703125,
-0.01552581787109375,
-0.0653076171875,
-0.022857666015625,
0.022552490234375,
-0.03338623046875,
-0.0836181640625,
0.052337646484375,
0.045989990234375,
0.045989990234375,
0.0097198486328125,
0.005706787109375,
0.036651611328125,
-0.0170135498046875,
0.0604248046875,
0.0009479522705078125,
-0.06402587890625,
0.0406494140625,
0.00099945068359375,
0.0271148681640625,
0.0206756591796875,
0.05230712890625,
-0.021697998046875,
-0.018890380859375,
-0.06268310546875,
-0.07586669921875,
0.050750732421875,
0.0261688232421875,
-0.018768310546875,
-0.002521514892578125,
0.0484619140625,
0.00946807861328125,
0.0063934326171875,
-0.0714111328125,
-0.02935791015625,
-0.03271484375,
-0.037506103515625,
0.0011148452758789062,
-0.0190582275390625,
0.002162933349609375,
-0.0322265625,
0.058441162109375,
-0.0161895751953125,
0.059295654296875,
0.045654296875,
-0.037872314453125,
-0.0027980804443359375,
0.005344390869140625,
0.0308380126953125,
0.042144775390625,
-0.0479736328125,
0.0205841064453125,
0.006755828857421875,
-0.060028076171875,
0.0015811920166015625,
0.017333984375,
-0.01535797119140625,
-0.0074920654296875,
0.039459228515625,
0.0555419921875,
-0.0001360177993774414,
-0.03460693359375,
0.0186309814453125,
0.01380157470703125,
-0.0130157470703125,
-0.007511138916015625,
-0.004375457763671875,
0.01293182373046875,
0.03265380859375,
0.046875,
-0.016326904296875,
0.0013637542724609375,
-0.034332275390625,
0.0316162109375,
0.0108489990234375,
-0.0197296142578125,
-0.04254150390625,
0.0550537109375,
-0.00606536865234375,
-0.01168060302734375,
0.058868408203125,
-0.0237884521484375,
-0.045867919921875,
0.047943115234375,
0.053314208984375,
0.06982421875,
-0.01126861572265625,
0.01702880859375,
0.0555419921875,
0.0134124755859375,
-0.00876617431640625,
0.024749755859375,
0.0157470703125,
-0.055206298828125,
-0.017303466796875,
-0.08416748046875,
-0.0047607421875,
0.01195526123046875,
-0.034271240234375,
0.01497650146484375,
-0.03533935546875,
-0.0164794921875,
0.005947113037109375,
0.021881103515625,
-0.047882080078125,
0.01117706298828125,
0.0105438232421875,
0.06683349609375,
-0.06146240234375,
0.087890625,
0.06317138671875,
-0.051300048828125,
-0.0518798828125,
-0.012725830078125,
-0.0109405517578125,
-0.049041748046875,
0.054229736328125,
0.0270233154296875,
0.009246826171875,
0.025909423828125,
-0.0413818359375,
-0.072021484375,
0.0982666015625,
0.035797119140625,
-0.056396484375,
-0.020599365234375,
0.0196685791015625,
0.040740966796875,
-0.0281219482421875,
0.032318115234375,
0.044403076171875,
0.023193359375,
0.0009636878967285156,
-0.057861328125,
0.0106964111328125,
-0.0237274169921875,
-0.00536346435546875,
0.003154754638671875,
-0.046875,
0.0736083984375,
-0.0257568359375,
-0.016845703125,
-0.0149688720703125,
0.062347412109375,
0.02227783203125,
-0.01049041748046875,
-0.0014057159423828125,
0.04681396484375,
0.05438232421875,
-0.0074462890625,
0.0709228515625,
-0.0284271240234375,
0.05108642578125,
0.0654296875,
0.00791168212890625,
0.060272216796875,
0.04339599609375,
-0.042816162109375,
0.029571533203125,
0.057861328125,
-0.0059661865234375,
0.04656982421875,
0.0171356201171875,
0.00604248046875,
-0.0196685791015625,
0.0051116943359375,
-0.04278564453125,
0.0170440673828125,
0.02886962890625,
-0.03375244140625,
-0.0015764236450195312,
0.0015916824340820312,
0.0008978843688964844,
-0.0250244140625,
0.0007538795471191406,
0.041168212890625,
0.021331787109375,
-0.0158538818359375,
0.07012939453125,
0.00466156005859375,
0.052398681640625,
-0.046875,
0.003780364990234375,
-0.03265380859375,
0.0245208740234375,
-0.017486572265625,
-0.046875,
0.0192108154296875,
-0.01134490966796875,
-0.012115478515625,
0.00443267822265625,
0.039825439453125,
-0.0352783203125,
-0.032501220703125,
0.0249176025390625,
0.018768310546875,
0.0256195068359375,
-0.00797271728515625,
-0.06103515625,
0.010406494140625,
0.007122039794921875,
-0.03778076171875,
0.019561767578125,
0.008941650390625,
0.01050567626953125,
0.0555419921875,
0.038787841796875,
-0.005420684814453125,
0.01540374755859375,
-0.018310546875,
0.05712890625,
-0.058685302734375,
-0.015625,
-0.0673828125,
0.0465087890625,
0.0038585662841796875,
-0.00946044921875,
0.0312347412109375,
0.048828125,
0.07244873046875,
-0.0271148681640625,
0.046966552734375,
-0.031585693359375,
0.009002685546875,
-0.035980224609375,
0.052947998046875,
-0.04193115234375,
0.009002685546875,
-0.002452850341796875,
-0.07269287109375,
-0.033782958984375,
0.059722900390625,
-0.0158843994140625,
0.019683837890625,
0.06317138671875,
0.06964111328125,
-0.0040435791015625,
-0.00485992431640625,
0.01311492919921875,
0.0360107421875,
0.042144775390625,
0.058258056640625,
0.0091094970703125,
-0.06939697265625,
0.038116455078125,
-0.034271240234375,
-0.00887298583984375,
-0.021148681640625,
-0.06317138671875,
-0.060333251953125,
-0.04156494140625,
-0.0310821533203125,
-0.037384033203125,
0.0243072509765625,
0.08843994140625,
0.06219482421875,
-0.07733154296875,
-0.01436614990234375,
-0.0097808837890625,
-0.023834228515625,
-0.01331329345703125,
-0.014312744140625,
0.056549072265625,
-0.004100799560546875,
-0.04998779296875,
0.0269012451171875,
0.01428985595703125,
0.025787353515625,
-0.00750732421875,
-0.0194091796875,
-0.04962158203125,
-0.006755828857421875,
0.03277587890625,
0.046661376953125,
-0.0511474609375,
-0.0211181640625,
0.01015472412109375,
-0.0041656494140625,
0.0214691162109375,
0.0272369384765625,
-0.05712890625,
0.029510498046875,
0.0452880859375,
0.034088134765625,
0.056976318359375,
-0.017120361328125,
0.04840087890625,
-0.051483154296875,
0.006252288818359375,
0.00702667236328125,
0.0250244140625,
0.0288543701171875,
-0.0247344970703125,
0.035919189453125,
0.03643798828125,
-0.0382080078125,
-0.058349609375,
0.0020198822021484375,
-0.06781005859375,
-0.020233154296875,
0.0811767578125,
-0.01654052734375,
-0.04449462890625,
0.012603759765625,
0.00667572021484375,
0.059417724609375,
-0.0194244384765625,
0.054656982421875,
0.02972412109375,
-0.01403045654296875,
-0.0231170654296875,
-0.040863037109375,
0.058746337890625,
0.03271484375,
-0.04119873046875,
-0.005107879638671875,
-0.002838134765625,
0.03717041015625,
0.00850677490234375,
0.0289306640625,
-0.02960205078125,
0.0127105712890625,
0.0009479522705078125,
0.0406494140625,
-0.029937744140625,
-0.0305938720703125,
-0.0213775634765625,
0.0189208984375,
-0.00923919677734375,
-0.01336669921875
]
] |
TheBloke/MythoMax-L2-13B-GPTQ | 2023-09-27T12:45:40.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"en",
"license:other",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/MythoMax-L2-13B-GPTQ | 86 | 44,933 | transformers | 2023-08-11T07:27:24 | ---
language:
- en
license: other
model_name: MythoMax L2 13B
base_model: Gryphe/MythoMax-L2-13b
inference: false
model_creator: Gryphe
model_type: llama
prompt_template: '```
{system_message}
### Instruction:
{prompt}
(For roleplay purposes, I suggest the following - Write <CHAR NAME>''s next reply
in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.)
### Response:
```
'
quantized_by: TheBloke
---
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# MythoMax L2 13B - GPTQ
- Model creator: [Gryphe](https://huggingface.co/Gryphe)
- Original model: [MythoMax L2 13B](https://huggingface.co/Gryphe/MythoMax-L2-13b)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Gryphe's MythoMax L2 13B](https://huggingface.co/Gryphe/MythoMax-L2-13b).
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/MythoMax-L2-13B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF)
* [Gryphe's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Gryphe/MythoMax-L2-13b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Custom
```
{system_message}
### Instruction:
{prompt}
(For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.)
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Gryphe's MythoMax L2 13B](https://huggingface.co/Gryphe/MythoMax-L2-13b).
<!-- licensing end -->
<!-- README_GPTQ.md-provided-files start -->
## Provided files and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the `main` branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
<details>
<summary>Explanation of GPTQ parameters</summary>
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, without Act Order and group size 128g. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 8.00 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.51 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
| [gptq-4bit-128g-actorder_True](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.26 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 13.65 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download from branches
- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/MythoMax-L2-13B-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ
```
- In Python Transformers code, the branch is the `revision` parameter; see below.
<!-- README_GPTQ.md-download-from-branches end -->
<!-- README_GPTQ.md-text-generation-webui start -->
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
1. Click the **Model tab**.
2. Under **Download custom model or LoRA**, enter `TheBloke/MythoMax-L2-13B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/MythoMax-L2-13B-GPTQ:main`
- see Provided Files above for the list of branches for each option.
3. Click **Download**.
4. The model will start downloading. Once it's finished it will say "Done".
5. In the top left, click the refresh icon next to **Model**.
6. In the **Model** dropdown, choose the model you just downloaded: `MythoMax-L2-13B-GPTQ`
7. The model will automatically load, and is now ready for use!
8. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
* Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
9. Once you're ready, click the **Text Generation tab** and enter a prompt to get started!
<!-- README_GPTQ.md-text-generation-webui end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers>=4.32.0 optimum>=1.12.0
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
```
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
pip3 install .
```
### For CodeLlama models only: you must use Transformers 4.33.0 or later.
If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
```shell
pip3 uninstall -y transformers
pip3 install git+https://github.com/huggingface/transformers.git
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/MythoMax-L2-13B-GPTQ"
# To use a different branch, change revision
# For example: revision="main"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
```
<!-- README_GPTQ.md-use-from-python end -->
<!-- README_GPTQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with [Occ4m's GPTQ-for-LLaMa fork](https://github.com/0cc4m/KoboldAI).
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
[Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) is compatible with all GPTQ models.
<!-- README_GPTQ.md-compatibility end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: Gryphe's MythoMax L2 13B
An improved, potentially even perfected variant of MythoMix, my [MythoLogic-L2](https://huggingface.co/Gryphe/MythoLogic-L2-13b) and [Huginn](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model, resulting in increased coherency across the entire structure.
The script and the acccompanying templates I used to produce both can [be found here](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML).
This model is proficient at both roleplaying and storywriting due to its unique nature.
Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoMax-L2-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ) (You're the best!)
## Model details
The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time)
This type of merge is incapable of being illustrated, as each of its 363 tensors had an unique ratio applied to it. As with my prior merges, gradients were part of these ratios to further finetune its behaviour.
## Prompt Format
This model primarily uses Alpaca formatting, so for optimal model performance, use:
```
<System prompt/Character Card>
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
```
---
license: other
---
| 17,650 | [
[
-0.037322998046875,
-0.050079345703125,
0.01424407958984375,
0.0137939453125,
-0.0258026123046875,
-0.006389617919921875,
0.007526397705078125,
-0.045196533203125,
0.0192413330078125,
0.0300445556640625,
-0.0455322265625,
-0.037200927734375,
-0.0305633544921875,
-0.006313323974609375,
-0.0180206298828125,
0.086669921875,
0.00652313232421875,
-0.0261383056640625,
-0.0135955810546875,
-0.0305023193359375,
-0.0212860107421875,
-0.037841796875,
-0.055938720703125,
-0.016754150390625,
0.0310821533203125,
0.0110626220703125,
0.07183837890625,
0.04803466796875,
0.0136871337890625,
0.022186279296875,
-0.01045989990234375,
-0.00087738037109375,
-0.038330078125,
-0.0144195556640625,
0.01255035400390625,
-0.024078369140625,
-0.049407958984375,
0.01393890380859375,
0.036346435546875,
0.0118865966796875,
-0.0304718017578125,
0.02239990234375,
0.004070281982421875,
0.04522705078125,
-0.032989501953125,
0.01267242431640625,
-0.021453857421875,
0.00621795654296875,
-0.0125274658203125,
0.01311492919921875,
-0.007671356201171875,
-0.039337158203125,
0.00904083251953125,
-0.06756591796875,
0.00832366943359375,
0.0042572021484375,
0.08563232421875,
0.014739990234375,
-0.047088623046875,
0.01078033447265625,
-0.024688720703125,
0.046173095703125,
-0.07318115234375,
0.0242767333984375,
0.039947509765625,
0.0172119140625,
-0.0082244873046875,
-0.0692138671875,
-0.043243408203125,
-0.004505157470703125,
-0.017333984375,
0.0222320556640625,
-0.037750244140625,
-0.0003211498260498047,
0.0357666015625,
0.055328369140625,
-0.06591796875,
-0.00865936279296875,
-0.0249481201171875,
-0.01947021484375,
0.0655517578125,
0.01314544677734375,
0.0259246826171875,
-0.015838623046875,
-0.030975341796875,
-0.0322265625,
-0.048431396484375,
0.007080078125,
0.0255126953125,
-0.0012226104736328125,
-0.049041748046875,
0.038177490234375,
-0.0168304443359375,
0.036529541015625,
0.01165008544921875,
-0.021270751953125,
0.033843994140625,
-0.042236328125,
-0.033843994140625,
-0.0252532958984375,
0.09112548828125,
0.03680419921875,
-0.016754150390625,
0.017669677734375,
-0.0022754669189453125,
-0.0047607421875,
-0.00473785400390625,
-0.07244873046875,
-0.02728271484375,
0.0293121337890625,
-0.040374755859375,
-0.0236053466796875,
-0.0098724365234375,
-0.056427001953125,
-0.01146697998046875,
-0.00792694091796875,
0.037689208984375,
-0.04345703125,
-0.036407470703125,
0.00841522216796875,
-0.0301055908203125,
0.032989501953125,
0.0232696533203125,
-0.044403076171875,
0.0428466796875,
0.028076171875,
0.054779052734375,
0.0089569091796875,
-0.00887298583984375,
-0.0156097412109375,
0.005794525146484375,
-0.01007080078125,
0.029205322265625,
-0.017303466796875,
-0.0316162109375,
-0.0288848876953125,
0.01448822021484375,
0.0041656494140625,
-0.020111083984375,
0.04205322265625,
-0.0230255126953125,
0.04034423828125,
-0.037322998046875,
-0.04449462890625,
-0.0310211181640625,
0.0020294189453125,
-0.049407958984375,
0.0936279296875,
0.0374755859375,
-0.0634765625,
0.016326904296875,
-0.0360107421875,
-0.00864410400390625,
0.0009336471557617188,
0.0006666183471679688,
-0.0374755859375,
-0.0091400146484375,
0.00966644287109375,
0.0215606689453125,
-0.034149169921875,
0.00701904296875,
-0.0283966064453125,
-0.01372528076171875,
0.0098876953125,
-0.033294677734375,
0.0950927734375,
0.0164794921875,
-0.0311431884765625,
-0.00792694091796875,
-0.050506591796875,
0.01070404052734375,
0.032196044921875,
-0.0097808837890625,
-0.008270263671875,
-0.0156402587890625,
0.01032257080078125,
0.01904296875,
0.0154266357421875,
-0.024017333984375,
0.03558349609375,
-0.014129638671875,
0.045135498046875,
0.04473876953125,
0.0016946792602539062,
0.01551055908203125,
-0.031951904296875,
0.0416259765625,
-0.0003535747528076172,
0.044677734375,
0.01187896728515625,
-0.05975341796875,
-0.04425048828125,
-0.0277252197265625,
0.0272979736328125,
0.048553466796875,
-0.04583740234375,
0.03271484375,
-0.00827789306640625,
-0.05389404296875,
-0.0284271240234375,
-0.0098419189453125,
0.033294677734375,
0.0303955078125,
0.03387451171875,
-0.034423828125,
-0.023468017578125,
-0.07318115234375,
0.007354736328125,
-0.035919189453125,
0.0006403923034667969,
0.039703369140625,
0.049285888671875,
-0.017852783203125,
0.05548095703125,
-0.0504150390625,
-0.004627227783203125,
0.0035533905029296875,
0.007205963134765625,
0.0274505615234375,
0.04046630859375,
0.06658935546875,
-0.05950927734375,
-0.043792724609375,
-0.00293731689453125,
-0.04833984375,
-0.007427215576171875,
0.00008928775787353516,
-0.0241241455078125,
0.02081298828125,
-0.0063629150390625,
-0.088134765625,
0.050872802734375,
0.040618896484375,
-0.05120849609375,
0.06243896484375,
-0.01412200927734375,
0.015167236328125,
-0.08636474609375,
0.006320953369140625,
0.00994873046875,
-0.0256805419921875,
-0.033294677734375,
0.008941650390625,
-0.0028858184814453125,
0.01172637939453125,
-0.0243072509765625,
0.050201416015625,
-0.03594970703125,
-0.004161834716796875,
0.004970550537109375,
-0.0123443603515625,
0.01678466796875,
0.039215087890625,
-0.0079498291015625,
0.06243896484375,
0.042999267578125,
-0.0300445556640625,
0.0478515625,
0.030670166015625,
-0.0002560615539550781,
0.0293731689453125,
-0.06427001953125,
0.01108551025390625,
0.01421356201171875,
0.03350830078125,
-0.06903076171875,
-0.022125244140625,
0.04571533203125,
-0.04425048828125,
0.032012939453125,
-0.027740478515625,
-0.036773681640625,
-0.03582763671875,
-0.0401611328125,
0.0288848876953125,
0.067138671875,
-0.0294189453125,
0.03204345703125,
0.0333251953125,
0.007080078125,
-0.05194091796875,
-0.049041748046875,
-0.01009368896484375,
-0.03155517578125,
-0.047271728515625,
0.0322265625,
-0.0084075927734375,
-0.005222320556640625,
0.00772857666015625,
-0.00411224365234375,
-0.00978851318359375,
-0.00910186767578125,
0.026458740234375,
0.02716064453125,
-0.0129852294921875,
-0.0100250244140625,
0.011627197265625,
-0.002674102783203125,
0.0029888153076171875,
-0.0277557373046875,
0.028656005859375,
-0.0171356201171875,
0.0018596649169921875,
-0.03857421875,
0.0182952880859375,
0.04351806640625,
-0.00202178955078125,
0.05438232421875,
0.058074951171875,
-0.0289764404296875,
0.01383209228515625,
-0.04083251953125,
-0.00980377197265625,
-0.035552978515625,
0.00872802734375,
-0.0181732177734375,
-0.061126708984375,
0.043121337890625,
0.031890869140625,
0.0089263916015625,
0.059844970703125,
0.035736083984375,
-0.002044677734375,
0.07177734375,
0.0316162109375,
-0.0169219970703125,
0.0229034423828125,
-0.035491943359375,
-0.0162353515625,
-0.057464599609375,
-0.01332855224609375,
-0.0238037109375,
-0.0167694091796875,
-0.06195068359375,
-0.043975830078125,
0.0274658203125,
0.016448974609375,
-0.050048828125,
0.0482177734375,
-0.048187255859375,
0.01427459716796875,
0.049163818359375,
0.0194854736328125,
0.01568603515625,
0.007965087890625,
-0.0120391845703125,
0.0048065185546875,
-0.0447998046875,
-0.019317626953125,
0.08575439453125,
0.03143310546875,
0.0447998046875,
0.0177154541015625,
0.033721923828125,
0.00994873046875,
0.0209808349609375,
-0.039093017578125,
0.04095458984375,
0.0031375885009765625,
-0.057464599609375,
-0.0219573974609375,
-0.047821044921875,
-0.0592041015625,
0.021514892578125,
-0.01021575927734375,
-0.0635986328125,
0.0300445556640625,
0.007076263427734375,
-0.025848388671875,
0.0238037109375,
-0.052947998046875,
0.07659912109375,
-0.006328582763671875,
-0.035003662109375,
-0.01209259033203125,
-0.061126708984375,
0.033111572265625,
0.0119781494140625,
-0.0010833740234375,
-0.00969696044921875,
-0.0145721435546875,
0.05975341796875,
-0.06329345703125,
0.05596923828125,
-0.01812744140625,
-0.0032787322998046875,
0.042388916015625,
-0.00737762451171875,
0.044036865234375,
0.01513671875,
0.006282806396484375,
0.0256805419921875,
0.031494140625,
-0.031890869140625,
-0.0304107666015625,
0.039337158203125,
-0.07427978515625,
-0.037628173828125,
-0.041717529296875,
-0.037567138671875,
-0.004573822021484375,
0.0037479400634765625,
0.037200927734375,
0.032806396484375,
-0.0005965232849121094,
0.006587982177734375,
0.05499267578125,
-0.023956298828125,
0.02642822265625,
0.0250396728515625,
-0.021575927734375,
-0.048492431640625,
0.058837890625,
0.003612518310546875,
0.0206146240234375,
0.0145721435546875,
0.01126861572265625,
-0.040863037109375,
-0.028839111328125,
-0.046417236328125,
0.035003662109375,
-0.032745361328125,
-0.029815673828125,
-0.0435791015625,
-0.017730712890625,
-0.031158447265625,
0.023406982421875,
-0.031097412109375,
-0.058502197265625,
-0.0308837890625,
-0.00738525390625,
0.06842041015625,
0.0323486328125,
-0.0220947265625,
0.0226593017578125,
-0.056976318359375,
0.017364501953125,
0.031982421875,
0.0199127197265625,
-0.010162353515625,
-0.05615234375,
-0.00014913082122802734,
0.011474609375,
-0.03631591796875,
-0.07659912109375,
0.043853759765625,
0.01070404052734375,
0.031890869140625,
0.0335693359375,
0.004558563232421875,
0.059539794921875,
-0.0190582275390625,
0.07208251953125,
0.0263824462890625,
-0.0653076171875,
0.037933349609375,
-0.0362548828125,
0.006744384765625,
0.0287933349609375,
0.04656982421875,
-0.03271484375,
-0.0209503173828125,
-0.0626220703125,
-0.055145263671875,
0.04180908203125,
0.03277587890625,
0.001110076904296875,
0.0180511474609375,
0.046478271484375,
0.0026950836181640625,
0.01268768310546875,
-0.06610107421875,
-0.053192138671875,
-0.027099609375,
-0.0070648193359375,
0.00732421875,
-0.016204833984375,
-0.032958984375,
-0.051910400390625,
0.06781005859375,
-0.0111236572265625,
0.0482177734375,
0.01641845703125,
0.0171356201171875,
-0.006107330322265625,
0.0024433135986328125,
0.0273590087890625,
0.050872802734375,
-0.020263671875,
-0.015869140625,
0.01323699951171875,
-0.05975341796875,
0.00934600830078125,
0.032562255859375,
-0.008209228515625,
-0.01103973388671875,
0.01416015625,
0.0667724609375,
-0.0077972412109375,
-0.023834228515625,
0.03753662109375,
-0.020599365234375,
-0.0301055908203125,
-0.01470947265625,
0.01465606689453125,
0.017364501953125,
0.031707763671875,
0.024749755859375,
-0.015777587890625,
0.024383544921875,
-0.038116455078125,
0.01462554931640625,
0.040557861328125,
-0.017242431640625,
-0.0293731689453125,
0.0625,
-0.00875091552734375,
0.01468658447265625,
0.05029296875,
-0.0212860107421875,
-0.0286712646484375,
0.0594482421875,
0.03875732421875,
0.054107666015625,
-0.0180511474609375,
0.0256500244140625,
0.042449951171875,
0.0169830322265625,
-0.002849578857421875,
0.0262603759765625,
-0.004390716552734375,
-0.042694091796875,
-0.0251922607421875,
-0.040618896484375,
-0.01922607421875,
0.02008056640625,
-0.0635986328125,
0.00858306884765625,
-0.029571533203125,
-0.033172607421875,
-0.0116424560546875,
0.0257720947265625,
-0.038177490234375,
0.0258941650390625,
0.0118560791015625,
0.07794189453125,
-0.058837890625,
0.06610107421875,
0.04541015625,
-0.0301513671875,
-0.07696533203125,
-0.018707275390625,
0.01702880859375,
-0.050079345703125,
0.0116424560546875,
-0.0029964447021484375,
0.0245513916015625,
-0.0017309188842773438,
-0.056060791015625,
-0.07244873046875,
0.11529541015625,
0.0250396728515625,
-0.040130615234375,
-0.002513885498046875,
0.0003268718719482422,
0.031494140625,
-0.0084686279296875,
0.049835205078125,
0.04583740234375,
0.030303955078125,
0.01959228515625,
-0.075439453125,
0.035308837890625,
-0.0290374755859375,
-0.0011911392211914062,
0.013214111328125,
-0.07861328125,
0.07098388671875,
-0.0005130767822265625,
-0.01372528076171875,
0.00951385498046875,
0.047882080078125,
0.037322998046875,
0.0102996826171875,
0.032989501953125,
0.07379150390625,
0.06170654296875,
-0.0228271484375,
0.095458984375,
-0.01053619384765625,
0.048370361328125,
0.05975341796875,
0.0036163330078125,
0.04656982421875,
0.018768310546875,
-0.05511474609375,
0.038299560546875,
0.07525634765625,
-0.00403594970703125,
0.028076171875,
-0.00201416015625,
-0.023468017578125,
-0.0119781494140625,
0.00940704345703125,
-0.0648193359375,
0.002574920654296875,
0.028167724609375,
-0.0179595947265625,
0.005626678466796875,
-0.017578125,
0.010833740234375,
-0.049835205078125,
-0.01201629638671875,
0.038421630859375,
0.022796630859375,
-0.0157012939453125,
0.060089111328125,
-0.00829315185546875,
0.043304443359375,
-0.04705810546875,
-0.0058746337890625,
-0.0333251953125,
-0.0088958740234375,
-0.021331787109375,
-0.061279296875,
0.01067352294921875,
-0.0160980224609375,
-0.00832366943359375,
0.0010652542114257812,
0.050567626953125,
-0.012481689453125,
-0.03436279296875,
0.0273895263671875,
0.032135009765625,
0.02117919921875,
-0.00443267822265625,
-0.08441162109375,
0.0167694091796875,
0.00022792816162109375,
-0.05120849609375,
0.033447265625,
0.0285491943359375,
0.00801849365234375,
0.055816650390625,
0.041290283203125,
-0.00982666015625,
-0.0018177032470703125,
-0.019012451171875,
0.07781982421875,
-0.05438232421875,
-0.0242462158203125,
-0.0550537109375,
0.045806884765625,
-0.011962890625,
-0.0374755859375,
0.059295654296875,
0.047149658203125,
0.04986572265625,
0.004489898681640625,
0.052734375,
-0.03265380859375,
0.01898193359375,
-0.0257110595703125,
0.050537109375,
-0.059417724609375,
0.0031299591064453125,
-0.0259246826171875,
-0.061279296875,
-0.00531768798828125,
0.046722412109375,
-0.007785797119140625,
0.0138092041015625,
0.034423828125,
0.060882568359375,
-0.0041046142578125,
0.01161956787109375,
0.00921630859375,
0.032470703125,
0.00458526611328125,
0.06597900390625,
0.057769775390625,
-0.06787109375,
0.0340576171875,
-0.0335693359375,
-0.02728271484375,
-0.0017957687377929688,
-0.058746337890625,
-0.053070068359375,
-0.0374755859375,
-0.05126953125,
-0.05029296875,
-0.0001646280288696289,
0.06494140625,
0.06402587890625,
-0.050628662109375,
-0.02508544921875,
0.0009102821350097656,
0.00542449951171875,
-0.0255584716796875,
-0.0225372314453125,
0.0302734375,
0.022247314453125,
-0.04583740234375,
0.01120758056640625,
0.006137847900390625,
0.021514892578125,
-0.002895355224609375,
-0.0261993408203125,
-0.0113372802734375,
-0.00049591064453125,
0.04541015625,
0.040985107421875,
-0.04364013671875,
-0.011474609375,
-0.0131988525390625,
-0.008636474609375,
0.016143798828125,
0.021759033203125,
-0.05596923828125,
-0.0010585784912109375,
0.0322265625,
0.01349639892578125,
0.0650634765625,
0.004962921142578125,
0.0256500244140625,
-0.03131103515625,
0.00907135009765625,
0.007015228271484375,
0.021331787109375,
-0.00035071372985839844,
-0.040618896484375,
0.054931640625,
0.04083251953125,
-0.04638671875,
-0.059783935546875,
-0.0079345703125,
-0.09405517578125,
-0.0165252685546875,
0.08642578125,
-0.0078125,
-0.0219268798828125,
0.0088958740234375,
-0.018768310546875,
0.0219879150390625,
-0.0313720703125,
0.019378662109375,
0.037506103515625,
-0.0211181640625,
-0.032989501953125,
-0.06036376953125,
0.0496826171875,
0.016998291015625,
-0.061859130859375,
-0.0038509368896484375,
0.04742431640625,
0.037689208984375,
0.00406646728515625,
0.061370849609375,
-0.022918701171875,
0.02972412109375,
0.0056915283203125,
0.004749298095703125,
0.0009813308715820312,
0.007495880126953125,
-0.02386474609375,
-0.0008654594421386719,
-0.0224609375,
-0.00009733438491821289
]
] |
yuvalkirstain/PickScore_v1 | 2023-05-08T08:32:12.000Z | [
"transformers",
"pytorch",
"safetensors",
"clip",
"zero-shot-image-classification",
"arxiv:2305.01569",
"endpoints_compatible",
"has_space",
"region:us"
] | zero-shot-image-classification | yuvalkirstain | null | null | yuvalkirstain/PickScore_v1 | 17 | 44,877 | transformers | 2023-04-24T08:08:20 | # Model Card for PickScore v1
This model is a scoring function for images generated from text. It takes as input a prompt and a generated image and outputs a score.
It can be used as a general scoring function, and for tasks such as human preference prediction, model evaluation, image ranking, and more.
See our paper [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://arxiv.org/abs/2305.01569) for more details.
## Model Details
### Model Description
This model was finetuned from CLIP-H using the [Pick-a-Pic dataset](https://huggingface.co/datasets/yuvalkirstain/pickapic_v1).
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [See the PickScore repo](https://github.com/yuvalkirstain/PickScore)
- **Paper:** [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://arxiv.org/abs/2305.01569).
- **Demo [optional]:** [Huggingface Spaces demo for PickScore](https://huggingface.co/spaces/yuvalkirstain/PickScore)
## How to Get Started with the Model
Use the code below to get started with the model.
```python
# import
from transformers import AutoProcessor, AutoModel
# load model
device = "cuda"
processor_name_or_path = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K"
model_pretrained_name_or_path = "yuvalkirstain/PickScore_v1"
processor = AutoProcessor.from_pretrained(processor_name_or_path)
model = AutoModel.from_pretrained(model_pretrained_name_or_path).eval().to(device)
def calc_probs(prompt, images):
# preprocess
image_inputs = processor(
images=images,
padding=True,
truncation=True,
max_length=77,
return_tensors="pt",
).to(device)
text_inputs = processor(
text=prompt,
padding=True,
truncation=True,
max_length=77,
return_tensors="pt",
).to(device)
with torch.no_grad():
# embed
image_embs = model.get_image_features(**image_inputs)
image_embs = image_embs / torch.norm(image_embs, dim=-1, keepdim=True)
text_embs = model.get_text_features(**text_inputs)
text_embs = text_embs / torch.norm(text_embs, dim=-1, keepdim=True)
# score
scores = model.logit_scale.exp() * (text_embs @ image_embs.T)[0]
# get probabilities if you have multiple images to choose from
probs = torch.softmax(scores, dim=-1)
return probs.cpu().tolist()
pil_images = [Image.open("my_amazing_images/1.jpg"), Image.open("my_amazing_images/2.jpg")]
prompt = "fantastic, increadible prompt"
print(calc_probs(prompt, pil_images))
```
## Training Details
### Training Data
This model was trained on the [Pick-a-Pic dataset](https://huggingface.co/datasets/yuvalkirstain/pickapic_v1).
### Training Procedure
TODO - add paper.
## Citation [optional]
If you find this work useful, please cite:
```bibtex
@inproceedings{Kirstain2023PickaPicAO,
title={Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation},
author={Yuval Kirstain and Adam Polyak and Uriel Singer and Shahbuland Matiana and Joe Penna and Omer Levy},
year={2023}
}
```
**APA:**
[More Information Needed]
| 3,227 | [
[
-0.030426025390625,
-0.055572509765625,
0.027252197265625,
0.003009796142578125,
-0.03289794921875,
-0.0204620361328125,
-0.00867462158203125,
-0.03497314453125,
0.0093841552734375,
0.017974853515625,
-0.047943115234375,
-0.047088623046875,
-0.04742431640625,
-0.01531982421875,
-0.0099639892578125,
0.0789794921875,
-0.00479888916015625,
-0.0010662078857421875,
-0.02203369140625,
-0.0045623779296875,
-0.0298309326171875,
-0.021575927734375,
-0.05908203125,
-0.011810302734375,
0.0166168212890625,
0.03509521484375,
0.04241943359375,
0.041717529296875,
0.055450439453125,
0.02545166015625,
-0.001003265380859375,
0.0007729530334472656,
-0.0278167724609375,
0.0008754730224609375,
0.007259368896484375,
-0.041595458984375,
-0.0276641845703125,
0.0360107421875,
0.03985595703125,
-0.00812530517578125,
0.0140228271484375,
0.040191650390625,
-0.01486968994140625,
0.018829345703125,
-0.0283660888671875,
0.00733184814453125,
-0.046905517578125,
0.01396942138671875,
-0.01177215576171875,
-0.0125885009765625,
-0.0268096923828125,
-0.039093017578125,
0.0098724365234375,
-0.035003662109375,
0.025482177734375,
-0.0030498504638671875,
0.095458984375,
0.016815185546875,
-0.0088653564453125,
-0.01739501953125,
-0.026336669921875,
0.058502197265625,
-0.041717529296875,
-0.007415771484375,
0.0233612060546875,
0.02728271484375,
0.0168609619140625,
-0.048858642578125,
-0.0292816162109375,
-0.015228271484375,
0.004276275634765625,
0.0200653076171875,
-0.00896453857421875,
-0.009307861328125,
0.04052734375,
0.02410888671875,
-0.0196075439453125,
0.00211334228515625,
-0.05511474609375,
-0.0210113525390625,
0.06500244140625,
0.0083770751953125,
0.036773681640625,
-0.02020263671875,
-0.037628173828125,
-0.0304412841796875,
-0.0225372314453125,
0.026153564453125,
0.031982421875,
0.0063323974609375,
-0.02703857421875,
0.05029296875,
0.01107025146484375,
0.052215576171875,
0.0223541259765625,
-0.0207366943359375,
0.042724609375,
-0.00856781005859375,
-0.01580810546875,
-0.01355743408203125,
0.0745849609375,
0.04229736328125,
0.0174407958984375,
0.0241546630859375,
-0.00829315185546875,
-0.0038814544677734375,
0.00550079345703125,
-0.07342529296875,
-0.03460693359375,
0.01436614990234375,
-0.044189453125,
-0.055908203125,
-0.004253387451171875,
-0.030364990234375,
-0.004611968994140625,
0.01267242431640625,
0.04522705078125,
-0.047149658203125,
-0.0083160400390625,
-0.01116180419921875,
-0.0303497314453125,
0.0211181640625,
0.0207977294921875,
-0.0516357421875,
0.003154754638671875,
-0.01123809814453125,
0.07403564453125,
-0.00949859619140625,
-0.037872314453125,
-0.02349853515625,
-0.022857666015625,
-0.0182952880859375,
0.08001708984375,
-0.016204833984375,
-0.03363037109375,
-0.02264404296875,
0.0012722015380859375,
-0.019317626953125,
-0.029754638671875,
0.050048828125,
-0.019561767578125,
0.034576416015625,
-0.00754547119140625,
-0.039581298828125,
-0.01020050048828125,
0.020294189453125,
-0.048553466796875,
0.0963134765625,
0.0144805908203125,
-0.06964111328125,
0.036895751953125,
-0.05792236328125,
-0.0158538818359375,
0.002803802490234375,
-0.009246826171875,
-0.0595703125,
0.005535125732421875,
0.022796630859375,
0.04364013671875,
-0.007610321044921875,
-0.004787445068359375,
-0.0440673828125,
-0.026275634765625,
0.0189056396484375,
-0.019317626953125,
0.07635498046875,
0.01039886474609375,
-0.004947662353515625,
0.012664794921875,
-0.041656494140625,
0.022674560546875,
0.046142578125,
-0.0224151611328125,
-0.002044677734375,
-0.0196533203125,
0.028564453125,
0.045074462890625,
0.0159454345703125,
-0.049407958984375,
0.0165863037109375,
-0.00428009033203125,
0.0258636474609375,
0.048431396484375,
-0.004047393798828125,
0.0313720703125,
-0.03289794921875,
0.03399658203125,
0.00899505615234375,
0.0228118896484375,
-0.0189971923828125,
-0.049896240234375,
-0.034271240234375,
-0.028839111328125,
0.0168609619140625,
0.040863037109375,
-0.048736572265625,
0.0384521484375,
0.0031585693359375,
-0.05621337890625,
-0.043304443359375,
-0.0085296630859375,
0.026458740234375,
0.0565185546875,
0.019317626953125,
-0.03753662109375,
-0.0304107666015625,
-0.07476806640625,
0.00019359588623046875,
-0.0020198822021484375,
-0.00228118896484375,
0.042877197265625,
0.0386962890625,
0.0126800537109375,
0.069580078125,
-0.04644775390625,
-0.02325439453125,
-0.0196380615234375,
-0.001983642578125,
0.03314208984375,
0.050537109375,
0.0753173828125,
-0.04449462890625,
-0.0325927734375,
-0.02947998046875,
-0.0537109375,
0.00676727294921875,
-0.001956939697265625,
-0.0181884765625,
0.0133209228515625,
0.0031566619873046875,
-0.059234619140625,
0.04449462890625,
0.0275115966796875,
-0.04266357421875,
0.07000732421875,
-0.02734375,
0.029449462890625,
-0.07989501953125,
0.01386260986328125,
0.0198516845703125,
-0.0142364501953125,
-0.029449462890625,
-0.0024127960205078125,
0.003459930419921875,
-0.00989532470703125,
-0.0618896484375,
0.068359375,
-0.0242462158203125,
-0.01107025146484375,
-0.01348876953125,
-0.0138702392578125,
0.0019626617431640625,
0.04400634765625,
0.02093505859375,
0.049072265625,
0.063720703125,
-0.041534423828125,
0.020843505859375,
0.04052734375,
-0.03497314453125,
0.04962158203125,
-0.0540771484375,
0.0182952880859375,
-0.0035858154296875,
0.0026397705078125,
-0.073974609375,
-0.0205078125,
0.01873779296875,
-0.056884765625,
0.0255126953125,
-0.014984130859375,
-0.0325927734375,
-0.052520751953125,
-0.0275115966796875,
0.034637451171875,
0.04693603515625,
-0.050811767578125,
0.0272216796875,
0.03240966796875,
0.0196075439453125,
-0.0275421142578125,
-0.0533447265625,
-0.0224761962890625,
-0.007411956787109375,
-0.05096435546875,
0.031463623046875,
-0.023406982421875,
0.0110015869140625,
0.004413604736328125,
0.011749267578125,
-0.01018524169921875,
-0.0025177001953125,
0.0158233642578125,
0.0494384765625,
0.0029926300048828125,
0.007419586181640625,
0.0010595321655273438,
-0.007030487060546875,
0.0031185150146484375,
-0.007434844970703125,
0.03460693359375,
-0.01457977294921875,
-0.009307861328125,
-0.043609619140625,
0.01045989990234375,
0.0183258056640625,
-0.003368377685546875,
0.04345703125,
0.060699462890625,
-0.031494140625,
-0.0116119384765625,
-0.027984619140625,
-0.01273345947265625,
-0.03338623046875,
0.035400390625,
-0.03424072265625,
-0.034576416015625,
0.046539306640625,
0.021148681640625,
0.0196685791015625,
0.05767822265625,
0.0523681640625,
-0.02764892578125,
0.0810546875,
0.03778076171875,
0.01389312744140625,
0.05682373046875,
-0.049346923828125,
-0.01641845703125,
-0.0543212890625,
-0.01436614990234375,
-0.017333984375,
-0.034759521484375,
-0.023529052734375,
-0.032196044921875,
0.0216064453125,
0.001861572265625,
-0.03167724609375,
0.025970458984375,
-0.055023193359375,
0.039794921875,
0.0572509765625,
0.039093017578125,
-0.01500701904296875,
0.0113983154296875,
-0.029327392578125,
-0.005123138427734375,
-0.057373046875,
-0.027313232421875,
0.09161376953125,
0.0310821533203125,
0.04705810546875,
-0.03704833984375,
0.057647705078125,
0.0127716064453125,
0.0241241455078125,
-0.07061767578125,
0.044921875,
-0.0198974609375,
-0.051513671875,
-0.00887298583984375,
-0.01441192626953125,
-0.040069580078125,
0.0026569366455078125,
-0.037933349609375,
-0.05609130859375,
-0.0035724639892578125,
0.030181884765625,
-0.0291748046875,
0.045135498046875,
-0.0640869140625,
0.0689697265625,
-0.033416748046875,
-0.039337158203125,
0.01250457763671875,
-0.0283203125,
0.0280303955078125,
0.0267791748046875,
-0.0119781494140625,
-0.01128387451171875,
0.0249481201171875,
0.0794677734375,
-0.0233306884765625,
0.05487060546875,
-0.0182342529296875,
0.0231170654296875,
0.040283203125,
-0.00392913818359375,
0.02001953125,
-0.0023441314697265625,
-0.01146697998046875,
0.02093505859375,
0.005458831787109375,
-0.035430908203125,
-0.019927978515625,
0.045440673828125,
-0.07110595703125,
-0.0177001953125,
-0.027435302734375,
-0.042724609375,
0.0038547515869140625,
0.0219573974609375,
0.06646728515625,
0.0333251953125,
-0.00658416748046875,
-0.01097869873046875,
0.044891357421875,
-0.0196533203125,
0.041229248046875,
-0.01261138916015625,
-0.0200347900390625,
-0.0322265625,
0.04986572265625,
0.00719451904296875,
0.00922393798828125,
-0.002933502197265625,
0.0135345458984375,
-0.0305328369140625,
-0.032989501953125,
-0.039215087890625,
0.0206451416015625,
-0.057769775390625,
-0.034393310546875,
-0.0328369140625,
-0.030487060546875,
-0.01678466796875,
-0.021453857421875,
-0.04144287109375,
-0.0281524658203125,
-0.048004150390625,
-0.01110076904296875,
0.040313720703125,
0.0310211181640625,
0.0011768341064453125,
0.0256195068359375,
-0.048095703125,
0.01407623291015625,
0.0184173583984375,
0.04327392578125,
-0.0140380859375,
-0.05792236328125,
-0.00803375244140625,
-0.0038814544677734375,
-0.0328369140625,
-0.0706787109375,
0.045013427734375,
0.0053558349609375,
0.042816162109375,
0.022857666015625,
-0.0229339599609375,
0.03759765625,
-0.016143798828125,
0.05194091796875,
0.0347900390625,
-0.0516357421875,
0.06396484375,
-0.024566650390625,
0.0413818359375,
0.040435791015625,
0.02703857421875,
-0.01175689697265625,
-0.0055694580078125,
-0.07373046875,
-0.040313720703125,
0.0755615234375,
0.012664794921875,
0.00508880615234375,
0.00885772705078125,
0.025970458984375,
0.004901885986328125,
0.0008487701416015625,
-0.0556640625,
-0.02142333984375,
-0.01904296875,
-0.019195556640625,
0.003551483154296875,
-0.01375579833984375,
-0.005207061767578125,
-0.040679931640625,
0.05474853515625,
-0.0101318359375,
0.047607421875,
0.0229339599609375,
-0.01241302490234375,
-0.01374053955078125,
-0.01418304443359375,
0.027557373046875,
0.0201416015625,
-0.0296630859375,
-0.0122528076171875,
0.00392913818359375,
-0.051300048828125,
-0.004825592041015625,
0.0021800994873046875,
-0.034912109375,
0.000016450881958007812,
0.01323699951171875,
0.0902099609375,
0.0017547607421875,
-0.0258331298828125,
0.033721923828125,
-0.01549530029296875,
-0.042266845703125,
-0.01436614990234375,
0.011566162109375,
-0.00797271728515625,
0.01271820068359375,
0.020172119140625,
0.04034423828125,
-0.0016460418701171875,
-0.026336669921875,
0.01355743408203125,
0.0341796875,
-0.035675048828125,
-0.02325439453125,
0.06109619140625,
0.0010061264038085938,
-0.0250701904296875,
0.065185546875,
-0.0181121826171875,
-0.03472900390625,
0.07659912109375,
0.04315185546875,
0.06494140625,
0.00018084049224853516,
0.038055419921875,
0.07427978515625,
0.00780487060546875,
-0.00823211669921875,
0.030517578125,
0.011138916015625,
-0.0655517578125,
0.00669097900390625,
-0.040802001953125,
-0.0168609619140625,
0.007183074951171875,
-0.035247802734375,
0.039398193359375,
-0.044403076171875,
-0.04608154296875,
-0.003269195556640625,
0.0223236083984375,
-0.083984375,
0.0275726318359375,
0.029144287109375,
0.076904296875,
-0.07086181640625,
0.054290771484375,
0.0677490234375,
-0.04608154296875,
-0.07061767578125,
-0.03131103515625,
-0.0007658004760742188,
-0.0594482421875,
0.04180908203125,
0.029144287109375,
0.01910400390625,
0.00455474853515625,
-0.065673828125,
-0.06561279296875,
0.09320068359375,
0.0205078125,
-0.00861358642578125,
0.0007085800170898438,
-0.033294677734375,
0.027862548828125,
-0.049652099609375,
0.06951904296875,
0.031707763671875,
0.0187530517578125,
0.02874755859375,
-0.054443359375,
0.006351470947265625,
-0.04083251953125,
0.0022182464599609375,
-0.006938934326171875,
-0.04473876953125,
0.0755615234375,
-0.05364990234375,
-0.016143798828125,
-0.004756927490234375,
0.03643798828125,
0.04632568359375,
0.006557464599609375,
0.032318115234375,
0.050262451171875,
0.0433349609375,
-0.00910186767578125,
0.08526611328125,
-0.006633758544921875,
0.043701171875,
0.0687255859375,
0.01155853271484375,
0.058349609375,
0.0279693603515625,
-0.0134124755859375,
0.0207977294921875,
0.0701904296875,
-0.03729248046875,
0.0360107421875,
-0.0015153884887695312,
0.0174560546875,
-0.0262603759765625,
0.0128631591796875,
-0.0140228271484375,
0.046234130859375,
0.01250457763671875,
-0.05224609375,
-0.020263671875,
0.0106048583984375,
-0.012786865234375,
-0.01544189453125,
-0.02825927734375,
0.03143310546875,
-0.013519287109375,
-0.043487548828125,
0.035125732421875,
-0.011627197265625,
0.0672607421875,
-0.034210205078125,
-0.0007376670837402344,
-0.0004982948303222656,
0.0053253173828125,
-0.0212249755859375,
-0.0821533203125,
0.008697509765625,
-0.0100250244140625,
-0.021270751953125,
-0.013519287109375,
0.07177734375,
-0.0173797607421875,
-0.0645751953125,
0.0048828125,
0.024261474609375,
0.0214080810546875,
0.0092010498046875,
-0.08660888671875,
0.01251220703125,
-0.0007834434509277344,
-0.042449951171875,
0.0177001953125,
-0.00811767578125,
0.0007548332214355469,
0.0411376953125,
0.04681396484375,
0.0020847320556640625,
0.005893707275390625,
-0.007663726806640625,
0.058319091796875,
-0.037445068359375,
-0.04107666015625,
-0.048797607421875,
0.046142578125,
-0.0286865234375,
-0.05767822265625,
0.03802490234375,
0.048431396484375,
0.0628662109375,
-0.03289794921875,
0.06439208984375,
-0.031494140625,
0.0221099853515625,
-0.031341552734375,
0.07501220703125,
-0.03582763671875,
-0.012359619140625,
-0.0194091796875,
-0.055206298828125,
-0.0168914794921875,
0.058135986328125,
-0.047149658203125,
0.015655517578125,
0.046539306640625,
0.054046630859375,
-0.0193328857421875,
-0.0168609619140625,
0.016845703125,
-0.00302886962890625,
0.004077911376953125,
0.05059814453125,
0.03851318359375,
-0.058929443359375,
0.03387451171875,
-0.0489501953125,
-0.024322509765625,
-0.004772186279296875,
-0.059844970703125,
-0.0740966796875,
-0.056915283203125,
-0.03662109375,
-0.0304412841796875,
-0.0179901123046875,
0.0616455078125,
0.06195068359375,
-0.048065185546875,
-0.01386260986328125,
0.01397705078125,
0.00811767578125,
-0.0150909423828125,
-0.018341064453125,
0.039642333984375,
-0.01552581787109375,
-0.0618896484375,
-0.0167083740234375,
-0.00124359130859375,
0.0191192626953125,
0.0081024169921875,
0.0021877288818359375,
-0.0271759033203125,
-0.00739288330078125,
0.03753662109375,
0.0240631103515625,
-0.023040771484375,
-0.018218994140625,
0.007381439208984375,
-0.00920867919921875,
0.0274810791015625,
0.0347900390625,
-0.05572509765625,
0.03302001953125,
0.044677734375,
0.0118865966796875,
0.053436279296875,
-0.01300811767578125,
0.01473236083984375,
-0.039581298828125,
0.01398468017578125,
0.01763916015625,
0.036590576171875,
0.02325439453125,
-0.03533935546875,
0.0225677490234375,
0.0201416015625,
-0.03369140625,
-0.04815673828125,
0.0019779205322265625,
-0.083740234375,
-0.0120697021484375,
0.076904296875,
-0.0101776123046875,
-0.044464111328125,
0.0318603515625,
-0.0341796875,
0.0197906494140625,
-0.02630615234375,
0.05316162109375,
0.039093017578125,
-0.01178741455078125,
-0.04193115234375,
-0.02410888671875,
0.0428466796875,
0.0014734268188476562,
-0.06317138671875,
-0.03619384765625,
0.03125,
0.0460205078125,
0.00910186767578125,
0.0704345703125,
-0.0167388916015625,
0.04302978515625,
0.0124664306640625,
0.0294342041015625,
-0.022216796875,
-0.01001739501953125,
-0.0186309814453125,
0.01020050048828125,
-0.0102691650390625,
-0.03765869140625
]
] |
Seethal/sentiment_analysis_generic_dataset | 2022-04-19T06:26:33.000Z | [
"transformers",
"pytorch",
"distilbert",
"text-classification",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | Seethal | null | null | Seethal/sentiment_analysis_generic_dataset | 19 | 44,801 | transformers | 2022-04-13T18:37:07 | ## BERT base model (uncased)
Pretrained model on English language using a masked language modeling (MLM) objective. This model is uncased: it does not make a difference between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives:
* Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
* Next sentence prediction (NSP): the model concatenates two masked sentences as inputs during pretraining. Sometimes they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to predict if the two sentences were following each other or not.
This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the BERT model as inputs.
## Model description [Seethal/sentiment_analysis_generic_dataset]
This is a fine-tuned downstream version of the bert-base-uncased model for sentiment analysis, this model is not intended for further downstream fine-tuning for any other tasks. This model is trained on a classified dataset for text classification. | 1,988 | [
[
-0.0270843505859375,
-0.045623779296875,
0.0142822265625,
0.025665283203125,
-0.0262451171875,
0.00592803955078125,
-0.0247955322265625,
-0.03436279296875,
0.017120361328125,
0.056640625,
-0.055389404296875,
-0.0250244140625,
-0.051849365234375,
0.0028171539306640625,
-0.0253448486328125,
0.09918212890625,
0.0114288330078125,
0.014862060546875,
-0.01366424560546875,
0.0233917236328125,
-0.032196044921875,
-0.06903076171875,
-0.029541015625,
-0.034637451171875,
0.029541015625,
0.008270263671875,
0.042236328125,
0.0186004638671875,
0.03564453125,
0.026153564453125,
-0.0003910064697265625,
-0.00670623779296875,
-0.0316162109375,
0.00009173154830932617,
0.0023822784423828125,
-0.032562255859375,
-0.009552001953125,
0.0227508544921875,
0.037841796875,
0.05645751953125,
0.014007568359375,
-0.0006289482116699219,
0.0233001708984375,
0.046600341796875,
-0.038543701171875,
0.020477294921875,
-0.057373046875,
0.01308441162109375,
-0.002651214599609375,
-0.0016202926635742188,
-0.034332275390625,
-0.01824951171875,
0.036956787109375,
-0.0011196136474609375,
0.019317626953125,
-0.005542755126953125,
0.0819091796875,
0.0005030632019042969,
-0.0255279541015625,
-0.026519775390625,
-0.0487060546875,
0.07122802734375,
-0.059356689453125,
0.0229034423828125,
0.0232086181640625,
0.00254058837890625,
-0.00372314453125,
-0.06561279296875,
-0.036163330078125,
-0.0218505859375,
-0.029144287109375,
0.0194091796875,
-0.0091552734375,
0.0200347900390625,
0.004146575927734375,
0.0157318115234375,
-0.0382080078125,
0.0030879974365234375,
-0.037353515625,
-0.015350341796875,
0.046722412109375,
-0.0240325927734375,
0.01190185546875,
-0.023895263671875,
-0.054473876953125,
0.0032978057861328125,
-0.0401611328125,
0.0168914794921875,
0.028839111328125,
0.034423828125,
-0.00348663330078125,
0.04132080078125,
0.0164337158203125,
0.0408935546875,
0.0089569091796875,
0.0005321502685546875,
0.0316162109375,
0.0083160400390625,
-0.0310516357421875,
0.0110626220703125,
0.0531005859375,
0.012237548828125,
0.04815673828125,
-0.0229034423828125,
-0.035736083984375,
0.002437591552734375,
0.027557373046875,
-0.046600341796875,
-0.01319122314453125,
0.00890350341796875,
-0.047882080078125,
-0.02587890625,
0.006710052490234375,
-0.0207672119140625,
0.01375579833984375,
-0.01910400390625,
0.05853271484375,
-0.0280609130859375,
-0.0024127960205078125,
0.0029010772705078125,
-0.00411224365234375,
0.016693115234375,
-0.0069732666015625,
-0.0667724609375,
0.0272369384765625,
0.042755126953125,
0.042755126953125,
-0.0203857421875,
-0.0186920166015625,
0.005573272705078125,
-0.006366729736328125,
-0.017181396484375,
0.042755126953125,
-0.033294677734375,
-0.01235198974609375,
0.0211181640625,
0.02447509765625,
-0.01479339599609375,
-0.011688232421875,
0.035400390625,
-0.046905517578125,
0.0394287109375,
-0.00829315185546875,
-0.056640625,
-0.036712646484375,
0.00925445556640625,
-0.034942626953125,
0.08251953125,
-0.0062713623046875,
-0.055023193359375,
0.0278167724609375,
-0.045166015625,
-0.043487548828125,
0.0015125274658203125,
0.00861358642578125,
-0.0242919921875,
0.01319122314453125,
0.014617919921875,
0.051116943359375,
0.0100860595703125,
0.0308990478515625,
0.00018978118896484375,
-0.02899169921875,
0.019561767578125,
-0.03851318359375,
0.068359375,
0.00240325927734375,
-0.037109375,
-0.0017423629760742188,
-0.04949951171875,
0.01253509521484375,
0.0025119781494140625,
-0.02679443359375,
-0.0231170654296875,
0.01500701904296875,
0.0115814208984375,
0.0231170654296875,
0.03350830078125,
-0.049163818359375,
-0.0016803741455078125,
-0.0496826171875,
0.024444580078125,
0.06695556640625,
-0.007747650146484375,
0.0287322998046875,
-0.0178070068359375,
0.0281524658203125,
-0.00848388671875,
0.002460479736328125,
-0.01629638671875,
-0.052398681640625,
-0.0767822265625,
-0.017547607421875,
0.046539306640625,
0.057098388671875,
-0.0302734375,
0.0704345703125,
0.005035400390625,
-0.014495849609375,
-0.05755615234375,
0.007564544677734375,
0.033721923828125,
0.029327392578125,
0.0240936279296875,
-0.030609130859375,
-0.06689453125,
-0.08978271484375,
0.005321502685546875,
-0.0002307891845703125,
-0.003818511962890625,
-0.003879547119140625,
0.04498291015625,
-0.0277099609375,
0.07159423828125,
-0.0203704833984375,
-0.0302581787109375,
-0.042327880859375,
0.024566650390625,
0.0170135498046875,
0.042724609375,
0.03533935546875,
-0.0479736328125,
-0.045440673828125,
-0.01824951171875,
-0.046234130859375,
-0.006256103515625,
-0.012725830078125,
-0.00780487060546875,
0.0230712890625,
0.031402587890625,
-0.0396728515625,
0.040191650390625,
0.052337646484375,
0.002063751220703125,
0.0240325927734375,
-0.02044677734375,
-0.0193939208984375,
-0.08447265625,
-0.01434326171875,
-0.01971435546875,
-0.01605224609375,
-0.049774169921875,
-0.01079559326171875,
-0.000518798828125,
-0.00888824462890625,
-0.033447265625,
0.0247344970703125,
-0.039794921875,
-0.00949859619140625,
-0.026031494140625,
-0.01119232177734375,
0.0016031265258789062,
0.06512451171875,
0.03204345703125,
0.043975830078125,
0.048583984375,
-0.040435791015625,
0.01398468017578125,
0.0131683349609375,
-0.0382080078125,
-0.00241851806640625,
-0.056365966796875,
0.0135955810546875,
-0.0173187255859375,
0.0031223297119140625,
-0.08978271484375,
0.0164031982421875,
-0.0090484619140625,
-0.048126220703125,
0.034759521484375,
0.0184783935546875,
-0.0286407470703125,
-0.033203125,
-0.01520538330078125,
0.00048279762268066406,
0.06134033203125,
-0.03070068359375,
0.0457763671875,
0.027374267578125,
-0.017578125,
-0.058197021484375,
-0.070556640625,
-0.00588226318359375,
0.0108184814453125,
-0.04095458984375,
0.0272369384765625,
-0.0053253173828125,
-0.0011758804321289062,
0.006450653076171875,
0.0057220458984375,
-0.0180511474609375,
-0.0011415481567382812,
0.0250701904296875,
0.0252532958984375,
-0.0192108154296875,
0.0172271728515625,
0.0065155029296875,
-0.004787445068359375,
0.012603759765625,
-0.0095977783203125,
0.0458984375,
-0.004848480224609375,
-0.00992584228515625,
-0.024749755859375,
0.042236328125,
0.0114898681640625,
-0.0097808837890625,
0.06927490234375,
0.050689697265625,
-0.03045654296875,
-0.0234527587890625,
-0.044189453125,
-0.026611328125,
-0.03643798828125,
0.03192138671875,
-0.0273895263671875,
-0.0677490234375,
0.03302001953125,
0.0287322998046875,
0.0166473388671875,
0.0438232421875,
0.050323486328125,
-0.045166015625,
0.076416015625,
0.0718994140625,
-0.01277923583984375,
0.020721435546875,
-0.0035572052001953125,
0.0271148681640625,
-0.044219970703125,
-0.027191162109375,
-0.0270538330078125,
-0.0340576171875,
-0.043670654296875,
-0.00536346435546875,
-0.0005288124084472656,
0.00856781005859375,
-0.0113983154296875,
0.031829833984375,
-0.046173095703125,
0.03289794921875,
0.0726318359375,
0.00888824462890625,
-0.00017762184143066406,
0.0157470703125,
-0.020843505859375,
-0.022552490234375,
-0.04034423828125,
-0.040283203125,
0.0859375,
0.039154052734375,
0.05328369140625,
-0.01477813720703125,
0.04998779296875,
0.038238525390625,
0.021728515625,
-0.05670166015625,
0.047882080078125,
-0.027191162109375,
-0.06964111328125,
-0.006744384765625,
-0.001125335693359375,
-0.0811767578125,
0.014129638671875,
-0.029449462890625,
-0.044769287109375,
0.0078125,
-0.00466156005859375,
-0.002590179443359375,
0.02496337890625,
-0.0697021484375,
0.042205810546875,
-0.031463623046875,
0.012420654296875,
0.0105133056640625,
-0.064453125,
0.015655517578125,
-0.0115966796875,
-0.0068817138671875,
0.006168365478515625,
0.0180511474609375,
0.0693359375,
-0.02227783203125,
0.0880126953125,
-0.008026123046875,
0.005863189697265625,
0.014862060546875,
-0.010650634765625,
0.0246429443359375,
-0.0301055908203125,
0.0185089111328125,
0.0266876220703125,
-0.014495849609375,
-0.02587890625,
-0.0279083251953125,
0.0306243896484375,
-0.07220458984375,
-0.044677734375,
-0.0430908203125,
-0.03643798828125,
-0.022064208984375,
0.019256591796875,
0.041534423828125,
0.0130462646484375,
-0.0190582275390625,
0.0296173095703125,
0.05267333984375,
-0.025054931640625,
0.04559326171875,
0.040069580078125,
-0.01129150390625,
-0.00798797607421875,
0.033294677734375,
0.0029582977294921875,
0.0262908935546875,
0.050933837890625,
0.004795074462890625,
-0.033477783203125,
-0.034912109375,
0.00783538818359375,
0.01446533203125,
-0.052581787109375,
-0.001720428466796875,
-0.06658935546875,
-0.05731201171875,
-0.04925537109375,
-0.0214996337890625,
-0.01983642578125,
-0.02264404296875,
-0.019927978515625,
-0.020721435546875,
0.0159149169921875,
0.057098388671875,
-0.0207366943359375,
0.0325927734375,
-0.0499267578125,
0.0229339599609375,
0.04254150390625,
0.0106964111328125,
-0.01474761962890625,
-0.046600341796875,
-0.01486968994140625,
0.0172119140625,
-0.01201629638671875,
-0.0643310546875,
0.040008544921875,
0.01169586181640625,
0.0482177734375,
0.03533935546875,
-0.0067291259765625,
0.035614013671875,
-0.057037353515625,
0.0546875,
0.015655517578125,
-0.07147216796875,
0.041778564453125,
-0.0015850067138671875,
0.01105499267578125,
0.034027099609375,
0.035552978515625,
-0.0236968994140625,
-0.03570556640625,
-0.043609619140625,
-0.0628662109375,
0.04681396484375,
0.027191162109375,
0.04144287109375,
-0.01168060302734375,
0.00931549072265625,
0.017364501953125,
0.03509521484375,
-0.10186767578125,
-0.031341552734375,
-0.0203857421875,
-0.01136016845703125,
-0.0234832763671875,
-0.04388427734375,
0.005523681640625,
-0.03070068359375,
0.057037353515625,
0.0263824462890625,
0.05194091796875,
0.001720428466796875,
-0.0184478759765625,
0.0108184814453125,
0.0189971923828125,
0.03570556640625,
0.0233001708984375,
-0.050872802734375,
-0.0024700164794921875,
-0.001598358154296875,
-0.049072265625,
-0.007442474365234375,
0.01032257080078125,
-0.0183868408203125,
0.0330810546875,
0.03717041015625,
0.07159423828125,
0.01525115966796875,
-0.0416259765625,
0.043701171875,
0.01910400390625,
-0.031280517578125,
-0.03955078125,
-0.00890350341796875,
-0.0008955001831054688,
0.0099945068359375,
0.038116455078125,
0.0027103424072265625,
-0.007266998291015625,
-0.05230712890625,
0.0302734375,
0.04278564453125,
-0.04071044921875,
-0.01236724853515625,
0.036712646484375,
0.0189056396484375,
-0.024078369140625,
0.048309326171875,
-0.0005679130554199219,
-0.058380126953125,
0.049530029296875,
0.056549072265625,
0.0809326171875,
-0.0161285400390625,
0.0267333984375,
0.005889892578125,
0.055572509765625,
0.009033203125,
0.0168914794921875,
0.00927734375,
-0.078857421875,
-0.040435791015625,
-0.0557861328125,
-0.016876220703125,
0.03521728515625,
-0.058197021484375,
0.0037631988525390625,
-0.0283203125,
-0.004199981689453125,
0.004940032958984375,
-0.0034332275390625,
-0.0504150390625,
0.046173095703125,
0.014129638671875,
0.056915283203125,
-0.07257080078125,
0.07244873046875,
0.03729248046875,
-0.0260162353515625,
-0.061981201171875,
-0.00672149658203125,
-0.0269012451171875,
-0.08599853515625,
0.07525634765625,
0.026092529296875,
0.006633758544921875,
-0.0032978057861328125,
-0.049407958984375,
-0.055999755859375,
0.04425048828125,
0.0074310302734375,
-0.0330810546875,
-0.01702880859375,
0.01751708984375,
0.045318603515625,
-0.05511474609375,
0.0159454345703125,
0.018829345703125,
0.0196380615234375,
0.0086517333984375,
-0.056304931640625,
-0.02398681640625,
-0.0182952880859375,
0.010589599609375,
0.003997802734375,
-0.015350341796875,
0.087646484375,
0.000591278076171875,
-0.0081634521484375,
-0.001613616943359375,
0.03961181640625,
-0.011688232421875,
-0.0111846923828125,
0.03338623046875,
0.03680419921875,
0.03411865234375,
-0.01512908935546875,
0.070068359375,
-0.0218505859375,
0.031219482421875,
0.08526611328125,
-0.022003173828125,
0.07574462890625,
0.0239410400390625,
-0.00909423828125,
0.060150146484375,
0.058807373046875,
-0.0114898681640625,
0.0704345703125,
0.005115509033203125,
-0.0045318603515625,
-0.00823211669921875,
0.01404571533203125,
-0.04046630859375,
0.03765869140625,
0.01337432861328125,
-0.057373046875,
-0.01212310791015625,
0.0201263427734375,
0.002536773681640625,
-0.003307342529296875,
-0.032958984375,
0.0570068359375,
-0.00516510009765625,
-0.047515869140625,
0.0303192138671875,
0.00807952880859375,
0.07098388671875,
-0.0673828125,
0.0142974853515625,
-0.00897979736328125,
0.010467529296875,
-0.005275726318359375,
-0.053497314453125,
0.022979736328125,
-0.0034275054931640625,
-0.02972412109375,
-0.03564453125,
0.0667724609375,
-0.04638671875,
-0.0577392578125,
0.0203857421875,
0.03143310546875,
0.023529052734375,
-0.006504058837890625,
-0.0709228515625,
-0.023101806640625,
0.01348876953125,
-0.0295257568359375,
0.017181396484375,
0.019256591796875,
0.01476287841796875,
0.04559326171875,
0.047210693359375,
0.0070037841796875,
0.0093231201171875,
0.007747650146484375,
0.052337646484375,
-0.047515869140625,
-0.04498291015625,
-0.054962158203125,
0.046966552734375,
-0.00030303001403808594,
-0.0065155029296875,
0.0579833984375,
0.03436279296875,
0.05810546875,
-0.031585693359375,
0.0618896484375,
0.0034961700439453125,
0.05645751953125,
-0.04461669921875,
0.04931640625,
-0.031494140625,
-0.000988006591796875,
-0.01690673828125,
-0.07940673828125,
-0.007770538330078125,
0.07861328125,
-0.009429931640625,
0.0169677734375,
0.06451416015625,
0.045135498046875,
0.01023101806640625,
-0.00722503662109375,
0.03143310546875,
0.020477294921875,
-0.01708984375,
0.032928466796875,
0.043426513671875,
-0.022491455078125,
0.03094482421875,
-0.0247650146484375,
-0.0079345703125,
0.0005440711975097656,
-0.060302734375,
-0.1060791015625,
-0.046966552734375,
-0.01629638671875,
-0.028594970703125,
0.0102386474609375,
0.05218505859375,
0.06378173828125,
-0.0767822265625,
-0.01506805419921875,
-0.006229400634765625,
-0.005523681640625,
-0.00705718994140625,
-0.02227783203125,
0.0254669189453125,
-0.041259765625,
-0.0576171875,
0.0124359130859375,
0.0193634033203125,
0.01511383056640625,
-0.039886474609375,
0.0169677734375,
-0.03961181640625,
0.0270843505859375,
0.053466796875,
0.00319671630859375,
-0.049652099609375,
-0.0220947265625,
0.0034046173095703125,
-0.01497650146484375,
0.00489044189453125,
0.04840087890625,
-0.05963134765625,
0.034027099609375,
0.0177001953125,
0.04571533203125,
0.036773681640625,
-0.0183563232421875,
0.05133056640625,
-0.09063720703125,
0.0304412841796875,
0.034027099609375,
0.0234832763671875,
0.0117340087890625,
-0.031494140625,
0.0194549560546875,
0.01010894775390625,
-0.03338623046875,
-0.0517578125,
0.01413726806640625,
-0.07098388671875,
-0.036376953125,
0.07940673828125,
-0.0181427001953125,
-0.006771087646484375,
-0.01317596435546875,
-0.0142364501953125,
0.00670623779296875,
-0.01500701904296875,
0.05572509765625,
0.07281494140625,
0.0161590576171875,
-0.02130126953125,
-0.0286865234375,
0.042022705078125,
0.0361328125,
-0.036102294921875,
-0.03668212890625,
0.01029205322265625,
0.0157012939453125,
0.010650634765625,
0.042999267578125,
0.009765625,
-0.0031795501708984375,
-0.02362060546875,
0.03662109375,
0.01226806640625,
-0.0182647705078125,
-0.00817108154296875,
0.01479339599609375,
-0.0305328369140625,
-0.048583984375
]
] |
sb3/ppo-CartPole-v1 | 2022-10-11T15:05:29.000Z | [
"stable-baselines3",
"CartPole-v1",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"has_space",
"region:us"
] | reinforcement-learning | sb3 | null | null | sb3/ppo-CartPole-v1 | 0 | 44,263 | stable-baselines3 | 2022-05-19T22:36:14 | ---
library_name: stable-baselines3
tags:
- CartPole-v1
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
---
# **PPO** Agent playing **CartPole-v1**
This is a trained model of a **PPO** agent playing **CartPole-v1**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo ppo --env CartPole-v1 -orga sb3 -f logs/
python enjoy.py --algo ppo --env CartPole-v1 -f logs/
```
## Training (with the RL Zoo)
```
python train.py --algo ppo --env CartPole-v1 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo ppo --env CartPole-v1 -f logs/ -orga sb3
```
## Hyperparameters
```python
OrderedDict([('batch_size', 256),
('clip_range', 'lin_0.2'),
('ent_coef', 0.0),
('gae_lambda', 0.8),
('gamma', 0.98),
('learning_rate', 'lin_0.001'),
('n_envs', 8),
('n_epochs', 20),
('n_steps', 32),
('n_timesteps', 100000.0),
('policy', 'MlpPolicy'),
('normalize', False)])
```
| 1,903 | [
[
-0.030120849609375,
-0.03436279296875,
0.0089111328125,
0.01082611083984375,
-0.0255126953125,
-0.004360198974609375,
0.0017709732055664062,
-0.018798828125,
0.00125885009765625,
0.03314208984375,
-0.044219970703125,
-0.048614501953125,
-0.03900146484375,
-0.005405426025390625,
0.01412200927734375,
0.08990478515625,
0.01071929931640625,
0.01403045654296875,
-0.0086212158203125,
-0.00794219970703125,
-0.0224761962890625,
-0.042694091796875,
-0.061676025390625,
-0.053741455078125,
0.0192718505859375,
0.0305328369140625,
0.059539794921875,
0.03643798828125,
0.02313232421875,
0.0257415771484375,
-0.0157623291015625,
-0.00168609619140625,
-0.03912353515625,
-0.0150604248046875,
-0.00623321533203125,
-0.0174560546875,
-0.06622314453125,
0.010101318359375,
0.0306549072265625,
0.006908416748046875,
-0.0199737548828125,
0.01421356201171875,
-0.004730224609375,
0.02880859375,
-0.04962158203125,
0.04241943359375,
-0.03167724609375,
0.026580810546875,
0.0066070556640625,
-0.00922393798828125,
-0.025115966796875,
-0.013641357421875,
0.0172119140625,
-0.08685302734375,
0.01029205322265625,
-0.0131072998046875,
0.11273193359375,
-0.0116119384765625,
-0.0251007080078125,
-0.01251983642578125,
-0.044586181640625,
0.0714111328125,
-0.060760498046875,
0.005584716796875,
0.04888916015625,
0.041107177734375,
-0.006572723388671875,
-0.058135986328125,
-0.02703857421875,
-0.0311431884765625,
-0.00482177734375,
0.0252227783203125,
-0.0017242431640625,
0.015411376953125,
0.0212249755859375,
0.009368896484375,
-0.04571533203125,
0.00606536865234375,
-0.0274200439453125,
-0.0243377685546875,
0.043243408203125,
0.024749755859375,
-0.012908935546875,
-0.00487518310546875,
-0.040069580078125,
-0.028564453125,
-0.02545166015625,
0.02783203125,
0.0279541015625,
0.023406982421875,
-0.0163726806640625,
0.040863037109375,
-0.034088134765625,
0.04296875,
-0.0018739700317382812,
-0.03460693359375,
0.033355712890625,
-0.00872039794921875,
-0.0206146240234375,
-0.01111602783203125,
0.05712890625,
0.039703369140625,
0.010955810546875,
0.0209503173828125,
-0.033905029296875,
-0.019927978515625,
0.0137939453125,
-0.0438232421875,
-0.026214599609375,
0.01934814453125,
-0.0109405517578125,
-0.03558349609375,
0.01245880126953125,
-0.06048583984375,
0.008636474609375,
-0.00988006591796875,
0.043365478515625,
-0.049224853515625,
-0.004192352294921875,
0.0115203857421875,
0.0037212371826171875,
0.04229736328125,
0.0309295654296875,
-0.05828857421875,
0.0295867919921875,
0.0504150390625,
0.061431884765625,
0.022705078125,
-0.0621337890625,
-0.03375244140625,
0.027099609375,
-0.0206451416015625,
0.057769775390625,
-0.00006818771362304688,
-0.0195465087890625,
0.0209197998046875,
0.002552032470703125,
-0.008758544921875,
-0.0284881591796875,
0.037994384765625,
-0.0452880859375,
0.00917816162109375,
-0.00965118408203125,
-0.0350341796875,
-0.0284271240234375,
0.04437255859375,
-0.046630859375,
0.07708740234375,
0.01483154296875,
-0.052825927734375,
0.033966064453125,
-0.041290283203125,
-0.0154876708984375,
0.008758544921875,
0.0007443428039550781,
-0.076416015625,
-0.0254364013671875,
0.006641387939453125,
0.01265716552734375,
-0.0097808837890625,
0.00490570068359375,
-0.0300445556640625,
-0.02191162109375,
0.003818511962890625,
0.003326416015625,
0.0709228515625,
0.01168060302734375,
-0.0169830322265625,
0.014923095703125,
-0.0523681640625,
0.01032257080078125,
0.031982421875,
-0.042022705078125,
0.0113067626953125,
0.0012960433959960938,
0.006633758544921875,
0.02398681640625,
0.0260162353515625,
-0.020599365234375,
0.0287933349609375,
-0.015869140625,
0.032684326171875,
0.046142578125,
0.00913238525390625,
0.01084136962890625,
-0.04681396484375,
0.041107177734375,
0.004413604736328125,
0.040283203125,
0.022216796875,
-0.038909912109375,
-0.040740966796875,
-0.0207061767578125,
-0.00576019287109375,
0.041015625,
-0.046356201171875,
0.050323486328125,
0.0027141571044921875,
-0.049774169921875,
-0.004970550537109375,
-0.01300048828125,
0.03363037109375,
0.0440673828125,
0.031829833984375,
-0.0006756782531738281,
-0.03619384765625,
-0.060333251953125,
0.014404296875,
-0.0291900634765625,
-0.004150390625,
0.0213775634765625,
0.06658935546875,
0.0026397705078125,
0.051422119140625,
-0.03277587890625,
-0.034210205078125,
-0.022613525390625,
0.01090240478515625,
0.030517578125,
0.050628662109375,
0.058502197265625,
-0.02593994140625,
-0.0276947021484375,
-0.0040130615234375,
-0.06982421875,
0.0203399658203125,
0.0085601806640625,
-0.00916290283203125,
-0.0040435791015625,
0.00514984130859375,
-0.0753173828125,
0.027313232421875,
0.0183563232421875,
-0.0211334228515625,
0.06024169921875,
-0.03509521484375,
0.01090240478515625,
-0.05169677734375,
0.01030731201171875,
-0.0067291259765625,
-0.00830078125,
-0.03338623046875,
0.0130157470703125,
-0.0073089599609375,
-0.0253143310546875,
-0.068359375,
0.0222015380859375,
-0.035247802734375,
-0.02398681640625,
-0.006877899169921875,
0.007965087890625,
0.009033203125,
0.04791259765625,
-0.0004930496215820312,
0.054931640625,
0.0782470703125,
-0.057647705078125,
0.02783203125,
0.03155517578125,
-0.006313323974609375,
0.0166015625,
-0.055328369140625,
0.02203369140625,
0.000026345252990722656,
0.03228759765625,
-0.055908203125,
-0.022308349609375,
0.040069580078125,
-0.0304412841796875,
0.007965087890625,
-0.0301971435546875,
-0.022674560546875,
-0.03350830078125,
-0.037017822265625,
0.03759765625,
0.0298309326171875,
-0.0239410400390625,
0.0264129638671875,
0.03399658203125,
0.023956298828125,
-0.061737060546875,
-0.0220794677734375,
-0.0169830322265625,
-0.0257110595703125,
-0.0288848876953125,
0.0181732177734375,
0.011871337890625,
-0.000972747802734375,
-0.007564544677734375,
0.0009589195251464844,
-0.0193634033203125,
0.005126953125,
0.00511932373046875,
0.017669677734375,
-0.017181396484375,
-0.008636474609375,
-0.0275115966796875,
-0.014434814453125,
0.006999969482421875,
-0.0309295654296875,
0.05120849609375,
-0.026947021484375,
0.0011796951293945312,
-0.05267333984375,
-0.00116729736328125,
0.045806884765625,
-0.016815185546875,
0.0596923828125,
0.03704833984375,
-0.037353515625,
-0.01438140869140625,
-0.002826690673828125,
-0.01251983642578125,
-0.0352783203125,
0.0282440185546875,
-0.035888671875,
-0.0220489501953125,
0.051422119140625,
0.01043701171875,
0.0078582763671875,
0.043914794921875,
0.02435302734375,
-0.0025806427001953125,
0.07952880859375,
0.03155517578125,
-0.007389068603515625,
0.03765869140625,
-0.0684814453125,
-0.0288238525390625,
-0.04791259765625,
-0.03277587890625,
-0.0457763671875,
-0.00004750490188598633,
-0.0277099609375,
-0.017974853515625,
0.017974853515625,
0.03277587890625,
-0.041961669921875,
0.043853759765625,
-0.0343017578125,
0.0294952392578125,
0.03167724609375,
0.01422882080078125,
0.0054168701171875,
0.0008511543273925781,
-0.021026611328125,
0.008056640625,
-0.0645751953125,
-0.052581787109375,
0.08538818359375,
0.02630615234375,
0.05419921875,
-0.001552581787109375,
0.043304443359375,
0.014923095703125,
0.017791748046875,
-0.05657958984375,
0.05328369140625,
0.0038166046142578125,
-0.04766845703125,
-0.0293426513671875,
-0.010711669921875,
-0.0809326171875,
0.030609130859375,
-0.0253448486328125,
-0.05535888671875,
-0.01015472412109375,
0.0271453857421875,
-0.0136871337890625,
0.0264739990234375,
-0.016143798828125,
0.0711669921875,
-0.01413726806640625,
-0.03265380859375,
-0.016632080078125,
-0.033721923828125,
0.0283355712890625,
0.0131683349609375,
-0.0011548995971679688,
-0.0185546875,
-0.008697509765625,
0.059478759765625,
-0.0640869140625,
0.03155517578125,
-0.040374755859375,
0.0246124267578125,
0.0555419921875,
-0.0065155029296875,
0.05145263671875,
0.037811279296875,
-0.0093994140625,
0.0250396728515625,
-0.0185546875,
-0.0604248046875,
-0.0181427001953125,
0.045501708984375,
-0.1033935546875,
-0.035888671875,
-0.056243896484375,
-0.03155517578125,
-0.0027923583984375,
0.0125274658203125,
0.0364990234375,
0.0193634033203125,
-0.0030765533447265625,
0.00672149658203125,
0.0322265625,
-0.006900787353515625,
0.034515380859375,
0.0489501953125,
-0.014801025390625,
-0.05401611328125,
0.04241943359375,
0.004108428955078125,
0.00493621826171875,
0.0206756591796875,
0.00992584228515625,
-0.027099609375,
-0.06005859375,
-0.0196075439453125,
0.02813720703125,
-0.0438232421875,
-0.024505615234375,
-0.027740478515625,
-0.02301025390625,
-0.03497314453125,
-0.00859832763671875,
-0.04302978515625,
-0.017547607421875,
-0.03509521484375,
-0.01470947265625,
0.03082275390625,
0.04425048828125,
-0.0180816650390625,
0.04022216796875,
-0.039581298828125,
0.0002789497375488281,
0.03814697265625,
0.00925445556640625,
-0.01146697998046875,
-0.045806884765625,
-0.032470703125,
-0.004306793212890625,
-0.046875,
-0.07720947265625,
0.044219970703125,
0.00775146484375,
0.05999755859375,
0.039276123046875,
-0.007427215576171875,
0.05364990234375,
-0.01873779296875,
0.06268310546875,
0.0113677978515625,
-0.057525634765625,
0.052825927734375,
-0.034912109375,
0.0139312744140625,
0.044891357421875,
0.04266357421875,
0.0008225440979003906,
-0.021759033203125,
-0.048065185546875,
-0.0643310546875,
0.08404541015625,
0.031707763671875,
-0.0187225341796875,
0.005290985107421875,
0.02813720703125,
-0.011871337890625,
0.006195068359375,
-0.07330322265625,
-0.019073486328125,
-0.039825439453125,
0.0267333984375,
-0.0238494873046875,
0.006992340087890625,
-0.0207366943359375,
-0.021484375,
0.07623291015625,
-0.0092620849609375,
0.03094482421875,
0.02801513671875,
-0.017059326171875,
-0.026580810546875,
-0.01479339599609375,
0.059417724609375,
0.057830810546875,
-0.056793212890625,
-0.0095367431640625,
0.018646240234375,
-0.038116455078125,
0.0258941650390625,
0.01381683349609375,
-0.00647735595703125,
0.006702423095703125,
0.0330810546875,
0.056427001953125,
0.0189056396484375,
-0.0270538330078125,
0.04486083984375,
0.002857208251953125,
-0.03839111328125,
-0.040496826171875,
-0.003482818603515625,
-0.01471710205078125,
0.010650634765625,
0.032867431640625,
-0.007274627685546875,
-0.01071929931640625,
-0.031707763671875,
0.02288818359375,
0.030792236328125,
-0.0325927734375,
-0.03515625,
0.0604248046875,
0.00225830078125,
-0.03955078125,
0.045745849609375,
-0.0198516845703125,
-0.034515380859375,
0.07940673828125,
0.036163330078125,
0.062255859375,
-0.011016845703125,
0.027099609375,
0.060089111328125,
0.0202789306640625,
-0.003570556640625,
0.017333984375,
0.01338958740234375,
-0.04931640625,
-0.01174163818359375,
-0.029296875,
-0.039276123046875,
0.05133056640625,
-0.06103515625,
0.03460693359375,
-0.04779052734375,
-0.03509521484375,
0.00399017333984375,
0.03375244140625,
-0.0533447265625,
0.008636474609375,
0.00559234619140625,
0.07183837890625,
-0.0677490234375,
0.08782958984375,
0.08233642578125,
-0.03955078125,
-0.05975341796875,
-0.0091400146484375,
-0.0060577392578125,
-0.048675537109375,
0.042236328125,
-0.0002180337905883789,
0.00972747802734375,
-0.0005693435668945312,
-0.040802001953125,
-0.068603515625,
0.1094970703125,
0.01418304443359375,
-0.0268707275390625,
0.01009368896484375,
0.01001739501953125,
0.04296875,
-0.0308380126953125,
0.0362548828125,
0.0107421875,
0.0290679931640625,
0.004695892333984375,
-0.05108642578125,
-0.01021575927734375,
0.00370025634765625,
-0.003772735595703125,
-0.0036144256591796875,
-0.0753173828125,
0.1129150390625,
-0.01041412353515625,
0.0135955810546875,
0.007183074951171875,
0.053192138671875,
0.0621337890625,
0.0296478271484375,
0.041107177734375,
0.04791259765625,
0.02996826171875,
0.004817962646484375,
0.05999755859375,
-0.036895751953125,
0.07916259765625,
0.07281494140625,
-0.0278472900390625,
0.0428466796875,
0.01383209228515625,
-0.02447509765625,
0.0261993408203125,
0.0478515625,
-0.01354217529296875,
0.04949951171875,
0.00658416748046875,
-0.017913818359375,
-0.01641845703125,
0.020477294921875,
-0.039703369140625,
0.028594970703125,
0.0084228515625,
-0.004993438720703125,
-0.036956787109375,
-0.0052032470703125,
0.0025348663330078125,
-0.01383209228515625,
-0.03204345703125,
0.048828125,
-0.0196380615234375,
-0.05316162109375,
0.06732177734375,
-0.00339508056640625,
0.0193634033203125,
-0.061737060546875,
-0.0122528076171875,
-0.0252685546875,
0.0252227783203125,
-0.004241943359375,
-0.04998779296875,
-0.003139495849609375,
-0.01450347900390625,
0.01068878173828125,
0.007633209228515625,
0.0506591796875,
-0.007366180419921875,
-0.0189971923828125,
0.0447998046875,
0.021881103515625,
0.0236053466796875,
0.02105712890625,
-0.08428955078125,
-0.0114288330078125,
-0.01459503173828125,
-0.0458984375,
0.03277587890625,
0.02069091796875,
0.00644683837890625,
0.057098388671875,
0.03363037109375,
-0.007709503173828125,
-0.0001646280288696289,
-0.0108795166015625,
0.07037353515625,
-0.04852294921875,
-0.039276123046875,
-0.0384521484375,
0.038909912109375,
0.0017099380493164062,
-0.057403564453125,
0.050079345703125,
0.072021484375,
0.0654296875,
-0.032562255859375,
0.03704833984375,
-0.001369476318359375,
-0.005802154541015625,
-0.0355224609375,
0.05120849609375,
-0.024200439453125,
-0.0017566680908203125,
-0.01430511474609375,
-0.06134033203125,
-0.0037994384765625,
0.060089111328125,
-0.01158905029296875,
-0.0064849853515625,
0.0338134765625,
0.0631103515625,
-0.0033740997314453125,
-0.0185546875,
0.03314208984375,
0.021575927734375,
0.0200653076171875,
0.061981201171875,
0.06573486328125,
-0.051483154296875,
0.06475830078125,
-0.048004150390625,
-0.01702880859375,
-0.029693603515625,
-0.054107666015625,
-0.0596923828125,
-0.01271820068359375,
-0.038177490234375,
-0.035888671875,
0.0258026123046875,
0.058929443359375,
0.07684326171875,
-0.06494140625,
-0.046417236328125,
-0.0241546630859375,
0.006092071533203125,
-0.048187255859375,
-0.0198211669921875,
0.015960693359375,
-0.024566650390625,
-0.052398681640625,
0.024627685546875,
-0.005374908447265625,
0.01544952392578125,
-0.0081024169921875,
-0.03656005859375,
-0.045806884765625,
-0.003955841064453125,
0.032135009765625,
0.040679931640625,
-0.034881591796875,
-0.03143310546875,
-0.03216552734375,
-0.02105712890625,
0.0251922607421875,
0.038360595703125,
-0.05712890625,
0.0034542083740234375,
0.0310211181640625,
-0.01390838623046875,
0.07177734375,
0.0026226043701171875,
0.02154541015625,
-0.034271240234375,
0.03363037109375,
0.031005859375,
0.025177001953125,
-0.005359649658203125,
-0.0113372802734375,
0.03607177734375,
0.0288238525390625,
-0.06268310546875,
-0.04931640625,
0.0024280548095703125,
-0.08319091796875,
-0.021881103515625,
0.061431884765625,
-0.045745849609375,
-0.02423095703125,
-0.000995635986328125,
-0.013519287109375,
0.0298919677734375,
-0.03668212890625,
0.044097900390625,
0.03369140625,
-0.016876220703125,
0.003612518310546875,
-0.053497314453125,
0.04461669921875,
0.018280029296875,
-0.0653076171875,
-0.02716064453125,
0.027008056640625,
0.028411865234375,
0.00904083251953125,
0.040802001953125,
-0.006633758544921875,
0.0294647216796875,
0.01678466796875,
0.0115203857421875,
-0.0207061767578125,
-0.0298004150390625,
-0.043548583984375,
0.0318603515625,
0.008087158203125,
-0.0298309326171875
]
] |
lmsys/vicuna-7b-v1.3 | 2023-08-01T18:26:56.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2302.13971",
"arxiv:2306.05685",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | lmsys | null | null | lmsys/vicuna-7b-v1.3 | 112 | 44,238 | transformers | 2023-06-18T03:36:42 | ---
inference: false
---
**NOTE: New version available**
Please check out a newer version of the weights [here](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md).
<br>
# Vicuna Model Card
## Model Details
Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture.
- **License:** Non-commercial license
- **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971).
### Model Sources
- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/
## Uses
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
## How to Get Started with the Model
- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights.
- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api.
## Training Details
Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
The training data is around 125K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
## Difference between different versions of Vicuna
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md) | 1,979 | [
[
-0.01258087158203125,
-0.06414794921875,
0.0270843505859375,
0.034271240234375,
-0.039825439453125,
-0.0162506103515625,
-0.0166778564453125,
-0.04339599609375,
0.0282440185546875,
0.0268402099609375,
-0.039947509765625,
-0.03717041015625,
-0.049285888671875,
-0.0024280548095703125,
-0.0115814208984375,
0.0650634765625,
0.007030487060546875,
0.015625,
-0.006587982177734375,
-0.02734375,
-0.06640625,
-0.037811279296875,
-0.076416015625,
-0.0263214111328125,
0.04693603515625,
0.03509521484375,
0.0472412109375,
0.03912353515625,
0.025299072265625,
0.0294647216796875,
-0.00727081298828125,
0.019744873046875,
-0.04473876953125,
0.004199981689453125,
0.02728271484375,
-0.065673828125,
-0.050872802734375,
-0.018768310546875,
0.041748046875,
0.00616455078125,
-0.0187835693359375,
0.0141754150390625,
0.0005087852478027344,
0.0352783203125,
-0.02496337890625,
0.0272979736328125,
-0.045257568359375,
-0.0195770263671875,
-0.01739501953125,
-0.042266845703125,
-0.0218963623046875,
-0.0244140625,
-0.0100250244140625,
-0.035552978515625,
-0.0037689208984375,
-0.004611968994140625,
0.0833740234375,
0.041168212890625,
-0.02874755859375,
-0.0139007568359375,
-0.0460205078125,
0.04541015625,
-0.0679931640625,
0.032318115234375,
0.032867431640625,
0.04534912109375,
-0.0170440673828125,
-0.043182373046875,
-0.037811279296875,
-0.0290069580078125,
0.005035400390625,
-0.004138946533203125,
-0.0198516845703125,
0.003612518310546875,
0.003955841064453125,
0.03521728515625,
-0.027191162109375,
0.029815673828125,
-0.04248046875,
0.0009722709655761719,
0.044525146484375,
0.0245819091796875,
0.01270294189453125,
-0.01293182373046875,
-0.02716064453125,
-0.029571533203125,
-0.0209808349609375,
-0.0022144317626953125,
0.02947998046875,
0.0379638671875,
-0.04144287109375,
0.040557861328125,
-0.0212860107421875,
0.044464111328125,
-0.0038051605224609375,
-0.015289306640625,
0.037933349609375,
-0.0086517333984375,
-0.032073974609375,
-0.01358795166015625,
0.0863037109375,
0.036651611328125,
0.0011491775512695312,
0.01276397705078125,
0.002841949462890625,
-0.01074981689453125,
0.01241302490234375,
-0.06048583984375,
0.0012636184692382812,
0.0377197265625,
-0.0218048095703125,
-0.03826904296875,
-0.014617919921875,
-0.02398681640625,
-0.036285400390625,
-0.0177459716796875,
0.032806396484375,
-0.033905029296875,
-0.0277862548828125,
0.0254974365234375,
0.0007839202880859375,
0.0234222412109375,
0.03863525390625,
-0.04742431640625,
0.033355712890625,
0.035736083984375,
0.07879638671875,
0.00023102760314941406,
-0.029571533203125,
-0.0164642333984375,
-0.029815673828125,
-0.01096343994140625,
0.06304931640625,
0.003116607666015625,
-0.019775390625,
-0.0093231201171875,
0.016326904296875,
-0.0033702850341796875,
-0.038055419921875,
0.05072021484375,
-0.0229644775390625,
0.027557373046875,
-0.0121612548828125,
-0.0382080078125,
0.0007891654968261719,
0.0170440673828125,
-0.047149658203125,
0.09210205078125,
0.005275726318359375,
-0.060272216796875,
0.007778167724609375,
-0.0384521484375,
-0.0013885498046875,
0.006008148193359375,
0.0013790130615234375,
-0.038848876953125,
-0.006664276123046875,
0.0015163421630859375,
0.0421142578125,
-0.0309295654296875,
0.0281982421875,
-0.018524169921875,
-0.0411376953125,
0.0174713134765625,
-0.032073974609375,
0.08056640625,
0.0189056396484375,
-0.023681640625,
0.033905029296875,
-0.05694580078125,
-0.00818634033203125,
0.02587890625,
-0.0241546630859375,
-0.0291900634765625,
-0.01038360595703125,
-0.0011091232299804688,
-0.0013856887817382812,
0.038360595703125,
-0.0235137939453125,
0.02435302734375,
-0.004810333251953125,
0.01526641845703125,
0.052642822265625,
-0.005374908447265625,
0.018951416015625,
-0.03253173828125,
0.0273590087890625,
-0.00357818603515625,
0.049530029296875,
0.0157012939453125,
-0.0372314453125,
-0.0791015625,
-0.032684326171875,
0.004009246826171875,
0.04803466796875,
-0.057586669921875,
0.050048828125,
-0.031402587890625,
-0.07806396484375,
-0.066162109375,
0.0183868408203125,
0.02874755859375,
0.00432586669921875,
0.0237579345703125,
-0.036712646484375,
-0.05328369140625,
-0.0670166015625,
-0.01280975341796875,
-0.0232696533203125,
-0.00478363037109375,
0.0297698974609375,
0.0189056396484375,
-0.036468505859375,
0.0601806640625,
-0.03704833984375,
-0.0257720947265625,
-0.01132965087890625,
-0.00015652179718017578,
0.005245208740234375,
0.028900146484375,
0.04669189453125,
-0.044342041015625,
-0.0267791748046875,
-0.0084228515625,
-0.0531005859375,
-0.0032634735107421875,
-0.004703521728515625,
-0.031494140625,
0.004856109619140625,
0.034088134765625,
-0.04864501953125,
0.027740478515625,
0.0517578125,
-0.031158447265625,
0.03521728515625,
-0.0172576904296875,
-0.0021724700927734375,
-0.10174560546875,
-0.0022640228271484375,
0.007740020751953125,
-0.035430908203125,
-0.04156494140625,
-0.0016641616821289062,
-0.001377105712890625,
0.0306396484375,
-0.052764892578125,
0.07421875,
-0.030731201171875,
0.01041412353515625,
-0.036163330078125,
-0.00701904296875,
-0.00801849365234375,
0.057861328125,
-0.0015802383422851562,
0.049224853515625,
0.02923583984375,
-0.06280517578125,
0.03515625,
0.01125335693359375,
-0.0213623046875,
0.02020263671875,
-0.06976318359375,
0.018707275390625,
0.00030159950256347656,
0.024139404296875,
-0.06298828125,
-0.0026607513427734375,
0.042510986328125,
-0.0421142578125,
0.01422882080078125,
-0.0024166107177734375,
-0.03448486328125,
-0.0142822265625,
-0.0206451416015625,
0.01495361328125,
0.024749755859375,
-0.032745361328125,
0.019927978515625,
0.035919189453125,
0.00959014892578125,
-0.04290771484375,
-0.04339599609375,
-0.0010957717895507812,
-0.028961181640625,
-0.007251739501953125,
0.0031948089599609375,
-0.0211029052734375,
-0.01751708984375,
-0.016510009765625,
0.007549285888671875,
-0.0072021484375,
0.00807952880859375,
0.0229644775390625,
0.0028247833251953125,
0.00322723388671875,
0.012542724609375,
-0.0118560791015625,
0.0011501312255859375,
-0.01177978515625,
-0.004974365234375,
0.07635498046875,
-0.03704833984375,
0.0074920654296875,
-0.0628662109375,
-0.0121917724609375,
0.043548583984375,
0.00768280029296875,
0.0947265625,
0.0633544921875,
-0.017791748046875,
0.014007568359375,
-0.051910400390625,
-0.01534271240234375,
-0.036773681640625,
0.032989501953125,
-0.01485443115234375,
-0.061920166015625,
0.044647216796875,
0.0293731689453125,
0.0246429443359375,
0.034271240234375,
0.05926513671875,
0.00838470458984375,
0.042572021484375,
0.06707763671875,
-0.01280975341796875,
0.0758056640625,
-0.0195770263671875,
-0.0110931396484375,
-0.0579833984375,
-0.0223541259765625,
-0.048248291015625,
-0.009521484375,
-0.050445556640625,
-0.04766845703125,
0.00034046173095703125,
-0.0022373199462890625,
-0.02655029296875,
0.055511474609375,
-0.040069580078125,
0.005374908447265625,
0.04266357421875,
0.025726318359375,
0.0216522216796875,
-0.00621795654296875,
0.018310546875,
0.01013946533203125,
-0.049530029296875,
-0.042877197265625,
0.07672119140625,
0.04931640625,
0.052703857421875,
0.0099029541015625,
0.045501708984375,
0.0196380615234375,
0.038482666015625,
-0.06842041015625,
0.0391845703125,
0.0199127197265625,
-0.053314208984375,
-0.031585693359375,
-0.0611572265625,
-0.0821533203125,
0.027435302734375,
-0.01345062255859375,
-0.056365966796875,
0.01016998291015625,
0.006778717041015625,
-0.01044464111328125,
0.0221710205078125,
-0.054412841796875,
0.05999755859375,
-0.03009033203125,
-0.0177154541015625,
-0.0036411285400390625,
-0.037017822265625,
0.04376220703125,
0.0111846923828125,
0.00994873046875,
-0.0149383544921875,
-0.0076446533203125,
0.06243896484375,
-0.048828125,
0.0858154296875,
-0.01287841796875,
-0.027618408203125,
0.01824951171875,
-0.0096435546875,
0.021209716796875,
0.00064849853515625,
0.003734588623046875,
0.0297088623046875,
0.00911712646484375,
-0.039764404296875,
-0.04144287109375,
0.04473876953125,
-0.08367919921875,
-0.02783203125,
-0.020538330078125,
-0.030914306640625,
0.006969451904296875,
0.012664794921875,
0.0267333984375,
0.021026611328125,
-0.01291656494140625,
0.0213165283203125,
0.040069580078125,
-0.0302734375,
-0.0013885498046875,
0.0352783203125,
-0.0236968994140625,
-0.033935546875,
0.047119140625,
-0.0020503997802734375,
0.01204681396484375,
0.043243408203125,
0.01517486572265625,
-0.00904083251953125,
-0.01247406005859375,
-0.0124969482421875,
0.02825927734375,
-0.03558349609375,
-0.0170745849609375,
-0.061370849609375,
-0.0156402587890625,
-0.031585693359375,
0.035003662109375,
-0.061767578125,
-0.0285186767578125,
-0.0233001708984375,
-0.0036067962646484375,
0.05657958984375,
0.0301971435546875,
0.023040771484375,
0.06463623046875,
-0.042999267578125,
0.01629638671875,
0.015960693359375,
0.0250701904296875,
0.0030956268310546875,
-0.053558349609375,
-0.039276123046875,
0.01279449462890625,
-0.0230255126953125,
-0.06109619140625,
0.037567138671875,
-0.006656646728515625,
0.03399658203125,
0.029754638671875,
-0.00003790855407714844,
0.05950927734375,
-0.0162811279296875,
0.04248046875,
0.0137176513671875,
-0.0379638671875,
0.03131103515625,
-0.018798828125,
0.0267486572265625,
0.04791259765625,
0.03021240234375,
-0.04730224609375,
-0.02239990234375,
-0.05859375,
-0.0548095703125,
0.036041259765625,
0.0240478515625,
0.0261077880859375,
-0.0016851425170898438,
0.035888671875,
0.00579071044921875,
0.0201873779296875,
-0.063720703125,
-0.0377197265625,
-0.00591278076171875,
-0.024383544921875,
-0.017333984375,
-0.0208740234375,
0.00246429443359375,
-0.032318115234375,
0.053131103515625,
-0.0086212158203125,
0.039947509765625,
0.004695892333984375,
-0.0020465850830078125,
-0.004024505615234375,
0.01122283935546875,
0.04931640625,
0.0221710205078125,
-0.036041259765625,
-0.0200347900390625,
0.01422119140625,
-0.03912353515625,
-0.006458282470703125,
0.00995635986328125,
0.0015325546264648438,
0.007549285888671875,
0.025054931640625,
0.10919189453125,
0.0283966064453125,
-0.037078857421875,
0.0277252197265625,
-0.05859375,
-0.0158843994140625,
-0.031402587890625,
0.01467132568359375,
0.01137542724609375,
0.03125,
0.00992584228515625,
-0.010223388671875,
-0.0085906982421875,
-0.0517578125,
-0.015869140625,
0.0277862548828125,
-0.03057861328125,
-0.0210113525390625,
0.0462646484375,
0.0133056640625,
-0.035369873046875,
0.0275115966796875,
0.003063201904296875,
-0.025421142578125,
0.0308074951171875,
0.01018524169921875,
0.0645751953125,
-0.0184326171875,
0.00836944580078125,
0.036468505859375,
0.0222320556640625,
-0.0125732421875,
0.01467132568359375,
-0.0157012939453125,
-0.0584716796875,
-0.000028967857360839844,
-0.050445556640625,
-0.044342041015625,
0.0228271484375,
-0.048553466796875,
0.03436279296875,
-0.0259552001953125,
-0.040252685546875,
-0.0293426513671875,
0.042236328125,
-0.06866455078125,
-0.00220489501953125,
-0.010589599609375,
0.064697265625,
-0.054779052734375,
0.07562255859375,
0.04473876953125,
-0.03436279296875,
-0.06707763671875,
-0.026153564453125,
-0.004795074462890625,
-0.06451416015625,
0.0117034912109375,
0.003841400146484375,
-0.0010585784912109375,
-0.007587432861328125,
-0.052581787109375,
-0.057098388671875,
0.10418701171875,
0.0281829833984375,
-0.04412841796875,
-0.0156707763671875,
-0.010833740234375,
0.048828125,
-0.00745391845703125,
0.043182373046875,
0.03021240234375,
0.013946533203125,
0.005199432373046875,
-0.09100341796875,
0.0004968643188476562,
-0.036651611328125,
-0.0011386871337890625,
-0.01416015625,
-0.08544921875,
0.06695556640625,
0.0032711029052734375,
-0.0027980804443359375,
0.0198822021484375,
0.0643310546875,
0.03857421875,
0.00821685791015625,
0.040863037109375,
0.0269775390625,
0.07354736328125,
0.00806427001953125,
0.0855712890625,
-0.011566162109375,
0.0151519775390625,
0.0888671875,
0.00518035888671875,
0.06494140625,
0.0312042236328125,
-0.0014638900756835938,
0.041534423828125,
0.0579833984375,
0.0187530517578125,
0.0146331787109375,
0.00013685226440429688,
0.00543975830078125,
0.0012979507446289062,
0.0038509368896484375,
-0.032806396484375,
0.03619384765625,
0.0180816650390625,
-0.01287841796875,
0.01032257080078125,
-0.007381439208984375,
0.0264434814453125,
-0.0229644775390625,
-0.0034809112548828125,
0.056396484375,
0.0229644775390625,
-0.04168701171875,
0.08001708984375,
0.01029205322265625,
0.0819091796875,
-0.055755615234375,
0.0187835693359375,
-0.036102294921875,
0.028289794921875,
-0.0008187294006347656,
-0.01433563232421875,
0.004001617431640625,
0.01074981689453125,
0.018646240234375,
0.0017614364624023438,
0.037139892578125,
-0.0275421142578125,
-0.02520751953125,
0.02716064453125,
0.040863037109375,
0.038665771484375,
0.0003523826599121094,
-0.056671142578125,
0.035400390625,
-0.0068359375,
-0.04388427734375,
0.017547607421875,
0.0275421142578125,
-0.01435089111328125,
0.07733154296875,
0.037384033203125,
0.009857177734375,
0.0020542144775390625,
0.0252838134765625,
0.06591796875,
-0.03741455078125,
-0.03240966796875,
-0.056182861328125,
0.0242919921875,
-0.004344940185546875,
-0.037017822265625,
0.06884765625,
0.0345458984375,
0.053314208984375,
0.01174163818359375,
0.029327392578125,
-0.0024471282958984375,
0.02105712890625,
-0.037139892578125,
0.054534912109375,
-0.061737060546875,
0.0156707763671875,
-0.02728271484375,
-0.0653076171875,
-0.01145172119140625,
0.04541015625,
-0.0131683349609375,
0.01213836669921875,
0.0340576171875,
0.057586669921875,
0.010467529296875,
-0.0189208984375,
0.019134521484375,
0.0231781005859375,
0.034820556640625,
0.036346435546875,
0.042633056640625,
-0.05975341796875,
0.039031982421875,
-0.01377105712890625,
-0.0213165283203125,
-0.037109375,
-0.0487060546875,
-0.08349609375,
-0.048858642578125,
-0.015289306640625,
-0.02203369140625,
0.01195526123046875,
0.0760498046875,
0.052978515625,
-0.02099609375,
-0.04791259765625,
0.006381988525390625,
-0.0030364990234375,
-0.019378662109375,
-0.016387939453125,
0.01555633544921875,
-0.00421905517578125,
-0.0673828125,
0.0145416259765625,
-0.024658203125,
0.0175933837890625,
-0.023193359375,
-0.0306854248046875,
-0.0224609375,
0.006732940673828125,
0.031402587890625,
0.039031982421875,
-0.03485107421875,
0.0007581710815429688,
-0.007549285888671875,
-0.03192138671875,
0.0136566162109375,
0.0232391357421875,
-0.052978515625,
0.004299163818359375,
0.028228759765625,
0.01161956787109375,
0.05072021484375,
-0.00441741943359375,
0.033905029296875,
-0.053863525390625,
0.043548583984375,
-0.006549835205078125,
0.030487060546875,
0.038848876953125,
-0.0254058837890625,
0.031646728515625,
-0.003643035888671875,
-0.028564453125,
-0.072265625,
-0.01433563232421875,
-0.07464599609375,
-0.014617919921875,
0.09295654296875,
0.02001953125,
-0.044708251953125,
0.0117340087890625,
-0.04345703125,
0.05133056640625,
-0.0269622802734375,
0.05645751953125,
0.03369140625,
0.0194854736328125,
-0.040283203125,
-0.055999755859375,
0.038360595703125,
0.0200042724609375,
-0.06549072265625,
0.00472259521484375,
0.020355224609375,
0.03302001953125,
-0.00030040740966796875,
0.09368896484375,
-0.003566741943359375,
0.000053822994232177734,
-0.01227569580078125,
0.038848876953125,
-0.0215911865234375,
-0.0298614501953125,
-0.01763916015625,
-0.027923583984375,
0.01427459716796875,
-0.024810791015625
]
] |
Vamsi/T5_Paraphrase_Paws | 2023-06-12T06:31:04.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"t5",
"text2text-generation",
"paraphrase-generation",
"text-generation",
"Conditional Generation",
"en",
"autotrain_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | Vamsi | null | null | Vamsi/T5_Paraphrase_Paws | 23 | 44,153 | transformers | 2022-03-02T23:29:05 | ---
language: "en"
tags:
- paraphrase-generation
- text-generation
- Conditional Generation
inference: false
---
# Paraphrase-Generation
## Model description
T5 Model for generating paraphrases of english sentences. Trained on the [Google PAWS](https://github.com/google-research-datasets/paws) dataset.
## How to use
## Requires sentencepiece: # !pip install sentencepiece
PyTorch and TF models available
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Vamsi/T5_Paraphrase_Paws")
model = AutoModelForSeq2SeqLM.from_pretrained("Vamsi/T5_Paraphrase_Paws").to('cuda')
sentence = "This is something which i cannot understand at all"
text = "paraphrase: " + sentence + " </s>"
encoding = tokenizer.encode_plus(text,pad_to_max_length=True, return_tensors="pt")
input_ids, attention_masks = encoding["input_ids"].to("cuda"), encoding["attention_mask"].to("cuda")
outputs = model.generate(
input_ids=input_ids, attention_mask=attention_masks,
max_length=256,
do_sample=True,
top_k=120,
top_p=0.95,
early_stopping=True,
num_return_sequences=5
)
for output in outputs:
line = tokenizer.decode(output, skip_special_tokens=True,clean_up_tokenization_spaces=True)
print(line)
```
For more reference on training your own T5 model or using this model, do check out [Paraphrase Generation](https://github.com/Vamsi995/Paraphrase-Generator).
| 1,455 | [
[
0.004302978515625,
-0.038909912109375,
0.0304412841796875,
0.02398681640625,
-0.036651611328125,
-0.011474609375,
0.00836181640625,
-0.003414154052734375,
0.00803375244140625,
0.04095458984375,
-0.0419921875,
-0.04498291015625,
-0.032623291015625,
0.0242919921875,
-0.033477783203125,
0.08642578125,
0.0031871795654296875,
0.01190185546875,
-0.01202392578125,
-0.0003714561462402344,
-0.01910400390625,
-0.031280517578125,
-0.0401611328125,
-0.020355224609375,
0.01287078857421875,
0.03411865234375,
0.019927978515625,
0.039398193359375,
0.0219573974609375,
0.0268096923828125,
-0.01288604736328125,
0.002079010009765625,
-0.024749755859375,
0.0018682479858398438,
-0.005672454833984375,
-0.034912109375,
-0.0265350341796875,
-0.011383056640625,
0.03497314453125,
0.033294677734375,
-0.00957489013671875,
0.0173492431640625,
-0.00150299072265625,
-0.0057373046875,
-0.03564453125,
0.0143585205078125,
-0.043426513671875,
0.0097808837890625,
-0.012054443359375,
-0.0175323486328125,
-0.027496337890625,
-0.02154541015625,
-0.003108978271484375,
-0.05596923828125,
0.0302276611328125,
0.0015573501586914062,
0.0963134765625,
0.0202789306640625,
-0.0234832763671875,
-0.03466796875,
-0.02520751953125,
0.06329345703125,
-0.06787109375,
-0.0030460357666015625,
0.038177490234375,
0.0157928466796875,
0.0006275177001953125,
-0.10723876953125,
-0.042938232421875,
-0.007389068603515625,
-0.005519866943359375,
0.004070281982421875,
0.0014295578002929688,
-0.004566192626953125,
0.0300750732421875,
0.037109375,
-0.044891357421875,
-0.043060302734375,
-0.053192138671875,
-0.013458251953125,
0.0306243896484375,
0.029388427734375,
0.028106689453125,
-0.03509521484375,
-0.0177154541015625,
-0.013946533203125,
-0.028289794921875,
0.014923095703125,
0.01557159423828125,
0.0008044242858886719,
-0.01235198974609375,
0.04644775390625,
-0.0195465087890625,
0.03411865234375,
0.0311431884765625,
-0.0093841552734375,
0.030181884765625,
-0.02935791015625,
-0.021759033203125,
-0.01529693603515625,
0.0687255859375,
0.02593994140625,
0.0086822509765625,
-0.0242919921875,
-0.010772705078125,
-0.00522613525390625,
0.018768310546875,
-0.07342529296875,
-0.0369873046875,
0.0189056396484375,
-0.0311431884765625,
-0.061187744140625,
0.01153564453125,
-0.043243408203125,
-0.0036144256591796875,
0.003864288330078125,
0.05078125,
-0.038482666015625,
0.003665924072265625,
0.0246429443359375,
-0.037353515625,
0.0274658203125,
-0.033294677734375,
-0.07537841796875,
0.0214691162109375,
0.025543212890625,
0.05450439453125,
0.0169830322265625,
-0.044891357421875,
-0.04498291015625,
0.016326904296875,
-0.01467132568359375,
0.03631591796875,
-0.032623291015625,
-0.034912109375,
-0.013427734375,
0.0242156982421875,
-0.0101776123046875,
-0.03289794921875,
0.06475830078125,
-0.0115814208984375,
0.050018310546875,
-0.00720977783203125,
-0.049346923828125,
-0.010589599609375,
0.00701904296875,
-0.0260467529296875,
0.068115234375,
-0.0003757476806640625,
-0.0697021484375,
0.0169219970703125,
-0.056121826171875,
-0.0450439453125,
0.00743865966796875,
-0.0010128021240234375,
-0.0491943359375,
0.01032257080078125,
0.03704833984375,
0.037628173828125,
-0.00984954833984375,
0.0281829833984375,
-0.039215087890625,
-0.0167236328125,
0.0181121826171875,
-0.009552001953125,
0.0784912109375,
0.01611328125,
-0.037384033203125,
0.00897216796875,
-0.057037353515625,
0.00957489013671875,
0.024749755859375,
-0.00952911376953125,
0.00408935546875,
-0.00994110107421875,
0.020294189453125,
0.03009033203125,
0.03387451171875,
-0.044647216796875,
0.0005941390991210938,
-0.03717041015625,
0.08355712890625,
0.0298004150390625,
0.022674560546875,
0.02239990234375,
-0.0369873046875,
0.038909912109375,
0.01270294189453125,
0.013641357421875,
-0.00768280029296875,
-0.01160430908203125,
-0.06146240234375,
0.0013341903686523438,
0.0208587646484375,
0.03399658203125,
-0.07391357421875,
0.03875732421875,
-0.020111083984375,
-0.03375244140625,
-0.05010986328125,
0.004405975341796875,
0.0258636474609375,
0.04827880859375,
0.037689208984375,
-0.004547119140625,
-0.04840087890625,
-0.0545654296875,
-0.0164031982421875,
0.004657745361328125,
-0.00707244873046875,
0.00579071044921875,
0.061065673828125,
0.00940704345703125,
0.05096435546875,
-0.038421630859375,
-0.01496124267578125,
-0.02655029296875,
0.02032470703125,
0.0086822509765625,
0.03192138671875,
0.03253173828125,
-0.05059814453125,
-0.02178955078125,
-0.03375244140625,
-0.0633544921875,
-0.01453399658203125,
-0.01174163818359375,
-0.01146697998046875,
-0.005779266357421875,
0.0396728515625,
-0.05474853515625,
0.0109405517578125,
0.0207977294921875,
-0.046112060546875,
0.0266265869140625,
-0.0225067138671875,
0.0038051605224609375,
-0.133544921875,
0.0328369140625,
-0.0094451904296875,
-0.01763916015625,
-0.0321044921875,
0.02099609375,
0.00533294677734375,
-0.01070404052734375,
-0.04010009765625,
0.038909912109375,
-0.0211029052734375,
0.0099945068359375,
-0.0165557861328125,
-0.00147247314453125,
0.0137939453125,
0.034088134765625,
0.0024318695068359375,
0.06488037109375,
0.039764404296875,
-0.05010986328125,
0.0288238525390625,
0.05242919921875,
-0.0176849365234375,
0.0183868408203125,
-0.07183837890625,
0.00897216796875,
0.01342010498046875,
0.01557159423828125,
-0.06787109375,
-0.038665771484375,
0.02020263671875,
-0.060302734375,
-0.01497650146484375,
0.01148223876953125,
-0.0263519287109375,
-0.033599853515625,
-0.033721923828125,
0.00811004638671875,
0.045684814453125,
-0.04425048828125,
0.031494140625,
0.022705078125,
-0.00812530517578125,
-0.050262451171875,
-0.0657958984375,
0.0273590087890625,
-0.04217529296875,
-0.044158935546875,
0.0269012451171875,
-0.006420135498046875,
0.01446533203125,
-0.004825592041015625,
0.00951385498046875,
-0.013031005859375,
0.0026454925537109375,
0.0017099380493164062,
-0.00047516822814941406,
-0.0082855224609375,
-0.00333404541015625,
0.005161285400390625,
0.00450897216796875,
0.0219573974609375,
-0.02532958984375,
0.042755126953125,
-0.01019287109375,
0.019927978515625,
-0.033172607421875,
0.01552581787109375,
0.05499267578125,
-0.02020263671875,
0.04144287109375,
0.05694580078125,
-0.02398681640625,
-0.01183319091796875,
-0.01558685302734375,
-0.0221405029296875,
-0.036529541015625,
0.0290679931640625,
-0.056976318359375,
-0.038421630859375,
0.04327392578125,
0.0236968994140625,
0.007061004638671875,
0.04376220703125,
0.03955078125,
-0.002643585205078125,
0.07501220703125,
0.02874755859375,
0.007228851318359375,
0.02056884765625,
-0.031402587890625,
0.0008525848388671875,
-0.054412841796875,
-0.01064300537109375,
-0.021728515625,
0.00141143798828125,
-0.035400390625,
-0.0103607177734375,
0.014617919921875,
0.0034656524658203125,
-0.0182647705078125,
0.0291900634765625,
-0.03985595703125,
0.0306243896484375,
0.05841064453125,
0.015838623046875,
-0.00007027387619018555,
0.00597381591796875,
-0.02032470703125,
-0.0017223358154296875,
-0.04791259765625,
-0.054931640625,
0.09478759765625,
0.016143798828125,
0.039154052734375,
-0.00948333740234375,
0.0587158203125,
0.0051116943359375,
-0.0223388671875,
-0.0399169921875,
0.04901123046875,
-0.0278472900390625,
-0.034912109375,
-0.01313018798828125,
-0.01079559326171875,
-0.071044921875,
0.0007266998291015625,
-0.00679779052734375,
-0.034942626953125,
-0.0139923095703125,
0.003009796142578125,
-0.0283660888671875,
0.0157470703125,
-0.047210693359375,
0.08782958984375,
0.0022144317626953125,
-0.01702880859375,
0.01253509521484375,
-0.0587158203125,
0.02520751953125,
0.0189056396484375,
-0.0233612060546875,
0.0176849365234375,
-0.0025634765625,
0.061798095703125,
-0.035552978515625,
0.0555419921875,
-0.0130615234375,
0.019805908203125,
0.0169219970703125,
-0.01322174072265625,
0.02117919921875,
-0.00565338134765625,
0.007488250732421875,
-0.01061248779296875,
0.00772857666015625,
-0.044189453125,
-0.017486572265625,
0.039825439453125,
-0.064697265625,
-0.037841796875,
-0.01441192626953125,
-0.034454345703125,
0.00020253658294677734,
0.013885498046875,
0.06072998046875,
0.032745361328125,
-0.0180206298828125,
0.032745361328125,
0.0274658203125,
-0.01074981689453125,
0.050079345703125,
0.00458526611328125,
0.005924224853515625,
-0.06011962890625,
0.0684814453125,
-0.00736236572265625,
0.0128326416015625,
0.0255584716796875,
0.0158233642578125,
-0.03472900390625,
-0.0241546630859375,
-0.0280609130859375,
0.02593994140625,
-0.05615234375,
0.004077911376953125,
-0.065673828125,
-0.025299072265625,
-0.0557861328125,
0.005611419677734375,
0.01122283935546875,
-0.03515625,
-0.0285186767578125,
-0.011932373046875,
0.0257415771484375,
0.046875,
0.002536773681640625,
0.03399658203125,
-0.048858642578125,
0.0281982421875,
0.01751708984375,
-0.0162353515625,
-0.0228729248046875,
-0.0599365234375,
-0.021636962890625,
-0.014373779296875,
-0.055633544921875,
-0.06298828125,
0.059661865234375,
0.0127410888671875,
0.0264129638671875,
0.020294189453125,
0.0090484619140625,
0.04541015625,
-0.0280914306640625,
0.0804443359375,
-0.0034465789794921875,
-0.08575439453125,
0.034454345703125,
-0.0352783203125,
0.031402587890625,
0.0232391357421875,
0.01491546630859375,
-0.04058837890625,
-0.055633544921875,
-0.07666015625,
-0.0733642578125,
0.052825927734375,
0.029022216796875,
0.01404571533203125,
-0.01137542724609375,
0.020538330078125,
0.00862884521484375,
0.017974853515625,
-0.073974609375,
-0.01122283935546875,
-0.038543701171875,
-0.057464599609375,
-0.01522064208984375,
-0.01446533203125,
-0.007232666015625,
-0.0155181884765625,
0.0665283203125,
-0.003086090087890625,
0.0328369140625,
0.017547607421875,
-0.0299072265625,
0.007663726806640625,
0.00811767578125,
0.0673828125,
0.048095703125,
-0.01751708984375,
-0.0020904541015625,
0.0277557373046875,
-0.034332275390625,
-0.0028553009033203125,
0.017974853515625,
-0.0285491943359375,
0.0204620361328125,
0.01690673828125,
0.087646484375,
-0.0117645263671875,
-0.02142333984375,
0.04248046875,
-0.01329803466796875,
-0.043243408203125,
-0.033477783203125,
-0.004608154296875,
0.027313232421875,
0.0169525146484375,
0.01776123046875,
-0.02197265625,
0.024749755859375,
-0.01544952392578125,
0.019927978515625,
0.0019702911376953125,
-0.003223419189453125,
-0.0245208740234375,
0.08978271484375,
0.0255584716796875,
-0.0211639404296875,
0.0479736328125,
-0.005947113037109375,
-0.0301513671875,
0.0557861328125,
0.042572021484375,
0.09271240234375,
-0.0026988983154296875,
0.0145416259765625,
0.03857421875,
0.006649017333984375,
-0.0043487548828125,
0.0274658203125,
-0.01239776611328125,
-0.0379638671875,
-0.0227508544921875,
-0.04718017578125,
-0.022491455078125,
0.063720703125,
-0.04718017578125,
0.028076171875,
-0.02532958984375,
0.00145721435546875,
0.011566162109375,
-0.00649261474609375,
-0.0305633544921875,
0.038909912109375,
0.0113067626953125,
0.04498291015625,
-0.0733642578125,
0.06036376953125,
0.0709228515625,
-0.0574951171875,
-0.0657958984375,
0.024078369140625,
-0.038177490234375,
-0.056915283203125,
0.045257568359375,
0.0248260498046875,
0.00789642333984375,
0.012420654296875,
-0.0545654296875,
-0.037139892578125,
0.09039306640625,
0.0212249755859375,
-0.00806427001953125,
-0.04058837890625,
0.01325225830078125,
0.033355712890625,
-0.035430908203125,
0.0198211669921875,
0.035186767578125,
0.011932373046875,
0.003116607666015625,
-0.055450439453125,
0.0162811279296875,
-0.0302276611328125,
0.007720947265625,
-0.00820159912109375,
-0.04058837890625,
0.07745361328125,
-0.00656890869140625,
0.006961822509765625,
0.0282440185546875,
0.051116943359375,
0.023773193359375,
0.01386260986328125,
0.026031494140625,
0.0462646484375,
0.038787841796875,
0.003818511962890625,
0.06414794921875,
-0.0478515625,
0.048095703125,
0.080322265625,
0.0150909423828125,
0.056915283203125,
0.04901123046875,
0.0090179443359375,
0.0274810791015625,
0.0594482421875,
-0.0204620361328125,
0.055511474609375,
0.00897216796875,
-0.0196533203125,
-0.025054931640625,
0.01812744140625,
-0.01507568359375,
0.02667236328125,
0.01678466796875,
-0.0546875,
-0.019927978515625,
0.009246826171875,
-0.003635406494140625,
-0.01168060302734375,
-0.006931304931640625,
0.05352783203125,
0.00688934326171875,
-0.054962158203125,
0.056427001953125,
0.00910186767578125,
0.0489501953125,
-0.0289764404296875,
-0.000518798828125,
-0.0195465087890625,
0.029571533203125,
-0.00305938720703125,
-0.054412841796875,
0.0233154296875,
0.00789642333984375,
-0.0033245086669921875,
-0.0171661376953125,
0.0439453125,
-0.046173095703125,
-0.0362548828125,
-0.0014514923095703125,
0.0231781005859375,
0.037139892578125,
0.01189422607421875,
-0.07147216796875,
-0.034454345703125,
0.01441192626953125,
-0.033477783203125,
-0.00811004638671875,
0.0361328125,
0.005046844482421875,
0.048736572265625,
0.0219573974609375,
-0.00907135009765625,
0.01470947265625,
-0.00885772705078125,
0.043243408203125,
-0.0631103515625,
-0.055511474609375,
-0.06475830078125,
0.045928955078125,
-0.0195465087890625,
-0.044464111328125,
0.04901123046875,
0.04827880859375,
0.0665283203125,
-0.042755126953125,
0.07183837890625,
-0.01849365234375,
0.03228759765625,
-0.040771484375,
0.055999755859375,
-0.047332763671875,
-0.021820068359375,
0.0041351318359375,
-0.03961181640625,
-0.00011539459228515625,
0.061737060546875,
-0.0167236328125,
0.00008618831634521484,
0.0784912109375,
0.072265625,
-0.01654052734375,
-0.01319122314453125,
0.02423095703125,
0.0279541015625,
0.0192718505859375,
0.0523681640625,
0.039642333984375,
-0.06201171875,
0.08154296875,
-0.03125,
0.033966064453125,
-0.0079803466796875,
-0.0479736328125,
-0.08148193359375,
-0.055694580078125,
-0.027984619140625,
-0.0543212890625,
0.006622314453125,
0.0609130859375,
0.043365478515625,
-0.06646728515625,
-0.0193939208984375,
-0.03912353515625,
-0.0227203369140625,
0.006320953369140625,
-0.0200042724609375,
0.036041259765625,
-0.047149658203125,
-0.07867431640625,
0.01387786865234375,
-0.017578125,
0.01067352294921875,
-0.0005016326904296875,
0.0013570785522460938,
-0.01317596435546875,
0.0098876953125,
0.015167236328125,
0.0174560546875,
-0.06390380859375,
-0.015869140625,
0.0079345703125,
-0.030548095703125,
0.0093841552734375,
0.027252197265625,
-0.035430908203125,
0.00958251953125,
0.0308074951171875,
0.03717041015625,
0.05401611328125,
-0.00688934326171875,
0.056671142578125,
-0.0518798828125,
0.0010843276977539062,
0.0058135986328125,
0.032073974609375,
0.042266845703125,
-0.01183319091796875,
0.038330078125,
0.03497314453125,
-0.0430908203125,
-0.05615234375,
-0.002185821533203125,
-0.07232666015625,
-0.0153656005859375,
0.09271240234375,
-0.02581787109375,
-0.043121337890625,
0.00885772705078125,
-0.02655029296875,
0.051116943359375,
-0.0178375244140625,
0.061187744140625,
0.0657958984375,
0.020416259765625,
-0.005893707275390625,
-0.0289764404296875,
0.041534423828125,
0.049163818359375,
-0.05767822265625,
-0.007747650146484375,
0.0205535888671875,
0.06201171875,
-0.0078887939453125,
0.029052734375,
-0.0096893310546875,
0.037841796875,
0.0141754150390625,
0.034942626953125,
-0.0211029052734375,
0.005641937255859375,
-0.034576416015625,
0.0274505615234375,
-0.005489349365234375,
-0.0626220703125
]
] |
openmmlab/upernet-convnext-small | 2023-01-19T10:45:20.000Z | [
"transformers",
"pytorch",
"upernet",
"vision",
"image-segmentation",
"en",
"arxiv:1807.10221",
"arxiv:2201.03545",
"license:mit",
"endpoints_compatible",
"has_space",
"region:us"
] | image-segmentation | openmmlab | null | null | openmmlab/upernet-convnext-small | 18 | 44,141 | transformers | 2023-01-13T14:24:39 | ---
language: en
license: mit
tags:
- vision
- image-segmentation
model_name: openmmlab/upernet-convnext-small
---
# UperNet, ConvNeXt small-sized backbone
UperNet framework for semantic segmentation, leveraging a ConvNeXt backbone. UperNet was introduced in the paper [Unified Perceptual Parsing for Scene Understanding](https://arxiv.org/abs/1807.10221) by Xiao et al.
Combining UperNet with a ConvNeXt backbone was introduced in the paper [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545).
Disclaimer: The team releasing UperNet + ConvNeXt did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) and a Pyramid Pooling Module (PPM).
Any visual backbone can be plugged into the UperNet framework. The framework predicts a semantic label per pixel.
## Intended uses & limitations
You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?search=openmmlab/upernet) to look for
fine-tuned versions (with various backbones) on a task that interests you.
### How to use
For code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/upernet#transformers.UperNetForSemanticSegmentation).
| 1,556 | [
[
-0.043487548828125,
-0.0179443359375,
0.0183563232421875,
0.03375244140625,
-0.0260162353515625,
-0.02203369140625,
0.01605224609375,
-0.044647216796875,
0.0279083251953125,
0.0545654296875,
-0.0638427734375,
-0.037994384765625,
-0.02490234375,
-0.01483917236328125,
-0.0295562744140625,
0.058624267578125,
0.0226898193359375,
0.0242462158203125,
-0.010162353515625,
-0.018707275390625,
-0.037506103515625,
-0.02197265625,
-0.04095458984375,
-0.034149169921875,
0.0180511474609375,
0.034820556640625,
0.06695556640625,
0.06475830078125,
0.032501220703125,
0.033843994140625,
-0.033966064453125,
-0.0194854736328125,
-0.00653076171875,
-0.01374053955078125,
-0.0268402099609375,
-0.020904541015625,
-0.032135009765625,
-0.004276275634765625,
0.044403076171875,
0.07037353515625,
-0.00220489501953125,
0.0092315673828125,
-0.00832366943359375,
0.051177978515625,
-0.0350341796875,
-0.007709503173828125,
-0.029052734375,
0.01267242431640625,
-0.0231781005859375,
0.0267486572265625,
-0.00792694091796875,
0.0019044876098632812,
0.046539306640625,
-0.043701171875,
0.00604248046875,
0.0123138427734375,
0.0721435546875,
0.0174560546875,
-0.02276611328125,
0.004192352294921875,
-0.0173797607421875,
0.06304931640625,
-0.0136260986328125,
0.02886962890625,
-0.025726318359375,
0.039886474609375,
-0.0107269287109375,
-0.08819580078125,
-0.0419921875,
-0.011383056640625,
-0.003753662109375,
0.0166778564453125,
-0.01837158203125,
0.0158843994140625,
0.006832122802734375,
0.0550537109375,
-0.0287628173828125,
0.0163421630859375,
-0.01317596435546875,
-0.022979736328125,
0.03125,
0.01473236083984375,
0.047332763671875,
-0.050445556640625,
-0.07452392578125,
-0.0280914306640625,
-0.04351806640625,
0.0019931793212890625,
0.0027141571044921875,
0.001674652099609375,
-0.020263671875,
0.048004150390625,
-0.01027679443359375,
0.06488037109375,
0.0157470703125,
0.025634765625,
-0.00160980224609375,
-0.026611328125,
-0.03997802734375,
0.01551055908203125,
0.031524658203125,
0.039154052734375,
0.02044677734375,
0.0025997161865234375,
-0.00611114501953125,
0.016326904296875,
0.0160980224609375,
-0.0699462890625,
-0.048309326171875,
0.0029964447021484375,
-0.05487060546875,
-0.039459228515625,
0.0030307769775390625,
-0.069091796875,
-0.0292816162109375,
-0.0243377685546875,
0.011993408203125,
-0.01398468017578125,
-0.01435089111328125,
0.0209503173828125,
-0.03173828125,
0.0350341796875,
0.033538818359375,
-0.060089111328125,
0.0267486572265625,
0.0416259765625,
0.051727294921875,
-0.00510406494140625,
-0.0006184577941894531,
-0.018463134765625,
-0.0007028579711914062,
0.01198577880859375,
0.0736083984375,
-0.03271484375,
-0.031585693359375,
-0.0265045166015625,
0.0307464599609375,
-0.0177764892578125,
-0.02911376953125,
0.04388427734375,
-0.032745361328125,
0.0194244384765625,
-0.009368896484375,
-0.036102294921875,
-0.033294677734375,
0.0193328857421875,
-0.054107666015625,
0.0626220703125,
0.0176544189453125,
-0.06732177734375,
0.02313232421875,
-0.052093505859375,
0.0146026611328125,
0.01360321044921875,
-0.0227203369140625,
-0.0261383056640625,
0.001861572265625,
0.006610870361328125,
0.032257080078125,
-0.025177001953125,
-0.00899505615234375,
-0.04119873046875,
-0.0039825439453125,
-0.005970001220703125,
-0.0143585205078125,
0.08599853515625,
0.0158843994140625,
-0.0117340087890625,
0.042999267578125,
-0.07989501953125,
0.0011320114135742188,
0.00958251953125,
-0.00818634033203125,
-0.03948974609375,
-0.0131072998046875,
0.0207061767578125,
0.0285797119140625,
0.0075225830078125,
-0.07696533203125,
0.007843017578125,
-0.0439453125,
0.0156402587890625,
0.049407958984375,
-0.003414154052734375,
0.05267333984375,
-0.00689697265625,
0.00927734375,
0.00434112548828125,
0.0188751220703125,
-0.0086517333984375,
-0.039886474609375,
-0.05694580078125,
-0.022430419921875,
0.0275115966796875,
0.0406494140625,
-0.0360107421875,
0.0271453857421875,
-0.004596710205078125,
-0.035125732421875,
-0.018768310546875,
-0.00830841064453125,
0.035858154296875,
0.0469970703125,
0.033447265625,
-0.02203369140625,
-0.055999755859375,
-0.0704345703125,
0.00496673583984375,
0.013916015625,
-0.02740478515625,
-0.0014438629150390625,
0.04241943359375,
-0.01497650146484375,
0.06689453125,
-0.03582763671875,
-0.035430908203125,
-0.0167083740234375,
-0.01534271240234375,
0.0024280548095703125,
0.06353759765625,
0.045318603515625,
-0.08843994140625,
-0.0240631103515625,
0.004009246826171875,
-0.054840087890625,
0.0209197998046875,
0.0174713134765625,
-0.0164031982421875,
-0.0175628662109375,
0.02862548828125,
-0.04302978515625,
0.04833984375,
0.0509033203125,
-0.04840087890625,
0.042388916015625,
-0.01412200927734375,
-0.0183868408203125,
-0.1058349609375,
-0.004535675048828125,
0.0156402587890625,
-0.0162506103515625,
-0.03607177734375,
0.0026988983154296875,
-0.0024433135986328125,
-0.0302276611328125,
-0.052398681640625,
0.05303955078125,
-0.037750244140625,
-0.0279998779296875,
-0.00786590576171875,
0.01087188720703125,
0.022125244140625,
0.03509521484375,
0.0179290771484375,
0.0215301513671875,
0.034881591796875,
-0.03558349609375,
0.044647216796875,
0.052032470703125,
-0.023590087890625,
0.061187744140625,
-0.07635498046875,
-0.0250701904296875,
0.0137481689453125,
0.021759033203125,
-0.068115234375,
-0.045623779296875,
0.0259246826171875,
-0.0106964111328125,
0.024566650390625,
-0.0213470458984375,
-0.0177764892578125,
-0.032440185546875,
-0.0233001708984375,
0.0292816162109375,
0.0196533203125,
-0.072509765625,
0.047576904296875,
0.053131103515625,
0.023193359375,
-0.03240966796875,
-0.05303955078125,
-0.0100860595703125,
-0.0205535888671875,
-0.10406494140625,
0.056365966796875,
0.00701141357421875,
-0.0200347900390625,
0.00714874267578125,
-0.0149688720703125,
-0.01226806640625,
-0.0002734661102294922,
0.0240631103515625,
0.0211181640625,
-0.00902557373046875,
-0.00301361083984375,
-0.00411224365234375,
-0.033203125,
-0.005870819091796875,
-0.03924560546875,
0.01605224609375,
-0.0411376953125,
-0.0146942138671875,
-0.03118896484375,
0.0259246826171875,
0.020355224609375,
-0.01439666748046875,
0.0218353271484375,
0.039306640625,
-0.02099609375,
-0.0214996337890625,
-0.0143280029296875,
-0.019256591796875,
-0.037261962890625,
0.004108428955078125,
-0.03216552734375,
-0.072021484375,
0.05859375,
-0.0291595458984375,
-0.0236968994140625,
0.038543701171875,
0.0235595703125,
-0.01380157470703125,
0.083251953125,
0.0615234375,
0.018218994140625,
0.037933349609375,
-0.02679443359375,
-0.0279998779296875,
-0.0819091796875,
-0.01873779296875,
-0.04302978515625,
-0.02313232421875,
-0.056243896484375,
-0.0164337158203125,
0.020233154296875,
0.01276397705078125,
-0.01203155517578125,
0.04095458984375,
-0.0721435546875,
0.033721923828125,
0.028076171875,
0.004093170166015625,
0.0217132568359375,
0.00199127197265625,
-0.044158935546875,
0.0053863525390625,
-0.0567626953125,
-0.01800537109375,
0.0302886962890625,
0.035736083984375,
0.055999755859375,
-0.01148223876953125,
0.019775390625,
0.0129241943359375,
0.0057525634765625,
-0.0455322265625,
0.054656982421875,
-0.024078369140625,
-0.065185546875,
-0.020965576171875,
-0.00460052490234375,
-0.07891845703125,
0.04595947265625,
-0.0050811767578125,
-0.0989990234375,
0.0609130859375,
0.0160675048828125,
-0.01511383056640625,
0.0298614501953125,
-0.048980712890625,
0.10308837890625,
0.002567291259765625,
-0.009857177734375,
0.006198883056640625,
-0.07342529296875,
0.0254364013671875,
0.0251312255859375,
-0.0281829833984375,
-0.01514434814453125,
0.01611328125,
0.04840087890625,
-0.06585693359375,
0.06982421875,
-0.0213165283203125,
0.01039886474609375,
0.03387451171875,
-0.005889892578125,
0.02813720703125,
0.00881195068359375,
0.006755828857421875,
0.03045654296875,
0.01800537109375,
-0.0280914306640625,
-0.0404052734375,
0.04736328125,
-0.043304443359375,
-0.01678466796875,
-0.020843505859375,
-0.0159454345703125,
0.0096435546875,
0.02679443359375,
0.0302886962890625,
0.058258056640625,
-0.022369384765625,
0.03192138671875,
0.05303955078125,
-0.00618743896484375,
0.034027099609375,
0.0152130126953125,
-0.0162506103515625,
-0.0190887451171875,
0.05859375,
-0.006397247314453125,
-0.0004870891571044922,
0.02313232421875,
0.024139404296875,
-0.034881591796875,
-0.0255889892578125,
-0.0689697265625,
0.006481170654296875,
-0.0609130859375,
-0.013671875,
-0.03631591796875,
-0.0002620220184326172,
0.001110076904296875,
-0.0261993408203125,
-0.061065673828125,
-0.04052734375,
-0.005970001220703125,
0.0122833251953125,
0.019989013671875,
0.0330810546875,
-0.01548004150390625,
0.053680419921875,
-0.057159423828125,
0.0090484619140625,
0.0164337158203125,
0.019683837890625,
-0.018646240234375,
-0.01148223876953125,
-0.00437164306640625,
0.007320404052734375,
-0.02203369140625,
-0.05169677734375,
0.01386260986328125,
-0.01038360595703125,
0.038116455078125,
0.0156402587890625,
-0.005229949951171875,
0.041351318359375,
0.001560211181640625,
0.04132080078125,
0.03192138671875,
-0.06988525390625,
0.041351318359375,
-0.029083251953125,
0.031494140625,
0.04522705078125,
0.02081298828125,
-0.035919189453125,
0.007694244384765625,
-0.047698974609375,
-0.053253173828125,
0.04595947265625,
0.0095977783203125,
-0.0087890625,
0.0084991455078125,
0.013397216796875,
-0.008544921875,
0.0015459060668945312,
-0.037353515625,
-0.00997161865234375,
-0.02288818359375,
-0.01145172119140625,
0.032318115234375,
-0.01727294921875,
-0.00848388671875,
-0.0270233154296875,
0.0233306884765625,
-0.01165771484375,
0.020111083984375,
0.0227813720703125,
-0.0082244873046875,
0.00566864013671875,
-0.004550933837890625,
0.0153961181640625,
0.0340576171875,
-0.03057861328125,
-0.0225067138671875,
0.00476837158203125,
-0.03765869140625,
-0.0027790069580078125,
0.021026611328125,
-0.02642822265625,
-0.0058135986328125,
0.00788116455078125,
0.051849365234375,
0.053985595703125,
-0.00833892822265625,
0.05145263671875,
-0.0260162353515625,
-0.01055145263671875,
-0.043182373046875,
0.0028247833251953125,
-0.0013408660888671875,
0.0255889892578125,
-0.0059356689453125,
0.0309906005859375,
0.015838623046875,
-0.012725830078125,
0.0364990234375,
0.0225677490234375,
-0.066162109375,
-0.02679443359375,
0.042266845703125,
0.038177490234375,
0.00853729248046875,
0.051849365234375,
0.006542205810546875,
-0.0311126708984375,
0.050262451171875,
0.0168304443359375,
0.06597900390625,
-0.01247406005859375,
0.017669677734375,
0.00658416748046875,
-0.0053253173828125,
0.0097198486328125,
0.01788330078125,
-0.028656005859375,
-0.0743408203125,
-0.049102783203125,
-0.06646728515625,
-0.0225830078125,
-0.01247406005859375,
-0.048980712890625,
0.0206451416015625,
-0.026336669921875,
0.00457763671875,
0.02410888671875,
0.007694244384765625,
-0.061370849609375,
0.043609619140625,
0.006000518798828125,
0.09918212890625,
-0.0361328125,
0.07269287109375,
0.077392578125,
-0.034942626953125,
-0.0736083984375,
-0.0228118896484375,
0.0200653076171875,
-0.05419921875,
0.050140380859375,
0.0267333984375,
-0.018646240234375,
0.015899658203125,
-0.03936767578125,
-0.04437255859375,
0.083740234375,
0.0016717910766601562,
-0.01140594482421875,
-0.0125579833984375,
-0.011871337890625,
0.0224151611328125,
-0.061187744140625,
0.0196380615234375,
0.034271240234375,
0.050537109375,
0.03997802734375,
-0.039306640625,
0.00878143310546875,
-0.0104522705078125,
0.0260162353515625,
-0.00022554397583007812,
-0.051055908203125,
0.05780029296875,
-0.0123291015625,
-0.026763916015625,
0.0288848876953125,
0.055999755859375,
0.005313873291015625,
0.0234222412109375,
0.053253173828125,
0.057769775390625,
0.036163330078125,
-0.023223876953125,
0.08721923828125,
0.003505706787109375,
0.018646240234375,
0.08160400390625,
-0.00021219253540039062,
0.028594970703125,
0.0241546630859375,
0.0150146484375,
0.0509033203125,
0.061279296875,
-0.0241546630859375,
0.033294677734375,
0.0170135498046875,
-0.00701141357421875,
-0.02813720703125,
-0.0136566162109375,
-0.029541015625,
0.07366943359375,
0.0240020751953125,
-0.02142333984375,
-0.052734375,
0.0104827880859375,
0.0018253326416015625,
-0.00470733642578125,
-0.03753662109375,
0.05487060546875,
0.01033782958984375,
-0.026947021484375,
0.023895263671875,
-0.005405426025390625,
0.0303802490234375,
-0.043670654296875,
-0.006237030029296875,
-0.0118560791015625,
0.03912353515625,
-0.017181396484375,
-0.0657958984375,
0.0394287109375,
-0.03179931640625,
-0.00667572021484375,
0.004543304443359375,
0.09320068359375,
-0.0111846923828125,
-0.0261993408203125,
0.04693603515625,
0.0235748291015625,
0.01263427734375,
-0.01134490966796875,
-0.085205078125,
0.021392822265625,
0.00289154052734375,
-0.033355712890625,
0.03912353515625,
0.037017822265625,
-0.01424407958984375,
0.055633544921875,
0.04736328125,
-0.0162506103515625,
-0.00977325439453125,
-0.002857208251953125,
0.09796142578125,
-0.044189453125,
-0.040252685546875,
-0.037689208984375,
0.07177734375,
-0.040283203125,
-0.030181884765625,
0.07720947265625,
0.020721435546875,
0.0809326171875,
-0.00848388671875,
0.0199127197265625,
-0.01067352294921875,
0.0236663818359375,
-0.0221405029296875,
0.0364990234375,
-0.06134033203125,
0.0044403076171875,
-0.0269012451171875,
-0.080322265625,
-0.034210205078125,
0.039825439453125,
-0.018035888671875,
-0.0006809234619140625,
0.04095458984375,
0.0634765625,
-0.017730712890625,
0.02716064453125,
0.028533935546875,
-0.006061553955078125,
0.0058746337890625,
0.006298065185546875,
0.06085205078125,
-0.0269317626953125,
0.043212890625,
-0.036346435546875,
-0.0252227783203125,
-0.01490020751953125,
-0.07196044921875,
-0.05517578125,
-0.023468017578125,
-0.010894775390625,
-0.02691650390625,
-0.0015897750854492188,
0.042083740234375,
0.0926513671875,
-0.05499267578125,
-0.009979248046875,
-0.032257080078125,
0.0204315185546875,
0.002338409423828125,
-0.0174102783203125,
0.029571533203125,
-0.00458526611328125,
-0.05072021484375,
0.026611328125,
0.038909912109375,
0.0073699951171875,
-0.0234222412109375,
-0.000545501708984375,
-0.014404296875,
-0.009033203125,
0.038604736328125,
0.040130615234375,
-0.0261993408203125,
-0.042327880859375,
-0.02032470703125,
0.004611968994140625,
0.0036754608154296875,
0.05657958984375,
-0.04339599609375,
0.040924072265625,
0.04718017578125,
0.03875732421875,
0.044403076171875,
0.01047515869140625,
0.049072265625,
-0.06329345703125,
0.035736083984375,
0.0009112358093261719,
0.0323486328125,
0.0272064208984375,
-0.01140594482421875,
0.040130615234375,
0.031707763671875,
-0.0560302734375,
-0.0275115966796875,
0.03875732421875,
-0.1004638671875,
-0.019775390625,
0.04583740234375,
-0.0142974853515625,
-0.06378173828125,
-0.0179595947265625,
-0.0196685791015625,
0.003406524658203125,
-0.020233154296875,
0.01617431640625,
0.02313232421875,
-0.00714874267578125,
-0.00853729248046875,
-0.0126953125,
0.054473876953125,
0.022216796875,
-0.03436279296875,
-0.01149749755859375,
0.037109375,
0.0185546875,
0.027435302734375,
0.0185699462890625,
-0.0303497314453125,
0.02313232421875,
0.0217437744140625,
0.02001953125,
-0.006725311279296875,
-0.0256195068359375,
-0.01453399658203125,
0.0199127197265625,
-0.0345458984375,
-0.0309600830078125
]
] |
digiplay/AbsoluteReality_v1.8.1 | 2023-08-03T18:05:25.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | digiplay | null | null | digiplay/AbsoluteReality_v1.8.1 | 5 | 43,801 | diffusers | 2023-08-03T16:58:32 | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/81458?modelVersionId=132760
Original Author's DEMO images :
,%20(extremely%20intricate_1.3),,%20(realistic),%20portrait%20of%20a%20girl,%20the%20most%20beautiful%20in%20the%20world,%20(medieval%20armor),%20m.jpeg)
.jpeg)
),%20intricate,%20(steel%20metal%20[rust]),%20elegant,.jpeg)
| 1,077 | [
[
-0.033905029296875,
-0.03790283203125,
0.02984619140625,
0.0209197998046875,
-0.0164794921875,
-0.0039043426513671875,
0.0124664306640625,
-0.024383544921875,
0.03668212890625,
0.033355712890625,
-0.06390380859375,
-0.035247802734375,
-0.02374267578125,
0.00030493736267089844,
-0.0136260986328125,
0.04052734375,
0.0023212432861328125,
0.002468109130859375,
0.00641632080078125,
0.01055145263671875,
-0.031646728515625,
-0.026214599609375,
-0.036712646484375,
0.0036067962646484375,
0.02069091796875,
0.022247314453125,
0.0626220703125,
0.03826904296875,
0.041473388671875,
0.029266357421875,
-0.0182037353515625,
0.00507354736328125,
-0.03216552734375,
-0.02288818359375,
0.00757598876953125,
-0.04034423828125,
-0.04998779296875,
0.01432037353515625,
0.026397705078125,
0.0292510986328125,
0.006931304931640625,
0.02435302734375,
0.0219879150390625,
0.03790283203125,
-0.0391845703125,
0.0191802978515625,
-0.005275726318359375,
0.0116729736328125,
-0.019805908203125,
-0.0268707275390625,
-0.025848388671875,
-0.0325927734375,
-0.0193328857421875,
-0.07684326171875,
0.022857666015625,
0.002674102783203125,
0.100341796875,
-0.01055145263671875,
-0.024200439453125,
-0.00391387939453125,
-0.0557861328125,
0.0498046875,
-0.0504150390625,
0.021331787109375,
0.006877899169921875,
0.04119873046875,
-0.0271453857421875,
-0.057403564453125,
-0.036041259765625,
0.023590087890625,
-0.031036376953125,
0.04449462890625,
-0.03839111328125,
-0.0214996337890625,
0.0263671875,
0.0328369140625,
-0.0670166015625,
-0.0064544677734375,
-0.039703369140625,
0.014678955078125,
0.043182373046875,
0.00836181640625,
0.040740966796875,
0.01168060302734375,
-0.05194091796875,
-0.0233917236328125,
-0.033477783203125,
0.0298004150390625,
0.0232391357421875,
-0.0034008026123046875,
-0.0394287109375,
0.034637451171875,
-0.00858306884765625,
0.048248291015625,
0.0305938720703125,
-0.025970458984375,
0.024261474609375,
-0.03271484375,
-0.0214996337890625,
-0.039947509765625,
0.0626220703125,
0.0784912109375,
0.0092926025390625,
0.00788116455078125,
0.0027484893798828125,
-0.03253173828125,
0.0179595947265625,
-0.0709228515625,
-0.01715087890625,
0.013397216796875,
-0.055206298828125,
-0.03082275390625,
0.01540374755859375,
-0.062225341796875,
0.00379180908203125,
0.005008697509765625,
0.01284027099609375,
-0.036895751953125,
-0.02886962890625,
-0.0001462697982788086,
-0.00989532470703125,
0.02642822265625,
0.02490234375,
-0.05206298828125,
0.0019683837890625,
0.0208587646484375,
0.05621337890625,
0.0253143310546875,
0.0016183853149414062,
0.01076507568359375,
0.0225372314453125,
-0.045196533203125,
0.061248779296875,
-0.016693115234375,
-0.04345703125,
-0.0125579833984375,
0.03204345703125,
-0.00604248046875,
-0.01006317138671875,
0.070068359375,
-0.03546142578125,
0.0021762847900390625,
-0.0255279541015625,
-0.01934814453125,
-0.03955078125,
0.02435302734375,
-0.062744140625,
0.0294189453125,
0.01560211181640625,
-0.08331298828125,
0.026123046875,
-0.029876708984375,
0.006214141845703125,
0.017730712890625,
-0.0131378173828125,
-0.042449951171875,
0.0117645263671875,
0.001247406005859375,
0.0282440185546875,
-0.0288543701171875,
-0.0196685791015625,
-0.053680419921875,
-0.0280914306640625,
0.026458740234375,
-0.0225372314453125,
0.087158203125,
0.0202484130859375,
-0.0390625,
-0.0091705322265625,
-0.066162109375,
0.00579833984375,
0.031463623046875,
0.004711151123046875,
-0.01424407958984375,
-0.02459716796875,
0.0204010009765625,
0.0295257568359375,
0.0194091796875,
-0.039215087890625,
0.022918701171875,
-0.0233306884765625,
0.0102996826171875,
0.042083740234375,
0.0231781005859375,
0.00595855712890625,
-0.05426025390625,
0.0667724609375,
-0.004974365234375,
0.050506591796875,
0.0011444091796875,
-0.0233154296875,
-0.062225341796875,
-0.058807373046875,
-0.001361846923828125,
0.0245819091796875,
-0.051513671875,
0.037933349609375,
-0.01253509521484375,
-0.078125,
-0.028839111328125,
-0.0233001708984375,
0.0396728515625,
0.0305633544921875,
0.001399993896484375,
-0.00872039794921875,
-0.024169921875,
-0.10809326171875,
-0.021759033203125,
-0.0045623779296875,
-0.00811767578125,
0.0296783447265625,
0.045318603515625,
0.0057373046875,
0.055938720703125,
-0.041839599609375,
-0.0173797607421875,
-0.002201080322265625,
-0.0005245208740234375,
0.05389404296875,
0.048583984375,
0.09686279296875,
-0.0743408203125,
-0.05328369140625,
-0.0019407272338867188,
-0.04840087890625,
0.0034770965576171875,
-0.005207061767578125,
-0.0299835205078125,
-0.016754150390625,
0.007022857666015625,
-0.054046630859375,
0.057403564453125,
0.03759765625,
-0.055084228515625,
0.07427978515625,
-0.0279541015625,
0.05291748046875,
-0.10186767578125,
0.02569580078125,
0.00290679931640625,
-0.00817108154296875,
-0.03887939453125,
0.045074462890625,
0.0017347335815429688,
0.006378173828125,
-0.04852294921875,
0.04095458984375,
-0.05889892578125,
0.02691650390625,
-0.0172576904296875,
-0.0195770263671875,
0.02099609375,
0.035919189453125,
-0.007213592529296875,
0.048065185546875,
0.026702880859375,
-0.012664794921875,
0.03582763671875,
0.0108642578125,
-0.035736083984375,
0.0498046875,
-0.0743408203125,
-0.015777587890625,
-0.0038909912109375,
0.012420654296875,
-0.09051513671875,
-0.034423828125,
0.01971435546875,
-0.03662109375,
0.0006046295166015625,
-0.00669097900390625,
-0.047882080078125,
-0.0322265625,
-0.04205322265625,
0.03009033203125,
0.036041259765625,
-0.035552978515625,
0.05517578125,
0.006931304931640625,
0.00547027587890625,
-0.020233154296875,
-0.058685302734375,
-0.0223541259765625,
-0.0290374755859375,
-0.050750732421875,
0.048004150390625,
-0.0199737548828125,
-0.0240020751953125,
-0.0209503173828125,
0.0230712890625,
-0.0174713134765625,
-0.0009374618530273438,
0.053192138671875,
0.04986572265625,
0.00452423095703125,
-0.025482177734375,
-0.0050506591796875,
0.005367279052734375,
0.01137542724609375,
0.00829315185546875,
0.045654296875,
-0.0141754150390625,
-0.0286407470703125,
-0.0733642578125,
0.01324462890625,
0.066650390625,
-0.00328826904296875,
0.05535888671875,
0.03558349609375,
-0.034820556640625,
0.00614166259765625,
-0.044708251953125,
0.000553131103515625,
-0.03961181640625,
0.0010080337524414062,
-0.06390380859375,
-0.01505279541015625,
0.04547119140625,
0.0146484375,
0.01367950439453125,
0.06744384765625,
0.0239410400390625,
-0.0195770263671875,
0.08258056640625,
0.0428466796875,
0.0175323486328125,
0.0252532958984375,
-0.0733642578125,
-0.0116424560546875,
-0.053619384765625,
-0.0328369140625,
-0.0265350341796875,
-0.042236328125,
-0.054443359375,
-0.040863037109375,
0.02862548828125,
0.007659912109375,
-0.043670654296875,
0.043731689453125,
-0.0377197265625,
0.0141448974609375,
0.042388916015625,
0.0251312255859375,
0.0180816650390625,
0.005664825439453125,
-0.0196380615234375,
-0.018218994140625,
-0.0310516357421875,
-0.034820556640625,
0.049713134765625,
0.006702423095703125,
0.038970947265625,
0.0203399658203125,
0.039886474609375,
0.0012750625610351562,
0.0072479248046875,
-0.0272369384765625,
0.02923583984375,
-0.00286865234375,
-0.07098388671875,
0.024505615234375,
-0.0170135498046875,
-0.06402587890625,
0.0224456787109375,
-0.0309295654296875,
-0.0369873046875,
0.04583740234375,
0.014404296875,
-0.0518798828125,
0.04376220703125,
-0.03955078125,
0.05364990234375,
-0.020599365234375,
-0.0265350341796875,
0.004093170166015625,
-0.01788330078125,
0.032073974609375,
0.01454925537109375,
0.046539306640625,
0.0069122314453125,
-0.0016469955444335938,
0.031951904296875,
-0.04669189453125,
0.051116943359375,
-0.0057525634765625,
0.0158843994140625,
0.0166473388671875,
0.0213623046875,
0.03350830078125,
0.01061248779296875,
-0.00258636474609375,
-0.017730712890625,
-0.0013828277587890625,
-0.034881591796875,
-0.0386962890625,
0.059173583984375,
-0.056915283203125,
-0.034027099609375,
-0.0499267578125,
-0.018768310546875,
0.0142059326171875,
0.01041412353515625,
0.0697021484375,
0.047698974609375,
-0.039581298828125,
0.0274810791015625,
0.0261383056640625,
0.00408935546875,
0.043914794921875,
0.01415252685546875,
-0.0169219970703125,
-0.04541015625,
0.040191650390625,
0.0184173583984375,
0.019744873046875,
0.0109710693359375,
-0.01125335693359375,
0.00574493408203125,
-0.0166168212890625,
-0.0225372314453125,
0.0284881591796875,
-0.0217132568359375,
-0.01031494140625,
-0.0330810546875,
-0.0187225341796875,
-0.0287628173828125,
-0.0372314453125,
-0.017608642578125,
-0.024932861328125,
-0.06268310546875,
0.0005941390991210938,
0.03326416015625,
0.04058837890625,
0.0200958251953125,
0.0281982421875,
-0.0298614501953125,
0.00873565673828125,
0.0298004150390625,
0.006938934326171875,
0.00518798828125,
-0.04974365234375,
0.013824462890625,
0.022613525390625,
-0.032470703125,
-0.07135009765625,
0.05853271484375,
-0.0031986236572265625,
0.0325927734375,
0.052276611328125,
0.00368499755859375,
0.0772705078125,
-0.034942626953125,
0.055084228515625,
0.048614501953125,
-0.0283355712890625,
0.0266876220703125,
-0.03643798828125,
0.0225372314453125,
0.04144287109375,
0.036041259765625,
-0.01678466796875,
-0.0176849365234375,
-0.0701904296875,
-0.068359375,
0.03350830078125,
0.028472900390625,
0.0005884170532226562,
0.0181427001953125,
0.0258941650390625,
0.00699615478515625,
-0.0066070556640625,
-0.056427001953125,
-0.039306640625,
-0.01435089111328125,
-0.01485443115234375,
-0.004497528076171875,
-0.0150146484375,
-0.01366424560546875,
-0.033172607421875,
0.07427978515625,
0.006557464599609375,
0.0239105224609375,
0.005603790283203125,
0.01280975341796875,
0.0173492431640625,
0.006195068359375,
0.0538330078125,
0.05230712890625,
-0.03314208984375,
-0.0194854736328125,
-0.01279449462890625,
-0.021270751953125,
0.00408172607421875,
0.00872802734375,
-0.0335693359375,
0.01428985595703125,
0.0284423828125,
0.0606689453125,
0.0160064697265625,
-0.0206298828125,
0.055419921875,
-0.0185394287109375,
-0.01511383056640625,
-0.06854248046875,
0.01474761962890625,
0.0220794677734375,
0.053253173828125,
0.0338134765625,
0.0184326171875,
0.037994384765625,
-0.037994384765625,
-0.009674072265625,
0.04132080078125,
-0.034820556640625,
-0.038482666015625,
0.07232666015625,
-0.00794219970703125,
-0.0219268798828125,
0.017822265625,
-0.0092010498046875,
-0.01995849609375,
0.06744384765625,
0.0401611328125,
0.0621337890625,
0.0013599395751953125,
0.0231475830078125,
0.051116943359375,
0.00933074951171875,
0.01108551025390625,
0.046966552734375,
0.01386260986328125,
-0.00408935546875,
0.0055694580078125,
-0.039337158203125,
-0.01299285888671875,
0.01357269287109375,
-0.050323486328125,
0.04486083984375,
-0.0487060546875,
-0.037689208984375,
0.0139007568359375,
0.00460052490234375,
-0.05474853515625,
0.05206298828125,
-0.0135040283203125,
0.08636474609375,
-0.0657958984375,
0.0506591796875,
0.032745361328125,
-0.051239013671875,
-0.06396484375,
-0.00878143310546875,
0.00258636474609375,
-0.04144287109375,
0.041046142578125,
0.0162353515625,
-0.010955810546875,
-0.00868988037109375,
-0.0521240234375,
-0.0699462890625,
0.09539794921875,
0.0281524658203125,
-0.05682373046875,
-0.013885498046875,
-0.0293121337890625,
0.024383544921875,
-0.048980712890625,
0.04010009765625,
0.01334381103515625,
0.033172607421875,
0.02130126953125,
-0.04852294921875,
-0.00443267822265625,
-0.0654296875,
0.0227508544921875,
-0.01910400390625,
-0.0953369140625,
0.0816650390625,
-0.00943756103515625,
-0.0132293701171875,
0.041259765625,
0.045440673828125,
0.026458740234375,
-0.0044708251953125,
0.04754638671875,
0.048126220703125,
0.0095672607421875,
-0.018707275390625,
0.09613037109375,
-0.0333251953125,
0.028289794921875,
0.0645751953125,
0.02557373046875,
0.053436279296875,
0.00555419921875,
-0.02392578125,
0.056182861328125,
0.0638427734375,
-0.0264892578125,
0.038818359375,
-0.0023136138916015625,
-0.016021728515625,
-0.006500244140625,
-0.0089569091796875,
-0.039947509765625,
0.0290069580078125,
-0.0031604766845703125,
-0.036956787109375,
0.008056640625,
0.004283905029296875,
0.0036468505859375,
0.0151519775390625,
-0.0316162109375,
0.03399658203125,
-0.01568603515625,
-0.021697998046875,
0.056365966796875,
-0.00919342041015625,
0.045166015625,
-0.03826904296875,
-0.0019350051879882812,
-0.01505279541015625,
0.0203094482421875,
-0.01485443115234375,
-0.047027587890625,
-0.00455474853515625,
-0.00004416704177856445,
-0.0180206298828125,
-0.020263671875,
0.040130615234375,
-0.00910186767578125,
-0.0830078125,
0.0199737548828125,
-0.0149993896484375,
0.01386260986328125,
0.01395416259765625,
-0.055877685546875,
0.01068115234375,
0.003692626953125,
-0.034698486328125,
-0.020111083984375,
0.01529693603515625,
0.0194244384765625,
0.03753662109375,
0.03076171875,
0.015380859375,
0.006000518798828125,
-0.0250701904296875,
0.06298828125,
-0.03900146484375,
-0.0298004150390625,
-0.055450439453125,
0.052734375,
-0.03704833984375,
-0.043701171875,
0.05950927734375,
0.0653076171875,
0.050506591796875,
-0.0382080078125,
0.044952392578125,
-0.006927490234375,
0.024505615234375,
-0.0252227783203125,
0.07598876953125,
-0.065673828125,
-0.0266265869140625,
-0.0196075439453125,
-0.06396484375,
-0.006618499755859375,
0.05438232421875,
0.001453399658203125,
0.0172576904296875,
0.01357269287109375,
0.0445556640625,
-0.01137542724609375,
-0.01068115234375,
0.017181396484375,
0.025054931640625,
0.0283355712890625,
0.0224456787109375,
0.035980224609375,
-0.047332763671875,
0.0245513916015625,
-0.04998779296875,
-0.03204345703125,
-0.031982421875,
-0.0467529296875,
-0.0667724609375,
-0.04388427734375,
-0.02178955078125,
-0.0198516845703125,
0.0035266876220703125,
0.060333251953125,
0.07257080078125,
-0.057159423828125,
-0.0313720703125,
0.012359619140625,
-0.021392822265625,
-0.02227783203125,
-0.017547607421875,
0.0236663818359375,
0.029754638671875,
-0.07196044921875,
0.011077880859375,
0.01432037353515625,
0.043304443359375,
-0.00778961181640625,
0.01715087890625,
-0.02813720703125,
0.0061187744140625,
0.020294189453125,
0.01201629638671875,
-0.044586181640625,
0.004364013671875,
0.002223968505859375,
-0.0163726806640625,
-0.00428009033203125,
0.0204620361328125,
-0.027191162109375,
0.0197296142578125,
0.045806884765625,
-0.00897979736328125,
0.039947509765625,
-0.0026836395263671875,
0.0301055908203125,
-0.0195770263671875,
0.0272369384765625,
0.009674072265625,
0.046905517578125,
0.01169586181640625,
-0.020751953125,
0.046417236328125,
0.0268096923828125,
-0.0255279541015625,
-0.05657958984375,
0.0029087066650390625,
-0.0823974609375,
-0.0233154296875,
0.059539794921875,
-0.0270843505859375,
-0.04559326171875,
0.0374755859375,
-0.020263671875,
0.01456451416015625,
0.004817962646484375,
0.037872314453125,
0.0599365234375,
0.01006317138671875,
-0.0030975341796875,
-0.0511474609375,
0.01326751708984375,
-0.008270263671875,
-0.054229736328125,
-0.022918701171875,
0.036224365234375,
0.031524658203125,
0.031951904296875,
0.02423095703125,
-0.034942626953125,
0.04217529296875,
-0.0027313232421875,
0.0404052734375,
-0.007106781005859375,
-0.01158905029296875,
0.0167999267578125,
0.031494140625,
-0.002468109130859375,
-0.032684326171875
]
] |
Helsinki-NLP/opus-mt-da-en | 2023-08-16T11:27:21.000Z | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"da",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-da-en | 3 | 43,696 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-da-en
* source languages: da
* target languages: en
* OPUS readme: [da-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/da-en/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2019-12-18.zip](https://object.pouta.csc.fi/OPUS-MT-models/da-en/opus-2019-12-18.zip)
* test set translations: [opus-2019-12-18.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/da-en/opus-2019-12-18.test.txt)
* test set scores: [opus-2019-12-18.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/da-en/opus-2019-12-18.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.da.en | 63.6 | 0.769 |
| 818 | [
[
-0.0216217041015625,
-0.038970947265625,
0.0204315185546875,
0.0267333984375,
-0.0309906005859375,
-0.0292510986328125,
-0.0294342041015625,
-0.004669189453125,
0.00494384765625,
0.0318603515625,
-0.049102783203125,
-0.043426513671875,
-0.04840087890625,
0.02008056640625,
-0.005924224853515625,
0.05364990234375,
-0.01142120361328125,
0.03515625,
0.01523590087890625,
-0.030853271484375,
-0.0264892578125,
-0.0303192138671875,
-0.037750244140625,
-0.022216796875,
0.0242919921875,
0.028228759765625,
0.0281219482421875,
0.032684326171875,
0.0665283203125,
0.0169525146484375,
-0.00611114501953125,
0.00815582275390625,
-0.03277587890625,
-0.004016876220703125,
0.0079345703125,
-0.03912353515625,
-0.06146240234375,
-0.00913238525390625,
0.07470703125,
0.030731201171875,
-0.00460052490234375,
0.0264129638671875,
-0.005321502685546875,
0.07171630859375,
-0.0269622802734375,
0.00925445556640625,
-0.04302978515625,
0.00021576881408691406,
-0.024993896484375,
-0.020660400390625,
-0.04925537109375,
-0.0159912109375,
0.0097808837890625,
-0.04901123046875,
-0.00824737548828125,
0.0039043426513671875,
0.10504150390625,
0.0294342041015625,
-0.034271240234375,
-0.0117645263671875,
-0.0418701171875,
0.0758056640625,
-0.061126708984375,
0.041107177734375,
0.034881591796875,
0.0226287841796875,
0.014984130859375,
-0.044036865234375,
-0.0272674560546875,
0.01007843017578125,
-0.0103912353515625,
0.0130462646484375,
-0.00829315185546875,
-0.0189361572265625,
0.019683837890625,
0.056365966796875,
-0.051300048828125,
0.0016736984252929688,
-0.03851318359375,
0.0027923583984375,
0.05523681640625,
0.006137847900390625,
0.01300811767578125,
-0.01108551025390625,
-0.0310516357421875,
-0.041778564453125,
-0.055328369140625,
0.0014829635620117188,
0.0283203125,
0.01546478271484375,
-0.036712646484375,
0.050018310546875,
-0.0092620849609375,
0.048675537109375,
0.00264739990234375,
0.000762939453125,
0.072509765625,
-0.02716064453125,
-0.0267791748046875,
-0.01409149169921875,
0.08740234375,
0.025146484375,
0.007381439208984375,
0.003467559814453125,
-0.0183868408203125,
-0.0157470703125,
0.0101165771484375,
-0.0679931640625,
-0.007701873779296875,
0.011474609375,
-0.032989501953125,
-0.00946807861328125,
0.004222869873046875,
-0.0496826171875,
0.0140380859375,
-0.03131103515625,
0.048095703125,
-0.0460205078125,
-0.0209197998046875,
0.0291748046875,
0.004241943359375,
0.02655029296875,
-0.002960205078125,
-0.047943115234375,
0.016754150390625,
0.02630615234375,
0.05462646484375,
-0.03411865234375,
-0.0203857421875,
-0.03851318359375,
-0.01334381103515625,
-0.0081024169921875,
0.0482177734375,
-0.0051727294921875,
-0.03179931640625,
-0.005321502685546875,
0.032257080078125,
-0.0294952392578125,
-0.0242156982421875,
0.10369873046875,
-0.0259552001953125,
0.050079345703125,
-0.034637451171875,
-0.040252685546875,
-0.030517578125,
0.033172607421875,
-0.047637939453125,
0.09149169921875,
0.00682830810546875,
-0.06304931640625,
0.019989013671875,
-0.0655517578125,
-0.01491546630859375,
-0.00405120849609375,
0.0015249252319335938,
-0.045623779296875,
0.006427764892578125,
0.01453399658203125,
0.0286712646484375,
-0.026214599609375,
0.0230865478515625,
0.000995635986328125,
-0.0255889892578125,
0.0019741058349609375,
-0.032684326171875,
0.0791015625,
0.0237274169921875,
-0.0278472900390625,
0.01605224609375,
-0.07177734375,
-0.004093170166015625,
0.0011281967163085938,
-0.0350341796875,
-0.017303466796875,
0.006977081298828125,
0.0210418701171875,
0.010833740234375,
0.0244598388671875,
-0.04833984375,
0.0222015380859375,
-0.050079345703125,
0.0138702392578125,
0.046142578125,
-0.0214996337890625,
0.026092529296875,
-0.032562255859375,
0.0255584716796875,
0.011749267578125,
0.0038509368896484375,
0.0026073455810546875,
-0.035552978515625,
-0.06085205078125,
-0.0236663818359375,
0.049346923828125,
0.07562255859375,
-0.057037353515625,
0.0675048828125,
-0.05181884765625,
-0.05657958984375,
-0.0599365234375,
-0.014556884765625,
0.0300750732421875,
0.027557373046875,
0.039825439453125,
-0.01371002197265625,
-0.031280517578125,
-0.078125,
-0.00479888916015625,
-0.00711822509765625,
-0.017364501953125,
0.01361083984375,
0.049072265625,
-0.017578125,
0.038909912109375,
-0.040985107421875,
-0.031890869140625,
-0.00608062744140625,
0.0109710693359375,
0.033935546875,
0.043792724609375,
0.04669189453125,
-0.06939697265625,
-0.04620361328125,
-0.003116607666015625,
-0.053192138671875,
-0.013275146484375,
0.0134429931640625,
-0.01198577880859375,
0.01276397705078125,
0.003437042236328125,
-0.023773193359375,
0.0106201171875,
0.05181884765625,
-0.0489501953125,
0.0399169921875,
-0.0151824951171875,
0.0267791748046875,
-0.10015869140625,
0.010040283203125,
-0.01461029052734375,
-0.00220489501953125,
-0.0284271240234375,
-0.0005083084106445312,
0.019439697265625,
0.0092315673828125,
-0.05810546875,
0.041748046875,
-0.02044677734375,
-0.000980377197265625,
0.0145111083984375,
-0.0010309219360351562,
0.006938934326171875,
0.053314208984375,
-0.00466156005859375,
0.0648193359375,
0.05877685546875,
-0.0430908203125,
0.01397705078125,
0.045257568359375,
-0.032989501953125,
0.031585693359375,
-0.062469482421875,
-0.0152587890625,
0.0258331298828125,
-0.008697509765625,
-0.046600341796875,
0.0085601806640625,
0.019073486328125,
-0.0450439453125,
0.030059814453125,
-0.0031909942626953125,
-0.059051513671875,
0.00010985136032104492,
-0.0203704833984375,
0.042144775390625,
0.0521240234375,
-0.0176239013671875,
0.042816162109375,
0.0121612548828125,
-0.0006847381591796875,
-0.035552978515625,
-0.073486328125,
-0.00395965576171875,
-0.031280517578125,
-0.058197021484375,
0.022735595703125,
-0.0316162109375,
-0.005489349365234375,
0.0019817352294921875,
0.0243377685546875,
-0.01027679443359375,
0.004718780517578125,
0.0048370361328125,
0.014190673828125,
-0.032073974609375,
0.00836181640625,
0.0029468536376953125,
-0.011260986328125,
-0.00873565673828125,
-0.01027679443359375,
0.043426513671875,
-0.0235137939453125,
-0.018280029296875,
-0.043426513671875,
0.0061187744140625,
0.0450439453125,
-0.032684326171875,
0.06488037109375,
0.039947509765625,
-0.0093536376953125,
0.00907135009765625,
-0.029327392578125,
0.00894927978515625,
-0.032196044921875,
0.0075531005859375,
-0.039520263671875,
-0.049591064453125,
0.03778076171875,
0.01165771484375,
0.02996826171875,
0.0650634765625,
0.05181884765625,
0.00872802734375,
0.0482177734375,
0.024932861328125,
0.0010166168212890625,
0.029266357421875,
-0.039276123046875,
-0.01221466064453125,
-0.0765380859375,
0.00762939453125,
-0.0526123046875,
-0.0255126953125,
-0.060943603515625,
-0.018768310546875,
0.0198822021484375,
-0.00200653076171875,
-0.0163421630859375,
0.051239013671875,
-0.040252685546875,
0.01490020751953125,
0.042755126953125,
-0.010040283203125,
0.025726318359375,
0.0007343292236328125,
-0.037506103515625,
-0.0179443359375,
-0.032958984375,
-0.0428466796875,
0.10015869140625,
0.027313232421875,
0.02313232421875,
0.0176849365234375,
0.03759765625,
0.00267791748046875,
0.0088958740234375,
-0.0469970703125,
0.031524658203125,
-0.022247314453125,
-0.05047607421875,
-0.0242767333984375,
-0.044769287109375,
-0.06683349609375,
0.033355712890625,
-0.016845703125,
-0.032684326171875,
0.0152587890625,
-0.007205963134765625,
-0.005451202392578125,
0.0333251953125,
-0.05230712890625,
0.08489990234375,
-0.0028400421142578125,
-0.0050048828125,
0.0157928466796875,
-0.030181884765625,
0.019378662109375,
-0.00524139404296875,
0.02008056640625,
-0.01152801513671875,
0.006198883056640625,
0.04852294921875,
-0.0060882568359375,
0.02880859375,
-0.003910064697265625,
-0.0124053955078125,
0.006664276123046875,
0.004047393798828125,
0.02606201171875,
-0.00933837890625,
-0.036346435546875,
0.03338623046875,
0.0074615478515625,
-0.03509521484375,
-0.0091400146484375,
0.04449462890625,
-0.053466796875,
-0.001659393310546875,
-0.03692626953125,
-0.054534912109375,
0.0019330978393554688,
0.024322509765625,
0.05126953125,
0.049530029296875,
-0.0224456787109375,
0.040130615234375,
0.05865478515625,
-0.0198822021484375,
0.030609130859375,
0.053192138671875,
-0.0096282958984375,
-0.04217529296875,
0.057342529296875,
0.0143890380859375,
0.02581787109375,
0.04205322265625,
0.00562286376953125,
-0.0128326416015625,
-0.055633544921875,
-0.052520751953125,
0.0191497802734375,
-0.0202484130859375,
-0.0128631591796875,
-0.042877197265625,
-0.004886627197265625,
-0.0225372314453125,
0.0225372314453125,
-0.0321044921875,
-0.043243408203125,
-0.0094757080078125,
-0.016571044921875,
0.016448974609375,
0.019378662109375,
-0.00449371337890625,
0.03179931640625,
-0.07403564453125,
0.020263671875,
-0.00437164306640625,
0.0272369384765625,
-0.031707763671875,
-0.06121826171875,
-0.03387451171875,
0.01019287109375,
-0.05322265625,
-0.054534912109375,
0.03912353515625,
0.01053619384765625,
0.01934814453125,
0.0233154296875,
0.0184783935546875,
0.02227783203125,
-0.0543212890625,
0.0712890625,
-0.00885009765625,
-0.05291748046875,
0.035919189453125,
-0.033935546875,
0.032745361328125,
0.06634521484375,
0.022918701171875,
-0.019500732421875,
-0.0325927734375,
-0.054718017578125,
-0.05694580078125,
0.055633544921875,
0.052886962890625,
-0.0112152099609375,
0.01088714599609375,
-0.00632476806640625,
0.00012242794036865234,
0.01103973388671875,
-0.08013916015625,
-0.0321044921875,
0.00678253173828125,
-0.0274505615234375,
-0.0168304443359375,
-0.0226593017578125,
-0.0182952880859375,
-0.01425933837890625,
0.080322265625,
0.01194000244140625,
0.01016998291015625,
0.0304107666015625,
-0.00988006591796875,
-0.0157623291015625,
0.0257568359375,
0.0689697265625,
0.043212890625,
-0.039459228515625,
-0.01343536376953125,
0.0218658447265625,
-0.03424072265625,
-0.006511688232421875,
0.01078033447265625,
-0.03546142578125,
0.0216522216796875,
0.030792236328125,
0.07696533203125,
0.00928497314453125,
-0.044586181640625,
0.03619384765625,
-0.02838134765625,
-0.03411865234375,
-0.045318603515625,
-0.0113525390625,
0.006526947021484375,
-0.002166748046875,
0.0214080810546875,
0.0074310302734375,
0.0165557861328125,
-0.0159454345703125,
0.01395416259765625,
0.0051422119140625,
-0.04681396484375,
-0.042144775390625,
0.037261962890625,
0.01302337646484375,
-0.0260162353515625,
0.034942626953125,
-0.031768798828125,
-0.03656005859375,
0.0312347412109375,
0.0091552734375,
0.07989501953125,
-0.01554107666015625,
-0.01387786865234375,
0.05615234375,
0.03839111328125,
-0.01396942138671875,
0.034637451171875,
0.00913238525390625,
-0.050018310546875,
-0.04248046875,
-0.061859130859375,
-0.01226806640625,
0.009185791015625,
-0.06219482421875,
0.031341552734375,
0.02813720703125,
0.0002605915069580078,
-0.0244598388671875,
0.02227783203125,
-0.03753662109375,
0.0122833251953125,
-0.023345947265625,
0.07904052734375,
-0.069091796875,
0.06988525390625,
0.03839111328125,
-0.0229034423828125,
-0.056365966796875,
-0.01338958740234375,
-0.01568603515625,
-0.0300750732421875,
0.046966552734375,
0.01313018798828125,
0.0219573974609375,
-0.0072174072265625,
-0.0112457275390625,
-0.057403564453125,
0.08514404296875,
0.01934814453125,
-0.0433349609375,
0.00035572052001953125,
0.00635528564453125,
0.03662109375,
-0.0280303955078125,
0.00740814208984375,
0.03369140625,
0.05609130859375,
0.0053558349609375,
-0.085693359375,
-0.0217437744140625,
-0.039337158203125,
-0.02734375,
0.03790283203125,
-0.039794921875,
0.072021484375,
0.03057861328125,
-0.01392364501953125,
0.0047454833984375,
0.046234130859375,
0.0234527587890625,
0.024261474609375,
0.04150390625,
0.08843994140625,
0.02740478515625,
-0.03375244140625,
0.0758056640625,
-0.0229644775390625,
0.033660888671875,
0.08538818359375,
-0.005512237548828125,
0.0679931640625,
0.025054931640625,
-0.0101165771484375,
0.040069580078125,
0.04547119140625,
-0.0204315185546875,
0.040130615234375,
0.004650115966796875,
0.0112152099609375,
-0.004489898681640625,
0.01544189453125,
-0.054901123046875,
0.02105712890625,
0.010833740234375,
-0.0110626220703125,
0.00446319580078125,
-0.00473785400390625,
0.0008945465087890625,
0.005401611328125,
-0.00858306884765625,
0.0487060546875,
0.000438690185546875,
-0.043121337890625,
0.057952880859375,
-0.003894805908203125,
0.054901123046875,
-0.05084228515625,
0.006313323974609375,
-0.002941131591796875,
0.0181427001953125,
0.000286102294921875,
-0.0406494140625,
0.039337158203125,
0.0000737905502319336,
-0.0216522216796875,
-0.0298309326171875,
0.00945281982421875,
-0.04058837890625,
-0.064208984375,
0.03424072265625,
0.03155517578125,
0.0255889892578125,
0.0005345344543457031,
-0.0628662109375,
0.0014257431030273438,
0.00577545166015625,
-0.046051025390625,
0.005550384521484375,
0.059051513671875,
0.024017333984375,
0.034454345703125,
0.04364013671875,
0.0208740234375,
0.01580810546875,
-0.0024871826171875,
0.046966552734375,
-0.0299835205078125,
-0.033294677734375,
-0.058868408203125,
0.059844970703125,
-0.0082855224609375,
-0.04901123046875,
0.056182861328125,
0.0738525390625,
0.07501220703125,
-0.01326751708984375,
0.0186309814453125,
-0.00905609130859375,
0.053558349609375,
-0.04852294921875,
0.0496826171875,
-0.06927490234375,
0.0181884765625,
-0.00794219970703125,
-0.071533203125,
-0.0127410888671875,
0.023895263671875,
-0.017181396484375,
-0.0240020751953125,
0.059661865234375,
0.047698974609375,
-0.0150146484375,
-0.0211334228515625,
0.024810791015625,
0.02447509765625,
0.016387939453125,
0.044281005859375,
0.0239715576171875,
-0.08026123046875,
0.04046630859375,
-0.02093505859375,
-0.00933074951171875,
0.00057220458984375,
-0.05755615234375,
-0.06256103515625,
-0.05078125,
-0.017303466796875,
-0.01349639892578125,
-0.0236358642578125,
0.0592041015625,
0.041900634765625,
-0.0701904296875,
-0.041015625,
0.0010728836059570312,
0.0094757080078125,
-0.0178375244140625,
-0.018280029296875,
0.05023193359375,
-0.0233306884765625,
-0.080078125,
0.035797119140625,
0.00360870361328125,
-0.005950927734375,
-0.000008225440979003906,
-0.025238037109375,
-0.041839599609375,
-0.0029144287109375,
0.02154541015625,
-0.0011472702026367188,
-0.039947509765625,
0.00997161865234375,
0.00962066650390625,
-0.0081787109375,
0.028228759765625,
0.0224456787109375,
-0.020721435546875,
0.01873779296875,
0.061767578125,
0.031524658203125,
0.033905029296875,
-0.01068115234375,
0.044647216796875,
-0.049652099609375,
0.02520751953125,
0.016632080078125,
0.044464111328125,
0.0266571044921875,
-0.00435638427734375,
0.0634765625,
0.01390838623046875,
-0.052886962890625,
-0.07781982421875,
0.0071563720703125,
-0.09100341796875,
-0.0012454986572265625,
0.0679931640625,
-0.0234832763671875,
-0.0203399658203125,
0.0256500244140625,
-0.01654052734375,
0.0129547119140625,
-0.025146484375,
0.035552978515625,
0.066650390625,
0.0322265625,
0.0098114013671875,
-0.05413818359375,
0.0280914306640625,
0.038970947265625,
-0.056854248046875,
-0.0149383544921875,
0.0179901123046875,
0.0085906982421875,
0.0285186767578125,
0.036651611328125,
-0.0254364013671875,
0.00933074951171875,
-0.020050048828125,
0.0279541015625,
-0.00884246826171875,
-0.01483917236328125,
-0.028717041015625,
0.00035572052001953125,
-0.005931854248046875,
-0.026611328125
]
] |
alx-ai/noggles-v21-6400-best | 2022-12-11T22:16:31.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | alx-ai | null | null | alx-ai/noggles-v21-6400-best | 1 | 43,584 | diffusers | 2022-12-11T22:02:07 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### noggles_v21_6400_BEST Dreambooth model trained by alxdfy with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Or you can run your new concept via `diffusers` [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb)
Sample pictures of this concept:
| 804 | [
[
-0.0294342041015625,
-0.061065673828125,
0.0396728515625,
0.030792236328125,
-0.026214599609375,
0.0213623046875,
0.02264404296875,
-0.02459716796875,
0.048980712890625,
0.0225677490234375,
-0.025634765625,
-0.0290069580078125,
-0.032684326171875,
-0.0210723876953125,
-0.038818359375,
0.05438232421875,
-0.01488494873046875,
-0.0012407302856445312,
-0.0033626556396484375,
0.0068359375,
-0.01517486572265625,
0.0144500732421875,
-0.052886962890625,
-0.03643798828125,
0.00963592529296875,
0.017059326171875,
0.046875,
0.0228729248046875,
0.01537322998046875,
0.016357421875,
-0.023834228515625,
-0.0236053466796875,
-0.028564453125,
0.02001953125,
0.003108978271484375,
-0.0241851806640625,
-0.049652099609375,
-0.01035308837890625,
0.038055419921875,
0.01457977294921875,
-0.0270843505859375,
0.02923583984375,
-0.00798797607421875,
0.031158447265625,
-0.050201416015625,
0.00260162353515625,
-0.02471923828125,
0.0164031982421875,
-0.033172607421875,
0.0235748291015625,
-0.0165863037109375,
-0.0281524658203125,
-0.0117950439453125,
-0.0295257568359375,
0.029388427734375,
0.0244903564453125,
0.084228515625,
0.00885772705078125,
-0.039398193359375,
0.02239990234375,
-0.019500732421875,
0.03558349609375,
-0.03411865234375,
0.04718017578125,
0.0027828216552734375,
0.0197906494140625,
-0.017730712890625,
-0.0496826171875,
-0.056427001953125,
-0.00482940673828125,
0.0290679931640625,
0.01044464111328125,
-0.00894927978515625,
0.0170440673828125,
0.0017213821411132812,
0.0210418701171875,
-0.048248291015625,
-0.00958251953125,
-0.036651611328125,
-0.0273284912109375,
0.03851318359375,
0.009246826171875,
-0.0044708251953125,
-0.0259246826171875,
-0.0682373046875,
-0.01097869873046875,
-0.036651611328125,
-0.01163482666015625,
0.01033782958984375,
-0.0107574462890625,
-0.04083251953125,
0.031158447265625,
-0.023895263671875,
0.059478759765625,
0.032989501953125,
-0.007122039794921875,
0.0667724609375,
-0.019012451171875,
-0.0205230712890625,
0.00547027587890625,
0.051300048828125,
0.028656005859375,
-0.00475311279296875,
-0.01398468017578125,
-0.01497650146484375,
0.0046539306640625,
0.0005092620849609375,
-0.08380126953125,
-0.03826904296875,
0.02569580078125,
-0.0423583984375,
-0.036285400390625,
-0.0255126953125,
-0.058349609375,
-0.0310516357421875,
0.0039520263671875,
0.04949951171875,
-0.0263671875,
-0.06695556640625,
0.00921630859375,
-0.01544189453125,
0.01453399658203125,
0.027496337890625,
-0.034027099609375,
0.0082244873046875,
0.0272674560546875,
0.08331298828125,
-0.0186920166015625,
-0.00461578369140625,
-0.0166473388671875,
0.00632476806640625,
-0.03759765625,
0.06573486328125,
-0.0118255615234375,
-0.016998291015625,
-0.022491455078125,
-0.00751495361328125,
-0.0214691162109375,
-0.03436279296875,
0.023468017578125,
-0.047393798828125,
-0.0006537437438964844,
0.017608642578125,
-0.0572509765625,
-0.0225830078125,
0.01078033447265625,
-0.0333251953125,
0.0474853515625,
0.00316619873046875,
-0.050140380859375,
0.016998291015625,
-0.079345703125,
0.0037326812744140625,
0.00942230224609375,
-0.0014181137084960938,
-0.03839111328125,
0.01261138916015625,
-0.03765869140625,
0.03857421875,
-0.00394439697265625,
0.012481689453125,
-0.03973388671875,
-0.0281219482421875,
0.0030498504638671875,
-0.0189056396484375,
0.08056640625,
0.0298919677734375,
-0.0275421142578125,
0.0160980224609375,
-0.058929443359375,
0.0107879638671875,
0.010040283203125,
0.0023860931396484375,
-0.00028705596923828125,
-0.05035400390625,
0.0210723876953125,
0.0013561248779296875,
0.00705718994140625,
-0.06341552734375,
0.00027942657470703125,
0.0005774497985839844,
-0.00688934326171875,
0.05792236328125,
0.0135955810546875,
0.0162506103515625,
-0.0155792236328125,
0.0638427734375,
0.002086639404296875,
0.017364501953125,
0.01526641845703125,
-0.0611572265625,
-0.0572509765625,
-0.0267486572265625,
0.0360107421875,
0.04229736328125,
-0.059478759765625,
0.006183624267578125,
0.027099609375,
-0.059967041015625,
-0.0299835205078125,
0.005092620849609375,
0.02716064453125,
0.0416259765625,
0.0236053466796875,
-0.0280914306640625,
-0.02490234375,
-0.052215576171875,
0.008514404296875,
-0.0087738037109375,
0.010162353515625,
0.00489044189453125,
0.03656005859375,
-0.0225677490234375,
0.05908203125,
-0.044281005859375,
0.003566741943359375,
-0.00424957275390625,
0.0020275115966796875,
0.0487060546875,
0.0484619140625,
0.053253173828125,
-0.057861328125,
-0.039215087890625,
-0.036376953125,
-0.047882080078125,
-0.004199981689453125,
0.01317596435546875,
-0.038482666015625,
0.0176544189453125,
0.02276611328125,
-0.07666015625,
0.037109375,
0.04620361328125,
-0.07708740234375,
0.054168701171875,
-0.0028667449951171875,
0.0143890380859375,
-0.0859375,
0.0017690658569335938,
0.0085906982421875,
-0.030914306640625,
-0.035247802734375,
0.0121917724609375,
0.029693603515625,
0.003040313720703125,
-0.056732177734375,
0.07086181640625,
-0.0290069580078125,
0.0391845703125,
-0.025665283203125,
-0.0131072998046875,
-0.009429931640625,
-0.0028133392333984375,
-0.00774383544921875,
0.036773681640625,
0.07464599609375,
-0.042510986328125,
0.038818359375,
0.04083251953125,
-0.03173828125,
0.02801513671875,
-0.047943115234375,
0.0103759765625,
-0.01678466796875,
0.0278778076171875,
-0.07733154296875,
-0.016815185546875,
0.040496826171875,
-0.0176239013671875,
0.026580810546875,
-0.01282501220703125,
-0.03643798828125,
-0.038604736328125,
-0.020050048828125,
0.033416748046875,
0.06512451171875,
-0.045074462890625,
0.01751708984375,
0.0255279541015625,
0.00998687744140625,
-0.04742431640625,
-0.0270233154296875,
-0.0034084320068359375,
-0.02581787109375,
-0.04986572265625,
0.04693603515625,
-0.02740478515625,
-0.0262603759765625,
-0.004058837890625,
-0.0205535888671875,
-0.01433563232421875,
-0.00510406494140625,
0.03375244140625,
0.046173095703125,
-0.02532958984375,
0.003887176513671875,
0.0035572052001953125,
-0.034149169921875,
-0.0134124755859375,
-0.007038116455078125,
0.046173095703125,
-0.03131103515625,
-0.003322601318359375,
-0.039031982421875,
-0.01195526123046875,
0.037933349609375,
0.0162506103515625,
0.06707763671875,
0.06170654296875,
-0.02862548828125,
-0.006763458251953125,
-0.05908203125,
-0.02032470703125,
-0.037200927734375,
-0.0036468505859375,
-0.034332275390625,
-0.035980224609375,
0.02618408203125,
0.00388336181640625,
-0.017669677734375,
0.0227203369140625,
0.036865234375,
-0.01380157470703125,
0.04412841796875,
0.05413818359375,
0.0183258056640625,
0.045379638671875,
-0.048309326171875,
0.007293701171875,
-0.047637939453125,
-0.021759033203125,
-0.006282806396484375,
-0.0223846435546875,
-0.024017333984375,
-0.05718994140625,
0.019500732421875,
0.03387451171875,
-0.029815673828125,
0.03802490234375,
-0.0126800537109375,
0.04864501953125,
0.0286865234375,
0.0193328857421875,
0.015228271484375,
0.004146575927734375,
-0.0206298828125,
0.02880859375,
-0.03912353515625,
-0.01885986328125,
0.07098388671875,
0.011688232421875,
0.0731201171875,
-0.00247955322265625,
0.07220458984375,
0.00884246826171875,
0.0163421630859375,
-0.01406097412109375,
0.049713134765625,
0.007587432861328125,
-0.07208251953125,
0.003810882568359375,
-0.0167694091796875,
-0.0611572265625,
0.0309906005859375,
-0.027923583984375,
-0.052734375,
0.0164794921875,
0.047943115234375,
-0.03887939453125,
0.04022216796875,
-0.0635986328125,
0.0760498046875,
-0.0013265609741210938,
-0.057708740234375,
-0.026031494140625,
-0.040283203125,
0.0239105224609375,
0.00876617431640625,
-0.0037364959716796875,
-0.02923583984375,
-0.0112457275390625,
0.050567626953125,
-0.01418304443359375,
0.049468994140625,
-0.057769775390625,
0.0108642578125,
0.031646728515625,
0.0008177757263183594,
0.0215911865234375,
0.005046844482421875,
-0.026641845703125,
0.029266357421875,
-0.0028591156005859375,
-0.05126953125,
-0.0018949508666992188,
0.047149658203125,
-0.033599853515625,
-0.024383544921875,
-0.037445068359375,
-0.037872314453125,
-0.004016876220703125,
0.0163726806640625,
0.03363037109375,
0.01291656494140625,
-0.00913238525390625,
0.01111602783203125,
0.065673828125,
0.00748443603515625,
0.0467529296875,
0.0496826171875,
-0.049774169921875,
-0.015106201171875,
0.0582275390625,
0.0018053054809570312,
0.024658203125,
0.006366729736328125,
0.020050048828125,
-0.0236663818359375,
-0.055206298828125,
-0.058013916015625,
0.0254364013671875,
-0.0288238525390625,
-0.04046630859375,
-0.04608154296875,
-0.019500732421875,
-0.0226898193359375,
-0.0107421875,
-0.04632568359375,
-0.044769287109375,
-0.019287109375,
-0.034027099609375,
0.06951904296875,
0.037200927734375,
-0.035858154296875,
0.02105712890625,
-0.032501220703125,
0.043975830078125,
0.005374908447265625,
0.02862548828125,
0.005809783935546875,
-0.027374267578125,
0.00208282470703125,
-0.005825042724609375,
-0.044647216796875,
-0.07659912109375,
0.026214599609375,
0.0005331039428710938,
0.047576904296875,
0.050262451171875,
-0.0023212432861328125,
0.04864501953125,
-0.01983642578125,
0.044219970703125,
0.04266357421875,
-0.06494140625,
0.039215087890625,
-0.0285797119140625,
0.00878143310546875,
0.02764892578125,
0.03717041015625,
-0.0268402099609375,
-0.02301025390625,
-0.06451416015625,
-0.07708740234375,
0.0183258056640625,
0.02239990234375,
0.00962066650390625,
0.01032257080078125,
0.031402587890625,
0.041046142578125,
0.03143310546875,
-0.057373046875,
-0.033050537109375,
-0.0008087158203125,
-0.013336181640625,
0.01418304443359375,
0.0038280487060546875,
0.003200531005859375,
-0.0238189697265625,
0.07666015625,
-0.0083465576171875,
0.03564453125,
0.00034165382385253906,
-0.00537109375,
-0.0158843994140625,
-0.0063323974609375,
0.0117950439453125,
0.061431884765625,
-0.03973388671875,
0.0022907257080078125,
-0.0010404586791992188,
-0.0300140380859375,
0.033660888671875,
0.007778167724609375,
-0.0296630859375,
0.0068817138671875,
-0.00916290283203125,
0.0677490234375,
-0.0198211669921875,
-0.033477783203125,
0.033447265625,
-0.00940704345703125,
-0.006500244140625,
-0.026397705078125,
0.0419921875,
0.024261474609375,
0.045074462890625,
0.005084991455078125,
0.05133056640625,
0.00994110107421875,
-0.01727294921875,
0.0151824951171875,
0.0246734619140625,
-0.0257568359375,
-0.012664794921875,
0.075439453125,
0.0219268798828125,
-0.0243988037109375,
0.046844482421875,
-0.048248291015625,
-0.00942230224609375,
0.062042236328125,
0.0570068359375,
0.07061767578125,
-0.02777099609375,
0.0394287109375,
0.0291595458984375,
-0.006866455078125,
-0.01227569580078125,
0.049346923828125,
-0.0147705078125,
-0.056427001953125,
-0.004093170166015625,
-0.052734375,
-0.02972412109375,
-0.001461029052734375,
-0.030487060546875,
0.0283050537109375,
-0.025634765625,
-0.01116180419921875,
-0.0045318603515625,
-0.01849365234375,
-0.060943603515625,
0.0091705322265625,
0.0161590576171875,
0.10101318359375,
-0.0633544921875,
0.06915283203125,
0.03900146484375,
-0.00453948974609375,
-0.025909423828125,
0.007091522216796875,
0.01157379150390625,
-0.0728759765625,
0.028778076171875,
0.0213775634765625,
-0.0085601806640625,
-0.004917144775390625,
-0.039215087890625,
-0.0816650390625,
0.09619140625,
0.040435791015625,
-0.051971435546875,
0.0208282470703125,
-0.051116943359375,
0.026153564453125,
-0.0237884521484375,
0.0187530517578125,
0.0148773193359375,
0.025177001953125,
0.018157958984375,
-0.071044921875,
0.00243377685546875,
-0.040374755859375,
-0.003612518310546875,
0.018829345703125,
-0.07568359375,
0.0599365234375,
-0.056671142578125,
0.01116180419921875,
0.0267181396484375,
0.04974365234375,
0.03057861328125,
0.052215576171875,
0.062042236328125,
0.055206298828125,
0.0572509765625,
0.0042572021484375,
0.07440185546875,
-0.0299835205078125,
0.042938232421875,
0.0711669921875,
-0.00778961181640625,
0.068603515625,
0.04156494140625,
-0.0038318634033203125,
0.057525634765625,
0.06610107421875,
-0.0017652511596679688,
0.062255859375,
0.02301025390625,
-0.0280303955078125,
-0.01398468017578125,
0.0189361572265625,
-0.060394287109375,
0.01551055908203125,
0.0270843505859375,
-0.017791748046875,
0.0060882568359375,
0.02691650390625,
0.021942138671875,
-0.05535888671875,
-0.0196685791015625,
0.026580810546875,
0.0006356239318847656,
-0.0307464599609375,
0.049041748046875,
-0.01287078857421875,
0.062255859375,
-0.0513916015625,
-0.005313873291015625,
-0.01146697998046875,
0.035247802734375,
-0.0219573974609375,
-0.051177978515625,
0.00569915771484375,
-0.00884246826171875,
0.005626678466796875,
-0.0250091552734375,
0.06365966796875,
-0.0221710205078125,
-0.052642822265625,
0.03741455078125,
0.032073974609375,
0.024627685546875,
0.00457763671875,
-0.055206298828125,
0.00002658367156982422,
0.0021514892578125,
-0.04296875,
0.00679779052734375,
-0.01445770263671875,
0.0254669189453125,
0.05206298828125,
0.021759033203125,
0.0014982223510742188,
0.0226898193359375,
-0.0206298828125,
0.03631591796875,
-0.04949951171875,
-0.037384033203125,
-0.053436279296875,
0.0369873046875,
-0.01285552978515625,
-0.0306549072265625,
0.059967041015625,
0.0511474609375,
0.0499267578125,
-0.0190582275390625,
0.045074462890625,
-0.036407470703125,
0.0220947265625,
-0.031890869140625,
0.056549072265625,
-0.043731689453125,
-0.0172119140625,
-0.020843505859375,
-0.07080078125,
0.0008411407470703125,
0.07354736328125,
0.008758544921875,
0.00652313232421875,
0.049652099609375,
0.072998046875,
-0.0281219482421875,
0.0189666748046875,
0.0090484619140625,
0.06292724609375,
-0.0017347335815429688,
0.018280029296875,
0.04486083984375,
-0.041351318359375,
0.0168609619140625,
-0.044189453125,
-0.03558349609375,
-0.0172119140625,
-0.069091796875,
-0.046661376953125,
-0.0195159912109375,
-0.06414794921875,
-0.0677490234375,
0.0198974609375,
0.07196044921875,
0.08660888671875,
-0.0738525390625,
-0.0286865234375,
-0.0205535888671875,
0.0214691162109375,
-0.009765625,
-0.0190582275390625,
0.028228759765625,
0.005859375,
-0.0445556640625,
0.0297698974609375,
0.00472259521484375,
0.03765869140625,
-0.00873565673828125,
-0.00397491455078125,
-0.006542205810546875,
-0.00429534912109375,
0.0310211181640625,
-0.0002498626708984375,
-0.024322509765625,
-0.0087738037109375,
-0.0159149169921875,
0.0255584716796875,
0.006580352783203125,
0.01462554931640625,
-0.07122802734375,
0.02825927734375,
0.047821044921875,
-0.00037169456481933594,
0.06500244140625,
-0.031402587890625,
0.0277557373046875,
-0.015899658203125,
0.0135955810546875,
-0.0024242401123046875,
0.038604736328125,
0.0099945068359375,
-0.01010894775390625,
0.05255126953125,
0.040679931640625,
-0.03192138671875,
-0.062225341796875,
0.005023956298828125,
-0.08349609375,
-0.0166015625,
0.06536865234375,
0.00836181640625,
-0.023651123046875,
-0.00008732080459594727,
-0.01413726806640625,
0.002899169921875,
-0.050933837890625,
0.0711669921875,
0.02081298828125,
-0.044830322265625,
-0.004215240478515625,
-0.0609130859375,
0.011383056640625,
0.01470184326171875,
-0.055999755859375,
-0.028717041015625,
0.0151214599609375,
0.04815673828125,
0.03564453125,
0.057647705078125,
0.0003249645233154297,
0.023681640625,
0.0297088623046875,
0.01043701171875,
0.0113983154296875,
-0.02423095703125,
-0.0006108283996582031,
0.03509521484375,
-0.01739501953125,
-0.04571533203125
]
] |
Xwin-LM/Xwin-LM-7B-V0.1 | 2023-09-21T05:42:01.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:llama2",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | Xwin-LM | null | null | Xwin-LM/Xwin-LM-7B-V0.1 | 75 | 43,494 | transformers | 2023-09-15T14:03:07 | ---
license: llama2
---
<h3 align="center">
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
</h3>
<p align="center">
<a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
</p>
**Step up your LLM alignment with Xwin-LM!**
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
## News
- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
## Model Card
| Model | Checkpoint | Report | License |
|------------|------------|-------------|------------------|
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
## Benchmarks
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|----------------------------------|------------|----------|-------------|
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
| GPT-4 | 95.28 | 84.66 | 50.00 |
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
| ChatGPT | 89.37 | 50.00 | 16.60 |
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
| Prompts | GTP4 response | Xwin-LM response |
|----------------|------------|--------|
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
### Xwin-LM performance on NLP foundation tasks.
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|------------------|-------------|-------------|-------------------|-------------------|------------|
| Text-davinci-003 | 56.9 | **85.2** | 59.3 | 82.2 | 70.9 |
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|Guanaco 30B | 57.6 | 63.7 | 50.7 | 85.1 | 64.3 |
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
| WizardLM-30B 1.0 | 58.8 | 62.5 | 52.4 | 83.3 | 64.2|
| Llama-2-7B-Chat | 48.3 | 52.9 | 45.6 | 78.6 | 56.4 |
| Llama-2-13B-Chat | 54.6 | 59.0 | 44.1 | 81.9 | 59.9 |
| Llama-2-70B-Chat | 63.9 | 64.6 | 52.8 | 85.9 | 66.8 |
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
| **Xwin-LM-13B-V0.1** | 56.6 | 62.4 | 45.5 | 83.0 | 61.9 |
| **Xwin-LM-70B-V0.1** | **69.6** | 70.5 | **60.1** | **87.1** | **71.8** |
## Inference
### Conversation templates
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
```
### HuggingFace Example
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
inputs = tokenizer(prompt, return_tensors="pt")
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(output)
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
```
### vllm Example
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions.
```python
from vllm import LLM, SamplingParams
(
prompt := "A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
"USER: Hello, can you help me? "
"ASSISTANT:"
)
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
outputs = llm.generate([prompt,], sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(generated_text)
```
## TODO
- [ ] Release the source code
- [ ] Release more capabilities, such as math, reasoning, and etc.
## Citation
Please consider citing our work if you use the data or code in this repo.
```
@software{xwin-lm,
title = {Xwin-LM},
author = {Xwin-LM Team},
url = {https://github.com/Xwin-LM/Xwin-LM},
version = {pre-release},
year = {2023},
month = {9},
}
```
## Acknowledgements
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
| 9,807 | [
[
-0.043365478515625,
-0.05535888671875,
0.031951904296875,
0.01116943359375,
-0.01384735107421875,
0.0099029541015625,
-0.0081787109375,
-0.05615234375,
0.0249786376953125,
0.0186309814453125,
-0.057373046875,
-0.053558349609375,
-0.05914306640625,
-0.004329681396484375,
-0.0157928466796875,
0.0750732421875,
-0.003582000732421875,
-0.02032470703125,
-0.003452301025390625,
-0.0177154541015625,
-0.0167236328125,
-0.0435791015625,
-0.056854248046875,
-0.032623291015625,
0.03997802734375,
-0.004657745361328125,
0.07366943359375,
0.058258056640625,
0.044952392578125,
0.031646728515625,
-0.01084136962890625,
0.01959228515625,
-0.03466796875,
0.0013647079467773438,
0.0119171142578125,
-0.046966552734375,
-0.059326171875,
0.022064208984375,
0.0404052734375,
0.020111083984375,
-0.00699615478515625,
0.0016918182373046875,
0.0093994140625,
0.04644775390625,
-0.0257110595703125,
0.01497650146484375,
-0.02508544921875,
0.00572967529296875,
-0.018768310546875,
-0.0247344970703125,
0.00025272369384765625,
-0.0250701904296875,
-0.0092926025390625,
-0.05352783203125,
0.0045928955078125,
0.0164794921875,
0.08758544921875,
0.032501220703125,
-0.0087890625,
-0.023101806640625,
-0.0249481201171875,
0.06182861328125,
-0.07666015625,
0.01413726806640625,
0.0168914794921875,
0.01300811767578125,
-0.02984619140625,
-0.04840087890625,
-0.049072265625,
-0.030853271484375,
-0.0135345458984375,
0.015289306640625,
-0.048309326171875,
0.00760650634765625,
0.021514892578125,
0.0277252197265625,
-0.041595458984375,
0.01091766357421875,
-0.00783538818359375,
-0.0018644332885742188,
0.05078125,
0.0168609619140625,
0.0284271240234375,
0.0017728805541992188,
-0.03765869140625,
-0.0239410400390625,
-0.039886474609375,
0.02703857421875,
0.02099609375,
0.0135345458984375,
-0.031768798828125,
0.033050537109375,
-0.0002796649932861328,
0.045989990234375,
0.01166534423828125,
-0.0447998046875,
0.03363037109375,
-0.028350830078125,
-0.018585205078125,
-0.0079803466796875,
0.08294677734375,
0.04864501953125,
-0.00893402099609375,
-0.0028972625732421875,
-0.020233154296875,
0.02239990234375,
-0.0174713134765625,
-0.0576171875,
-0.00225830078125,
0.0233154296875,
-0.03997802734375,
-0.0293731689453125,
-0.006252288818359375,
-0.03631591796875,
-0.0131988525390625,
-0.0050201416015625,
0.028350830078125,
-0.034454345703125,
-0.004367828369140625,
0.006061553955078125,
-0.01511383056640625,
0.037261962890625,
0.031829833984375,
-0.044403076171875,
0.02178955078125,
0.04925537109375,
0.06658935546875,
-0.035491943359375,
-0.0286102294921875,
-0.04229736328125,
-0.0124969482421875,
-0.020233154296875,
0.033660888671875,
-0.0096282958984375,
-0.028289794921875,
-0.034393310546875,
0.015869140625,
0.002490997314453125,
-0.0325927734375,
0.0286102294921875,
-0.020111083984375,
0.0292205810546875,
-0.025848388671875,
-0.04833984375,
-0.0015096664428710938,
0.033050537109375,
-0.0340576171875,
0.08056640625,
-0.0008730888366699219,
-0.0640869140625,
0.0030078887939453125,
-0.056488037109375,
-0.014404296875,
-0.0230712890625,
-0.01136016845703125,
-0.028076171875,
-0.0139923095703125,
0.01483154296875,
0.0338134765625,
-0.0267791748046875,
0.01287841796875,
-0.0185394287109375,
-0.0265350341796875,
0.016754150390625,
-0.03765869140625,
0.0904541015625,
0.01175689697265625,
-0.072509765625,
-0.0005254745483398438,
-0.047210693359375,
0.00908660888671875,
0.031768798828125,
-0.0191802978515625,
-0.0039043426513671875,
0.0070343017578125,
-0.0282745361328125,
0.021575927734375,
0.032989501953125,
-0.04681396484375,
0.0302886962890625,
-0.03851318359375,
0.0249176025390625,
0.053680419921875,
-0.0161895751953125,
0.0248260498046875,
-0.048309326171875,
0.042633056640625,
-0.002307891845703125,
0.0177154541015625,
-0.005062103271484375,
-0.0526123046875,
-0.0623779296875,
-0.0287017822265625,
0.00577545166015625,
0.06878662109375,
-0.050262451171875,
0.04412841796875,
-0.006290435791015625,
-0.04656982421875,
-0.037445068359375,
0.00795745849609375,
0.05010986328125,
0.0302581787109375,
0.035308837890625,
-0.0110321044921875,
-0.0261688232421875,
-0.059844970703125,
0.00885772705078125,
-0.02838134765625,
0.0163726806640625,
0.031890869140625,
0.03533935546875,
-0.0244293212890625,
0.07147216796875,
-0.040679931640625,
-0.016876220703125,
-0.0257110595703125,
-0.01035308837890625,
0.02935791015625,
0.036712646484375,
0.06719970703125,
-0.035064697265625,
-0.0266571044921875,
0.006542205810546875,
-0.070068359375,
-0.01387786865234375,
-0.0003170967102050781,
-0.025054931640625,
0.0343017578125,
0.0204010009765625,
-0.0592041015625,
0.036895751953125,
0.05078125,
-0.04205322265625,
0.04974365234375,
-0.00958251953125,
0.01739501953125,
-0.07177734375,
0.004833221435546875,
-0.00757598876953125,
-0.032958984375,
-0.03594970703125,
0.0191497802734375,
-0.01407623291015625,
0.023590087890625,
-0.0343017578125,
0.0743408203125,
-0.0435791015625,
0.00399017333984375,
-0.0117034912109375,
0.036102294921875,
0.004222869873046875,
0.048583984375,
-0.01145172119140625,
0.065185546875,
0.032257080078125,
-0.02105712890625,
0.0263671875,
0.01236724853515625,
-0.01491546630859375,
0.01763916015625,
-0.058074951171875,
-0.0012750625610351562,
0.0079803466796875,
0.0221710205078125,
-0.07135009765625,
0.021484375,
0.04083251953125,
-0.0513916015625,
0.03485107421875,
0.00727081298828125,
-0.0186004638671875,
-0.028045654296875,
-0.037261962890625,
-0.00750732421875,
0.04266357421875,
-0.037109375,
0.030792236328125,
0.022186279296875,
-0.00969696044921875,
-0.06695556640625,
-0.049652099609375,
0.013427734375,
-0.0114593505859375,
-0.0576171875,
0.036590576171875,
-0.022918701171875,
-0.036895751953125,
-0.01161956787109375,
0.0026397705078125,
0.0226593017578125,
0.013946533203125,
0.024383544921875,
0.03692626953125,
-0.0196685791015625,
-0.0229949951171875,
0.00012373924255371094,
-0.0168609619140625,
0.001003265380859375,
0.003276824951171875,
0.036651611328125,
-0.0289306640625,
-0.0276947021484375,
-0.0249176025390625,
0.0250091552734375,
0.039520263671875,
-0.01116943359375,
0.049835205078125,
0.047576904296875,
-0.005489349365234375,
0.005130767822265625,
-0.0482177734375,
-0.0095367431640625,
-0.037384033203125,
0.0238037109375,
-0.01580810546875,
-0.061798095703125,
0.0498046875,
0.0286102294921875,
0.033203125,
0.039337158203125,
0.044769287109375,
-0.018890380859375,
0.08746337890625,
0.046173095703125,
-0.028900146484375,
0.03436279296875,
-0.0513916015625,
0.0017614364624023438,
-0.046966552734375,
-0.01202392578125,
-0.03289794921875,
-0.040802001953125,
-0.053558349609375,
-0.0390625,
0.019683837890625,
0.00823974609375,
-0.015716552734375,
0.031768798828125,
-0.04364013671875,
0.01145172119140625,
0.05010986328125,
0.0038051605224609375,
0.0186920166015625,
-0.0097198486328125,
-0.01617431640625,
0.004207611083984375,
-0.04962158203125,
-0.04541015625,
0.056732177734375,
0.0302276611328125,
0.056640625,
0.013275146484375,
0.0750732421875,
0.0248260498046875,
0.018463134765625,
-0.03802490234375,
0.053863525390625,
-0.005680084228515625,
-0.046661376953125,
-0.022674560546875,
-0.0390625,
-0.0804443359375,
0.01788330078125,
-0.01461029052734375,
-0.06744384765625,
0.023590087890625,
0.01224517822265625,
-0.031982421875,
0.040435791015625,
-0.03472900390625,
0.0596923828125,
-0.0401611328125,
-0.037567138671875,
0.0105133056640625,
-0.070068359375,
0.03118896484375,
0.0251312255859375,
0.00968170166015625,
-0.0283203125,
-0.027069091796875,
0.0596923828125,
-0.04864501953125,
0.060577392578125,
-0.0263671875,
-0.01291656494140625,
0.0260772705078125,
-0.0016260147094726562,
0.052276611328125,
-0.01375579833984375,
-0.005756378173828125,
0.0250701904296875,
0.02313232421875,
-0.0209808349609375,
-0.03985595703125,
0.058441162109375,
-0.08453369140625,
-0.053680419921875,
-0.047332763671875,
-0.037841796875,
0.0069732666015625,
-0.0003371238708496094,
0.0352783203125,
0.02655029296875,
-0.007282257080078125,
0.003505706787109375,
0.040191650390625,
-0.0291900634765625,
0.042877197265625,
0.032135009765625,
-0.032379150390625,
-0.026458740234375,
0.06756591796875,
0.008697509765625,
0.028533935546875,
0.0300445556640625,
0.003940582275390625,
-0.0193328857421875,
-0.0307159423828125,
-0.041748046875,
0.018280029296875,
-0.04376220703125,
-0.0361328125,
-0.056488037109375,
-0.020233154296875,
-0.01001739501953125,
-0.01323699951171875,
-0.0214385986328125,
-0.038543701171875,
-0.034271240234375,
0.002498626708984375,
0.034942626953125,
0.036895751953125,
-0.005588531494140625,
0.029754638671875,
-0.049224853515625,
0.0189971923828125,
0.004131317138671875,
0.0009870529174804688,
-0.01030731201171875,
-0.040771484375,
0.0009102821350097656,
0.01122283935546875,
-0.043212890625,
-0.07012939453125,
0.049072265625,
0.01690673828125,
0.05712890625,
0.0283203125,
0.004276275634765625,
0.040771484375,
-0.024688720703125,
0.07049560546875,
0.02716064453125,
-0.058380126953125,
0.0304412841796875,
-0.0232391357421875,
0.01129150390625,
0.03289794921875,
0.022979736328125,
-0.027069091796875,
-0.04376220703125,
-0.047332763671875,
-0.0557861328125,
0.053558349609375,
0.0293121337890625,
-0.00829315185546875,
-0.007701873779296875,
0.0255126953125,
-0.0005478858947753906,
0.0126495361328125,
-0.06304931640625,
-0.06292724609375,
-0.004276275634765625,
-0.00777435302734375,
-0.01276397705078125,
-0.00604248046875,
-0.002227783203125,
-0.0264434814453125,
0.0743408203125,
-0.005218505859375,
0.04595947265625,
0.0281982421875,
-0.001087188720703125,
0.006229400634765625,
0.01070404052734375,
0.049468994140625,
0.044158935546875,
-0.02093505859375,
-0.006122589111328125,
0.015960693359375,
-0.03338623046875,
0.0272064208984375,
0.0250091552734375,
-0.01812744140625,
-0.000980377197265625,
0.041900634765625,
0.06658935546875,
0.004428863525390625,
-0.03533935546875,
0.0477294921875,
-0.009002685546875,
-0.0128173828125,
-0.00722503662109375,
0.024017333984375,
0.01629638671875,
0.0379638671875,
0.03204345703125,
-0.00864410400390625,
0.004810333251953125,
-0.04974365234375,
0.0006284713745117188,
0.058441162109375,
-0.025390625,
-0.00829315185546875,
0.0511474609375,
0.00707244873046875,
-0.016571044921875,
0.023773193359375,
-0.039703369140625,
-0.054443359375,
0.059906005859375,
0.041961669921875,
0.054443359375,
-0.0140380859375,
-0.0012521743774414062,
0.0262298583984375,
0.03192138671875,
0.0027008056640625,
0.027587890625,
0.0004680156707763672,
-0.04559326171875,
-0.0233154296875,
-0.053680419921875,
-0.0244293212890625,
-0.005107879638671875,
-0.0279693603515625,
0.0163421630859375,
-0.0265960693359375,
-0.038360595703125,
-0.00894927978515625,
0.036041259765625,
-0.04248046875,
0.0014448165893554688,
0.020233154296875,
0.095458984375,
-0.041595458984375,
0.0634765625,
0.030059814453125,
-0.01678466796875,
-0.052154541015625,
-0.0276641845703125,
0.0157928466796875,
-0.0704345703125,
0.0286865234375,
0.006099700927734375,
-0.0229339599609375,
-0.00395965576171875,
-0.053009033203125,
-0.07098388671875,
0.10418701171875,
0.0345458984375,
-0.061187744140625,
-0.015380859375,
-0.0013723373413085938,
0.019378662109375,
-0.031341552734375,
0.0301361083984375,
0.054901123046875,
0.046630859375,
-0.004909515380859375,
-0.07623291015625,
0.01495361328125,
-0.044281005859375,
-0.01253509521484375,
0.017242431640625,
-0.05291748046875,
0.07110595703125,
-0.0272064208984375,
-0.00632476806640625,
0.0266876220703125,
0.053558349609375,
0.045501708984375,
0.028076171875,
0.03985595703125,
0.0447998046875,
0.052337646484375,
-0.033660888671875,
0.087890625,
-0.040618896484375,
0.02728271484375,
0.078125,
-0.0016489028930664062,
0.053955078125,
0.025390625,
-0.042510986328125,
0.039825439453125,
0.052734375,
0.0093994140625,
0.020050048828125,
0.00609588623046875,
-0.01079559326171875,
-0.00817108154296875,
0.018035888671875,
-0.051788330078125,
0.0247650146484375,
0.0159912109375,
-0.0301361083984375,
-0.007549285888671875,
0.0002846717834472656,
0.023590087890625,
-0.0207366943359375,
-0.00972747802734375,
0.052398681640625,
0.01294708251953125,
-0.039276123046875,
0.063720703125,
0.00836181640625,
0.08197021484375,
-0.07135009765625,
-0.0004215240478515625,
-0.031982421875,
0.014923095703125,
-0.0190887451171875,
-0.06170654296875,
-0.00048279762268066406,
-0.0028438568115234375,
-0.0142669677734375,
0.00640869140625,
0.046417236328125,
-0.017852783203125,
-0.03765869140625,
0.051788330078125,
0.043853759765625,
0.0257110595703125,
-0.00022459030151367188,
-0.08221435546875,
0.0302276611328125,
0.0161895751953125,
-0.03765869140625,
0.0274505615234375,
0.019287109375,
-0.00531005859375,
0.062469482421875,
0.048095703125,
0.0005941390991210938,
0.00695037841796875,
-0.0212249755859375,
0.072265625,
-0.05352783203125,
-0.0306549072265625,
-0.07733154296875,
0.0273590087890625,
-0.0022716522216796875,
-0.02001953125,
0.0633544921875,
0.038177490234375,
0.03692626953125,
0.0260162353515625,
0.051422119140625,
-0.0260162353515625,
0.024017333984375,
-0.02520751953125,
0.05914306640625,
-0.060577392578125,
0.0184783935546875,
-0.03033447265625,
-0.069580078125,
-0.00600433349609375,
0.048980712890625,
-0.0193023681640625,
0.0228424072265625,
0.025299072265625,
0.07244873046875,
0.0004551410675048828,
-0.014404296875,
0.0285186767578125,
0.02838134765625,
0.029693603515625,
0.056488037109375,
0.056640625,
-0.037994384765625,
0.040557861328125,
-0.034454345703125,
-0.036651611328125,
-0.01332855224609375,
-0.0782470703125,
-0.05078125,
-0.029754638671875,
-0.0193023681640625,
-0.030303955078125,
0.0192108154296875,
0.0947265625,
0.051239013671875,
-0.047454833984375,
-0.025054931640625,
0.0242462158203125,
0.0087432861328125,
-0.0196533203125,
-0.0187835693359375,
0.03228759765625,
-0.015045166015625,
-0.0513916015625,
0.02716064453125,
0.01541900634765625,
0.0166778564453125,
-0.028839111328125,
-0.032257080078125,
-0.0198516845703125,
0.00942230224609375,
0.044036865234375,
0.028076171875,
-0.06787109375,
-0.005878448486328125,
0.017913818359375,
-0.0217132568359375,
0.026763916015625,
0.01495361328125,
-0.06317138671875,
0.00981903076171875,
0.020111083984375,
0.0186920166015625,
0.045166015625,
-0.005199432373046875,
0.023101806640625,
-0.03472900390625,
0.00011706352233886719,
0.004413604736328125,
0.04205322265625,
0.026092529296875,
-0.034088134765625,
0.04205322265625,
0.0099945068359375,
-0.046051025390625,
-0.052154541015625,
-0.0125274658203125,
-0.08642578125,
-0.0125274658203125,
0.07794189453125,
-0.0257110595703125,
-0.0275421142578125,
0.01338958740234375,
-0.03314208984375,
0.01502227783203125,
-0.035797119140625,
0.0308380126953125,
0.032867431640625,
-0.02166748046875,
-0.005596160888671875,
-0.048309326171875,
0.033538818359375,
0.011993408203125,
-0.06365966796875,
0.0016641616821289062,
0.023406982421875,
0.025390625,
0.02880859375,
0.058441162109375,
-0.005748748779296875,
0.0159912109375,
-0.015838623046875,
0.0204925537109375,
-0.01425933837890625,
-0.004428863525390625,
-0.01116943359375,
-0.0057830810546875,
-0.00251007080078125,
-0.01702880859375
]
] |
timm/convmixer_768_32.in1k | 2023-04-24T03:13:30.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2201.09792",
"license:mit",
"region:us"
] | image-classification | timm | null | null | timm/convmixer_768_32.in1k | 2 | 43,449 | timm | 2023-04-24T03:13:13 | ---
tags:
- image-classification
- timm
library_name: timm
license: mit
datasets:
- imagenet-1k
---
# Model card for convmixer_768_32.in1k
A ConvMixer image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 21.1
- GMACs: 19.5
- Activations (M): 26.0
- Image size: 224 x 224
- **Papers:**
- Patches Are All You Need?: https://arxiv.org/abs/2201.09792
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/locuslab/convmixer
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('convmixer_768_32.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'convmixer_768_32.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 768, 32, 32) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{Chen2021CrossViTCM,
title={CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification},
author={Chun-Fu Chen and Quanfu Fan and Rameswar Panda},
journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
year={2021},
pages={347-356}
}
```
| 2,729 | [
[
-0.042205810546875,
-0.02362060546875,
-0.0080413818359375,
0.0159912109375,
-0.026947021484375,
-0.0227813720703125,
-0.00865936279296875,
-0.023529052734375,
0.0107421875,
0.0279388427734375,
-0.039825439453125,
-0.042633056640625,
-0.059967041015625,
-0.0119781494140625,
-0.01424407958984375,
0.0704345703125,
-0.0023288726806640625,
0.01319122314453125,
-0.021636962890625,
-0.036773681640625,
-0.0172882080078125,
-0.024169921875,
-0.06597900390625,
-0.033416748046875,
0.0200958251953125,
0.02349853515625,
0.036773681640625,
0.040496826171875,
0.048675537109375,
0.032867431640625,
-0.0015726089477539062,
0.0007753372192382812,
-0.024383544921875,
-0.023406982421875,
0.03070068359375,
-0.0472412109375,
-0.026092529296875,
0.0221099853515625,
0.0565185546875,
0.0232086181640625,
0.0023097991943359375,
0.034271240234375,
0.0173797607421875,
0.031036376953125,
-0.025115966796875,
0.0127716064453125,
-0.0299224853515625,
0.0189056396484375,
-0.01160430908203125,
0.00814056396484375,
-0.02789306640625,
-0.030609130859375,
0.0168914794921875,
-0.034271240234375,
0.033782958984375,
0.00382232666015625,
0.08856201171875,
0.0251617431640625,
-0.00836944580078125,
0.004955291748046875,
-0.0189971923828125,
0.060791015625,
-0.05987548828125,
0.030487060546875,
0.0141754150390625,
0.01352691650390625,
-0.00678253173828125,
-0.07275390625,
-0.046966552734375,
-0.012176513671875,
-0.012725830078125,
0.0005135536193847656,
-0.0218658447265625,
0.0030269622802734375,
0.032989501953125,
0.025421142578125,
-0.03955078125,
0.006526947021484375,
-0.0443115234375,
-0.0159912109375,
0.03802490234375,
0.0065155029296875,
0.0205535888671875,
-0.006793975830078125,
-0.045654296875,
-0.034332275390625,
-0.0153350830078125,
0.037689208984375,
0.01519775390625,
0.0018892288208007812,
-0.048095703125,
0.028472900390625,
0.01181793212890625,
0.040557861328125,
0.0181427001953125,
-0.02471923828125,
0.043975830078125,
0.00621795654296875,
-0.038543701171875,
-0.00594329833984375,
0.0819091796875,
0.03729248046875,
0.01812744140625,
0.006591796875,
0.0008559226989746094,
-0.016143798828125,
-0.00920867919921875,
-0.09210205078125,
-0.0207672119140625,
0.024566650390625,
-0.045745849609375,
-0.022430419921875,
0.023284912109375,
-0.046783447265625,
-0.00693511962890625,
-0.0086822509765625,
0.041717529296875,
-0.03607177734375,
-0.0185546875,
0.0066680908203125,
-0.0220184326171875,
0.039703369140625,
0.0103302001953125,
-0.035308837890625,
0.0214996337890625,
0.02545166015625,
0.0794677734375,
0.0010175704956054688,
-0.026702880859375,
-0.02545166015625,
-0.0269622802734375,
-0.014984130859375,
0.031280517578125,
-0.017547607421875,
-0.0155792236328125,
-0.0213775634765625,
0.034820556640625,
-0.0184326171875,
-0.046417236328125,
0.029022216796875,
-0.00965118408203125,
0.023529052734375,
0.007076263427734375,
-0.022369384765625,
-0.036865234375,
0.031768798828125,
-0.0340576171875,
0.08447265625,
0.022918701171875,
-0.07135009765625,
0.024444580078125,
-0.035003662109375,
-0.0033016204833984375,
-0.0061798095703125,
0.004512786865234375,
-0.08673095703125,
-0.0174102783203125,
0.0050506591796875,
0.0596923828125,
-0.0208892822265625,
0.0096435546875,
-0.046783447265625,
-0.021728515625,
0.03375244140625,
-0.006862640380859375,
0.079833984375,
0.00527191162109375,
-0.0266571044921875,
0.01464080810546875,
-0.057373046875,
0.00745391845703125,
0.0250244140625,
-0.01812744140625,
-0.00894927978515625,
-0.0531005859375,
0.019989013671875,
0.0263824462890625,
0.0096893310546875,
-0.05712890625,
0.0203399658203125,
-0.0083160400390625,
0.0247650146484375,
0.041168212890625,
-0.0030975341796875,
0.0228118896484375,
-0.026702880859375,
0.02685546875,
0.0221405029296875,
0.03533935546875,
0.00551605224609375,
-0.044921875,
-0.072509765625,
-0.03692626953125,
0.019195556640625,
0.036529541015625,
-0.0377197265625,
0.0328369140625,
-0.004756927490234375,
-0.06866455078125,
-0.03790283203125,
0.0012073516845703125,
0.045074462890625,
0.04046630859375,
0.026702880859375,
-0.0345458984375,
-0.042633056640625,
-0.07196044921875,
0.00627899169921875,
0.018524169921875,
-0.0005397796630859375,
0.01873779296875,
0.047576904296875,
-0.0168914794921875,
0.04168701171875,
-0.032379150390625,
-0.0212554931640625,
-0.0104827880859375,
0.00632476806640625,
0.0316162109375,
0.06396484375,
0.06573486328125,
-0.049530029296875,
-0.041656494140625,
-0.0164947509765625,
-0.0653076171875,
0.0191192626953125,
-0.0031490325927734375,
-0.0189056396484375,
0.01313018798828125,
0.01422882080078125,
-0.043701171875,
0.048004150390625,
0.019439697265625,
-0.02239990234375,
0.032989501953125,
-0.0158843994140625,
0.01519012451171875,
-0.087890625,
0.007526397705078125,
0.040283203125,
-0.013946533203125,
-0.03900146484375,
-0.0032482147216796875,
0.0073394775390625,
0.0017118453979492188,
-0.047515869140625,
0.046905517578125,
-0.03399658203125,
0.005023956298828125,
-0.0123748779296875,
-0.029693603515625,
-0.0011682510375976562,
0.062103271484375,
-0.0015115737915039062,
0.020172119140625,
0.0650634765625,
-0.047393798828125,
0.043731689453125,
0.0382080078125,
-0.016082763671875,
0.037200927734375,
-0.047576904296875,
0.0098876953125,
-0.0005211830139160156,
0.020050048828125,
-0.07879638671875,
-0.01029205322265625,
0.03472900390625,
-0.04583740234375,
0.047332763671875,
-0.038604736328125,
-0.0227813720703125,
-0.043212890625,
-0.03948974609375,
0.03466796875,
0.049072265625,
-0.051727294921875,
0.03131103515625,
0.021514892578125,
0.01947021484375,
-0.050079345703125,
-0.06268310546875,
-0.022064208984375,
-0.0249176025390625,
-0.051025390625,
0.0198822021484375,
-0.0028324127197265625,
0.00634765625,
-0.000010132789611816406,
0.00025391578674316406,
-0.0080108642578125,
-0.01505279541015625,
0.039794921875,
0.032562255859375,
-0.01776123046875,
-0.01216888427734375,
-0.0225372314453125,
-0.0129852294921875,
0.010040283203125,
-0.019622802734375,
0.035430908203125,
-0.016754150390625,
-0.00669097900390625,
-0.05511474609375,
-0.0016202926635742188,
0.04656982421875,
-0.013946533203125,
0.060791015625,
0.082275390625,
-0.041046142578125,
-0.0031261444091796875,
-0.0318603515625,
-0.0164794921875,
-0.034759521484375,
0.0308074951171875,
-0.029693603515625,
-0.032440185546875,
0.0595703125,
0.003490447998046875,
0.0081634521484375,
0.0469970703125,
0.026641845703125,
0.0026721954345703125,
0.0667724609375,
0.05511474609375,
0.017791748046875,
0.055267333984375,
-0.07427978515625,
-0.0158843994140625,
-0.068115234375,
-0.046905517578125,
-0.0301055908203125,
-0.047760009765625,
-0.053375244140625,
-0.0210113525390625,
0.0299072265625,
-0.007770538330078125,
-0.031494140625,
0.034912109375,
-0.0634765625,
0.004840850830078125,
0.061431884765625,
0.041107177734375,
-0.0243682861328125,
0.007785797119140625,
-0.014862060546875,
0.0016851425170898438,
-0.057525634765625,
-0.01012420654296875,
0.07269287109375,
0.033172607421875,
0.06268310546875,
-0.0190277099609375,
0.039337158203125,
-0.019866943359375,
0.0284423828125,
-0.044647216796875,
0.0404052734375,
-0.0185699462890625,
-0.027801513671875,
-0.0035858154296875,
-0.01666259765625,
-0.0750732421875,
0.0120849609375,
-0.032318115234375,
-0.05523681640625,
0.031463623046875,
0.01410675048828125,
-0.0207061767578125,
0.053924560546875,
-0.055755615234375,
0.08135986328125,
-0.01238250732421875,
-0.0287933349609375,
0.0098724365234375,
-0.054351806640625,
0.03466796875,
0.00824737548828125,
-0.016082763671875,
-0.0036754608154296875,
0.0186004638671875,
0.0836181640625,
-0.04638671875,
0.066650390625,
-0.035369873046875,
0.033233642578125,
0.032501220703125,
-0.01155853271484375,
0.019805908203125,
-0.004489898681640625,
-0.002162933349609375,
0.0292205810546875,
0.01403045654296875,
-0.0308990478515625,
-0.03350830078125,
0.048858642578125,
-0.075927734375,
-0.02667236328125,
-0.03533935546875,
-0.045135498046875,
0.01186370849609375,
0.0006031990051269531,
0.049530029296875,
0.05426025390625,
0.01100921630859375,
0.03240966796875,
0.05242919921875,
-0.0245208740234375,
0.03564453125,
-0.0016622543334960938,
-0.0109100341796875,
-0.0377197265625,
0.05999755859375,
0.016387939453125,
0.00838470458984375,
0.01328277587890625,
0.01458740234375,
-0.0231475830078125,
-0.03094482421875,
-0.02093505859375,
0.0259246826171875,
-0.046600341796875,
-0.0379638671875,
-0.052734375,
-0.039215087890625,
-0.032318115234375,
-0.004364013671875,
-0.029144287109375,
-0.02349853515625,
-0.0246429443359375,
0.015777587890625,
0.052947998046875,
0.037841796875,
-0.004974365234375,
0.04791259765625,
-0.05267333984375,
0.007030487060546875,
0.010406494140625,
0.042205810546875,
-0.0090789794921875,
-0.0706787109375,
-0.019561767578125,
-0.0016546249389648438,
-0.03802490234375,
-0.052001953125,
0.042205810546875,
0.0120849609375,
0.04571533203125,
0.034576416015625,
-0.01116180419921875,
0.0550537109375,
0.0019254684448242188,
0.03326416015625,
0.028167724609375,
-0.046295166015625,
0.037689208984375,
0.005512237548828125,
0.01666259765625,
0.0019397735595703125,
0.034942626953125,
-0.02587890625,
-0.01364898681640625,
-0.0736083984375,
-0.04705810546875,
0.068115234375,
0.0094146728515625,
-0.00496673583984375,
0.0341796875,
0.050689697265625,
0.00940704345703125,
-0.0034732818603515625,
-0.064453125,
-0.032989501953125,
-0.0274658203125,
-0.0239105224609375,
-0.00592041015625,
-0.004947662353515625,
0.0037593841552734375,
-0.05535888671875,
0.060791015625,
-0.003173828125,
0.039794921875,
0.0206451416015625,
-0.002277374267578125,
-0.0103302001953125,
-0.027587890625,
0.0308685302734375,
0.0174560546875,
-0.0281524658203125,
0.0038585662841796875,
0.02081298828125,
-0.046051025390625,
0.005176544189453125,
0.01922607421875,
-0.0023174285888671875,
0.0007939338684082031,
0.022613525390625,
0.06646728515625,
0.0016603469848632812,
0.0035858154296875,
0.035614013671875,
-0.02105712890625,
-0.0282745361328125,
-0.0235748291015625,
0.01030731201171875,
-0.0069732666015625,
0.03533935546875,
0.0168609619140625,
0.03607177734375,
-0.0001837015151977539,
-0.01325225830078125,
0.018524169921875,
0.049530029296875,
-0.036773681640625,
-0.0222015380859375,
0.056793212890625,
-0.0091705322265625,
-0.0179290771484375,
0.0645751953125,
-0.00047135353088378906,
-0.03656005859375,
0.0859375,
0.0341796875,
0.0723876953125,
-0.0189361572265625,
-0.004512786865234375,
0.0653076171875,
0.014892578125,
0.002567291259765625,
0.00989532470703125,
0.011199951171875,
-0.055694580078125,
0.0023670196533203125,
-0.045745849609375,
-0.011474609375,
0.031219482421875,
-0.03961181640625,
0.03509521484375,
-0.046478271484375,
-0.023834228515625,
0.0172119140625,
0.019012451171875,
-0.06866455078125,
0.021636962890625,
0.008636474609375,
0.0721435546875,
-0.061431884765625,
0.06268310546875,
0.0611572265625,
-0.042694091796875,
-0.06829833984375,
-0.01776123046875,
-0.00582122802734375,
-0.06793212890625,
0.03424072265625,
0.03961181640625,
0.00826263427734375,
0.0094451904296875,
-0.07489013671875,
-0.0460205078125,
0.0985107421875,
0.0341796875,
-0.0195159912109375,
0.027313232421875,
-0.0010118484497070312,
0.01446533203125,
-0.02935791015625,
0.034332275390625,
0.0149688720703125,
0.027984619140625,
0.029632568359375,
-0.052703857421875,
0.0172119140625,
-0.0295562744140625,
-0.00005936622619628906,
0.0160675048828125,
-0.0687255859375,
0.06976318359375,
-0.031768798828125,
-0.0015811920166015625,
0.006381988525390625,
0.04949951171875,
0.0161895751953125,
0.0188446044921875,
0.04241943359375,
0.0560302734375,
0.036346435546875,
-0.017852783203125,
0.0631103515625,
-0.0093841552734375,
0.046905517578125,
0.04150390625,
0.0282135009765625,
0.03594970703125,
0.0270233154296875,
-0.01436614990234375,
0.0281524658203125,
0.084716796875,
-0.038482666015625,
0.0223388671875,
0.014373779296875,
-0.00032401084899902344,
-0.0201416015625,
0.005489349365234375,
-0.0350341796875,
0.037994384765625,
0.0177001953125,
-0.03253173828125,
-0.0109100341796875,
0.0198516845703125,
-0.00003629922866821289,
-0.032379150390625,
-0.0217742919921875,
0.034210205078125,
0.00673675537109375,
-0.042205810546875,
0.056640625,
-0.0006074905395507812,
0.0699462890625,
-0.033721923828125,
-0.008636474609375,
-0.0198211669921875,
0.041351318359375,
-0.02392578125,
-0.06903076171875,
0.021759033203125,
-0.0211181640625,
-0.001392364501953125,
0.00621795654296875,
0.051849365234375,
-0.0372314453125,
-0.043426513671875,
0.0164031982421875,
0.01465606689453125,
0.036224365234375,
-0.0015401840209960938,
-0.08642578125,
0.00600433349609375,
0.0007119178771972656,
-0.035400390625,
0.01812744140625,
0.02801513671875,
0.0009098052978515625,
0.0631103515625,
0.045166015625,
-0.0238800048828125,
0.01479339599609375,
-0.015655517578125,
0.06072998046875,
-0.033721923828125,
-0.022369384765625,
-0.063232421875,
0.045166015625,
-0.004207611083984375,
-0.041351318359375,
0.04345703125,
0.05517578125,
0.0679931640625,
-0.01142120361328125,
0.0394287109375,
-0.01354217529296875,
-0.003643035888671875,
-0.021026611328125,
0.0506591796875,
-0.046417236328125,
-0.017669677734375,
-0.011962890625,
-0.049041748046875,
-0.0360107421875,
0.0458984375,
-0.01245880126953125,
0.01947021484375,
0.034576416015625,
0.07354736328125,
-0.03253173828125,
-0.0258331298828125,
0.0193939208984375,
0.017120361328125,
0.005970001220703125,
0.03778076171875,
0.036651611328125,
-0.06243896484375,
0.037841796875,
-0.046112060546875,
-0.02532958984375,
-0.00965118408203125,
-0.0439453125,
-0.07708740234375,
-0.061798095703125,
-0.0513916015625,
-0.0487060546875,
-0.0196533203125,
0.06854248046875,
0.0789794921875,
-0.05621337890625,
-0.0147552490234375,
0.0128631591796875,
0.008636474609375,
-0.018951416015625,
-0.01641845703125,
0.038543701171875,
-0.006862640380859375,
-0.0667724609375,
-0.037506103515625,
-0.0005660057067871094,
0.0303955078125,
-0.005950927734375,
-0.0216217041015625,
-0.023956298828125,
-0.015045166015625,
0.016357421875,
0.026123046875,
-0.044525146484375,
-0.013763427734375,
-0.0089263916015625,
-0.01151275634765625,
0.034271240234375,
0.025970458984375,
-0.044891357421875,
0.0238189697265625,
0.033294677734375,
0.0199432373046875,
0.0667724609375,
-0.0261077880859375,
0.00577545166015625,
-0.0609130859375,
0.0401611328125,
-0.0186309814453125,
0.048736572265625,
0.0276031494140625,
-0.0293731689453125,
0.0355224609375,
0.034027099609375,
-0.037384033203125,
-0.053680419921875,
-0.0169525146484375,
-0.0953369140625,
-0.002208709716796875,
0.06597900390625,
-0.023956298828125,
-0.049560546875,
0.0242462158203125,
-0.019317626953125,
0.0546875,
-0.004352569580078125,
0.02911376953125,
0.0158538818359375,
-0.0107421875,
-0.051055908203125,
-0.026336669921875,
0.032257080078125,
-0.00567626953125,
-0.047088623046875,
-0.0390625,
-0.00438690185546875,
0.05712890625,
0.0172119140625,
0.028350830078125,
-0.00860595703125,
0.0146331787109375,
0.007015228271484375,
0.051605224609375,
-0.0225372314453125,
0.003173828125,
-0.021636962890625,
0.0016384124755859375,
-0.0172576904296875,
-0.062286376953125
]
] |
timm/ghostnet_100.in1k | 2023-08-20T06:13:05.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1911.11907",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/ghostnet_100.in1k | 0 | 43,274 | timm | 2023-08-19T23:28:44 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for ghostnet_100.in1k
A GhostNet image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 5.2
- GMACs: 0.1
- Activations (M): 3.5
- Image size: 224 x 224
- **Papers:**
- GhostNet: More Features from Cheap Operations: https://arxiv.org/abs/1911.11907
- **Original:** https://github.com/huawei-noah/Efficient-AI-Backbones
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('ghostnet_100.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'ghostnet_100.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 16, 112, 112])
# torch.Size([1, 24, 56, 56])
# torch.Size([1, 40, 28, 28])
# torch.Size([1, 80, 14, 14])
# torch.Size([1, 160, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'ghostnet_100.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 960, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Citation
```bibtex
@InProceedings{Han_2020_CVPR,
author = {Han, Kai and Wang, Yunhe and Tian, Qi and Guo, Jianyuan and Xu, Chunjing and Xu, Chang},
title = {GhostNet: More Features From Cheap Operations},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
```
| 3,541 | [
[
-0.037628173828125,
-0.0304107666015625,
0.00568389892578125,
0.011199951171875,
-0.0294036865234375,
-0.0254364013671875,
-0.013519287109375,
-0.0263671875,
0.03485107421875,
0.04498291015625,
-0.028564453125,
-0.051055908203125,
-0.05352783203125,
-0.012359619140625,
-0.01428985595703125,
0.08160400390625,
0.006069183349609375,
0.0095367431640625,
0.0006289482116699219,
-0.034027099609375,
-0.01424407958984375,
-0.025787353515625,
-0.06903076171875,
-0.0213165283203125,
0.023468017578125,
0.0102996826171875,
0.0390625,
0.05682373046875,
0.0281219482421875,
0.036895751953125,
0.00276947021484375,
0.0036525726318359375,
-0.017181396484375,
-0.0292816162109375,
0.028961181640625,
-0.035736083984375,
-0.03656005859375,
0.0169219970703125,
0.057952880859375,
0.042633056640625,
0.01422119140625,
0.03314208984375,
0.0206756591796875,
0.039154052734375,
-0.0164794921875,
0.00762939453125,
-0.033905029296875,
0.0039825439453125,
-0.0061187744140625,
0.00396728515625,
-0.0126190185546875,
-0.0275726318359375,
0.0149688720703125,
-0.03814697265625,
0.035186767578125,
0.007720947265625,
0.09771728515625,
0.020721435546875,
0.00684356689453125,
-0.001361846923828125,
-0.006011962890625,
0.061370849609375,
-0.0577392578125,
0.01143646240234375,
0.03387451171875,
0.013458251953125,
-0.01097869873046875,
-0.06268310546875,
-0.040740966796875,
-0.0092315673828125,
-0.013824462890625,
-0.0089111328125,
-0.0024566650390625,
-0.002429962158203125,
0.0155487060546875,
0.022918701171875,
-0.03814697265625,
0.006763458251953125,
-0.045867919921875,
-0.0201873779296875,
0.04931640625,
0.006031036376953125,
0.01302337646484375,
-0.0215911865234375,
-0.03289794921875,
-0.0262908935546875,
-0.0086212158203125,
0.0191497802734375,
0.030242919921875,
0.0177154541015625,
-0.043731689453125,
0.031280517578125,
0.0025005340576171875,
0.039520263671875,
0.00977325439453125,
-0.0279083251953125,
0.037994384765625,
0.00943756103515625,
-0.039520263671875,
0.00437164306640625,
0.0712890625,
0.02239990234375,
0.01251983642578125,
0.00897216796875,
-0.01210784912109375,
-0.03289794921875,
-0.0007009506225585938,
-0.07586669921875,
-0.0304107666015625,
0.032440185546875,
-0.056884765625,
-0.037078857421875,
0.0264892578125,
-0.05035400390625,
-0.0175323486328125,
0.0040283203125,
0.050628662109375,
-0.03302001953125,
-0.0281219482421875,
0.01519775390625,
-0.0216522216796875,
0.02593994140625,
0.0148162841796875,
-0.041595458984375,
0.02392578125,
0.0289764404296875,
0.07977294921875,
0.00021660327911376953,
-0.039276123046875,
-0.022674560546875,
-0.02423095703125,
-0.023284912109375,
0.02972412109375,
0.0015878677368164062,
-0.00527191162109375,
-0.026153564453125,
0.03216552734375,
-0.006008148193359375,
-0.045013427734375,
0.01114654541015625,
-0.0102386474609375,
0.0243682861328125,
0.0018949508666992188,
-0.016571044921875,
-0.047607421875,
0.0177154541015625,
-0.037200927734375,
0.09100341796875,
0.0243072509765625,
-0.060791015625,
0.023895263671875,
-0.0307159423828125,
-0.01038360595703125,
-0.013824462890625,
0.0019063949584960938,
-0.078857421875,
-0.002407073974609375,
0.00659942626953125,
0.06793212890625,
-0.01202392578125,
0.00041484832763671875,
-0.03961181640625,
-0.0272979736328125,
0.026519775390625,
-0.00479888916015625,
0.08074951171875,
0.007198333740234375,
-0.0438232421875,
0.01091766357421875,
-0.06207275390625,
0.01337432861328125,
0.037200927734375,
-0.0187530517578125,
-0.0172119140625,
-0.04632568359375,
0.0206451416015625,
0.01244354248046875,
0.012939453125,
-0.03485107421875,
0.019866943359375,
-0.0111846923828125,
0.02264404296875,
0.046142578125,
-0.01058197021484375,
0.0245819091796875,
-0.0293121337890625,
0.00830841064453125,
0.01233673095703125,
0.01715087890625,
-0.01090240478515625,
-0.05157470703125,
-0.06719970703125,
-0.04718017578125,
0.0258636474609375,
0.029876708984375,
-0.036346435546875,
0.05084228515625,
-0.007595062255859375,
-0.05035400390625,
-0.040679931640625,
0.00255584716796875,
0.04180908203125,
0.040313720703125,
0.031982421875,
-0.039794921875,
-0.03680419921875,
-0.06732177734375,
0.0056915283203125,
0.006778717041015625,
-0.00293731689453125,
0.01282501220703125,
0.054046630859375,
-0.0006361007690429688,
0.04052734375,
-0.0310516357421875,
-0.0277557373046875,
-0.01387786865234375,
0.0115203857421875,
0.02642822265625,
0.07232666015625,
0.05859375,
-0.04766845703125,
-0.0287322998046875,
-0.0136871337890625,
-0.07440185546875,
0.015777587890625,
-0.0205078125,
-0.01201629638671875,
0.027008056640625,
-0.004589080810546875,
-0.037750244140625,
0.053497314453125,
0.02093505859375,
-0.0201416015625,
0.02532958984375,
-0.0181427001953125,
0.022552490234375,
-0.087158203125,
0.0037288665771484375,
0.0249786376953125,
-0.01047515869140625,
-0.035888671875,
0.0040740966796875,
-0.00147247314453125,
-0.0080108642578125,
-0.039520263671875,
0.051361083984375,
-0.050994873046875,
-0.0211181640625,
-0.01654052734375,
-0.0177154541015625,
-0.0013828277587890625,
0.066650390625,
0.0019216537475585938,
0.0220489501953125,
0.06640625,
-0.04510498046875,
0.03326416015625,
0.021484375,
-0.01084136962890625,
0.027008056640625,
-0.043365478515625,
0.0172882080078125,
0.002651214599609375,
0.014495849609375,
-0.0772705078125,
-0.0244598388671875,
0.03094482421875,
-0.04425048828125,
0.0450439453125,
-0.040283203125,
-0.0265960693359375,
-0.030242919921875,
-0.044158935546875,
0.0225677490234375,
0.056671142578125,
-0.051116943359375,
0.03582763671875,
0.0205078125,
0.032562255859375,
-0.044647216796875,
-0.07208251953125,
-0.00939178466796875,
-0.0278472900390625,
-0.052947998046875,
0.0200347900390625,
0.01230621337890625,
0.007541656494140625,
0.0160369873046875,
-0.004169464111328125,
-0.01708984375,
-0.004642486572265625,
0.0419921875,
0.0235748291015625,
-0.0234832763671875,
-0.023529052734375,
-0.01953125,
-0.00937652587890625,
0.0019512176513671875,
-0.0369873046875,
0.0443115234375,
-0.017333984375,
-0.0163421630859375,
-0.063720703125,
-0.0035343170166015625,
0.0248870849609375,
0.01050567626953125,
0.066162109375,
0.0792236328125,
-0.045928955078125,
-0.00940704345703125,
-0.041107177734375,
-0.02392578125,
-0.035186767578125,
0.02972412109375,
-0.033721923828125,
-0.0301513671875,
0.0633544921875,
0.007228851318359375,
-0.0015535354614257812,
0.046478271484375,
0.0210418701171875,
0.0003769397735595703,
0.050079345703125,
0.0506591796875,
0.01047515869140625,
0.03521728515625,
-0.0714111328125,
-0.0243988037109375,
-0.0635986328125,
-0.039031982421875,
-0.0277252197265625,
-0.03558349609375,
-0.0450439453125,
-0.0254364013671875,
0.022918701171875,
0.01983642578125,
-0.0184173583984375,
0.045989990234375,
-0.06768798828125,
0.0035724639892578125,
0.04632568359375,
0.04638671875,
-0.022613525390625,
0.01318359375,
-0.0142974853515625,
0.00222015380859375,
-0.0447998046875,
-0.0288848876953125,
0.08148193359375,
0.033203125,
0.041534423828125,
-0.021453857421875,
0.05859375,
-0.012969970703125,
0.0178375244140625,
-0.036468505859375,
0.050048828125,
-0.002964019775390625,
-0.0289459228515625,
-0.0199432373046875,
-0.0232696533203125,
-0.07318115234375,
0.00922393798828125,
-0.025634765625,
-0.05511474609375,
0.0114593505859375,
0.00873565673828125,
-0.015869140625,
0.06146240234375,
-0.056610107421875,
0.06201171875,
-0.0142669677734375,
-0.0295562744140625,
0.006961822509765625,
-0.045196533203125,
0.029052734375,
-0.0028705596923828125,
-0.01922607421875,
-0.0037746429443359375,
0.0026912689208984375,
0.0770263671875,
-0.04742431640625,
0.06341552734375,
-0.0301666259765625,
0.0259552001953125,
0.03289794921875,
-0.01239776611328125,
0.0241546630859375,
-0.0016374588012695312,
-0.01142120361328125,
0.04400634765625,
-0.00341033935546875,
-0.0447998046875,
-0.041534423828125,
0.040679931640625,
-0.06817626953125,
-0.02874755859375,
-0.032562255859375,
-0.0212554931640625,
0.02264404296875,
0.00930023193359375,
0.04498291015625,
0.042755126953125,
0.0159759521484375,
0.0176849365234375,
0.052001953125,
-0.03582763671875,
0.037841796875,
-0.00437164306640625,
-0.0178070068359375,
-0.03973388671875,
0.06707763671875,
0.0214385986328125,
0.003833770751953125,
0.006061553955078125,
0.0092620849609375,
-0.0165863037109375,
-0.04949951171875,
-0.032623291015625,
0.0252532958984375,
-0.047027587890625,
-0.0256195068359375,
-0.05047607421875,
-0.03936767578125,
-0.0361328125,
-0.01177978515625,
-0.036895751953125,
-0.0305023193359375,
-0.0303192138671875,
0.027069091796875,
0.049346923828125,
0.043701171875,
-0.01073455810546875,
0.0380859375,
-0.040374755859375,
0.01496124267578125,
0.0145111083984375,
0.034027099609375,
-0.003940582275390625,
-0.0689697265625,
-0.02801513671875,
-0.00965118408203125,
-0.021331787109375,
-0.062408447265625,
0.045684814453125,
0.0006055831909179688,
0.045654296875,
0.03106689453125,
-0.0135040283203125,
0.06365966796875,
-0.0016002655029296875,
0.05255126953125,
0.020355224609375,
-0.05706787109375,
0.0390625,
-0.004718780517578125,
0.0031299591064453125,
0.005062103271484375,
0.0321044921875,
-0.011566162109375,
-0.007480621337890625,
-0.07177734375,
-0.04241943359375,
0.06732177734375,
0.01448822021484375,
-0.0015516281127929688,
0.031829833984375,
0.058868408203125,
0.00612640380859375,
0.007762908935546875,
-0.051513671875,
-0.040313720703125,
-0.037109375,
-0.011383056640625,
0.00348663330078125,
0.003093719482421875,
-0.001224517822265625,
-0.04486083984375,
0.05364990234375,
-0.0085601806640625,
0.058807373046875,
0.0210418701171875,
0.0022029876708984375,
-0.00015664100646972656,
-0.037506103515625,
0.046905517578125,
0.023040771484375,
-0.0250701904296875,
0.00576019287109375,
0.0287017822265625,
-0.05438232421875,
-0.0010213851928710938,
0.0082550048828125,
0.00778961181640625,
0.0012044906616210938,
0.03338623046875,
0.060546875,
0.0034046173095703125,
0.00922393798828125,
0.031982421875,
0.00119781494140625,
-0.031890869140625,
-0.031036376953125,
0.014556884765625,
-0.01271820068359375,
0.0299224853515625,
0.0450439453125,
0.027374267578125,
-0.005542755126953125,
-0.01314544677734375,
0.023895263671875,
0.0416259765625,
-0.0210418701171875,
-0.025238037109375,
0.052459716796875,
-0.020843505859375,
-0.0189666748046875,
0.055084228515625,
-0.01471710205078125,
-0.03643798828125,
0.08111572265625,
0.0280609130859375,
0.083984375,
-0.00023806095123291016,
-0.0026645660400390625,
0.055084228515625,
0.02520751953125,
-0.007358551025390625,
0.006374359130859375,
0.0160369873046875,
-0.04888916015625,
0.004669189453125,
-0.04351806640625,
0.00015878677368164062,
0.044036865234375,
-0.03863525390625,
0.035888671875,
-0.0634765625,
-0.017852783203125,
0.004405975341796875,
0.0290069580078125,
-0.06402587890625,
0.01885986328125,
-0.0035343170166015625,
0.055023193359375,
-0.055908203125,
0.0692138671875,
0.058868408203125,
-0.047607421875,
-0.07568359375,
-0.0010595321655273438,
0.00815582275390625,
-0.0731201171875,
0.044189453125,
0.03271484375,
0.0089874267578125,
0.005420684814453125,
-0.07012939453125,
-0.05072021484375,
0.098388671875,
0.034088134765625,
0.006519317626953125,
0.0241241455078125,
-0.0086212158203125,
0.016510009765625,
-0.040496826171875,
0.03143310546875,
0.00614166259765625,
0.0335693359375,
0.00933837890625,
-0.052154541015625,
0.0266571044921875,
-0.0213623046875,
0.0084228515625,
0.00528717041015625,
-0.062744140625,
0.07379150390625,
-0.025787353515625,
-0.0110015869140625,
0.008331298828125,
0.0576171875,
0.022613525390625,
0.0200347900390625,
0.039154052734375,
0.0560302734375,
0.03680419921875,
-0.017059326171875,
0.0589599609375,
-0.00250244140625,
0.037322998046875,
0.0341796875,
0.0254058837890625,
0.036773681640625,
0.01448822021484375,
-0.0056915283203125,
0.028656005859375,
0.08587646484375,
-0.040069580078125,
0.022613525390625,
0.0168609619140625,
0.007061004638671875,
-0.004894256591796875,
0.0214385986328125,
-0.03167724609375,
0.0360107421875,
0.00936126708984375,
-0.031402587890625,
-0.00788116455078125,
0.01256561279296875,
0.00843048095703125,
-0.0202484130859375,
-0.017578125,
0.035797119140625,
-0.00572967529296875,
-0.023712158203125,
0.07025146484375,
0.01052093505859375,
0.0750732421875,
-0.031402587890625,
-0.012359619140625,
-0.0228424072265625,
0.007701873779296875,
-0.03497314453125,
-0.054229736328125,
0.02252197265625,
-0.0214691162109375,
0.0010366439819335938,
0.0031795501708984375,
0.0450439453125,
-0.023040771484375,
-0.030487060546875,
0.01346588134765625,
0.013519287109375,
0.064453125,
-0.0008258819580078125,
-0.09051513671875,
0.0189208984375,
0.005046844482421875,
-0.04498291015625,
0.035247802734375,
0.037841796875,
0.002124786376953125,
0.0509033203125,
0.051544189453125,
0.0038089752197265625,
0.0177459716796875,
-0.0313720703125,
0.06329345703125,
-0.0439453125,
-0.0242462158203125,
-0.0545654296875,
0.05535888671875,
-0.0163421630859375,
-0.05072021484375,
0.04998779296875,
0.052642822265625,
0.06329345703125,
-0.005573272705078125,
0.039794921875,
-0.0115966796875,
-0.0028438568115234375,
-0.040557861328125,
0.06048583984375,
-0.0509033203125,
0.003154754638671875,
-0.0174407958984375,
-0.06036376953125,
-0.019500732421875,
0.053863525390625,
-0.003879547119140625,
0.03204345703125,
0.0435791015625,
0.07501220703125,
-0.0240020751953125,
-0.026641845703125,
0.02508544921875,
-0.0028438568115234375,
-0.00714111328125,
0.02716064453125,
0.024993896484375,
-0.0711669921875,
0.0250091552734375,
-0.052215576171875,
-0.020843505859375,
-0.0086822509765625,
-0.056060791015625,
-0.08453369140625,
-0.07550048828125,
-0.0482177734375,
-0.058807373046875,
-0.01320648193359375,
0.06719970703125,
0.0897216796875,
-0.05413818359375,
-0.0118560791015625,
0.011688232421875,
0.017120361328125,
-0.0261993408203125,
-0.0181427001953125,
0.05126953125,
-0.01412200927734375,
-0.06658935546875,
-0.0170135498046875,
0.0028705596923828125,
0.0301666259765625,
-0.0215911865234375,
-0.017547607421875,
-0.01079559326171875,
-0.01593017578125,
0.0074310302734375,
0.029205322265625,
-0.0504150390625,
-0.0157623291015625,
-0.0193939208984375,
-0.0196380615234375,
0.017242431640625,
0.0357666015625,
-0.04608154296875,
0.0079345703125,
0.0253143310546875,
0.036407470703125,
0.0633544921875,
-0.022064208984375,
-0.0064849853515625,
-0.060821533203125,
0.05047607421875,
-0.0211334228515625,
0.027374267578125,
0.028564453125,
-0.0439453125,
0.04150390625,
0.0399169921875,
-0.032440185546875,
-0.06536865234375,
-0.018646240234375,
-0.08349609375,
-0.0218963623046875,
0.063232421875,
-0.0258331298828125,
-0.046173095703125,
0.007511138916015625,
0.0019006729125976562,
0.04742431640625,
-0.00988006591796875,
0.0430908203125,
0.014801025390625,
-0.009857177734375,
-0.04620361328125,
-0.0406494140625,
0.040435791015625,
0.005168914794921875,
-0.046539306640625,
-0.046783447265625,
0.002544403076171875,
0.05126953125,
0.0277252197265625,
0.04095458984375,
-0.005451202392578125,
0.0024738311767578125,
0.0160675048828125,
0.041015625,
-0.034393310546875,
-0.0082855224609375,
-0.0399169921875,
0.00855255126953125,
-0.023284912109375,
-0.05706787109375
]
] |
EleutherAI/gpt-neo-2.7B | 2023-07-09T15:52:52.000Z | [
"transformers",
"pytorch",
"jax",
"rust",
"safetensors",
"gpt_neo",
"text-generation",
"text generation",
"causal-lm",
"en",
"dataset:EleutherAI/pile",
"license:mit",
"endpoints_compatible",
"has_space",
"region:us"
] | text-generation | EleutherAI | null | null | EleutherAI/gpt-neo-2.7B | 365 | 43,224 | transformers | 2022-03-02T23:29:04 | ---
language:
- en
tags:
- text generation
- pytorch
- causal-lm
license: mit
datasets:
- EleutherAI/pile
---
# GPT-Neo 2.7B
## Model Description
GPT-Neo 2.7B is a transformer model designed using EleutherAI's replication of the GPT-3 architecture. GPT-Neo refers to the class of models, while 2.7B represents the number of parameters of this particular pre-trained model.
## Training data
GPT-Neo 2.7B was trained on the Pile, a large scale curated dataset created by EleutherAI for the purpose of training this model.
## Training procedure
This model was trained for 420 billion tokens over 400,000 steps. It was trained as a masked autoregressive language model, using cross-entropy loss.
## Intended Use and Limitations
This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. The model is best at what it was pretrained for however, which is generating texts from a prompt.
### How to use
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
```py
>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='EleutherAI/gpt-neo-2.7B')
>>> generator("EleutherAI has", do_sample=True, min_length=50)
[{'generated_text': 'EleutherAI has made a commitment to create new software packages for each of its major clients and has'}]
```
### Limitations and Biases
GPT-Neo was trained as an autoregressive language model. This means that its core functionality is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work.
GPT-Neo was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending on your usecase GPT-Neo may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile.
As with all language models, it is hard to predict in advance how GPT-Neo will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.
## Eval results
All evaluations were done using our [evaluation harness](https://github.com/EleutherAI/lm-evaluation-harness). Some results for GPT-2 and GPT-3 are inconsistent with the values reported in the respective papers. We are currently looking into why, and would greatly appreciate feedback and further testing of our eval harness. If you would like to contribute evaluations you have done, please reach out on our [Discord](https://discord.gg/vtRgjbM).
### Linguistic Reasoning
| Model and Size | Pile BPB | Pile PPL | Wikitext PPL | Lambada PPL | Lambada Acc | Winogrande | Hellaswag |
| ---------------- | ---------- | ---------- | ------------- | ----------- | ----------- | ---------- | ----------- |
| GPT-Neo 1.3B | 0.7527 | 6.159 | 13.10 | 7.498 | 57.23% | 55.01% | 38.66% |
| GPT-2 1.5B | 1.0468 | ----- | 17.48 | 10.634 | 51.21% | 59.40% | 40.03% |
| **GPT-Neo 2.7B** | **0.7165** | **5.646** | **11.39** | **5.626** | **62.22%** | **56.50%** | **42.73%** |
| GPT-3 Ada | 0.9631 | ----- | ----- | 9.954 | 51.60% | 52.90% | 35.93% |
### Physical and Scientific Reasoning
| Model and Size | MathQA | PubMedQA | Piqa |
| ---------------- | ---------- | ---------- | ----------- |
| GPT-Neo 1.3B | 24.05% | 54.40% | 71.11% |
| GPT-2 1.5B | 23.64% | 58.33% | 70.78% |
| **GPT-Neo 2.7B** | **24.72%** | **57.54%** | **72.14%** |
| GPT-3 Ada | 24.29% | 52.80% | 68.88% |
### Down-Stream Applications
TBD
### BibTeX entry and citation info
To cite this model, use
```bibtex
@software{gpt-neo,
author = {Black, Sid and
Leo, Gao and
Wang, Phil and
Leahy, Connor and
Biderman, Stella},
title = {{GPT-Neo: Large Scale Autoregressive Language
Modeling with Mesh-Tensorflow}},
month = mar,
year = 2021,
note = {{If you use this software, please cite it using
these metadata.}},
publisher = {Zenodo},
version = {1.0},
doi = {10.5281/zenodo.5297715},
url = {https://doi.org/10.5281/zenodo.5297715}
}
@article{gao2020pile,
title={The Pile: An 800GB Dataset of Diverse Text for Language Modeling},
author={Gao, Leo and Biderman, Stella and Black, Sid and Golding, Laurence and Hoppe, Travis and Foster, Charles and Phang, Jason and He, Horace and Thite, Anish and Nabeshima, Noa and others},
journal={arXiv preprint arXiv:2101.00027},
year={2020}
}
``` | 5,008 | [
[
-0.041748046875,
-0.0679931640625,
0.0301055908203125,
0.0022563934326171875,
-0.01483154296875,
-0.00970458984375,
-0.007259368896484375,
-0.034942626953125,
0.016815185546875,
0.0225067138671875,
-0.01386260986328125,
-0.0272064208984375,
-0.05352783203125,
0.005901336669921875,
-0.0457763671875,
0.09228515625,
0.01036834716796875,
-0.03350830078125,
0.0150604248046875,
0.0091400146484375,
-0.014984130859375,
-0.03656005859375,
-0.047760009765625,
-0.017913818359375,
0.0269012451171875,
-0.00792694091796875,
0.058258056640625,
0.054931640625,
0.01415252685546875,
0.025726318359375,
-0.00901031494140625,
-0.005718231201171875,
-0.027801513671875,
-0.011810302734375,
-0.006076812744140625,
-0.00428009033203125,
-0.04449462890625,
0.004688262939453125,
0.04595947265625,
0.0333251953125,
-0.01372528076171875,
0.0106658935546875,
0.006038665771484375,
0.040252685546875,
-0.02606201171875,
0.00800323486328125,
-0.03857421875,
-0.0263214111328125,
-0.01306915283203125,
0.001430511474609375,
-0.02093505859375,
-0.0126190185546875,
0.00403594970703125,
-0.04022216796875,
0.027008056640625,
0.004108428955078125,
0.0958251953125,
0.0194854736328125,
-0.021270751953125,
-0.0085601806640625,
-0.046478271484375,
0.045196533203125,
-0.068603515625,
0.022308349609375,
0.033721923828125,
-0.00335693359375,
0.00799560546875,
-0.04888916015625,
-0.045440673828125,
-0.013153076171875,
-0.022247314453125,
0.017852783203125,
-0.03057861328125,
-0.00949859619140625,
0.026031494140625,
0.03564453125,
-0.07061767578125,
0.004547119140625,
-0.035308837890625,
-0.01534271240234375,
0.049957275390625,
0.002323150634765625,
0.024688720703125,
-0.04620361328125,
-0.0270538330078125,
-0.0260467529296875,
-0.03497314453125,
-0.00804901123046875,
0.043182373046875,
0.01386260986328125,
-0.0242462158203125,
0.03961181640625,
-0.0066070556640625,
0.0469970703125,
-0.00937652587890625,
0.01036834716796875,
0.037933349609375,
-0.04034423828125,
-0.0232086181640625,
-0.01395416259765625,
0.1065673828125,
0.01163482666015625,
0.0181884765625,
0.007415771484375,
-0.02197265625,
0.006961822509765625,
0.01409912109375,
-0.0731201171875,
-0.0179595947265625,
0.0178680419921875,
-0.022918701171875,
-0.0238037109375,
0.0125732421875,
-0.061737060546875,
-0.0025482177734375,
-0.01189422607421875,
0.0279083251953125,
-0.036712646484375,
-0.04205322265625,
0.003173828125,
-0.00855255126953125,
0.007366180419921875,
0.0157623291015625,
-0.06427001953125,
0.027862548828125,
0.05560302734375,
0.07525634765625,
0.007442474365234375,
-0.025238037109375,
-0.013763427734375,
-0.007076263427734375,
-0.0227508544921875,
0.064208984375,
-0.022979736328125,
-0.01360321044921875,
-0.020477294921875,
0.01111602783203125,
-0.017822265625,
-0.0176239013671875,
0.031707763671875,
-0.01395416259765625,
0.052215576171875,
-0.0011053085327148438,
-0.0302581787109375,
-0.0173492431640625,
0.00881195068359375,
-0.05609130859375,
0.0919189453125,
0.039825439453125,
-0.072021484375,
0.01015472412109375,
-0.045745849609375,
-0.0019989013671875,
0.00909423828125,
0.002262115478515625,
-0.035919189453125,
-0.01580810546875,
0.0102691650390625,
0.01508331298828125,
-0.04144287109375,
0.04345703125,
-0.0164642333984375,
-0.0224456787109375,
0.005535125732421875,
-0.037994384765625,
0.0816650390625,
0.028594970703125,
-0.042266845703125,
-0.004528045654296875,
-0.0487060546875,
-0.00560760498046875,
0.0224761962890625,
-0.0092315673828125,
-0.02532958984375,
-0.01178741455078125,
0.01375579833984375,
0.03125,
0.012298583984375,
-0.0206298828125,
0.0185699462890625,
-0.033111572265625,
0.045135498046875,
0.0537109375,
-0.01221466064453125,
0.0262603759765625,
-0.03204345703125,
0.051727294921875,
-0.018463134765625,
-0.001728057861328125,
-0.0074615478515625,
-0.047607421875,
-0.04449462890625,
-0.02093505859375,
0.03424072265625,
0.048095703125,
-0.04486083984375,
0.037506103515625,
-0.0271148681640625,
-0.045074462890625,
-0.037322998046875,
-0.0026340484619140625,
0.028533935546875,
0.03558349609375,
0.035003662109375,
-0.00164794921875,
-0.04266357421875,
-0.07244873046875,
-0.0017251968383789062,
-0.040679931640625,
-0.0033740997314453125,
0.026458740234375,
0.052642822265625,
-0.0283966064453125,
0.06646728515625,
-0.0305328369140625,
-0.00128173828125,
-0.0245361328125,
0.0222015380859375,
0.0350341796875,
0.032135009765625,
0.05096435546875,
-0.040069580078125,
-0.0447998046875,
0.009002685546875,
-0.03778076171875,
-0.0269012451171875,
0.0011749267578125,
-0.00925445556640625,
0.02972412109375,
0.0256500244140625,
-0.06048583984375,
0.01702880859375,
0.053009033203125,
-0.05511474609375,
0.050506591796875,
-0.01515960693359375,
-0.003864288330078125,
-0.08880615234375,
0.0311126708984375,
0.00897979736328125,
-0.0179901123046875,
-0.041412353515625,
-0.01522064208984375,
-0.00429534912109375,
0.0034923553466796875,
-0.0177001953125,
0.066162109375,
-0.0284423828125,
0.004642486572265625,
-0.0132293701171875,
0.0110931396484375,
0.007602691650390625,
0.033843994140625,
0.001922607421875,
0.0523681640625,
0.033477783203125,
-0.034393310546875,
0.018096923828125,
0.007381439208984375,
-0.01531982421875,
0.0188751220703125,
-0.068359375,
0.003978729248046875,
-0.0032405853271484375,
0.0186309814453125,
-0.06732177734375,
0.00048422813415527344,
0.0343017578125,
-0.04132080078125,
0.028228759765625,
-0.0260009765625,
-0.036895751953125,
-0.042083740234375,
-0.019805908203125,
0.017181396484375,
0.042144775390625,
-0.0111541748046875,
0.036102294921875,
0.0286407470703125,
-0.0282440185546875,
-0.05352783203125,
-0.03509521484375,
-0.003513336181640625,
-0.028564453125,
-0.047210693359375,
0.026458740234375,
-0.0069427490234375,
-0.017730712890625,
0.01385498046875,
0.00966644287109375,
0.006740570068359375,
-0.0006823539733886719,
-0.0028247833251953125,
0.026641845703125,
-0.006298065185546875,
-0.006275177001953125,
-0.00630950927734375,
-0.021514892578125,
0.0108642578125,
-0.012420654296875,
0.06256103515625,
-0.0297698974609375,
0.0009002685546875,
-0.01453399658203125,
0.0227813720703125,
0.044677734375,
-0.005298614501953125,
0.0450439453125,
0.062347412109375,
-0.02203369140625,
-0.00074005126953125,
-0.037994384765625,
-0.011505126953125,
-0.03228759765625,
0.055023193359375,
-0.0178985595703125,
-0.06439208984375,
0.045074462890625,
0.02642822265625,
0.0050811767578125,
0.06622314453125,
0.050262451171875,
0.00968170166015625,
0.08172607421875,
0.03900146484375,
-0.01297760009765625,
0.037139892578125,
-0.04241943359375,
0.006134033203125,
-0.080810546875,
-0.006298065185546875,
-0.052001953125,
-0.01387786865234375,
-0.06903076171875,
-0.0303802490234375,
0.007457733154296875,
0.00112152099609375,
-0.0404052734375,
0.041473388671875,
-0.047088623046875,
0.01270294189453125,
0.036163330078125,
-0.0189056396484375,
0.0140838623046875,
-0.00945281982421875,
-0.00812530517578125,
0.01666259765625,
-0.055877685546875,
-0.041961669921875,
0.07763671875,
0.035308837890625,
0.039794921875,
0.01018524169921875,
0.044403076171875,
0.00792694091796875,
0.0294342041015625,
-0.053924560546875,
0.028564453125,
-0.0172882080078125,
-0.07000732421875,
-0.03021240234375,
-0.0543212890625,
-0.09283447265625,
0.0401611328125,
-0.0011491775512695312,
-0.06280517578125,
0.020111083984375,
0.005245208740234375,
-0.0199737548828125,
0.022979736328125,
-0.059661865234375,
0.0753173828125,
-0.0169677734375,
-0.026031494140625,
-0.0009646415710449219,
-0.041015625,
0.0276336669921875,
-0.006252288818359375,
0.037353515625,
-0.011871337890625,
-0.006427764892578125,
0.06353759765625,
-0.044342041015625,
0.052642822265625,
-0.00505828857421875,
-0.0088348388671875,
0.0347900390625,
0.00882720947265625,
0.051055908203125,
0.0093994140625,
0.0019197463989257812,
0.01416778564453125,
0.00249481201171875,
-0.0136566162109375,
-0.0279083251953125,
0.05572509765625,
-0.07391357421875,
-0.041412353515625,
-0.057403564453125,
-0.041717529296875,
0.020477294921875,
0.027099609375,
0.027252197265625,
0.0311126708984375,
-0.00963592529296875,
0.0194854736328125,
0.034027099609375,
-0.029052734375,
0.04315185546875,
0.033111572265625,
-0.029510498046875,
-0.03790283203125,
0.06744384765625,
0.0151214599609375,
0.0181732177734375,
0.0236053466796875,
0.03564453125,
-0.030609130859375,
-0.027099609375,
-0.035247802734375,
0.04541015625,
-0.0272674560546875,
-0.0146331787109375,
-0.06988525390625,
-0.021728515625,
-0.038360595703125,
0.004581451416015625,
-0.03778076171875,
-0.0305328369140625,
-0.017822265625,
-0.010894775390625,
0.035247802734375,
0.056732177734375,
-0.0035877227783203125,
0.015228271484375,
-0.04046630859375,
0.0187225341796875,
0.0248565673828125,
0.024139404296875,
-0.00879669189453125,
-0.056884765625,
-0.01302337646484375,
0.005832672119140625,
-0.0189056396484375,
-0.068359375,
0.0660400390625,
-0.0033893585205078125,
0.044891357421875,
0.0162811279296875,
-0.00820159912109375,
0.028900146484375,
-0.0283966064453125,
0.05609130859375,
0.00632476806640625,
-0.0609130859375,
0.0350341796875,
-0.05023193359375,
0.0217132568359375,
0.0217742919921875,
0.03656005859375,
-0.045867919921875,
-0.034912109375,
-0.08880615234375,
-0.0869140625,
0.06304931640625,
0.02301025390625,
0.0028057098388671875,
-0.0098876953125,
0.0036334991455078125,
-0.00531005859375,
0.006877899169921875,
-0.07598876953125,
-0.0286407470703125,
-0.0347900390625,
-0.0021266937255859375,
-0.0176239013671875,
-0.0148162841796875,
0.0019254684448242188,
-0.02337646484375,
0.06231689453125,
-0.005367279052734375,
0.03363037109375,
0.004772186279296875,
-0.0045166015625,
0.0015707015991210938,
0.0201873779296875,
0.037017822265625,
0.04644775390625,
-0.0289154052734375,
0.0060577392578125,
0.0038700103759765625,
-0.05120849609375,
-0.005542755126953125,
0.032135009765625,
-0.0322265625,
0.00252532958984375,
0.0123138427734375,
0.0723876953125,
-0.0095977783203125,
-0.0238189697265625,
0.033660888671875,
0.0020732879638671875,
-0.03228759765625,
-0.0209808349609375,
-0.0010595321655273438,
0.0108184814453125,
0.001499176025390625,
0.02020263671875,
-0.0030975341796875,
0.0140228271484375,
-0.0396728515625,
0.002490997314453125,
0.032379150390625,
-0.0194854736328125,
-0.0298614501953125,
0.0484619140625,
-0.0018568038940429688,
-0.00939178466796875,
0.04864501953125,
-0.0277557373046875,
-0.051055908203125,
0.0467529296875,
0.04425048828125,
0.06536865234375,
-0.02349853515625,
0.0310516357421875,
0.059722900390625,
0.042816162109375,
-0.01210784912109375,
0.006175994873046875,
0.0195770263671875,
-0.051055908203125,
-0.039337158203125,
-0.051300048828125,
-0.01000213623046875,
0.037322998046875,
-0.02716064453125,
0.024078369140625,
-0.01512908935546875,
-0.0186004638671875,
-0.01456451416015625,
0.01715087890625,
-0.0389404296875,
0.0142974853515625,
0.0183563232421875,
0.0389404296875,
-0.08050537109375,
0.059326171875,
0.05010986328125,
-0.039154052734375,
-0.06585693359375,
-0.0305633544921875,
-0.0019893646240234375,
-0.0428466796875,
0.0219879150390625,
0.0002651214599609375,
0.01125335693359375,
0.01186370849609375,
-0.0325927734375,
-0.088134765625,
0.08001708984375,
0.0192108154296875,
-0.036102294921875,
-0.004344940185546875,
-0.00008589029312133789,
0.05047607421875,
-0.01297760009765625,
0.0626220703125,
0.04052734375,
0.04339599609375,
-0.0022068023681640625,
-0.0828857421875,
0.024658203125,
-0.05718994140625,
0.0092620849609375,
0.0277557373046875,
-0.061614990234375,
0.08575439453125,
-0.00016558170318603516,
-0.0076141357421875,
-0.01242828369140625,
0.0278472900390625,
0.0343017578125,
0.002140045166015625,
0.035980224609375,
0.060516357421875,
0.05682373046875,
-0.024444580078125,
0.099365234375,
-0.0203094482421875,
0.049957275390625,
0.07293701171875,
0.0185089111328125,
0.049713134765625,
0.01922607421875,
-0.0355224609375,
0.053924560546875,
0.0445556640625,
-0.00848388671875,
0.0209197998046875,
0.003753662109375,
0.005901336669921875,
-0.006229400634765625,
0.003757476806640625,
-0.053436279296875,
0.0147552490234375,
0.034210205078125,
-0.0341796875,
-0.0074310302734375,
-0.02642822265625,
0.027923583984375,
-0.0225830078125,
-0.0015745162963867188,
0.042816162109375,
0.00984954833984375,
-0.050323486328125,
0.059295654296875,
-0.0008058547973632812,
0.0504150390625,
-0.04241943359375,
0.006557464599609375,
-0.01019287109375,
0.0009889602661132812,
-0.019195556640625,
-0.04901123046875,
0.0184173583984375,
0.01091766357421875,
-0.0079803466796875,
-0.02313232421875,
0.044036865234375,
-0.021240234375,
-0.040557861328125,
0.0228729248046875,
0.045867919921875,
0.0175628662109375,
-0.01279449462890625,
-0.06964111328125,
-0.00262451171875,
-0.0026702880859375,
-0.050079345703125,
0.02532958984375,
0.050018310546875,
-0.00351715087890625,
0.04327392578125,
0.06103515625,
0.0123138427734375,
-0.00667572021484375,
0.0215911865234375,
0.07427978515625,
-0.048858642578125,
-0.038818359375,
-0.06304931640625,
0.04730224609375,
-0.005382537841796875,
-0.03277587890625,
0.053680419921875,
0.048553466796875,
0.054412841796875,
0.01367950439453125,
0.064453125,
-0.038665771484375,
0.0396728515625,
-0.0161895751953125,
0.04864501953125,
-0.0330810546875,
0.0171966552734375,
-0.045440673828125,
-0.09173583984375,
-0.00530242919921875,
0.062744140625,
-0.034515380859375,
0.033966064453125,
0.0693359375,
0.05291748046875,
0.00562286376953125,
-0.01171875,
0.002773284912109375,
0.03533935546875,
0.030059814453125,
0.05322265625,
0.06103515625,
-0.0498046875,
0.043212890625,
-0.03662109375,
-0.017913818359375,
-0.01200103759765625,
-0.0692138671875,
-0.056884765625,
-0.040374755859375,
-0.034942626953125,
-0.04608154296875,
-0.00634765625,
0.057861328125,
0.0361328125,
-0.046356201171875,
-0.0295257568359375,
-0.0210723876953125,
0.00899505615234375,
-0.0196533203125,
-0.0234832763671875,
0.0382080078125,
-0.0091400146484375,
-0.0645751953125,
0.0068817138671875,
-0.003604888916015625,
0.01250457763671875,
-0.0186614990234375,
-0.0157928466796875,
-0.0296630859375,
-0.00682830810546875,
0.036468505859375,
0.02178955078125,
-0.042816162109375,
-0.011962890625,
0.01056671142578125,
-0.015960693359375,
0.0043792724609375,
0.0298309326171875,
-0.05609130859375,
0.0133056640625,
0.061065673828125,
0.01302337646484375,
0.052520751953125,
0.0135040283203125,
0.035919189453125,
-0.0288543701171875,
0.003513336181640625,
0.0197296142578125,
0.036956787109375,
0.025054931640625,
-0.0261383056640625,
0.04791259765625,
0.0308074951171875,
-0.05181884765625,
-0.05560302734375,
-0.0093536376953125,
-0.081298828125,
-0.02435302734375,
0.11590576171875,
0.00821685791015625,
-0.0207366943359375,
-0.01052093505859375,
-0.01215362548828125,
0.018585205078125,
-0.040313720703125,
0.051849365234375,
0.055694580078125,
0.00525665283203125,
-0.02178955078125,
-0.05609130859375,
0.02972412109375,
0.0160369873046875,
-0.06011962890625,
0.0144195556640625,
0.0357666015625,
0.0233001708984375,
0.020721435546875,
0.05322265625,
-0.026458740234375,
0.0103607177734375,
0.00429534912109375,
0.0110015869140625,
-0.01235198974609375,
-0.0177154541015625,
-0.0190887451171875,
0.000568389892578125,
-0.01448822021484375,
0.02532958984375
]
] |
microsoft/wavlm-base-plus | 2021-12-22T17:23:24.000Z | [
"transformers",
"pytorch",
"wavlm",
"feature-extraction",
"speech",
"en",
"arxiv:1912.07875",
"arxiv:2106.06909",
"arxiv:2101.00390",
"arxiv:2110.13900",
"has_space",
"region:us"
] | feature-extraction | microsoft | null | null | microsoft/wavlm-base-plus | 7 | 43,218 | transformers | 2022-03-02T23:29:05 | ---
language:
- en
datasets:
tags:
- speech
inference: false
---
# WavLM-Base-Plus
[Microsoft's WavLM](https://github.com/microsoft/unilm/tree/master/wavlm)
The base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz.
**Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out [this blog](https://huggingface.co/blog/fine-tune-wav2vec2-english) for more in-detail explanation of how to fine-tune the model.
The model was pre-trained on:
- 60,000 hours of [Libri-Light](https://arxiv.org/abs/1912.07875)
- 10,000 hours of [GigaSpeech](https://arxiv.org/abs/2106.06909)
- 24,000 hours of [VoxPopuli](https://arxiv.org/abs/2101.00390)
[Paper: WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://arxiv.org/abs/2110.13900)
Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei
**Abstract**
*Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. In this paper, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM is built based on the HuBERT framework, with an emphasis on both spoken content modeling and speaker identity preservation. We first equip the Transformer structure with gated relative position bias to improve its capability on recognition tasks. For better speaker discrimination, we propose an utterance mixing training strategy, where additional overlapped utterances are created unsupervisely and incorporated during model training. Lastly, we scale up the training dataset from 60k hours to 94k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks.*
The original model can be found under https://github.com/microsoft/unilm/tree/master/wavlm.
# Usage
This is an English pre-trained speech model that has to be fine-tuned on a downstream task like speech recognition or audio classification before it can be
used in inference. The model was pre-trained in English and should therefore perform well only in English. The model has been shown to work well on the [SUPERB benchmark](https://superbbenchmark.org/).
**Note**: The model was pre-trained on phonemes rather than characters. This means that one should make sure that the input text is converted to a sequence
of phonemes before fine-tuning.
## Speech Recognition
To fine-tune the model for speech recognition, see [the official speech recognition example](https://github.com/huggingface/transformers/tree/master/examples/pytorch/speech-recognition).
## Speech Classification
To fine-tune the model for speech classification, see [the official audio classification example](https://github.com/huggingface/transformers/tree/master/examples/pytorch/audio-classification).
## Speaker Verification
TODO
## Speaker Diarization
TODO
# Contribution
The model was contributed by [cywang](https://huggingface.co/cywang) and [patrickvonplaten](https://huggingface.co/patrickvonplaten).
# License
The official license can be found [here](https://github.com/microsoft/UniSpeech/blob/main/LICENSE)
 | 3,904 | [
[
-0.0245819091796875,
-0.0489501953125,
0.0081939697265625,
0.0106658935546875,
-0.0184326171875,
-0.005741119384765625,
-0.0140380859375,
-0.050323486328125,
-0.011871337890625,
0.031219482421875,
-0.048492431640625,
-0.0413818359375,
-0.0369873046875,
-0.01384735107421875,
-0.02392578125,
0.0657958984375,
0.0287628173828125,
0.0192108154296875,
-0.005352020263671875,
-0.0077056884765625,
-0.035430908203125,
-0.060028076171875,
-0.043975830078125,
-0.037811279296875,
0.0218048095703125,
0.005275726318359375,
0.0184173583984375,
0.03125,
0.00861358642578125,
0.0222625732421875,
-0.0259857177734375,
0.0010690689086914062,
-0.0268707275390625,
-0.005657196044921875,
0.0000546574592590332,
-0.0140838623046875,
-0.0560302734375,
0.01580810546875,
0.042388916015625,
0.038360595703125,
-0.029083251953125,
0.04150390625,
0.0130157470703125,
0.0244598388671875,
-0.0281219482421875,
0.01068115234375,
-0.061676025390625,
-0.00386810302734375,
-0.0259552001953125,
-0.004360198974609375,
-0.0216827392578125,
0.0096282958984375,
0.01515960693359375,
-0.030181884765625,
0.0073089599609375,
0.00482177734375,
0.0623779296875,
0.0256195068359375,
-0.0276641845703125,
-0.0058135986328125,
-0.057037353515625,
0.0765380859375,
-0.06842041015625,
0.06549072265625,
0.03485107421875,
0.0121917724609375,
0.002452850341796875,
-0.06500244140625,
-0.03790283203125,
-0.0257720947265625,
0.0200347900390625,
0.0190277099609375,
-0.0308685302734375,
0.0136871337890625,
0.030731201171875,
0.0178375244140625,
-0.05511474609375,
0.020751953125,
-0.0416259765625,
-0.04486083984375,
0.057647705078125,
-0.0095977783203125,
0.00519561767578125,
0.0011243820190429688,
-0.02850341796875,
-0.00505828857421875,
-0.034881591796875,
0.02734375,
0.0136260986328125,
0.0379638671875,
-0.02703857421875,
0.023223876953125,
0.002529144287109375,
0.056915283203125,
-0.00800323486328125,
-0.026702880859375,
0.05615234375,
-0.0096282958984375,
-0.0245819091796875,
0.0259552001953125,
0.06292724609375,
-0.008819580078125,
0.026885986328125,
0.00850677490234375,
-0.0205230712890625,
0.00637054443359375,
0.007587432861328125,
-0.05010986328125,
-0.019775390625,
0.03338623046875,
-0.03607177734375,
-0.006282806396484375,
-0.013092041015625,
-0.0032672882080078125,
0.006011962890625,
-0.0540771484375,
0.045623779296875,
-0.03179931640625,
-0.031890869140625,
0.0010995864868164062,
0.006938934326171875,
0.01305389404296875,
0.0136871337890625,
-0.0484619140625,
0.0173492431640625,
0.044097900390625,
0.05242919921875,
-0.019775390625,
-0.0309295654296875,
-0.0574951171875,
-0.0024585723876953125,
-0.007747650146484375,
0.0328369140625,
-0.010711669921875,
-0.03192138671875,
-0.016998291015625,
-0.005489349365234375,
0.01058197021484375,
-0.037017822265625,
0.047607421875,
-0.0264434814453125,
0.0179443359375,
0.0153656005859375,
-0.05950927734375,
-0.005046844482421875,
-0.0098114013671875,
-0.0277862548828125,
0.07965087890625,
-0.005401611328125,
-0.056243896484375,
0.0121002197265625,
-0.052215576171875,
-0.04510498046875,
0.00768280029296875,
0.0092315673828125,
-0.0291900634765625,
-0.005462646484375,
0.00824737548828125,
0.034881591796875,
-0.00505828857421875,
0.01910400390625,
-0.004119873046875,
-0.0237884521484375,
0.005214691162109375,
-0.037017822265625,
0.083740234375,
0.034210205078125,
-0.0208282470703125,
0.0335693359375,
-0.08544921875,
0.00926971435546875,
0.0019254684448242188,
-0.031005859375,
-0.00439453125,
-0.004528045654296875,
0.03271484375,
0.0239105224609375,
0.0244903564453125,
-0.053924560546875,
-0.01413726806640625,
-0.042633056640625,
0.04083251953125,
0.041473388671875,
-0.0214996337890625,
0.022918701171875,
-0.00930023193359375,
0.0243682861328125,
-0.00527191162109375,
0.022918701171875,
-0.0086669921875,
-0.0386962890625,
-0.044708251953125,
-0.019622802734375,
0.03375244140625,
0.0595703125,
-0.01557159423828125,
0.0609130859375,
-0.009490966796875,
-0.03826904296875,
-0.07183837890625,
0.01032257080078125,
0.035614013671875,
0.0518798828125,
0.059295654296875,
-0.0026645660400390625,
-0.07012939453125,
-0.049072265625,
-0.003047943115234375,
-0.011871337890625,
-0.0213470458984375,
0.0144805908203125,
0.01580810546875,
-0.026275634765625,
0.0760498046875,
-0.01385498046875,
-0.033447265625,
-0.007320404052734375,
0.0013742446899414062,
0.0189208984375,
0.052520751953125,
0.0147247314453125,
-0.06201171875,
-0.013427734375,
-0.0196685791015625,
-0.030059814453125,
-0.00696563720703125,
0.02105712890625,
0.007289886474609375,
0.01450347900390625,
0.045318603515625,
-0.0369873046875,
0.020904541015625,
0.054443359375,
-0.004833221435546875,
0.04644775390625,
-0.01385498046875,
-0.0284576416015625,
-0.0830078125,
0.005207061767578125,
-0.0064697265625,
-0.03717041015625,
-0.0550537109375,
-0.0254364013671875,
0.002735137939453125,
-0.024749755859375,
-0.05224609375,
0.034912109375,
-0.032623291015625,
-0.001308441162109375,
-0.0218353271484375,
0.007785797119140625,
-0.0131378173828125,
0.039703369140625,
0.0093536376953125,
0.052032470703125,
0.059814453125,
-0.0560302734375,
0.03448486328125,
0.015289306640625,
-0.0249481201171875,
0.0236663818359375,
-0.06640625,
0.027923583984375,
0.0009303092956542969,
0.0194244384765625,
-0.076416015625,
0.01491546630859375,
-0.007049560546875,
-0.0516357421875,
0.039031982421875,
-0.011199951171875,
-0.0191802978515625,
-0.0418701171875,
0.00616455078125,
0.018768310546875,
0.07080078125,
-0.03887939453125,
0.048614501953125,
0.045318603515625,
-0.0037899017333984375,
-0.03515625,
-0.05950927734375,
-0.00974273681640625,
-0.005420684814453125,
-0.041290283203125,
0.042999267578125,
-0.0167236328125,
0.00091552734375,
-0.02239990234375,
-0.01227569580078125,
0.008087158203125,
-0.0007991790771484375,
0.03106689453125,
0.0194549560546875,
-0.017303466796875,
0.0167083740234375,
-0.0208282470703125,
-0.01514434814453125,
-0.0037136077880859375,
-0.034820556640625,
0.053466796875,
-0.01073455810546875,
-0.020843505859375,
-0.061737060546875,
0.0184173583984375,
0.0379638671875,
-0.044769287109375,
0.01256561279296875,
0.0765380859375,
-0.0216522216796875,
-0.007709503173828125,
-0.05987548828125,
-0.004421234130859375,
-0.035797119140625,
0.042633056640625,
-0.029693603515625,
-0.0718994140625,
0.0199432373046875,
0.0136871337890625,
0.01090240478515625,
0.03778076171875,
0.0321044921875,
-0.02142333984375,
0.07830810546875,
0.03814697265625,
-0.0294189453125,
0.04412841796875,
-0.0171051025390625,
-0.005023956298828125,
-0.06719970703125,
-0.0219879150390625,
-0.037200927734375,
-0.0035381317138671875,
-0.03509521484375,
-0.02593994140625,
0.004791259765625,
0.00864410400390625,
-0.021392822265625,
0.0296783447265625,
-0.054443359375,
-0.0011396408081054688,
0.05072021484375,
-0.0009541511535644531,
0.004302978515625,
0.0053558349609375,
-0.01158905029296875,
-0.0009822845458984375,
-0.041015625,
-0.022491455078125,
0.07080078125,
0.040313720703125,
0.04766845703125,
-0.0139312744140625,
0.059326171875,
0.02130126953125,
-0.0007696151733398438,
-0.05755615234375,
0.0293426513671875,
-0.0086517333984375,
-0.035064697265625,
-0.03411865234375,
-0.031280517578125,
-0.0770263671875,
0.0264739990234375,
-0.01873779296875,
-0.056915283203125,
-0.0067596435546875,
0.025299072265625,
-0.0186614990234375,
0.011383056640625,
-0.052215576171875,
0.054595947265625,
-0.026214599609375,
0.005290985107421875,
-0.015380859375,
-0.058502197265625,
0.007114410400390625,
0.0044708251953125,
0.0310821533203125,
-0.020751953125,
0.0224609375,
0.07110595703125,
-0.0245361328125,
0.04541015625,
-0.038848876953125,
-0.0150299072265625,
0.0208587646484375,
-0.02215576171875,
0.028961181640625,
-0.026123046875,
-0.005542755126953125,
0.03155517578125,
0.0200347900390625,
-0.0249786376953125,
-0.0251312255859375,
0.033172607421875,
-0.06793212890625,
-0.033599853515625,
-0.006786346435546875,
-0.03192138671875,
-0.032257080078125,
0.0109100341796875,
0.039520263671875,
0.05169677734375,
-0.0073089599609375,
0.0240325927734375,
0.045806884765625,
-0.00531768798828125,
0.03271484375,
0.053619384765625,
-0.029754638671875,
-0.0272064208984375,
0.07232666015625,
0.0267333984375,
0.0094757080078125,
0.027618408203125,
0.0267791748046875,
-0.04351806640625,
-0.05609130859375,
-0.01367950439453125,
0.002811431884765625,
-0.035186767578125,
-0.0029544830322265625,
-0.057220458984375,
-0.03887939453125,
-0.05474853515625,
0.028350830078125,
-0.040496826171875,
-0.013885498046875,
-0.039947509765625,
-0.002056121826171875,
0.0243072509765625,
0.03924560546875,
-0.001178741455078125,
0.01256561279296875,
-0.05499267578125,
0.034942626953125,
0.033843994140625,
0.0096435546875,
0.0089569091796875,
-0.0771484375,
-0.0144805908203125,
0.023590087890625,
-0.0042877197265625,
-0.04644775390625,
0.01861572265625,
0.0189971923828125,
0.06011962890625,
0.01561737060546875,
-0.0002810955047607422,
0.054534912109375,
-0.051300048828125,
0.06884765625,
0.02386474609375,
-0.082763671875,
0.0584716796875,
-0.01016998291015625,
0.042327880859375,
0.027923583984375,
0.0178680419921875,
-0.0299072265625,
-0.0157928466796875,
-0.0537109375,
-0.0635986328125,
0.0484619140625,
0.0154876708984375,
0.0183258056640625,
0.0224151611328125,
0.004261016845703125,
-0.007747650146484375,
0.01165008544921875,
-0.055206298828125,
-0.04083251953125,
-0.03662109375,
-0.01364898681640625,
-0.0244903564453125,
-0.02392578125,
0.010284423828125,
-0.059722900390625,
0.0665283203125,
0.0175933837890625,
0.00782012939453125,
0.023590087890625,
-0.025909423828125,
0.0204925537109375,
0.0231781005859375,
0.051055908203125,
0.043670654296875,
-0.026092529296875,
0.002239227294921875,
0.0287017822265625,
-0.04425048828125,
0.005283355712890625,
0.0270843505859375,
0.0095672607421875,
0.00893402099609375,
0.032257080078125,
0.09259033203125,
0.0180511474609375,
-0.037750244140625,
0.036590576171875,
0.0031909942626953125,
-0.0270843505859375,
-0.035919189453125,
0.00662994384765625,
0.018463134765625,
0.01280975341796875,
0.046844482421875,
-0.00063323974609375,
0.005588531494140625,
-0.033935546875,
0.0205230712890625,
0.029693603515625,
-0.043304443359375,
-0.0172882080078125,
0.05706787109375,
0.0213470458984375,
-0.05242919921875,
0.033599853515625,
-0.01100921630859375,
-0.043365478515625,
0.021270751953125,
0.055511474609375,
0.05792236328125,
-0.05206298828125,
-0.0120391845703125,
0.02008056640625,
0.0064544677734375,
0.01216888427734375,
0.03350830078125,
-0.03558349609375,
-0.046966552734375,
-0.03173828125,
-0.0701904296875,
-0.01430511474609375,
0.0325927734375,
-0.05023193359375,
0.010955810546875,
-0.0244903564453125,
-0.025238037109375,
0.0164794921875,
0.00672149658203125,
-0.06011962890625,
0.0313720703125,
0.031524658203125,
0.06634521484375,
-0.04248046875,
0.091796875,
0.03717041015625,
-0.0205230712890625,
-0.0810546875,
-0.01511383056640625,
-0.007598876953125,
-0.057708740234375,
0.046905517578125,
0.01016998291015625,
-0.02899169921875,
0.028839111328125,
-0.050872802734375,
-0.07080078125,
0.07440185546875,
0.0212249755859375,
-0.07147216796875,
0.0002880096435546875,
-0.0071868896484375,
0.0372314453125,
-0.0216064453125,
-0.0009355545043945312,
0.0309295654296875,
0.0163116455078125,
0.0103302001953125,
-0.0965576171875,
-0.0113525390625,
-0.0227203369140625,
-0.0030384063720703125,
-0.0208892822265625,
-0.0281982421875,
0.07073974609375,
-0.01067352294921875,
-0.0111541748046875,
-0.007717132568359375,
0.057647705078125,
0.0225067138671875,
0.014373779296875,
0.057891845703125,
0.02911376953125,
0.0782470703125,
0.0037937164306640625,
0.058074951171875,
-0.0226287841796875,
0.027587890625,
0.1075439453125,
-0.01959228515625,
0.0869140625,
0.0231475830078125,
-0.0430908203125,
0.027008056640625,
0.03564453125,
-0.012054443359375,
0.03521728515625,
0.0252227783203125,
-0.00733184814453125,
-0.021087646484375,
-0.00666046142578125,
-0.0540771484375,
0.0516357421875,
0.0116119384765625,
-0.01094818115234375,
0.00899505615234375,
0.0296478271484375,
-0.01549530029296875,
-0.0223236083984375,
-0.033721923828125,
0.059356689453125,
0.0239715576171875,
-0.0158233642578125,
0.060791015625,
-0.013519287109375,
0.08197021484375,
-0.059906005859375,
0.01532745361328125,
0.0213470458984375,
0.004150390625,
-0.0284271240234375,
-0.039642333984375,
0.0004482269287109375,
-0.0005865097045898438,
-0.018035888671875,
-0.014892578125,
0.05859375,
-0.048614501953125,
-0.0355224609375,
0.043609619140625,
0.0225830078125,
0.0269317626953125,
-0.0237884521484375,
-0.064208984375,
0.0164794921875,
0.0018138885498046875,
-0.016845703125,
0.01385498046875,
0.003093719482421875,
0.01904296875,
0.039398193359375,
0.074462890625,
0.0183868408203125,
0.00858306884765625,
0.038970947265625,
0.036376953125,
-0.040374755859375,
-0.059295654296875,
-0.0557861328125,
0.05029296875,
-0.0010528564453125,
-0.0201873779296875,
0.058380126953125,
0.04718017578125,
0.0687255859375,
0.003719329833984375,
0.0528564453125,
0.0235595703125,
0.062225341796875,
-0.04217529296875,
0.06036376953125,
-0.05303955078125,
-0.0020599365234375,
-0.0307769775390625,
-0.06549072265625,
-0.0105438232421875,
0.049072265625,
-0.002117156982421875,
0.01284027099609375,
0.020416259765625,
0.04705810546875,
-0.0024051666259765625,
0.002197265625,
0.04937744140625,
0.022430419921875,
0.019775390625,
0.01491546630859375,
0.06048583984375,
-0.032928466796875,
0.0479736328125,
-0.0174407958984375,
-0.00786590576171875,
-0.00540924072265625,
-0.050201416015625,
-0.06292724609375,
-0.060394287109375,
-0.0276947021484375,
-0.0235595703125,
-0.0026493072509765625,
0.08642578125,
0.09320068359375,
-0.0673828125,
-0.022216796875,
0.001781463623046875,
-0.01256561279296875,
-0.0092315673828125,
-0.0146331787109375,
0.0301971435546875,
-0.0192108154296875,
-0.03924560546875,
0.049041748046875,
0.000125885009765625,
0.02783203125,
-0.010986328125,
-0.02105712890625,
-0.01500701904296875,
-0.00751495361328125,
0.053466796875,
0.021636962890625,
-0.070556640625,
-0.0046844482421875,
-0.0165557861328125,
0.000027477741241455078,
0.013885498046875,
0.043975830078125,
-0.059722900390625,
0.034088134765625,
0.0244140625,
0.02813720703125,
0.06683349609375,
0.002620697021484375,
0.0194244384765625,
-0.065185546875,
0.02142333984375,
0.027191162109375,
0.03717041015625,
0.033416748046875,
-0.0092926025390625,
0.0056915283203125,
0.0143890380859375,
-0.044158935546875,
-0.068359375,
0.00742340087890625,
-0.0897216796875,
-0.017333984375,
0.0797119140625,
0.0023593902587890625,
-0.00843048095703125,
-0.0183563232421875,
-0.038421630859375,
0.04913330078125,
-0.0287017822265625,
0.018096923828125,
0.039306640625,
-0.0088348388671875,
-0.01444244384765625,
-0.033599853515625,
0.047576904296875,
0.0209197998046875,
-0.03790283203125,
0.0055999755859375,
0.02276611328125,
0.04034423828125,
0.012786865234375,
0.058837890625,
0.004314422607421875,
0.00653076171875,
-0.00679779052734375,
0.0303192138671875,
-0.030120849609375,
-0.013946533203125,
-0.041351318359375,
0.007289886474609375,
-0.002178192138671875,
-0.040008544921875
]
] |
microsoft/unixcoder-base | 2022-11-09T04:01:00.000Z | [
"transformers",
"pytorch",
"roberta",
"feature-extraction",
"en",
"arxiv:2203.03850",
"arxiv:1910.09700",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | feature-extraction | microsoft | null | null | microsoft/unixcoder-base | 25 | 43,209 | transformers | 2022-03-23T05:47:38 | ---
language:
- en
license: apache-2.0
---
# Model Card for UniXcoder-base
# Model Details
## Model Description
UniXcoder is a unified cross-modal pre-trained model that leverages multimodal data (i.e. code comment and AST) to pretrain code representation.
- **Developed by:** Microsoft Team
- **Shared by [Optional]:** Hugging Face
- **Model type:** Feature Engineering
- **Language(s) (NLP):** en
- **License:** Apache-2.0
- **Related Models:**
- **Parent Model:** RoBERTa
- **Resources for more information:**
- [Associated Paper](https://arxiv.org/abs/2203.03850)
# Uses
## Direct Use
Feature Engineering
## Downstream Use [Optional]
More information needed
## Out-of-Scope Use
More information needed
# Bias, Risks, and Limitations
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
## Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
# Training Details
## Training Data
More information needed
## Training Procedure
### Preprocessing
More information needed
### Speeds, Sizes, Times
More information needed
# Evaluation
## Testing Data, Factors & Metrics
### Testing Data
More information needed
### Factors
The model creators note in the [associated paper](https://arxiv.org/abs/2203.03850):
> UniXcoder has slightly worse BLEU-4 scores on both code summarization and generation tasks. The main reasons may come from two aspects. One is the amount of NL-PL pairs in the pre-training data
### Metrics
The model creators note in the [associated paper](https://arxiv.org/abs/2203.03850):
> We evaluate UniXcoder on five tasks over nine public datasets, including two understanding tasks, two generation tasks and an autoregressive task. To further evaluate the performance of code fragment embeddings, we also propose a new task called zero-shot code-to-code search.
## Results
The model creators note in the [associated paper](https://arxiv.org/abs/2203.03850):
>Taking zero-shot code-code search task as an example, after removing contrastive learning, the performance drops from 20.45% to 13.73%.
# Model Examination
More information needed
# Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** More information needed
- **Hours used:** More information needed
- **Cloud Provider:** More information needed
- **Compute Region:** More information needed
- **Carbon Emitted:** More information needed
# Technical Specifications [optional]
## Model Architecture and Objective
More information needed
## Compute Infrastructure
More information needed
### Hardware
More information needed
### Software
More information needed
# Citation
**BibTeX:**
```
@misc{https://doi.org/10.48550/arxiv.2203.03850,
doi = {10.48550/ARXIV.2203.03850},
url = {https://arxiv.org/abs/2203.03850},
author = {Guo, Daya and Lu, Shuai and Duan, Nan and Wang, Yanlin and Zhou, Ming and Yin, Jian},
keywords = {Computation and Language (cs.CL), Programming Languages (cs.PL), Software Engineering (cs.SE), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {UniXcoder: Unified Cross-Modal Pre-training for Code
```
# Glossary [optional]
More information needed
# More Information [optional]
More information needed
# Model Card Authors [optional]
Microsoft Team in collaboration with Ezi Ozoani and the Hugging Face Team.
# Model Card Contact
More information needed
# How to Get Started with the Model
Use the code below to get started with the model.
<details>
<summary> Click to expand </summary>
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("microsoft/unixcoder-base")
model = AutoModel.from_pretrained("microsoft/unixcoder-base")
```
</details>
| 4,493 | [
[
-0.0260467529296875,
-0.043609619140625,
0.033172607421875,
-0.005191802978515625,
-0.02734375,
0.00383758544921875,
-0.01175689697265625,
-0.0259552001953125,
-0.00001055002212524414,
0.04119873046875,
-0.0323486328125,
-0.035736083984375,
-0.052520751953125,
0.001739501953125,
-0.03668212890625,
0.07275390625,
0.0008597373962402344,
0.007450103759765625,
-0.01470947265625,
0.00511932373046875,
-0.022125244140625,
-0.06658935546875,
-0.00855255126953125,
0.004428863525390625,
0.00762939453125,
0.0175018310546875,
0.0447998046875,
0.06427001953125,
0.044586181640625,
0.0255584716796875,
0.00812530517578125,
-0.033935546875,
-0.030487060546875,
-0.0239715576171875,
0.0096588134765625,
-0.036773681640625,
-0.046142578125,
0.002574920654296875,
0.051971435546875,
0.047027587890625,
-0.00975799560546875,
0.0218658447265625,
-0.00841522216796875,
0.031280517578125,
-0.05224609375,
0.0016183853149414062,
-0.05206298828125,
0.01141357421875,
-0.021697998046875,
-0.011688232421875,
-0.0255584716796875,
-0.00507354736328125,
-0.0222015380859375,
-0.039886474609375,
0.0226593017578125,
0.0016660690307617188,
0.065673828125,
0.0266265869140625,
-0.025146484375,
-0.014556884765625,
-0.045562744140625,
0.06890869140625,
-0.0692138671875,
0.052947998046875,
0.01105499267578125,
-0.006458282470703125,
0.01126861572265625,
-0.05621337890625,
-0.048583984375,
-0.0212554931640625,
-0.00910186767578125,
0.009674072265625,
-0.0162506103515625,
0.020263671875,
0.048126220703125,
0.039794921875,
-0.042724609375,
-0.0022144317626953125,
-0.047943115234375,
-0.02069091796875,
0.0386962890625,
0.01171875,
0.0217132568359375,
-0.0277557373046875,
-0.0301055908203125,
-0.0218353271484375,
-0.0236358642578125,
0.0210723876953125,
0.0267181396484375,
0.01535797119140625,
-0.0296783447265625,
0.0313720703125,
-0.004352569580078125,
0.045257568359375,
0.0095062255859375,
-0.007099151611328125,
0.03961181640625,
-0.0328369140625,
-0.0357666015625,
-0.013641357421875,
0.07550048828125,
0.00970458984375,
-0.0120849609375,
-0.00449371337890625,
-0.0189971923828125,
0.01531219482421875,
0.0323486328125,
-0.07476806640625,
-0.02490234375,
0.02349853515625,
-0.0535888671875,
-0.022430419921875,
0.03216552734375,
-0.03631591796875,
0.01318359375,
-0.0252838134765625,
0.0196380615234375,
-0.032806396484375,
-0.033172607421875,
0.0012378692626953125,
-0.0193634033203125,
0.021270751953125,
0.00890350341796875,
-0.03778076171875,
0.0186920166015625,
0.04095458984375,
0.04290771484375,
-0.01302337646484375,
-0.035186767578125,
-0.025115966796875,
-0.010009765625,
-0.012542724609375,
0.0298919677734375,
-0.048919677734375,
-0.034576416015625,
-0.0244598388671875,
0.020355224609375,
-0.0026760101318359375,
-0.0171051025390625,
0.0192718505859375,
-0.02825927734375,
0.040802001953125,
-0.0110931396484375,
-0.032958984375,
-0.020782470703125,
0.005397796630859375,
-0.043975830078125,
0.08905029296875,
0.029205322265625,
-0.06646728515625,
0.016632080078125,
-0.075927734375,
-0.0194091796875,
0.00885772705078125,
-0.02008056640625,
-0.028900146484375,
0.004878997802734375,
-0.005451202392578125,
0.04425048828125,
-0.04156494140625,
0.039886474609375,
-0.0204925537109375,
-0.03497314453125,
0.00728607177734375,
-0.008331298828125,
0.0772705078125,
0.035858154296875,
-0.03924560546875,
0.00774383544921875,
-0.047576904296875,
0.0151824951171875,
0.006450653076171875,
-0.02783203125,
-0.00550079345703125,
-0.01654052734375,
0.024749755859375,
0.0235443115234375,
0.01435089111328125,
-0.046600341796875,
0.01123046875,
-0.00942230224609375,
0.027923583984375,
0.047210693359375,
-0.0234375,
0.03167724609375,
-0.00963592529296875,
0.05596923828125,
0.021270751953125,
0.040283203125,
-0.024566650390625,
-0.014862060546875,
-0.0469970703125,
-0.01486968994140625,
0.02947998046875,
0.047637939453125,
-0.055450439453125,
0.04400634765625,
-0.0173187255859375,
-0.04193115234375,
-0.03668212890625,
0.0157470703125,
0.05877685546875,
0.0205078125,
0.035003662109375,
-0.055023193359375,
-0.0565185546875,
-0.061553955078125,
-0.00514984130859375,
-0.01030731201171875,
-0.0014791488647460938,
0.0189971923828125,
0.052490234375,
-0.04095458984375,
0.06732177734375,
-0.039215087890625,
-0.0036029815673828125,
-0.0209503173828125,
0.004947662353515625,
0.01146697998046875,
0.061798095703125,
0.045166015625,
-0.06317138671875,
-0.03497314453125,
-0.0132293701171875,
-0.0487060546875,
0.005466461181640625,
-0.0158843994140625,
0.004329681396484375,
0.0295867919921875,
0.045806884765625,
-0.01428985595703125,
0.0245208740234375,
0.04473876953125,
-0.0191497802734375,
0.04119873046875,
-0.007663726806640625,
0.0156402587890625,
-0.093994140625,
0.037628173828125,
-0.0145416259765625,
-0.0063934326171875,
-0.03961181640625,
0.025970458984375,
0.0161895751953125,
-0.0191802978515625,
-0.037200927734375,
0.0213623046875,
-0.051727294921875,
-0.00247955322265625,
-0.00844573974609375,
-0.02349853515625,
-0.00931549072265625,
0.061126708984375,
0.01200103759765625,
0.057952880859375,
0.05364990234375,
-0.0413818359375,
0.0123748779296875,
-0.005001068115234375,
-0.006072998046875,
0.0273590087890625,
-0.055572509765625,
0.0302276611328125,
0.0093536376953125,
0.010986328125,
-0.049774169921875,
-0.0101776123046875,
0.011993408203125,
-0.04620361328125,
0.033355712890625,
-0.0208587646484375,
-0.040435791015625,
-0.03875732421875,
-0.0270233154296875,
0.035675048828125,
0.0487060546875,
-0.0203094482421875,
0.04827880859375,
0.033233642578125,
0.011138916015625,
-0.04583740234375,
-0.06396484375,
0.0006074905395507812,
0.00592041015625,
-0.030181884765625,
0.0265045166015625,
-0.0302276611328125,
0.014923095703125,
0.0068511962890625,
0.003795623779296875,
-0.016998291015625,
0.01071929931640625,
0.034637451171875,
0.027252197265625,
-0.025970458984375,
-0.01099395751953125,
-0.01303863525390625,
-0.0155181884765625,
0.0112457275390625,
-0.01499176025390625,
0.039215087890625,
-0.0220947265625,
-0.0238800048828125,
-0.029052734375,
0.03912353515625,
0.038543701171875,
-0.0198516845703125,
0.0452880859375,
0.055694580078125,
-0.01396942138671875,
0.0007839202880859375,
-0.053070068359375,
-0.00371551513671875,
-0.037017822265625,
0.04248046875,
-0.0196990966796875,
-0.07000732421875,
0.034759521484375,
0.0064239501953125,
-0.01340484619140625,
0.043060302734375,
0.026397705078125,
0.0034618377685546875,
0.06451416015625,
0.075439453125,
-0.012054443359375,
0.048919677734375,
-0.04052734375,
0.0095367431640625,
-0.0670166015625,
-0.0132598876953125,
-0.05035400390625,
0.004451751708984375,
-0.04962158203125,
-0.042816162109375,
0.00728607177734375,
0.01788330078125,
-0.031280517578125,
0.0504150390625,
-0.06732177734375,
0.033538818359375,
0.04425048828125,
-0.00909423828125,
-0.01165008544921875,
-0.012939453125,
-0.022674560546875,
0.00844573974609375,
-0.0609130859375,
-0.016510009765625,
0.07952880859375,
0.029083251953125,
0.053558349609375,
-0.0063934326171875,
0.06317138671875,
0.0202178955078125,
0.0008025169372558594,
-0.0264434814453125,
0.039215087890625,
-0.0237274169921875,
-0.045074462890625,
-0.007450103759765625,
-0.051300048828125,
-0.049346923828125,
-0.005077362060546875,
-0.01153564453125,
-0.048858642578125,
0.03076171875,
0.0124053955078125,
-0.0178985595703125,
0.041748046875,
-0.05609130859375,
0.08624267578125,
-0.034759521484375,
-0.01268768310546875,
-0.000926971435546875,
-0.060760498046875,
0.0280609130859375,
-0.0035991668701171875,
0.0236053466796875,
0.0171661376953125,
0.004730224609375,
0.06353759765625,
-0.03863525390625,
0.06805419921875,
-0.02880859375,
0.0135040283203125,
0.006122589111328125,
-0.0005035400390625,
0.02227783203125,
-0.0202789306640625,
-0.0114593505859375,
0.033294677734375,
0.0290069580078125,
-0.034820556640625,
-0.018157958984375,
0.043426513671875,
-0.07421875,
-0.0278778076171875,
-0.0404052734375,
-0.02783203125,
0.01406097412109375,
0.02630615234375,
0.031280517578125,
0.028533935546875,
-0.012847900390625,
0.034759521484375,
0.04345703125,
-0.035797119140625,
0.03155517578125,
0.04046630859375,
-0.0153350830078125,
-0.037933349609375,
0.06451416015625,
0.007732391357421875,
0.027923583984375,
0.028045654296875,
-0.0024929046630859375,
-0.00563812255859375,
-0.03131103515625,
-0.02880859375,
0.005420684814453125,
-0.051666259765625,
-0.033782958984375,
-0.064697265625,
-0.029541015625,
-0.045074462890625,
-0.024322509765625,
-0.038970947265625,
-0.016448974609375,
-0.0220184326171875,
0.00861358642578125,
0.020751953125,
0.050537109375,
-0.007476806640625,
0.027557373046875,
-0.06292724609375,
0.0246124267578125,
-0.00005823373794555664,
0.04742431640625,
0.004573822021484375,
-0.03521728515625,
-0.029022216796875,
0.012359619140625,
-0.0234222412109375,
-0.05987548828125,
0.01739501953125,
0.0013570785522460938,
0.050537109375,
0.0175018310546875,
0.01557159423828125,
0.05078125,
-0.003704071044921875,
0.07537841796875,
0.029937744140625,
-0.09246826171875,
0.042327880859375,
-0.0045013427734375,
0.037353515625,
0.04638671875,
0.03363037109375,
-0.04229736328125,
-0.02203369140625,
-0.061309814453125,
-0.05706787109375,
0.09014892578125,
0.00844573974609375,
0.01421356201171875,
0.0009469985961914062,
0.0164642333984375,
-0.0038814544677734375,
0.01531219482421875,
-0.076904296875,
-0.0225067138671875,
-0.0382080078125,
0.0082244873046875,
0.00505828857421875,
-0.0208587646484375,
0.0126495361328125,
-0.03509521484375,
0.0513916015625,
-0.01229095458984375,
0.0498046875,
0.0196380615234375,
-0.0325927734375,
-0.01177215576171875,
0.026092529296875,
0.03460693359375,
0.0252838134765625,
-0.0281219482421875,
-0.0023059844970703125,
0.0159149169921875,
-0.042144775390625,
-0.01318359375,
0.019378662109375,
-0.006168365478515625,
-0.01030731201171875,
0.0286712646484375,
0.06964111328125,
0.01483154296875,
-0.036529541015625,
0.056854248046875,
-0.00649261474609375,
-0.022552490234375,
-0.0263671875,
0.01629638671875,
0.0011844635009765625,
-0.0074310302734375,
0.027130126953125,
0.0172882080078125,
0.0175628662109375,
-0.055572509765625,
0.005725860595703125,
0.0305328369140625,
-0.0335693359375,
-0.0201873779296875,
0.055084228515625,
0.0210418701171875,
-0.0163421630859375,
0.048583984375,
-0.0196990966796875,
-0.0655517578125,
0.061798095703125,
0.03509521484375,
0.0777587890625,
-0.01464080810546875,
-0.00005888938903808594,
0.039337158203125,
0.0305023193359375,
0.016143798828125,
0.0311737060546875,
-0.0285491943359375,
-0.03594970703125,
-0.021209716796875,
-0.04949951171875,
-0.01540374755859375,
-0.01209259033203125,
-0.05908203125,
0.0258636474609375,
-0.041839599609375,
-0.003307342529296875,
-0.005100250244140625,
0.0163421630859375,
-0.0750732421875,
0.01393890380859375,
0.01401519775390625,
0.0679931640625,
-0.055084228515625,
0.087646484375,
0.049102783203125,
-0.05120849609375,
-0.07244873046875,
-0.01473236083984375,
-0.003658294677734375,
-0.0447998046875,
0.04193115234375,
0.0118865966796875,
-0.005229949951171875,
-0.01018524169921875,
-0.0477294921875,
-0.0615234375,
0.091796875,
0.0246124267578125,
-0.0535888671875,
-0.008087158203125,
0.02093505859375,
0.03271484375,
-0.039794921875,
0.051666259765625,
0.019378662109375,
0.025482177734375,
0.0064239501953125,
-0.089599609375,
0.0211639404296875,
-0.042449951171875,
0.0233001708984375,
0.0194091796875,
-0.04632568359375,
0.0814208984375,
-0.0169525146484375,
-0.020660400390625,
-0.007648468017578125,
0.018157958984375,
0.0008554458618164062,
0.01236724853515625,
0.0411376953125,
0.037567138671875,
0.0435791015625,
0.0032901763916015625,
0.0948486328125,
-0.051116943359375,
0.0318603515625,
0.0750732421875,
-0.006870269775390625,
0.06317138671875,
0.0281982421875,
-0.0236358642578125,
0.047454833984375,
0.032135009765625,
-0.027191162109375,
0.0182342529296875,
-0.0018415451049804688,
0.0213165283203125,
-0.02362060546875,
0.00351715087890625,
-0.061370849609375,
0.0248870849609375,
0.006351470947265625,
-0.050018310546875,
0.004241943359375,
-0.0036945343017578125,
0.005565643310546875,
-0.0125579833984375,
-0.004428863525390625,
0.06500244140625,
-0.00919342041015625,
-0.03448486328125,
0.052734375,
0.0214691162109375,
0.07855224609375,
-0.06756591796875,
0.00009441375732421875,
-0.004276275634765625,
0.01338958740234375,
-0.027130126953125,
-0.042694091796875,
0.027252197265625,
0.00458526611328125,
-0.030242919921875,
-0.0203857421875,
0.033782958984375,
-0.021240234375,
-0.048919677734375,
0.043975830078125,
0.02008056640625,
0.01702880859375,
-0.0041961669921875,
-0.0792236328125,
0.0294647216796875,
0.0248565673828125,
-0.002941131591796875,
0.0248870849609375,
0.0218658447265625,
0.010894775390625,
0.02215576171875,
0.06866455078125,
-0.01290130615234375,
0.00608062744140625,
-0.01421356201171875,
0.08636474609375,
-0.068115234375,
-0.041412353515625,
-0.04449462890625,
0.049072265625,
-0.0034618377685546875,
-0.0279693603515625,
0.0455322265625,
0.0682373046875,
0.08148193359375,
-0.017578125,
0.0621337890625,
-0.033294677734375,
0.0246734619140625,
-0.0308685302734375,
0.04962158203125,
-0.053558349609375,
0.0246124267578125,
-0.03961181640625,
-0.0640869140625,
-0.01593017578125,
0.032684326171875,
-0.0160369873046875,
0.0183868408203125,
0.053863525390625,
0.07586669921875,
-0.024261474609375,
-0.005374908447265625,
0.0278778076171875,
0.0264434814453125,
0.011077880859375,
0.044158935546875,
0.041046142578125,
-0.05059814453125,
0.039520263671875,
-0.039642333984375,
-0.01224517822265625,
-0.007049560546875,
-0.072509765625,
-0.05810546875,
-0.058837890625,
-0.0304718017578125,
-0.0182647705078125,
0.005199432373046875,
0.0751953125,
0.07659912109375,
-0.0670166015625,
-0.03240966796875,
0.00337982177734375,
-0.00684356689453125,
-0.003326416015625,
-0.0181427001953125,
0.01824951171875,
-0.0234527587890625,
-0.0294647216796875,
-0.003093719482421875,
0.004375457763671875,
-0.007556915283203125,
-0.0222015380859375,
-0.0283355712890625,
-0.0196533203125,
-0.0058746337890625,
0.03240966796875,
0.022674560546875,
-0.0643310546875,
0.00020301342010498047,
0.01323699951171875,
-0.0171966552734375,
0.011688232421875,
0.07086181640625,
-0.05718994140625,
0.030303955078125,
0.0287322998046875,
0.028900146484375,
0.037994384765625,
-0.0146331787109375,
0.0386962890625,
-0.044219970703125,
0.010955810546875,
0.0146636962890625,
0.032928466796875,
0.0227813720703125,
-0.045654296875,
0.032684326171875,
0.0187225341796875,
-0.039520263671875,
-0.06756591796875,
-0.007396697998046875,
-0.082275390625,
-0.0377197265625,
0.0775146484375,
-0.009918212890625,
-0.022003173828125,
-0.004364013671875,
-0.0186309814453125,
0.012664794921875,
-0.03271484375,
0.02862548828125,
0.032684326171875,
0.006687164306640625,
-0.032073974609375,
-0.022552490234375,
0.032318115234375,
0.0164337158203125,
-0.0513916015625,
0.004352569580078125,
0.03515625,
0.037841796875,
0.0213623046875,
0.060455322265625,
-0.015655517578125,
0.038665771484375,
0.0121612548828125,
0.05120849609375,
-0.0290679931640625,
-0.0151824951171875,
-0.0294342041015625,
0.006046295166015625,
-0.0033321380615234375,
-0.00508880615234375
]
] |
rinna/japanese-roberta-base | 2023-03-22T04:11:46.000Z | [
"transformers",
"pytorch",
"tf",
"safetensors",
"roberta",
"fill-mask",
"ja",
"japanese",
"masked-lm",
"nlp",
"dataset:cc100",
"dataset:wikipedia",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | rinna | null | null | rinna/japanese-roberta-base | 28 | 42,874 | transformers | 2022-03-02T23:29:05 | ---
language: ja
thumbnail: https://github.com/rinnakk/japanese-gpt2/blob/master/rinna.png
tags:
- ja
- japanese
- roberta
- masked-lm
- nlp
license: mit
datasets:
- cc100
- wikipedia
mask_token: "[MASK]"
widget:
- text: "[CLS]4年に1度[MASK]は開かれる。"
---
# japanese-roberta-base
This repository provides a base-sized Japanese RoBERTa model. The model was trained using code from Github repository [rinnakk/japanese-pretrained-models](https://github.com/rinnakk/japanese-pretrained-models) by [rinna Co., Ltd.](https://corp.rinna.co.jp/)
# How to load the model
~~~~
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("rinna/japanese-roberta-base", use_fast=False)
tokenizer.do_lower_case = True # due to some bug of tokenizer config loading
model = AutoModelForMaskedLM.from_pretrained("rinna/japanese-roberta-base")
~~~~
# How to use the model for masked token prediction
## Note 1: Use `[CLS]`
To predict a masked token, be sure to add a `[CLS]` token before the sentence for the model to correctly encode it, as it is used during the model training.
## Note 2: Use `[MASK]` after tokenization
A) Directly typing `[MASK]` in an input string and B) replacing a token with `[MASK]` after tokenization will yield different token sequences, and thus different prediction results. It is more appropriate to use `[MASK]` after tokenization (as it is consistent with how the model was pretrained). However, the Huggingface Inference API only supports typing `[MASK]` in the input string and produces less robust predictions.
## Note 3: Provide `position_ids` as an argument explicitly
When `position_ids` are not provided for a `Roberta*` model, Huggingface's `transformers` will automatically construct it but start from `padding_idx` instead of `0` (see [issue](https://github.com/rinnakk/japanese-pretrained-models/issues/3) and function `create_position_ids_from_input_ids()` in Huggingface's [implementation](https://github.com/huggingface/transformers/blob/master/src/transformers/models/roberta/modeling_roberta.py)), which unfortunately does not work as expected with `rinna/japanese-roberta-base` since the `padding_idx` of the corresponding tokenizer is not `0`. So please be sure to constrcut the `position_ids` by yourself and make it start from position id `0`.
## Example
Here is an example by to illustrate how our model works as a masked language model. Notice the difference between running the following code example and running the Huggingface Inference API.
~~~~
# original text
text = "4年に1度オリンピックは開かれる。"
# prepend [CLS]
text = "[CLS]" + text
# tokenize
tokens = tokenizer.tokenize(text)
print(tokens) # output: ['[CLS]', '▁4', '年に', '1', '度', 'オリンピック', 'は', '開かれる', '。']
# mask a token
masked_idx = 5
tokens[masked_idx] = tokenizer.mask_token
print(tokens) # output: ['[CLS]', '▁4', '年に', '1', '度', '[MASK]', 'は', '開かれる', '。']
# convert to ids
token_ids = tokenizer.convert_tokens_to_ids(tokens)
print(token_ids) # output: [4, 1602, 44, 24, 368, 6, 11, 21583, 8]
# convert to tensor
import torch
token_tensor = torch.LongTensor([token_ids])
# provide position ids explicitly
position_ids = list(range(0, token_tensor.size(1)))
print(position_ids) # output: [0, 1, 2, 3, 4, 5, 6, 7, 8]
position_id_tensor = torch.LongTensor([position_ids])
# get the top 10 predictions of the masked token
with torch.no_grad():
outputs = model(input_ids=token_tensor, position_ids=position_id_tensor)
predictions = outputs[0][0, masked_idx].topk(10)
for i, index_t in enumerate(predictions.indices):
index = index_t.item()
token = tokenizer.convert_ids_to_tokens([index])[0]
print(i, token)
"""
0 総会
1 サミット
2 ワールドカップ
3 フェスティバル
4 大会
5 オリンピック
6 全国大会
7 党大会
8 イベント
9 世界選手権
"""
~~~~
# Model architecture
A 12-layer, 768-hidden-size transformer-based masked language model.
# Training
The model was trained on [Japanese CC-100](http://data.statmt.org/cc-100/ja.txt.xz) and [Japanese Wikipedia](https://dumps.wikimedia.org/jawiki/) to optimize a masked language modelling objective on 8*V100 GPUs for around 15 days. It reaches ~3.9 perplexity on a dev set sampled from CC-100.
# Tokenization
The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based tokenizer, the vocabulary was trained on the Japanese Wikipedia using the official sentencepiece training script.
# Licenese
[The MIT license](https://opensource.org/licenses/MIT)
| 4,475 | [
[
-0.017242431640625,
-0.04364013671875,
0.01751708984375,
0.026123046875,
-0.032684326171875,
0.00476837158203125,
-0.01177978515625,
-0.0187225341796875,
0.03009033203125,
0.0394287109375,
-0.039093017578125,
-0.040740966796875,
-0.05419921875,
0.013916015625,
-0.0098724365234375,
0.0992431640625,
0.0038738250732421875,
0.0098724365234375,
-0.0005960464477539062,
0.002666473388671875,
-0.039794921875,
-0.04693603515625,
-0.0477294921875,
-0.0248565673828125,
0.022552490234375,
0.0030651092529296875,
0.046356201171875,
0.050689697265625,
0.02685546875,
0.038238525390625,
-0.004535675048828125,
-0.0008974075317382812,
-0.015289306640625,
-0.0081329345703125,
-0.00007069110870361328,
-0.03912353515625,
-0.041351318359375,
0.0098876953125,
0.045623779296875,
0.04791259765625,
0.02130126953125,
0.011444091796875,
-0.01529693603515625,
0.0165557861328125,
-0.0279693603515625,
0.014984130859375,
-0.046142578125,
-0.006618499755859375,
-0.0219879150390625,
0.006130218505859375,
-0.0309906005859375,
-0.00939178466796875,
0.000591278076171875,
-0.05712890625,
0.01056671142578125,
0.011322021484375,
0.0931396484375,
0.0130157470703125,
-0.0144805908203125,
-0.01279449462890625,
-0.034576416015625,
0.067626953125,
-0.061859130859375,
0.013671875,
0.034027099609375,
0.00640869140625,
-0.01458740234375,
-0.07257080078125,
-0.04241943359375,
-0.01149749755859375,
-0.01261138916015625,
-0.0020389556884765625,
0.0014171600341796875,
0.00518035888671875,
0.0301666259765625,
0.02215576171875,
-0.0440673828125,
0.00533294677734375,
-0.045501708984375,
-0.0262298583984375,
0.043548583984375,
-0.0014028549194335938,
0.0257720947265625,
-0.026519775390625,
-0.03546142578125,
-0.022918701171875,
-0.031341552734375,
-0.00836181640625,
0.036224365234375,
0.036407470703125,
-0.0286102294921875,
0.04290771484375,
-0.0231781005859375,
0.040618896484375,
0.0257415771484375,
-0.0109710693359375,
0.050537109375,
-0.0090179443359375,
-0.0293426513671875,
-0.003200531005859375,
0.06805419921875,
0.0257110595703125,
0.030914306640625,
-0.0152435302734375,
-0.003925323486328125,
0.01087188720703125,
-0.005828857421875,
-0.06427001953125,
-0.0240020751953125,
0.0272369384765625,
-0.03350830078125,
-0.031524658203125,
0.01995849609375,
-0.046966552734375,
-0.003803253173828125,
-0.005825042724609375,
0.048248291015625,
-0.0296783447265625,
-0.0325927734375,
0.0244903564453125,
-0.0205230712890625,
0.005352020263671875,
0.004657745361328125,
-0.06719970703125,
0.0223388671875,
0.0552978515625,
0.053863525390625,
0.005611419677734375,
-0.0309906005859375,
-0.0242462158203125,
-0.00760650634765625,
-0.0166015625,
0.033660888671875,
-0.0256195068359375,
-0.029022216796875,
0.0017786026000976562,
0.0229339599609375,
-0.019256591796875,
-0.0286865234375,
0.033447265625,
-0.0259246826171875,
0.042572021484375,
0.0002218484878540039,
-0.0279083251953125,
-0.00345611572265625,
0.0133056640625,
-0.032012939453125,
0.08251953125,
0.0147552490234375,
-0.06085205078125,
0.0214996337890625,
-0.04693603515625,
-0.032012939453125,
0.00908660888671875,
0.00045800209045410156,
-0.0496826171875,
0.0081634521484375,
0.0143890380859375,
0.031951904296875,
0.0167083740234375,
0.02435302734375,
-0.020751953125,
-0.033416748046875,
0.03076171875,
-0.0092620849609375,
0.0723876953125,
0.01361846923828125,
-0.0343017578125,
0.0230865478515625,
-0.058746337890625,
0.001251220703125,
0.009429931640625,
-0.00812530517578125,
-0.0269317626953125,
-0.0328369140625,
0.0203704833984375,
0.00641632080078125,
0.01666259765625,
-0.0552978515625,
0.0325927734375,
-0.047088623046875,
0.040863037109375,
0.065673828125,
-0.0115814208984375,
0.03851318359375,
-0.020355224609375,
0.043975830078125,
0.00864410400390625,
-0.004642486572265625,
-0.0172119140625,
-0.042999267578125,
-0.06451416015625,
-0.026092529296875,
0.036224365234375,
0.03326416015625,
-0.063720703125,
0.040924072265625,
-0.030029296875,
-0.041259765625,
-0.030517578125,
-0.03448486328125,
0.035614013671875,
0.0273895263671875,
0.0220184326171875,
-0.0248565673828125,
-0.07281494140625,
-0.048309326171875,
-0.0209197998046875,
-0.0238037109375,
0.0010433197021484375,
0.0005626678466796875,
0.06072998046875,
-0.0194854736328125,
0.04681396484375,
-0.027923583984375,
-0.0175628662109375,
-0.012420654296875,
0.0107574462890625,
0.045013427734375,
0.07342529296875,
0.034576416015625,
-0.045318603515625,
-0.03179931640625,
-0.0117645263671875,
-0.046112060546875,
0.0143585205078125,
-0.0161895751953125,
-0.0312347412109375,
0.0089874267578125,
0.0210418701171875,
-0.0628662109375,
0.04290771484375,
0.0291290283203125,
-0.046112060546875,
0.042205810546875,
-0.0087890625,
0.010009765625,
-0.09893798828125,
0.0018978118896484375,
-0.01386260986328125,
-0.01042938232421875,
-0.051666259765625,
0.01488494873046875,
-0.00312042236328125,
-0.01232147216796875,
-0.034088134765625,
0.05975341796875,
-0.0295562744140625,
0.00635528564453125,
-0.01084136962890625,
-0.01406097412109375,
0.0017080307006835938,
0.036285400390625,
0.005397796630859375,
0.051239013671875,
0.04052734375,
-0.0421142578125,
0.02520751953125,
0.035125732421875,
-0.020843505859375,
0.01030731201171875,
-0.05255126953125,
0.01299285888671875,
-0.00428009033203125,
0.0173797607421875,
-0.06683349609375,
-0.030487060546875,
0.040679931640625,
-0.05126953125,
0.03546142578125,
-0.02001953125,
-0.028228759765625,
-0.0377197265625,
-0.02447509765625,
0.045013427734375,
0.040863037109375,
-0.03448486328125,
0.046295166015625,
0.017425537109375,
0.01027679443359375,
-0.063720703125,
-0.067138671875,
0.003284454345703125,
-0.035888671875,
-0.036834716796875,
0.050048828125,
-0.01329803466796875,
-0.0012750625610351562,
0.00243377685546875,
0.0027618408203125,
-0.0001081228256225586,
0.01666259765625,
0.0256805419921875,
0.033660888671875,
-0.0181427001953125,
-0.0063629150390625,
-0.017730712890625,
-0.0283966064453125,
0.0183868408203125,
-0.02386474609375,
0.0615234375,
-0.0091552734375,
-0.015380859375,
-0.04486083984375,
-0.0018835067749023438,
0.042022705078125,
-0.016998291015625,
0.063232421875,
0.06304931640625,
-0.045440673828125,
0.0014362335205078125,
-0.031036376953125,
-0.01067352294921875,
-0.0390625,
0.0389404296875,
-0.05902099609375,
-0.049468994140625,
0.060546875,
0.01107025146484375,
-0.011810302734375,
0.047332763671875,
0.035369873046875,
0.00408935546875,
0.06982421875,
0.03656005859375,
-0.008880615234375,
0.035400390625,
-0.038726806640625,
0.01947021484375,
-0.07293701171875,
-0.0214996337890625,
-0.035125732421875,
-0.004131317138671875,
-0.063232421875,
-0.01800537109375,
0.01146697998046875,
0.005115509033203125,
-0.029510498046875,
0.041839599609375,
-0.055419921875,
0.02557373046875,
0.053192138671875,
0.01009368896484375,
-0.007266998291015625,
0.003810882568359375,
-0.006679534912109375,
-0.00592803955078125,
-0.04193115234375,
-0.02587890625,
0.091064453125,
0.03546142578125,
0.045135498046875,
-0.00345611572265625,
0.06646728515625,
-0.008575439453125,
0.023956298828125,
-0.04241943359375,
0.038726806640625,
-0.0201873779296875,
-0.057098388671875,
-0.00855255126953125,
-0.01493072509765625,
-0.076171875,
0.0197906494140625,
-0.0144500732421875,
-0.0643310546875,
0.0041046142578125,
-0.01222991943359375,
-0.025787353515625,
0.020111083984375,
-0.027587890625,
0.07720947265625,
-0.01023101806640625,
-0.023406982421875,
0.0131683349609375,
-0.034454345703125,
0.026885986328125,
0.01291656494140625,
0.0172882080078125,
-0.00443267822265625,
0.012664794921875,
0.0743408203125,
-0.0303192138671875,
0.0699462890625,
-0.0187225341796875,
0.0261993408203125,
0.004032135009765625,
-0.005687713623046875,
0.0285491943359375,
0.00677490234375,
-0.00928497314453125,
0.0220794677734375,
-0.0007443428039550781,
-0.031280517578125,
-0.037994384765625,
0.058135986328125,
-0.07135009765625,
-0.052734375,
-0.0498046875,
-0.024200439453125,
0.01617431640625,
0.0262298583984375,
0.050750732421875,
0.052459716796875,
0.0037326812744140625,
0.01641845703125,
0.0333251953125,
-0.0177764892578125,
0.036224365234375,
0.0018510818481445312,
-0.0284423828125,
-0.04766845703125,
0.048980712890625,
0.0163421630859375,
0.00025010108947753906,
0.0159454345703125,
0.0166168212890625,
-0.0255279541015625,
-0.0360107421875,
-0.038482666015625,
0.03546142578125,
-0.04486083984375,
-0.0164642333984375,
-0.0457763671875,
-0.0287933349609375,
-0.0601806640625,
-0.006011962890625,
-0.0174102783203125,
-0.0390625,
-0.0222320556640625,
-0.0172882080078125,
0.0238189697265625,
0.040435791015625,
-0.0127716064453125,
0.0350341796875,
-0.038482666015625,
0.01464080810546875,
-0.008392333984375,
0.02490234375,
-0.009002685546875,
-0.049713134765625,
-0.0266571044921875,
-0.01105499267578125,
-0.0025787353515625,
-0.0616455078125,
0.04779052734375,
-0.0002944469451904297,
0.04058837890625,
0.023345947265625,
0.006744384765625,
0.0670166015625,
-0.031524658203125,
0.055908203125,
0.00583648681640625,
-0.07379150390625,
0.03253173828125,
-0.028411865234375,
0.0259246826171875,
0.0270843505859375,
0.020294189453125,
-0.037811279296875,
-0.034912109375,
-0.06695556640625,
-0.0657958984375,
0.053375244140625,
0.0257110595703125,
0.0350341796875,
-0.0128936767578125,
0.027984619140625,
0.010894775390625,
0.0152435302734375,
-0.08746337890625,
-0.04058837890625,
-0.0328369140625,
-0.0323486328125,
-0.004253387451171875,
-0.019744873046875,
-0.004352569580078125,
-0.028076171875,
0.07244873046875,
0.003620147705078125,
0.037322998046875,
0.0141448974609375,
-0.00672149658203125,
-0.000037789344787597656,
-0.00904083251953125,
0.051239013671875,
0.0379638671875,
-0.02349853515625,
-0.003856658935546875,
0.0132904052734375,
-0.0311737060546875,
-0.00656890869140625,
0.0035915374755859375,
-0.0143585205078125,
0.027587890625,
0.039215087890625,
0.0811767578125,
0.0218658447265625,
-0.01461029052734375,
0.03662109375,
0.0027370452880859375,
-0.00888824462890625,
-0.059844970703125,
-0.00537872314453125,
-0.00464630126953125,
-0.003597259521484375,
0.0279083251953125,
0.00943756103515625,
-0.004119873046875,
-0.037109375,
0.01300048828125,
0.034881591796875,
-0.015411376953125,
-0.03179931640625,
0.065673828125,
0.00867462158203125,
-0.034576416015625,
0.0433349609375,
-0.00909423828125,
-0.0616455078125,
0.05828857421875,
0.047637939453125,
0.0723876953125,
-0.0083160400390625,
0.006519317626953125,
0.0635986328125,
0.0174102783203125,
0.01030731201171875,
0.0147247314453125,
-0.004547119140625,
-0.061187744140625,
-0.02691650390625,
-0.05499267578125,
0.00015044212341308594,
0.0286865234375,
-0.047393798828125,
0.0277557373046875,
-0.049224853515625,
-0.0261688232421875,
-0.0032787322998046875,
0.00920867919921875,
-0.063720703125,
0.0309906005859375,
-0.00473785400390625,
0.056671142578125,
-0.0799560546875,
0.06915283203125,
0.0577392578125,
-0.04498291015625,
-0.07122802734375,
-0.017578125,
-0.0184173583984375,
-0.0645751953125,
0.056427001953125,
0.03643798828125,
0.0211334228515625,
0.004680633544921875,
-0.036285400390625,
-0.08453369140625,
0.06719970703125,
-0.01291656494140625,
-0.01059722900390625,
-0.00690460205078125,
0.00933074951171875,
0.034912109375,
-0.037200927734375,
0.041778564453125,
0.01910400390625,
0.0338134765625,
-0.01412200927734375,
-0.07025146484375,
0.0013132095336914062,
-0.027679443359375,
0.0083160400390625,
0.0034885406494140625,
-0.037811279296875,
0.09332275390625,
-0.0007801055908203125,
-0.01849365234375,
0.041778564453125,
0.06475830078125,
0.0246124267578125,
0.0178070068359375,
0.0293121337890625,
0.0469970703125,
0.041748046875,
-0.0288848876953125,
0.06915283203125,
-0.0198211669921875,
0.03692626953125,
0.060638427734375,
0.00730133056640625,
0.056976318359375,
0.033660888671875,
-0.0177001953125,
0.07366943359375,
0.0599365234375,
-0.01776123046875,
0.043365478515625,
0.00872039794921875,
-0.008026123046875,
-0.0052642822265625,
0.0133209228515625,
-0.037811279296875,
0.04241943359375,
0.020477294921875,
-0.0251922607421875,
0.01137542724609375,
0.01885986328125,
0.031524658203125,
0.004573822021484375,
-0.0196380615234375,
0.053863525390625,
-0.004787445068359375,
-0.0601806640625,
0.04705810546875,
0.01678466796875,
0.07672119140625,
-0.030975341796875,
0.00801849365234375,
-0.0106353759765625,
0.0228424072265625,
-0.012664794921875,
-0.0408935546875,
0.01410675048828125,
-0.0093994140625,
-0.004695892333984375,
-0.0168304443359375,
0.053466796875,
-0.035888671875,
-0.05352783203125,
0.0088043212890625,
0.011016845703125,
0.031463623046875,
0.01313018798828125,
-0.05352783203125,
0.0125274658203125,
0.00431060791015625,
-0.0280914306640625,
0.0264892578125,
0.02001953125,
-0.0037708282470703125,
0.043731689453125,
0.0711669921875,
-0.00029206275939941406,
0.0060272216796875,
0.0018873214721679688,
0.055816650390625,
-0.0435791015625,
-0.050689697265625,
-0.069580078125,
0.06390380859375,
-0.012115478515625,
-0.04937744140625,
0.05462646484375,
0.040618896484375,
0.0740966796875,
-0.029449462890625,
0.046295166015625,
-0.006378173828125,
0.03173828125,
-0.043365478515625,
0.060516357421875,
-0.0274810791015625,
-0.0032901763916015625,
-0.0111236572265625,
-0.06927490234375,
-0.0277099609375,
0.06341552734375,
-0.0174560546875,
0.01165771484375,
0.045196533203125,
0.05535888671875,
0.0032825469970703125,
-0.032073974609375,
0.0206146240234375,
0.0243072509765625,
0.0149993896484375,
0.0244293212890625,
0.040924072265625,
-0.066162109375,
0.0139007568359375,
-0.047332763671875,
-0.0136260986328125,
-0.0183868408203125,
-0.0648193359375,
-0.0731201171875,
-0.05499267578125,
-0.039306640625,
-0.05731201171875,
0.0009059906005859375,
0.070068359375,
0.0675048828125,
-0.06884765625,
-0.0126953125,
-0.005092620849609375,
0.0025463104248046875,
-0.0016422271728515625,
-0.0192413330078125,
0.03753662109375,
-0.020233154296875,
-0.081787109375,
0.0209503173828125,
-0.0098876953125,
0.0141143798828125,
-0.01158905029296875,
-0.0037326812744140625,
-0.00698089599609375,
-0.00664520263671875,
0.0160064697265625,
0.023162841796875,
-0.07916259765625,
-0.043060302734375,
-0.005107879638671875,
-0.01345062255859375,
0.0021076202392578125,
0.0205230712890625,
-0.07421875,
0.033050537109375,
0.0291748046875,
0.02490234375,
0.055633544921875,
0.00249481201171875,
0.04498291015625,
-0.056182861328125,
0.041229248046875,
0.00205230712890625,
0.03955078125,
0.03546142578125,
-0.0296630859375,
0.0394287109375,
0.0276336669921875,
-0.030853271484375,
-0.08074951171875,
0.007808685302734375,
-0.067138671875,
-0.0160675048828125,
0.07855224609375,
-0.0213775634765625,
-0.03759765625,
0.0101318359375,
-0.0164642333984375,
0.037384033203125,
-0.007442474365234375,
0.052520751953125,
0.053497314453125,
0.01219940185546875,
-0.000553131103515625,
-0.00977325439453125,
0.041595458984375,
0.037933349609375,
-0.0295562744140625,
-0.0258636474609375,
-0.005558013916015625,
0.03619384765625,
0.027252197265625,
0.043731689453125,
-0.004405975341796875,
0.00966644287109375,
0.00997161865234375,
0.0174102783203125,
-0.0224456787109375,
-0.012420654296875,
-0.026397705078125,
-0.0033054351806640625,
-0.002758026123046875,
-0.049041748046875
]
] |
beomi/KcELECTRA-base | 2023-04-03T14:53:16.000Z | [
"transformers",
"pytorch",
"electra",
"pretraining",
"korean",
"ko",
"en",
"doi:10.57967/hf/0017",
"license:mit",
"endpoints_compatible",
"has_space",
"region:us"
] | null | beomi | null | null | beomi/KcELECTRA-base | 14 | 42,853 | transformers | 2022-03-02T23:29:05 | ---
language:
- ko
- en
tags:
- electra
- korean
license: "mit"
---
# KcELECTRA: Korean comments ELECTRA
** Updates on 2022.10.08 **
- KcELECTRA-base-v2022 (구 v2022-dev) 모델 이름이 변경되었습니다. --> KcELECTRA-base 레포의 `v2022`로 통합되었습니다.
- 위 모델의 세부 스코어를 추가하였습니다.
- 기존 KcELECTRA-base(v2021) 대비 대부분의 downstream task에서 ~1%p 수준의 성능 향상이 있습니다.
---
공개된 한국어 Transformer 계열 모델들은 대부분 한국어 위키, 뉴스 기사, 책 등 잘 정제된 데이터를 기반으로 학습한 모델입니다. 한편, 실제로 NSMC와 같은 User-Generated Noisy text domain 데이터셋은 정제되지 않았고 구어체 특징에 신조어가 많으며, 오탈자 등 공식적인 글쓰기에서 나타나지 않는 표현들이 빈번하게 등장합니다.
KcELECTRA는 위와 같은 특성의 데이터셋에 적용하기 위해, 네이버 뉴스에서 댓글과 대댓글을 수집해, 토크나이저와 ELECTRA모델을 처음부터 학습한 Pretrained ELECTRA 모델입니다.
기존 KcBERT 대비 데이터셋 증가 및 vocab 확장을 통해 상당한 수준으로 성능이 향상되었습니다.
KcELECTRA는 Huggingface의 Transformers 라이브러리를 통해 간편히 불러와 사용할 수 있습니다. (별도의 파일 다운로드가 필요하지 않습니다.)
```
💡 NOTE 💡
General Corpus로 학습한 KoELECTRA가 보편적인 task에서는 성능이 더 잘 나올 가능성이 높습니다.
KcBERT/KcELECTRA는 User genrated, Noisy text에 대해서 보다 잘 동작하는 PLM입니다.
```
## KcELECTRA Performance
- Finetune 코드는 https://github.com/Beomi/KcBERT-finetune 에서 찾아보실 수 있습니다.
- 해당 Repo의 각 Checkpoint 폴더에서 Step별 세부 스코어를 확인하실 수 있습니다.
| | Size<br/>(용량) | **NSMC**<br/>(acc) | **Naver NER**<br/>(F1) | **PAWS**<br/>(acc) | **KorNLI**<br/>(acc) | **KorSTS**<br/>(spearman) | **Question Pair**<br/>(acc) | **KorQuaD (Dev)**<br/>(EM/F1) |
| :----------------- | :-------------: | :----------------: | :--------------------: | :----------------: | :------------------: | :-----------------------: | :-------------------------: | :---------------------------: |
| **KcELECTRA-base-v2022** | 475M | **91.97** | 87.35 | 76.50 | 82.12 | 83.67 | 95.12 | 69.00 / 90.40 |
| **KcELECTRA-base** | 475M | 91.71 | 86.90 | 74.80 | 81.65 | 82.65 | **95.78** | 70.60 / 90.11 |
| KcBERT-Base | 417M | 89.62 | 84.34 | 66.95 | 74.85 | 75.57 | 93.93 | 60.25 / 84.39 |
| KcBERT-Large | 1.2G | 90.68 | 85.53 | 70.15 | 76.99 | 77.49 | 94.06 | 62.16 / 86.64 |
| KoBERT | 351M | 89.63 | 86.11 | 80.65 | 79.00 | 79.64 | 93.93 | 52.81 / 80.27 |
| XLM-Roberta-Base | 1.03G | 89.49 | 86.26 | 82.95 | 79.92 | 79.09 | 93.53 | 64.70 / 88.94 |
| HanBERT | 614M | 90.16 | 87.31 | 82.40 | 80.89 | 83.33 | 94.19 | 78.74 / 92.02 |
| KoELECTRA-Base | 423M | 90.21 | 86.87 | 81.90 | 80.85 | 83.21 | 94.20 | 61.10 / 89.59 |
| KoELECTRA-Base-v2 | 423M | 89.70 | 87.02 | 83.90 | 80.61 | 84.30 | 94.72 | 84.34 / 92.58 |
| KoELECTRA-Base-v3 | 423M | 90.63 | **88.11** | **84.45** | **82.24** | **85.53** | 95.25 | **84.83 / 93.45** |
| DistilKoBERT | 108M | 88.41 | 84.13 | 62.55 | 70.55 | 73.21 | 92.48 | 54.12 / 77.80 |
\*HanBERT의 Size는 Bert Model과 Tokenizer DB를 합친 것입니다.
\***config의 세팅을 그대로 하여 돌린 결과이며, hyperparameter tuning을 추가적으로 할 시 더 좋은 성능이 나올 수 있습니다.**
## How to use
### Requirements
- `pytorch ~= 1.8.0`
- `transformers ~= 4.11.3`
- `emoji ~= 0.6.0`
- `soynlp ~= 0.0.493`
### Default usage
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("beomi/KcELECTRA-base")
model = AutoModel.from_pretrained("beomi/KcELECTRA-base")
```
> 💡 이전 KcBERT 관련 코드들에서 `AutoTokenizer`, `AutoModel` 을 사용한 경우 `.from_pretrained("beomi/kcbert-base")` 부분을 `.from_pretrained("beomi/KcELECTRA-base")` 로만 변경해주시면 즉시 사용이 가능합니다.
### Pretrain & Finetune Colab 링크 모음
#### Pretrain Data
- KcBERT학습에 사용한 데이터 + 이후 2021.03월 초까지 수집한 댓글
- 약 17GB
- 댓글-대댓글을 묶은 기반으로 Document 구성
#### Pretrain Code
- https://github.com/KLUE-benchmark/KLUE-ELECTRA Repo를 통한 Pretrain
#### Finetune Code
- https://github.com/Beomi/KcBERT-finetune Repo를 통한 Finetune 및 스코어 비교
#### Finetune Samples
- NSMC with PyTorch-Lightning 1.3.0, GPU, Colab <a href="https://colab.research.google.com/drive/1Hh63kIBAiBw3Hho--BvfdUWLu-ysMFF0?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
## Train Data & Preprocessing
### Raw Data
학습 데이터는 2019.01.01 ~ 2021.03.09 사이에 작성된 **댓글 많은 뉴스/혹은 전체 뉴스** 기사들의 **댓글과 대댓글**을 모두 수집한 데이터입니다.
데이터 사이즈는 텍스트만 추출시 **약 17.3GB이며, 1억8천만개 이상의 문장**으로 이뤄져 있습니다.
> KcBERT는 2019.01-2020.06의 텍스트로, 정제 후 약 9천만개 문장으로 학습을 진행했습니다.
### Preprocessing
PLM 학습을 위해서 전처리를 진행한 과정은 다음과 같습니다.
1. 한글 및 영어, 특수문자, 그리고 이모지(🥳)까지!
정규표현식을 통해 한글, 영어, 특수문자를 포함해 Emoji까지 학습 대상에 포함했습니다.
한편, 한글 범위를 `ㄱ-ㅎ가-힣` 으로 지정해 `ㄱ-힣` 내의 한자를 제외했습니다.
2. 댓글 내 중복 문자열 축약
`ㅋㅋㅋㅋㅋ`와 같이 중복된 글자를 `ㅋㅋ`와 같은 것으로 합쳤습니다.
3. Cased Model
KcBERT는 영문에 대해서는 대소문자를 유지하는 Cased model입니다.
4. 글자 단위 10글자 이하 제거
10글자 미만의 텍스트는 단일 단어로 이뤄진 경우가 많아 해당 부분을 제외했습니다.
5. 중복 제거
중복적으로 쓰인 댓글을 제거하기 위해 완전히 일치하는 중복 댓글을 하나로 합쳤습니다.
6. `OOO` 제거
네이버 댓글의 경우, 비속어는 자체 필터링을 통해 `OOO` 로 표시합니다. 이 부분을 공백으로 제거하였습니다.
아래 명령어로 pip로 설치한 뒤, 아래 clean함수로 클리닝을 하면 Downstream task에서 보다 성능이 좋아집니다. (`[UNK]` 감소)
```bash
pip install soynlp emoji
```
아래 `clean` 함수를 Text data에 사용해주세요.
```python
import re
import emoji
from soynlp.normalizer import repeat_normalize
emojis = ''.join(emoji.UNICODE_EMOJI.keys())
pattern = re.compile(f'[^ .,?!/@$%~％·∼()\x00-\x7Fㄱ-ㅣ가-힣{emojis}]+')
url_pattern = re.compile(
r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*)')
import re
import emoji
from soynlp.normalizer import repeat_normalize
pattern = re.compile(f'[^ .,?!/@$%~％·∼()\x00-\x7Fㄱ-ㅣ가-힣]+')
url_pattern = re.compile(
r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*)')
def clean(x):
x = pattern.sub(' ', x)
x = emoji.replace_emoji(x, replace='') #emoji 삭제
x = url_pattern.sub('', x)
x = x.strip()
x = repeat_normalize(x, num_repeats=2)
return x
```
> 💡 Finetune Score에서는 위 `clean` 함수를 적용하지 않았습니다.
### Cleaned Data
- KcBERT 외 추가 데이터는 정리 후 공개 예정입니다.
## Tokenizer, Model Train
Tokenizer는 Huggingface의 [Tokenizers](https://github.com/huggingface/tokenizers) 라이브러리를 통해 학습을 진행했습니다.
그 중 `BertWordPieceTokenizer` 를 이용해 학습을 진행했고, Vocab Size는 `30000`으로 진행했습니다.
Tokenizer를 학습하는 것에는 전체 데이터를 통해 학습을 진행했고, 모델의 General Downstream task에 대응하기 위해 KoELECTRA에서 사용한 Vocab을 겹치지 않는 부분을 추가로 넣어주었습니다. (실제로 두 모델이 겹치는 부분은 약 5000토큰이었습니다.)
TPU `v3-8` 을 이용해 약 10일 학습을 진행했고, 현재 Huggingface에 공개된 모델은 848k step을 학습한 모델 weight가 업로드 되어있습니다.
(100k step별 Checkpoint를 통해 성능 평가를 진행하였습니다. 해당 부분은 `KcBERT-finetune` repo를 참고해주세요.)
모델 학습 Loss는 Step에 따라 초기 100-200k 사이에 급격히 Loss가 줄어들다 학습 종료까지도 지속적으로 loss가 감소하는 것을 볼 수 있습니다.
### KcELECTRA Pretrain Step별 Downstream task 성능 비교
> 💡 아래 표는 전체 ckpt가 아닌 일부에 대해서만 테스트를 진행한 결과입니다.
- 위와 같이 KcBERT-base, KcBERT-large 대비 **모든 데이터셋에 대해** KcELECTRA-base가 더 높은 성능을 보입니다.
- KcELECTRA pretrain에서도 Train step이 늘어감에 따라 점진적으로 성능이 향상되는 것을 볼 수 있습니다.
## 인용표기/Citation
KcELECTRA를 인용하실 때는 아래 양식을 통해 인용해주세요.
```
@misc{lee2021kcelectra,
author = {Junbum Lee},
title = {KcELECTRA: Korean comments ELECTRA},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/Beomi/KcELECTRA}}
}
```
논문을 통한 사용 외에는 MIT 라이센스를 표기해주세요. ☺️
## Acknowledgement
KcELECTRA Model을 학습하는 GCP/TPU 환경은 [TFRC](https://www.tensorflow.org/tfrc?hl=ko) 프로그램의 지원을 받았습니다.
모델 학습 과정에서 많은 조언을 주신 [Monologg](https://github.com/monologg/) 님 감사합니다 :)
## Reference
### Github Repos
- [KcBERT by Beomi](https://github.com/Beomi/KcBERT)
- [BERT by Google](https://github.com/google-research/bert)
- [KoBERT by SKT](https://github.com/SKTBrain/KoBERT)
- [KoELECTRA by Monologg](https://github.com/monologg/KoELECTRA/)
- [Transformers by Huggingface](https://github.com/huggingface/transformers)
- [Tokenizers by Hugginface](https://github.com/huggingface/tokenizers)
- [ELECTRA train code by KLUE](https://github.com/KLUE-benchmark/KLUE-ELECTRA)
### Blogs
- [Monologg님의 KoELECTRA 학습기](https://monologg.kr/categories/NLP/ELECTRA/)
- [Colab에서 TPU로 BERT 처음부터 학습시키기 - Tensorflow/Google ver.](https://beomi.github.io/2020/02/26/Train-BERT-from-scratch-on-colab-TPU-Tensorflow-ver/)
| 9,512 | [
[
-0.044647216796875,
-0.0419921875,
0.0224609375,
0.030426025390625,
-0.0299835205078125,
0.001804351806640625,
-0.00356292724609375,
-0.010406494140625,
0.042510986328125,
0.0233612060546875,
-0.037353515625,
-0.044219970703125,
-0.044647216796875,
0.0162506103515625,
0.0032958984375,
0.051239013671875,
-0.0189666748046875,
0.01021575927734375,
0.00756072998046875,
-0.004154205322265625,
-0.051483154296875,
-0.033416748046875,
-0.04168701171875,
-0.026031494140625,
0.0017976760864257812,
0.03448486328125,
0.037689208984375,
0.028411865234375,
0.0322265625,
0.031005859375,
-0.00969696044921875,
-0.007781982421875,
-0.0104217529296875,
-0.004947662353515625,
0.0203704833984375,
-0.037567138671875,
-0.01922607421875,
-0.0153961181640625,
0.0270233154296875,
0.0394287109375,
0.003910064697265625,
0.00800323486328125,
0.004444122314453125,
0.06396484375,
-0.03680419921875,
0.00885772705078125,
-0.007694244384765625,
0.01502227783203125,
0.002429962158203125,
-0.009735107421875,
-0.0022373199462890625,
-0.042755126953125,
-0.0034694671630859375,
-0.048095703125,
0.0067291259765625,
0.0027141571044921875,
0.0963134765625,
0.004322052001953125,
-0.0193328857421875,
-0.020904541015625,
-0.037384033203125,
0.06585693359375,
-0.05682373046875,
0.0298919677734375,
0.0278778076171875,
0.01194000244140625,
-0.01702880859375,
-0.05706787109375,
-0.05059814453125,
-0.01244354248046875,
-0.0238037109375,
0.0321044921875,
-0.00777435302734375,
-0.0173187255859375,
0.0235595703125,
0.0247802734375,
-0.0279388427734375,
-0.005794525146484375,
-0.01788330078125,
-0.0228271484375,
0.048065185546875,
-0.0007386207580566406,
0.03619384765625,
-0.037689208984375,
-0.0384521484375,
-0.013702392578125,
-0.0289764404296875,
0.024078369140625,
0.02667236328125,
0.0006442070007324219,
-0.029876708984375,
0.046875,
-0.0249176025390625,
0.031524658203125,
0.0225677490234375,
-0.007328033447265625,
0.05975341796875,
-0.043182373046875,
-0.035675048828125,
0.01317596435546875,
0.07525634765625,
0.0362548828125,
0.0173187255859375,
0.0016727447509765625,
0.0024566650390625,
-0.00855255126953125,
-0.0012416839599609375,
-0.06622314453125,
-0.03302001953125,
0.033355712890625,
-0.047210693359375,
-0.027191162109375,
0.004833221435546875,
-0.07977294921875,
0.01000213623046875,
-0.0221099853515625,
0.04541015625,
-0.045806884765625,
-0.030120849609375,
0.001628875732421875,
-0.0137176513671875,
0.007568359375,
0.0254974365234375,
-0.050445556640625,
0.0184783935546875,
0.00847625732421875,
0.05767822265625,
0.0171661376953125,
-0.00368499755859375,
0.00789642333984375,
0.003421783447265625,
-0.0196990966796875,
0.04400634765625,
0.0008668899536132812,
-0.0345458984375,
-0.0089111328125,
0.0233001708984375,
-0.0248870849609375,
-0.0237274169921875,
0.043365478515625,
-0.0189361572265625,
0.0029201507568359375,
-0.0308837890625,
-0.0306396484375,
-0.0121917724609375,
0.0139923095703125,
-0.0438232421875,
0.08331298828125,
0.009063720703125,
-0.0638427734375,
0.02105712890625,
-0.045501708984375,
-0.0302276611328125,
-0.00862884521484375,
-0.0014066696166992188,
-0.045318603515625,
-0.015106201171875,
0.02886962890625,
0.037628173828125,
-0.00673675537109375,
-0.0207061767578125,
0.0015401840209960938,
-0.0215606689453125,
0.0196533203125,
-0.006839752197265625,
0.08514404296875,
0.034027099609375,
-0.037261962890625,
0.0038318634033203125,
-0.07708740234375,
0.0252685546875,
0.029144287109375,
-0.035369873046875,
-0.01045989990234375,
-0.031005859375,
0.005443572998046875,
0.029998779296875,
0.0240478515625,
-0.04833984375,
-0.0005965232849121094,
-0.035614013671875,
0.042022705078125,
0.07403564453125,
0.00882720947265625,
0.0261688232421875,
-0.030853271484375,
0.04107666015625,
0.01214599609375,
0.00724029541015625,
-0.006134033203125,
-0.026519775390625,
-0.07037353515625,
-0.02593994140625,
0.029632568359375,
0.047119140625,
-0.0467529296875,
0.06439208984375,
-0.00788116455078125,
-0.0518798828125,
-0.044219970703125,
-0.003078460693359375,
0.022186279296875,
0.03326416015625,
0.037017822265625,
-0.002960205078125,
-0.054290771484375,
-0.054779052734375,
-0.01371002197265625,
-0.006198883056640625,
-0.0000972747802734375,
0.039642333984375,
0.059326171875,
-0.0143280029296875,
0.06329345703125,
-0.05010986328125,
-0.0220184326171875,
-0.025054931640625,
-0.00286102294921875,
0.043609619140625,
0.0594482421875,
0.054962158203125,
-0.06744384765625,
-0.0709228515625,
0.00325775146484375,
-0.056549072265625,
-0.0036144256591796875,
-0.0070037841796875,
-0.0171661376953125,
0.01483154296875,
0.037872314453125,
-0.058197021484375,
0.040985107421875,
0.021881103515625,
-0.0411376953125,
0.06427001953125,
-0.0225372314453125,
0.029754638671875,
-0.09124755859375,
0.0262603759765625,
-0.007198333740234375,
-0.004764556884765625,
-0.042144775390625,
-0.00797271728515625,
0.0027866363525390625,
0.004184722900390625,
-0.04412841796875,
0.037811279296875,
-0.045501708984375,
0.0245513916015625,
0.004344940185546875,
0.00007212162017822266,
-0.0010118484497070312,
0.049346923828125,
-0.0156707763671875,
0.044647216796875,
0.035919189453125,
-0.05255126953125,
0.02593994140625,
0.0211639404296875,
-0.036773681640625,
0.0230865478515625,
-0.057037353515625,
-0.0031070709228515625,
-0.0080108642578125,
0.01357269287109375,
-0.09600830078125,
-0.0200347900390625,
0.046112060546875,
-0.050262451171875,
0.0281219482421875,
-0.005123138427734375,
-0.025604248046875,
-0.048095703125,
-0.037689208984375,
0.0132598876953125,
0.039154052734375,
-0.03179931640625,
0.0418701171875,
0.0123748779296875,
-0.00853729248046875,
-0.044281005859375,
-0.052459716796875,
-0.0162506103515625,
-0.01007843017578125,
-0.047088623046875,
0.052490234375,
-0.014434814453125,
-0.00241851806640625,
-0.00923919677734375,
-0.0130462646484375,
-0.01190185546875,
-0.003833770751953125,
0.023529052734375,
0.0221099853515625,
-0.00344085693359375,
-0.0085906982421875,
0.0025539398193359375,
-0.0114898681640625,
0.00566864013671875,
0.00820159912109375,
0.07037353515625,
-0.0080718994140625,
-0.0170440673828125,
-0.0625,
0.0145111083984375,
0.049591064453125,
0.0010194778442382812,
0.0611572265625,
0.053985595703125,
-0.00997161865234375,
0.018402099609375,
-0.039154052734375,
-0.0005984306335449219,
-0.040496826171875,
0.0208282470703125,
-0.0335693359375,
-0.043487548828125,
0.050079345703125,
-0.0154266357421875,
-0.0203094482421875,
0.06243896484375,
0.042510986328125,
-0.0178985595703125,
0.08563232421875,
0.03399658203125,
-0.01108551025390625,
0.034271240234375,
-0.051849365234375,
0.0232391357421875,
-0.061553955078125,
-0.047576904296875,
-0.044342041015625,
-0.022003173828125,
-0.0509033203125,
-0.01165008544921875,
0.021484375,
0.0219268798828125,
-0.0274810791015625,
0.034454345703125,
-0.06072998046875,
0.0017614364624023438,
0.030853271484375,
0.0276031494140625,
-0.00653839111328125,
-0.003459930419921875,
-0.033233642578125,
0.0029754638671875,
-0.04937744140625,
-0.0222320556640625,
0.0802001953125,
0.024200439453125,
0.044281005859375,
-0.0013408660888671875,
0.050628662109375,
0.01074981689453125,
-0.004222869873046875,
-0.05157470703125,
0.04327392578125,
0.01357269287109375,
-0.039093017578125,
-0.027801513671875,
-0.0223388671875,
-0.07379150390625,
0.0283050537109375,
-0.0167694091796875,
-0.068603515625,
0.02789306640625,
0.006793975830078125,
-0.02569580078125,
0.0247955322265625,
-0.060333251953125,
0.072265625,
-0.0195159912109375,
-0.02691650390625,
-0.0007472038269042969,
-0.055267333984375,
0.00756072998046875,
0.00734710693359375,
0.0186004638671875,
-0.011474609375,
0.01096343994140625,
0.06829833984375,
-0.07916259765625,
0.038299560546875,
-0.0203094482421875,
0.008941650390625,
0.041168212890625,
-0.0233001708984375,
0.0516357421875,
0.0042266845703125,
-0.0033779144287109375,
0.01424407958984375,
-0.0008649826049804688,
-0.0295562744140625,
-0.01422882080078125,
0.06463623046875,
-0.07220458984375,
-0.032562255859375,
-0.041900634765625,
-0.0128021240234375,
0.01824951171875,
0.030303955078125,
0.050689697265625,
0.00782012939453125,
0.00290679931640625,
0.0186767578125,
0.029083251953125,
-0.0280609130859375,
0.053680419921875,
0.01245880126953125,
-0.001766204833984375,
-0.040557861328125,
0.058929443359375,
0.0228118896484375,
0.00846099853515625,
0.0234527587890625,
0.0167083740234375,
-0.0308380126953125,
-0.0267791748046875,
-0.0311279296875,
0.0160369873046875,
-0.0447998046875,
-0.0181884765625,
-0.05999755859375,
-0.0080718994140625,
-0.054595947265625,
-0.024749755859375,
-0.0247344970703125,
-0.04010009765625,
-0.021087646484375,
-0.01062774658203125,
0.041656494140625,
0.0208282470703125,
-0.00994110107421875,
0.02838134765625,
-0.042083740234375,
0.0219879150390625,
0.007793426513671875,
0.01296234130859375,
0.011627197265625,
-0.0280914306640625,
-0.0165557861328125,
0.005939483642578125,
-0.031829833984375,
-0.0775146484375,
0.04638671875,
-0.025787353515625,
0.038909912109375,
0.02606201171875,
-0.0037326812744140625,
0.056427001953125,
-0.02850341796875,
0.06463623046875,
0.043609619140625,
-0.0723876953125,
0.05755615234375,
-0.01922607421875,
0.0207977294921875,
0.04290771484375,
0.045013427734375,
-0.037628173828125,
-0.005130767822265625,
-0.0478515625,
-0.07904052734375,
0.06256103515625,
0.038330078125,
-0.006465911865234375,
0.00861358642578125,
0.01074981689453125,
-0.0193023681640625,
0.0208892822265625,
-0.055206298828125,
-0.05950927734375,
-0.039093017578125,
-0.01274871826171875,
0.01369476318359375,
-0.00341033935546875,
0.005496978759765625,
-0.05035400390625,
0.063720703125,
0.0222320556640625,
0.051605224609375,
0.039825439453125,
-0.00997161865234375,
-0.0037174224853515625,
0.0190887451171875,
0.032012939453125,
0.045745849609375,
-0.026031494140625,
-0.015625,
0.03045654296875,
-0.059478759765625,
0.0251617431640625,
-0.0014171600341796875,
-0.02972412109375,
0.0175018310546875,
0.00811004638671875,
0.053375244140625,
0.006000518798828125,
-0.03143310546875,
0.037994384765625,
0.00040435791015625,
-0.0213623046875,
-0.045013427734375,
-0.0018100738525390625,
0.0030994415283203125,
-0.0010461807250976562,
0.026031494140625,
0.01262664794921875,
-0.00885772705078125,
-0.039276123046875,
0.005130767822265625,
0.0186004638671875,
-0.032196044921875,
-0.007381439208984375,
0.047821044921875,
0.0035419464111328125,
-0.01824951171875,
0.034759521484375,
-0.004344940185546875,
-0.06103515625,
0.08123779296875,
0.04656982421875,
0.0570068359375,
-0.0389404296875,
0.01165008544921875,
0.06597900390625,
0.0151214599609375,
0.00542449951171875,
0.04217529296875,
0.01013946533203125,
-0.04412841796875,
-0.007457733154296875,
-0.05517578125,
0.006443023681640625,
0.034088134765625,
-0.039337158203125,
0.0244140625,
-0.048065185546875,
-0.0248260498046875,
0.00920867919921875,
0.01091766357421875,
-0.0574951171875,
0.039154052734375,
-0.017547607421875,
0.05810546875,
-0.0653076171875,
0.049102783203125,
0.05633544921875,
-0.046356201171875,
-0.06829833984375,
-0.0004992485046386719,
-0.0182647705078125,
-0.055511474609375,
0.0545654296875,
0.01398468017578125,
0.011260986328125,
0.005809783935546875,
-0.0312042236328125,
-0.08013916015625,
0.0977783203125,
-0.004695892333984375,
-0.033905029296875,
0.0251312255859375,
0.0171661376953125,
0.032440185546875,
-0.006038665771484375,
0.03271484375,
0.033905029296875,
0.051055908203125,
0.0024929046630859375,
-0.05999755859375,
0.035888671875,
-0.0304718017578125,
-0.01030731201171875,
0.022735595703125,
-0.08306884765625,
0.08160400390625,
-0.01239776611328125,
0.0027904510498046875,
0.005985260009765625,
0.040679931640625,
0.0182037353515625,
0.01483917236328125,
0.041229248046875,
0.046295166015625,
0.040252685546875,
-0.01483154296875,
0.0701904296875,
-0.0258636474609375,
0.039581298828125,
0.036712646484375,
0.0152130126953125,
0.03399658203125,
0.036590576171875,
-0.04840087890625,
0.045654296875,
0.045013427734375,
-0.0316162109375,
0.05084228515625,
0.0064544677734375,
-0.02813720703125,
-0.007358551025390625,
0.004436492919921875,
-0.04547119140625,
0.022430419921875,
0.0144500732421875,
-0.039337158203125,
0.00867462158203125,
0.00868988037109375,
0.020172119140625,
-0.01412200927734375,
-0.037445068359375,
0.031768798828125,
0.005626678466796875,
-0.050201416015625,
0.0509033203125,
0.00617218017578125,
0.048004150390625,
-0.039794921875,
0.003734588623046875,
0.00614166259765625,
0.0161590576171875,
-0.0303802490234375,
-0.0511474609375,
-0.003765106201171875,
-0.00948333740234375,
-0.0174102783203125,
-0.0013818740844726562,
0.06256103515625,
-0.004222869873046875,
-0.0533447265625,
0.0282440185546875,
0.01236724853515625,
0.0187835693359375,
0.00843048095703125,
-0.06768798828125,
0.0031871795654296875,
0.021270751953125,
-0.03045654296875,
0.02667236328125,
0.0172576904296875,
0.01541900634765625,
0.04473876953125,
0.058837890625,
0.003955841064453125,
0.0194549560546875,
-0.001697540283203125,
0.07598876953125,
-0.052947998046875,
-0.046142578125,
-0.0701904296875,
0.04986572265625,
-0.018341064453125,
-0.031402587890625,
0.07073974609375,
0.05413818359375,
0.06121826171875,
-0.0210723876953125,
0.0787353515625,
-0.03515625,
0.02923583984375,
-0.039825439453125,
0.0689697265625,
-0.0426025390625,
-0.00705718994140625,
-0.036376953125,
-0.046600341796875,
-0.0008473396301269531,
0.06494140625,
-0.0184478759765625,
0.0244903564453125,
0.052520751953125,
0.04913330078125,
0.00524139404296875,
-0.00218963623046875,
0.0007576942443847656,
0.038116455078125,
0.0094451904296875,
0.0430908203125,
0.03436279296875,
-0.06561279296875,
0.048828125,
-0.055023193359375,
-0.00029158592224121094,
-0.037689208984375,
-0.040557861328125,
-0.0667724609375,
-0.018341064453125,
-0.033843994140625,
-0.02880859375,
-0.014190673828125,
0.06719970703125,
0.037506103515625,
-0.07281494140625,
-0.015380859375,
-0.0246124267578125,
0.016448974609375,
-0.031646728515625,
-0.0230865478515625,
0.06280517578125,
-0.014373779296875,
-0.0638427734375,
0.00940704345703125,
-0.01064300537109375,
0.021087646484375,
0.01329803466796875,
-0.01094818115234375,
-0.040191650390625,
-0.005054473876953125,
0.043121337890625,
0.0209197998046875,
-0.039825439453125,
-0.0172576904296875,
-0.005657196044921875,
-0.0071258544921875,
0.0195465087890625,
0.0276336669921875,
-0.043243408203125,
0.021575927734375,
0.056243896484375,
0.0012531280517578125,
0.05303955078125,
0.0015811920166015625,
0.0190582275390625,
-0.033782958984375,
0.01666259765625,
0.0032196044921875,
0.035614013671875,
-0.003871917724609375,
-0.034027099609375,
0.04388427734375,
0.03472900390625,
-0.049591064453125,
-0.0552978515625,
-0.01439666748046875,
-0.08526611328125,
-0.037109375,
0.07464599609375,
-0.01433563232421875,
-0.02838134765625,
-0.0130767822265625,
-0.032928466796875,
0.042572021484375,
-0.032806396484375,
0.04547119140625,
0.048309326171875,
-0.0170135498046875,
0.00788116455078125,
-0.0518798828125,
0.040496826171875,
0.04351806640625,
-0.053802490234375,
-0.032928466796875,
0.007404327392578125,
0.036712646484375,
0.0302276611328125,
0.06097412109375,
-0.0011653900146484375,
0.0182952880859375,
0.0005002021789550781,
0.0166015625,
-0.0005426406860351562,
0.0030689239501953125,
-0.006626129150390625,
0.0088958740234375,
-0.03363037109375,
-0.05023193359375
]
] |
ku-nlp/deberta-v2-base-japanese | 2023-05-12T14:13:03.000Z | [
"transformers",
"pytorch",
"safetensors",
"deberta-v2",
"fill-mask",
"deberta",
"ja",
"dataset:wikipedia",
"dataset:cc100",
"dataset:oscar",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | ku-nlp | null | null | ku-nlp/deberta-v2-base-japanese | 23 | 42,800 | transformers | 2023-01-05T08:04:14 | ---
language: ja
license: cc-by-sa-4.0
library_name: transformers
tags:
- deberta
- deberta-v2
- fill-mask
datasets:
- wikipedia
- cc100
- oscar
metrics:
- accuracy
mask_token: "[MASK]"
widget:
- text: "京都 大学 で 自然 言語 処理 を [MASK] する 。"
---
# Model Card for Japanese DeBERTa V2 base
## Model description
This is a Japanese DeBERTa V2 base model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.
## How to use
You can use this model for masked language modeling as follows:
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained('ku-nlp/deberta-v2-base-japanese')
model = AutoModelForMaskedLM.from_pretrained('ku-nlp/deberta-v2-base-japanese')
sentence = '京都 大学 で 自然 言語 処理 を [MASK] する 。' # input should be segmented into words by Juman++ in advance
encoding = tokenizer(sentence, return_tensors='pt')
...
```
You can also fine-tune this model on downstream tasks.
## Tokenization
The input text should be segmented into words by [Juman++](https://github.com/ku-nlp/jumanpp) in advance. [Juman++ 2.0.0-rc3](https://github.com/ku-nlp/jumanpp/releases/tag/v2.0.0-rc3) was used for pre-training. Each word is tokenized into subwords by [sentencepiece](https://github.com/google/sentencepiece).
## Training data
We used the following corpora for pre-training:
- Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents)
- Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)
- Japanese portion of OSCAR (54GB, 326M sentences, 25M documents)
Note that we filtered out documents annotated with "header", "footer", or "noisy" tags in OSCAR.
Also note that Japanese Wikipedia was duplicated 10 times to make the total size of the corpus comparable to that of CC-100 and OSCAR. As a result, the total size of the training data is 171GB.
## Training procedure
We first segmented texts in the corpora into words using [Juman++](https://github.com/ku-nlp/jumanpp).
Then, we built a sentencepiece model with 32000 tokens including words ([JumanDIC](https://github.com/ku-nlp/JumanDIC)) and subwords induced by the unigram language model of [sentencepiece](https://github.com/google/sentencepiece).
We tokenized the segmented corpora into subwords using the sentencepiece model and trained the Japanese DeBERTa model using [transformers](https://github.com/huggingface/transformers) library.
The training took three weeks using 8 NVIDIA A100-SXM4-40GB GPUs.
The following hyperparameters were used during pre-training:
- learning_rate: 2e-4
- per_device_train_batch_size: 44
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 6
- total_train_batch_size: 2,112
- max_seq_length: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear schedule with warmup
- training_steps: 500,000
- warmup_steps: 10,000
The accuracy of the trained model on the masked language modeling task was 0.779.
The evaluation set consists of 5,000 randomly sampled documents from each of the training corpora.
## Fine-tuning on NLU tasks
We fine-tuned the following models and evaluated them on the dev set of JGLUE.
We tuned learning rate and training epochs for each model and task following [the JGLUE paper](https://www.jstage.jst.go.jp/article/jnlp/30/1/30_63/_pdf/-char/ja).
| Model | MARC-ja/acc | JSTS/pearson | JSTS/spearman | JNLI/acc | JSQuAD/EM | JSQuAD/F1 | JComQA/acc |
|-------------------------------|-------------|--------------|---------------|----------|-----------|-----------|------------|
| Waseda RoBERTa base | 0.965 | 0.913 | 0.876 | 0.905 | 0.853 | 0.916 | 0.853 |
| Waseda RoBERTa large (seq512) | 0.969 | 0.925 | 0.890 | 0.928 | 0.910 | 0.955 | 0.900 |
| LUKE Japanese base* | 0.965 | 0.916 | 0.877 | 0.912 | - | - | 0.842 |
| LUKE Japanese large* | 0.965 | 0.932 | 0.902 | 0.927 | - | - | 0.893 |
| DeBERTaV2 base | 0.970 | 0.922 | 0.886 | 0.922 | 0.899 | 0.951 | 0.873 |
| DeBERTaV2 large | 0.968 | 0.925 | 0.892 | 0.924 | 0.912 | 0.959 | 0.890 |
*The scores of LUKE are from [the official repository](https://github.com/studio-ousia/luke).
## Acknowledgments
This work was supported by Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures (JHPCN) through General Collaboration Project no. jh221004, "Developing a Platform for Constructing and Sharing of Large-Scale Japanese Language Models".
For training models, we used the mdx: a platform for the data-driven future.
| 4,860 | [
[
-0.039794921875,
-0.06842041015625,
0.02410888671875,
-0.007476806640625,
-0.0261688232421875,
0.0027618408203125,
-0.0249176025390625,
-0.0311431884765625,
0.0277557373046875,
0.03668212890625,
-0.04425048828125,
-0.053741455078125,
-0.053131103515625,
-0.00013935565948486328,
-0.00782012939453125,
0.06866455078125,
-0.00284576416015625,
0.004886627197265625,
0.00824737548828125,
-0.0032405853271484375,
-0.043365478515625,
-0.0303497314453125,
-0.05047607421875,
-0.0232086181640625,
0.0213623046875,
0.0266265869140625,
0.055633544921875,
0.0462646484375,
0.021759033203125,
0.0204925537109375,
-0.00891876220703125,
0.007171630859375,
-0.027618408203125,
-0.01041412353515625,
0.00537109375,
-0.045867919921875,
-0.029998779296875,
0.0057373046875,
0.04803466796875,
0.056060791015625,
-0.001983642578125,
0.0171661376953125,
0.0015583038330078125,
0.05010986328125,
-0.0440673828125,
0.022064208984375,
-0.042999267578125,
0.0156707763671875,
-0.02294921875,
-0.0015010833740234375,
-0.0254364013671875,
0.0006337165832519531,
-0.0013208389282226562,
-0.06622314453125,
0.006427764892578125,
-0.007045745849609375,
0.08795166015625,
0.0155181884765625,
-0.0120697021484375,
-0.01171112060546875,
-0.0380859375,
0.05413818359375,
-0.05743408203125,
0.0245513916015625,
0.046356201171875,
0.0023593902587890625,
-0.00858306884765625,
-0.043121337890625,
-0.052398681640625,
-0.0194244384765625,
-0.0238189697265625,
0.02813720703125,
-0.018157958984375,
-0.00839996337890625,
0.042327880859375,
0.0197601318359375,
-0.06756591796875,
0.020751953125,
-0.036163330078125,
-0.001922607421875,
0.0517578125,
0.0111236572265625,
0.0245819091796875,
-0.0282745361328125,
-0.0230560302734375,
-0.0263214111328125,
-0.042022705078125,
0.01107025146484375,
0.04144287109375,
0.01467132568359375,
-0.028533935546875,
0.03375244140625,
-0.0261383056640625,
0.04486083984375,
0.00896453857421875,
-0.0245513916015625,
0.04388427734375,
-0.0149383544921875,
-0.0227203369140625,
0.0030689239501953125,
0.08551025390625,
0.015869140625,
0.01006317138671875,
0.006122589111328125,
0.004726409912109375,
0.00865936279296875,
0.016326904296875,
-0.06402587890625,
-0.0195770263671875,
0.00872039794921875,
-0.02581787109375,
-0.021331787109375,
-0.0006213188171386719,
-0.05322265625,
-0.0018815994262695312,
-0.03564453125,
0.03997802734375,
-0.041534423828125,
-0.02587890625,
0.0114593505859375,
0.00037860870361328125,
0.01300048828125,
0.0113372802734375,
-0.07171630859375,
0.021575927734375,
0.03131103515625,
0.054046630859375,
-0.004901885986328125,
-0.0252532958984375,
-0.0174560546875,
-0.008209228515625,
-0.028778076171875,
0.02093505859375,
-0.0282745361328125,
-0.026702880859375,
-0.0147705078125,
0.0211944580078125,
-0.026763916015625,
-0.0279998779296875,
0.0367431640625,
-0.0298309326171875,
0.0364990234375,
-0.0032215118408203125,
-0.046722412109375,
-0.0238800048828125,
0.0221710205078125,
-0.042266845703125,
0.078369140625,
0.0233306884765625,
-0.06414794921875,
0.027374267578125,
-0.04754638671875,
-0.0159149169921875,
0.01568603515625,
-0.01232147216796875,
-0.04107666015625,
-0.00731658935546875,
0.031585693359375,
0.0355224609375,
-0.01140594482421875,
0.03692626953125,
-0.017791748046875,
-0.03521728515625,
0.0133819580078125,
-0.027679443359375,
0.08807373046875,
0.01515960693359375,
-0.05029296875,
-0.00960540771484375,
-0.07489013671875,
-0.0016069412231445312,
0.0308990478515625,
-0.012939453125,
-0.03045654296875,
-0.0273895263671875,
0.0017938613891601562,
0.019866943359375,
0.0146331787109375,
-0.0360107421875,
0.021026611328125,
-0.036163330078125,
0.02099609375,
0.0345458984375,
-0.008941650390625,
0.02264404296875,
-0.00473785400390625,
0.0516357421875,
0.0137481689453125,
0.015838623046875,
-0.0167083740234375,
-0.032318115234375,
-0.0775146484375,
-0.0206451416015625,
0.0360107421875,
0.0379638671875,
-0.0556640625,
0.0621337890625,
-0.0255126953125,
-0.0609130859375,
-0.0552978515625,
-0.00533294677734375,
0.04046630859375,
0.0428466796875,
0.032470703125,
-0.03759765625,
-0.042572021484375,
-0.07977294921875,
0.0166778564453125,
-0.00946807861328125,
0.00858306884765625,
0.009918212890625,
0.055419921875,
-0.0216064453125,
0.053314208984375,
-0.040771484375,
-0.0200653076171875,
-0.0155792236328125,
0.005290985107421875,
0.0291748046875,
0.049285888671875,
0.03936767578125,
-0.04248046875,
-0.042572021484375,
-0.00481414794921875,
-0.06683349609375,
0.00484466552734375,
-0.00449371337890625,
-0.0158538818359375,
0.03021240234375,
0.04083251953125,
-0.0504150390625,
0.0256500244140625,
0.04364013671875,
-0.0257720947265625,
0.0372314453125,
-0.01239776611328125,
0.0034847259521484375,
-0.103759765625,
0.036773681640625,
-0.00289154052734375,
-0.0133819580078125,
-0.04669189453125,
0.01983642578125,
0.0003821849822998047,
-0.01430511474609375,
-0.0305633544921875,
0.037811279296875,
-0.035003662109375,
0.00029730796813964844,
-0.0211639404296875,
0.01824951171875,
0.006008148193359375,
0.06591796875,
0.024688720703125,
0.056732177734375,
0.046234130859375,
-0.034637451171875,
0.004840850830078125,
0.023040771484375,
-0.051849365234375,
0.0253753662109375,
-0.0552978515625,
0.005199432373046875,
-0.00978851318359375,
0.01497650146484375,
-0.061309814453125,
-0.01384735107421875,
0.03509521484375,
-0.03533935546875,
0.039581298828125,
-0.019287109375,
-0.0369873046875,
-0.033660888671875,
-0.01486968994140625,
0.01238250732421875,
0.04833984375,
-0.0288238525390625,
0.0235443115234375,
0.03460693359375,
-0.0106048583984375,
-0.0570068359375,
-0.044647216796875,
-0.00414276123046875,
-0.01983642578125,
-0.032958984375,
0.0391845703125,
-0.007144927978515625,
0.00003808736801147461,
-0.00218963623046875,
0.01202392578125,
0.0081939697265625,
0.0211334228515625,
0.0234222412109375,
0.03485107421875,
-0.00933074951171875,
-0.0037899017333984375,
0.0104217529296875,
-0.01522064208984375,
0.00011396408081054688,
-0.0027904510498046875,
0.071044921875,
-0.003963470458984375,
-0.0091094970703125,
-0.044952392578125,
0.0124053955078125,
0.036956787109375,
-0.0137786865234375,
0.06689453125,
0.0654296875,
-0.020111083984375,
0.0076141357421875,
-0.0302276611328125,
0.001190185546875,
-0.0311431884765625,
0.04315185546875,
-0.038116455078125,
-0.06744384765625,
0.042205810546875,
0.02362060546875,
0.0016613006591796875,
0.0645751953125,
0.0430908203125,
0.005588531494140625,
0.0814208984375,
0.03045654296875,
-0.017608642578125,
0.02978515625,
-0.05401611328125,
-0.003955841064453125,
-0.0780029296875,
-0.0189971923828125,
-0.03460693359375,
-0.01500701904296875,
-0.06353759765625,
-0.0208282470703125,
0.0259552001953125,
0.0243377685546875,
-0.0271148681640625,
0.04461669921875,
-0.035675048828125,
0.03326416015625,
0.050628662109375,
0.006267547607421875,
0.01435089111328125,
0.006641387939453125,
-0.0110626220703125,
-0.00860595703125,
-0.058929443359375,
-0.0318603515625,
0.08526611328125,
0.04071044921875,
0.04315185546875,
-0.006641387939453125,
0.051361083984375,
0.002429962158203125,
0.0009775161743164062,
-0.049591064453125,
0.0352783203125,
-0.012664794921875,
-0.056976318359375,
-0.019256591796875,
-0.03173828125,
-0.07989501953125,
0.03289794921875,
-0.018280029296875,
-0.057769775390625,
0.007305145263671875,
-0.003986358642578125,
-0.01678466796875,
0.01488494873046875,
-0.04046630859375,
0.07598876953125,
-0.00594329833984375,
-0.01666259765625,
-0.01309967041015625,
-0.060028076171875,
0.034210205078125,
-0.005641937255859375,
0.01102447509765625,
-0.007503509521484375,
0.0166778564453125,
0.07440185546875,
-0.0297698974609375,
0.059417724609375,
-0.0181121826171875,
0.0020236968994140625,
0.022125244140625,
-0.00506591796875,
0.031951904296875,
0.0124969482421875,
0.01384735107421875,
0.029022216796875,
0.00434112548828125,
-0.0214996337890625,
-0.0279083251953125,
0.048919677734375,
-0.088134765625,
-0.0391845703125,
-0.04022216796875,
-0.0280303955078125,
-0.006267547607421875,
0.020111083984375,
0.037750244140625,
0.03863525390625,
-0.004619598388671875,
0.027313232421875,
0.046783447265625,
-0.0226898193359375,
0.03045654296875,
0.051239013671875,
-0.0244903564453125,
-0.035919189453125,
0.0562744140625,
0.0168609619140625,
0.018798828125,
0.031280517578125,
0.0120849609375,
-0.0213470458984375,
-0.041168212890625,
-0.05462646484375,
0.0249176025390625,
-0.043243408203125,
-0.007434844970703125,
-0.06512451171875,
-0.0274505615234375,
-0.0305023193359375,
0.004241943359375,
-0.033447265625,
-0.035675048828125,
-0.0227203369140625,
-0.0001983642578125,
0.0113983154296875,
0.0280303955078125,
0.0145263671875,
0.0234375,
-0.05474853515625,
0.00719451904296875,
0.004055023193359375,
0.01080322265625,
-0.005626678466796875,
-0.06793212890625,
-0.031097412109375,
0.0110321044921875,
-0.0215606689453125,
-0.04736328125,
0.04046630859375,
-0.00848388671875,
0.03839111328125,
0.017364501953125,
-0.01227569580078125,
0.058929443359375,
-0.0308380126953125,
0.068603515625,
0.0196685791015625,
-0.06414794921875,
0.05487060546875,
-0.0305633544921875,
0.039520263671875,
0.0626220703125,
0.05364990234375,
-0.042633056640625,
-0.0333251953125,
-0.07379150390625,
-0.058349609375,
0.06964111328125,
0.0181121826171875,
0.006488800048828125,
-0.0005621910095214844,
0.01568603515625,
0.006702423095703125,
0.013214111328125,
-0.073486328125,
-0.03485107421875,
-0.005748748779296875,
-0.018463134765625,
-0.0166778564453125,
-0.009552001953125,
-0.001148223876953125,
-0.0286865234375,
0.08404541015625,
-0.0087890625,
0.0156402587890625,
0.01313018798828125,
-0.0224761962890625,
0.0015239715576171875,
0.0124969482421875,
0.0517578125,
0.04632568359375,
-0.0202484130859375,
-0.0100250244140625,
0.0090484619140625,
-0.04833984375,
0.0010051727294921875,
0.02545166015625,
-0.042572021484375,
0.016632080078125,
0.0323486328125,
0.093505859375,
0.0017375946044921875,
-0.048431396484375,
0.0389404296875,
-0.0022563934326171875,
-0.032958984375,
-0.0455322265625,
0.0169219970703125,
-0.0018138885498046875,
0.005863189697265625,
0.01056671142578125,
-0.01458740234375,
0.006443023681640625,
-0.047210693359375,
-0.00786590576171875,
0.02410888671875,
-0.031646728515625,
-0.0210113525390625,
0.04998779296875,
0.00026798248291015625,
-0.006443023681640625,
0.047821044921875,
-0.0237579345703125,
-0.0389404296875,
0.04376220703125,
0.04486083984375,
0.0604248046875,
-0.01523590087890625,
0.017242431640625,
0.06744384765625,
0.0179443359375,
0.0032253265380859375,
0.004009246826171875,
0.00624847412109375,
-0.04754638671875,
-0.0292205810546875,
-0.0655517578125,
-0.01216888427734375,
0.045440673828125,
-0.051605224609375,
0.0200347900390625,
-0.0244598388671875,
-0.00896453857421875,
0.0057525634765625,
0.0260467529296875,
-0.0504150390625,
0.026763916015625,
0.0240325927734375,
0.054412841796875,
-0.06817626953125,
0.0706787109375,
0.039306640625,
-0.046722412109375,
-0.073486328125,
-0.02276611328125,
-0.01505279541015625,
-0.069580078125,
0.050994873046875,
0.0268096923828125,
0.0173187255859375,
-0.00014781951904296875,
-0.0269012451171875,
-0.08001708984375,
0.092529296875,
0.01074981689453125,
-0.0728759765625,
0.001934051513671875,
0.01776123046875,
0.04644775390625,
-0.0187835693359375,
0.0308990478515625,
0.043792724609375,
0.0214996337890625,
-0.008056640625,
-0.07232666015625,
0.005283355712890625,
-0.032135009765625,
0.00968170166015625,
0.02587890625,
-0.051422119140625,
0.05804443359375,
0.0139007568359375,
-0.006256103515625,
-0.00004988908767700195,
0.033233642578125,
0.0283203125,
0.00228118896484375,
0.043731689453125,
0.07427978515625,
0.049163818359375,
-0.00739288330078125,
0.0689697265625,
-0.0259552001953125,
0.031982421875,
0.0823974609375,
-0.001338958740234375,
0.058013916015625,
0.019195556640625,
-0.0305023193359375,
0.050750732421875,
0.0394287109375,
-0.0161590576171875,
0.034271240234375,
0.0100860595703125,
-0.004726409912109375,
-0.00360107421875,
-0.00395965576171875,
-0.03662109375,
0.05389404296875,
0.0229949951171875,
-0.041778564453125,
0.00974273681640625,
0.01500701904296875,
0.037353515625,
-0.00591278076171875,
-0.0206451416015625,
0.05706787109375,
-0.00405120849609375,
-0.07489013671875,
0.056243896484375,
0.01424407958984375,
0.04937744140625,
-0.05499267578125,
0.01528167724609375,
-0.01666259765625,
0.0122528076171875,
0.0015430450439453125,
-0.050628662109375,
0.01461029052734375,
0.006633758544921875,
-0.00542449951171875,
0.0008225440979003906,
0.0411376953125,
-0.04296875,
-0.04962158203125,
0.0160369873046875,
0.0270538330078125,
0.01488494873046875,
0.006076812744140625,
-0.0660400390625,
0.006954193115234375,
0.00812530517578125,
-0.041656494140625,
0.0335693359375,
0.006778717041015625,
0.00594329833984375,
0.0271148681640625,
0.0457763671875,
-0.007656097412109375,
-0.007171630859375,
0.0202789306640625,
0.05755615234375,
-0.03741455078125,
-0.0345458984375,
-0.067138671875,
0.041595458984375,
-0.01739501953125,
-0.039825439453125,
0.058349609375,
0.056427001953125,
0.0843505859375,
-0.011962890625,
0.049896240234375,
-0.020111083984375,
0.032867431640625,
-0.060638427734375,
0.049835205078125,
-0.047454833984375,
-0.004932403564453125,
-0.02801513671875,
-0.07281494140625,
-0.014007568359375,
0.0521240234375,
-0.0164337158203125,
0.006786346435546875,
0.04840087890625,
0.06256103515625,
-0.00023555755615234375,
-0.01062774658203125,
0.0172271728515625,
0.01049041748046875,
0.01898193359375,
0.053375244140625,
0.0428466796875,
-0.060638427734375,
0.0276947021484375,
-0.046478271484375,
-0.00553131103515625,
-0.009063720703125,
-0.040740966796875,
-0.0711669921875,
-0.051025390625,
-0.041534423828125,
-0.024139404296875,
-0.00461578369140625,
0.07269287109375,
0.054229736328125,
-0.0477294921875,
-0.0173492431640625,
-0.015838623046875,
-0.0243682861328125,
-0.00875091552734375,
-0.0192413330078125,
0.044921875,
-0.0231475830078125,
-0.07366943359375,
0.02410888671875,
0.002590179443359375,
0.00634765625,
-0.0214996337890625,
-0.00855255126953125,
-0.026123046875,
-0.019256591796875,
0.038299560546875,
0.00388336181640625,
-0.047393798828125,
-0.00905609130859375,
-0.002178192138671875,
-0.0177001953125,
0.00495147705078125,
0.0226898193359375,
-0.05322265625,
0.038482666015625,
0.0260162353515625,
0.0305938720703125,
0.06829833984375,
-0.01166534423828125,
0.01557159423828125,
-0.0528564453125,
0.026611328125,
0.004901885986328125,
0.03741455078125,
0.022674560546875,
-0.01468658447265625,
0.05706787109375,
0.0303497314453125,
-0.03887939453125,
-0.050537109375,
0.0021495819091796875,
-0.0875244140625,
-0.026947021484375,
0.0806884765625,
-0.016876220703125,
-0.0237579345703125,
0.01025390625,
-0.0169677734375,
0.02789306640625,
-0.006359100341796875,
0.046417236328125,
0.053802490234375,
0.0209197998046875,
-0.01229095458984375,
-0.045379638671875,
0.028564453125,
0.03131103515625,
-0.0634765625,
-0.0095977783203125,
0.0294952392578125,
0.0263214111328125,
0.031768798828125,
0.058349609375,
-0.01262664794921875,
0.01224517822265625,
0.006988525390625,
0.01190185546875,
-0.0137939453125,
-0.023101806640625,
-0.0236053466796875,
0.0008177757263183594,
-0.0019931793212890625,
-0.01497650146484375
]
] |
stablediffusionapi/juggernaut-xl-v5 | 2023-09-26T15:40:42.000Z | [
"diffusers",
"stablediffusionapi.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | stablediffusionapi | null | null | stablediffusionapi/juggernaut-xl-v5 | 6 | 42,590 | diffusers | 2023-09-26T15:38:29 | ---
license: creativeml-openrail-m
tags:
- stablediffusionapi.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# Juggernaut XL V5 API Inference
## Get API Key
Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed.
Replace Key in below code, change **model_id** to "juggernaut-xl-v5"
Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs)
Try model for free: [Generate Images](https://stablediffusionapi.com/models/juggernaut-xl-v5)
Model link: [View model](https://stablediffusionapi.com/models/juggernaut-xl-v5)
Credits: [View credits](https://civitai.com/?query=Juggernaut%20XL%20V5)
View all models: [View Models](https://stablediffusionapi.com/models)
import requests
import json
url = "https://stablediffusionapi.com/api/v4/dreambooth"
payload = json.dumps({
"key": "your_api_key",
"model_id": "juggernaut-xl-v5",
"prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K",
"negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime",
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": None,
"guidance_scale": 7.5,
"multi_lingual": "no",
"panorama": "no",
"self_attention": "no",
"upscale": "no",
"embeddings": "embeddings_model_id",
"lora": "lora_model_id",
"webhook": None,
"track_id": None
})
headers = {
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.text)
> Use this coupon code to get 25% off **DMGG0RBN** | 2,491 | [
[
-0.0411376953125,
-0.048858642578125,
0.0304107666015625,
0.01467132568359375,
-0.03533935546875,
0.0159149169921875,
0.025665283203125,
-0.02935791015625,
0.038482666015625,
0.0472412109375,
-0.06689453125,
-0.05413818359375,
-0.03314208984375,
0.0074462890625,
-0.017181396484375,
0.05743408203125,
0.00885009765625,
-0.01540374755859375,
-0.0164794921875,
0.004474639892578125,
-0.03802490234375,
-0.0183258056640625,
-0.033111572265625,
-0.0114288330078125,
0.01509857177734375,
-0.0098419189453125,
0.046630859375,
0.05120849609375,
0.0195465087890625,
0.022491455078125,
-0.02618408203125,
-0.01126861572265625,
-0.039031982421875,
-0.0278167724609375,
-0.0211944580078125,
-0.05731201171875,
-0.0391845703125,
-0.0111541748046875,
0.02838134765625,
0.027679443359375,
-0.007083892822265625,
0.04156494140625,
-0.007045745849609375,
0.045074462890625,
-0.057708740234375,
0.0245513916015625,
-0.01506805419921875,
0.019683837890625,
-0.00885009765625,
0.00566864013671875,
-0.014190673828125,
0.0005488395690917969,
-0.01495361328125,
-0.07391357421875,
0.0171356201171875,
0.0196380615234375,
0.09429931640625,
0.02777099609375,
-0.017913818359375,
-0.0025577545166015625,
-0.03875732421875,
0.065673828125,
-0.061248779296875,
0.0279083251953125,
0.006137847900390625,
0.0201263427734375,
-0.00469970703125,
-0.06903076171875,
-0.048858642578125,
0.032379150390625,
0.012237548828125,
0.0295867919921875,
-0.052734375,
-0.0199432373046875,
0.029083251953125,
0.0227508544921875,
-0.045806884765625,
-0.00965118408203125,
-0.047332763671875,
-0.0068511962890625,
0.047149658203125,
0.0254669189453125,
0.01532745361328125,
-0.0238037109375,
-0.039947509765625,
-0.0268707275390625,
-0.037841796875,
0.037322998046875,
0.0516357421875,
0.015655517578125,
-0.049163818359375,
0.03704833984375,
-0.02618408203125,
0.060546875,
0.024871826171875,
-0.01519012451171875,
0.05133056640625,
-0.00716400146484375,
-0.026458740234375,
-0.0179901123046875,
0.07159423828125,
0.049560546875,
-0.0215606689453125,
0.019439697265625,
-0.0108184814453125,
0.0030517578125,
0.0178680419921875,
-0.08465576171875,
-0.0163116455078125,
0.06268310546875,
-0.04022216796875,
-0.03289794921875,
0.005985260009765625,
-0.06884765625,
-0.0173187255859375,
0.0013437271118164062,
0.0298614501953125,
-0.02239990234375,
-0.0303955078125,
0.03192138671875,
-0.0294189453125,
0.004558563232421875,
0.01617431640625,
-0.052886962890625,
0.011199951171875,
0.03759765625,
0.054412841796875,
0.0110626220703125,
0.005046844482421875,
0.007598876953125,
0.0218353271484375,
-0.02642822265625,
0.0748291015625,
-0.00865936279296875,
-0.033660888671875,
-0.0198822021484375,
0.02203369140625,
0.004909515380859375,
-0.04925537109375,
0.04815673828125,
-0.033477783203125,
-0.01280975341796875,
-0.01235198974609375,
-0.03582763671875,
-0.047515869140625,
0.01181793212890625,
-0.052734375,
0.027374267578125,
0.007717132568359375,
-0.06268310546875,
0.021697998046875,
-0.051239013671875,
-0.00705718994140625,
0.01317596435546875,
-0.00449371337890625,
-0.0484619140625,
-0.01129150390625,
0.0192413330078125,
0.0249176025390625,
-0.00865936279296875,
-0.01189422607421875,
-0.058624267578125,
-0.02142333984375,
0.02166748046875,
0.0041046142578125,
0.10211181640625,
0.0278167724609375,
-0.0160675048828125,
-0.0013074874877929688,
-0.0528564453125,
0.0013875961303710938,
0.0517578125,
-0.0061187744140625,
-0.0008597373962402344,
-0.0100555419921875,
0.00026726722717285156,
-0.000522613525390625,
0.0218963623046875,
-0.02947998046875,
0.01421356201171875,
-0.0276947021484375,
0.017791748046875,
0.039306640625,
0.0125885009765625,
0.0069427490234375,
-0.0300750732421875,
0.061737060546875,
0.019561767578125,
0.027862548828125,
0.0024433135986328125,
-0.046783447265625,
-0.03314208984375,
-0.039215087890625,
0.01384735107421875,
0.041473388671875,
-0.0338134765625,
0.025146484375,
-0.00872802734375,
-0.05694580078125,
-0.032257080078125,
0.0006670951843261719,
0.0268402099609375,
0.02825927734375,
0.01259613037109375,
-0.027923583984375,
-0.048126220703125,
-0.07666015625,
-0.01207733154296875,
-0.006076812744140625,
-0.0016908645629882812,
0.026458740234375,
0.039276123046875,
-0.02593994140625,
0.060791015625,
-0.06591796875,
-0.0080718994140625,
-0.0230560302734375,
-0.0007672309875488281,
0.06640625,
0.04119873046875,
0.07354736328125,
-0.059417724609375,
-0.02447509765625,
-0.0215301513671875,
-0.0513916015625,
-0.0032958984375,
0.0157318115234375,
-0.008758544921875,
-0.004199981689453125,
0.004680633544921875,
-0.0648193359375,
0.042083740234375,
0.036712646484375,
-0.03692626953125,
0.055419921875,
-0.0077056884765625,
0.031585693359375,
-0.0849609375,
0.01326751708984375,
0.004741668701171875,
-0.02630615234375,
-0.0338134765625,
0.03839111328125,
0.0030727386474609375,
-0.002288818359375,
-0.059722900390625,
0.045166015625,
-0.0311431884765625,
0.01180267333984375,
-0.017608642578125,
0.0006361007690429688,
0.01007080078125,
0.027374267578125,
-0.005527496337890625,
0.0268707275390625,
0.053955078125,
-0.036651611328125,
0.043060302734375,
0.02239990234375,
-0.0272674560546875,
0.0511474609375,
-0.0528564453125,
-0.0006499290466308594,
-0.006320953369140625,
0.0413818359375,
-0.0706787109375,
-0.039520263671875,
0.04095458984375,
-0.045806884765625,
-0.004467010498046875,
-0.046051025390625,
-0.049560546875,
-0.060394287109375,
-0.0175933837890625,
0.0270843505859375,
0.06402587890625,
-0.0295867919921875,
0.0479736328125,
0.035308837890625,
0.01479339599609375,
-0.0528564453125,
-0.05413818359375,
-0.0300750732421875,
-0.0295257568359375,
-0.044403076171875,
0.0203857421875,
-0.0174102783203125,
-0.0233306884765625,
-0.0059967041015625,
0.0006442070007324219,
-0.017669677734375,
-0.01190948486328125,
0.033905029296875,
0.0352783203125,
-0.005237579345703125,
-0.0325927734375,
0.01142120361328125,
-0.00612640380859375,
0.01120758056640625,
-0.024688720703125,
0.047271728515625,
-0.0028705596923828125,
-0.0184783935546875,
-0.052276611328125,
-0.0002541542053222656,
0.04541015625,
0.0038700103759765625,
0.036773681640625,
0.053131103515625,
-0.044097900390625,
-0.00795745849609375,
-0.031097412109375,
-0.01496124267578125,
-0.036468505859375,
0.01207733154296875,
-0.0302581787109375,
-0.0322265625,
0.06781005859375,
0.00556182861328125,
0.003620147705078125,
0.046783447265625,
0.046234130859375,
-0.006244659423828125,
0.09197998046875,
0.025146484375,
0.01067352294921875,
0.0082550048828125,
-0.057037353515625,
-0.00019681453704833984,
-0.061248779296875,
-0.0098419189453125,
-0.01458740234375,
-0.02386474609375,
-0.018585205078125,
-0.03515625,
0.0204620361328125,
0.0283050537109375,
-0.02392578125,
0.036834716796875,
-0.040069580078125,
0.028594970703125,
0.0243072509765625,
0.0223541259765625,
0.010040283203125,
-0.0033931732177734375,
-0.02044677734375,
0.00026702880859375,
-0.03814697265625,
-0.015899658203125,
0.0760498046875,
0.0076446533203125,
0.053314208984375,
0.01971435546875,
0.037261962890625,
-0.0020751953125,
-0.006008148193359375,
-0.0300140380859375,
0.0364990234375,
0.0090179443359375,
-0.09051513671875,
0.0235748291015625,
-0.0184173583984375,
-0.0799560546875,
0.0301971435546875,
-0.0322265625,
-0.072998046875,
0.0267333984375,
0.0295562744140625,
-0.05938720703125,
0.040008544921875,
-0.048614501953125,
0.06939697265625,
0.005054473876953125,
-0.042694091796875,
-0.01384735107421875,
-0.041046142578125,
0.0555419921875,
-0.0037212371826171875,
0.0465087890625,
-0.024078369140625,
-0.0142364501953125,
0.04595947265625,
-0.03759765625,
0.0706787109375,
-0.01654052734375,
0.00485992431640625,
0.05010986328125,
0.0066986083984375,
0.032958984375,
0.031097412109375,
0.007671356201171875,
0.0267333984375,
0.01557159423828125,
-0.03680419921875,
-0.0352783203125,
0.050567626953125,
-0.0526123046875,
-0.04449462890625,
-0.02191162109375,
-0.034881591796875,
0.010528564453125,
0.0283660888671875,
0.03826904296875,
0.01461029052734375,
0.011993408203125,
0.005390167236328125,
0.0433349609375,
-0.01210784912109375,
0.03143310546875,
0.028594970703125,
-0.0557861328125,
-0.045684814453125,
0.052703857421875,
-0.0018167495727539062,
0.0228271484375,
0.01049041748046875,
0.0213165283203125,
-0.034423828125,
-0.03228759765625,
-0.046417236328125,
0.019287109375,
-0.049713134765625,
-0.03033447265625,
-0.0611572265625,
0.004108428955078125,
-0.051483154296875,
-0.01482391357421875,
-0.052154541015625,
-0.0227508544921875,
-0.04669189453125,
0.00106048583984375,
0.043975830078125,
0.0291748046875,
-0.01114654541015625,
0.01617431640625,
-0.050628662109375,
0.024169921875,
0.00864410400390625,
0.00971221923828125,
-0.001026153564453125,
-0.042938232421875,
-0.007293701171875,
0.006458282470703125,
-0.052886962890625,
-0.06915283203125,
0.0523681640625,
-0.028656005859375,
0.029144287109375,
0.0555419921875,
0.005718231201171875,
0.07476806640625,
-0.0113983154296875,
0.06732177734375,
0.0301513671875,
-0.06256103515625,
0.045806884765625,
-0.050689697265625,
0.0272674560546875,
0.0172119140625,
0.0247802734375,
-0.011138916015625,
-0.0252532958984375,
-0.07147216796875,
-0.078125,
0.042633056640625,
0.021148681640625,
0.002513885498046875,
0.02117919921875,
0.020965576171875,
0.0054168701171875,
0.0225067138671875,
-0.072509765625,
-0.0399169921875,
-0.0200653076171875,
0.003139495849609375,
0.01436614990234375,
0.016265869140625,
-0.0213165283203125,
-0.035552978515625,
0.053009033203125,
-0.005481719970703125,
0.02130126953125,
0.014190673828125,
0.016571044921875,
-0.01532745361328125,
-0.005035400390625,
0.03936767578125,
0.049102783203125,
-0.03155517578125,
-0.0181884765625,
0.0098724365234375,
-0.02996826171875,
0.0021572113037109375,
0.01554107666015625,
-0.017669677734375,
-0.0018053054809570312,
0.0104217529296875,
0.058837890625,
-0.0014448165893554688,
-0.051239013671875,
0.053619384765625,
-0.004673004150390625,
-0.0257568359375,
-0.0457763671875,
0.0157928466796875,
0.03240966796875,
0.0479736328125,
0.0282440185546875,
0.023101806640625,
0.02191162109375,
-0.0176239013671875,
-0.00678253173828125,
0.029571533203125,
-0.0187835693359375,
-0.03131103515625,
0.08477783203125,
-0.014862060546875,
-0.0190582275390625,
0.0127410888671875,
-0.03155517578125,
-0.01032257080078125,
0.0555419921875,
0.0574951171875,
0.050506591796875,
-0.004093170166015625,
0.0024394989013671875,
0.05889892578125,
0.00995635986328125,
-0.006366729736328125,
0.041748046875,
0.0178375244140625,
-0.032470703125,
-0.0172576904296875,
-0.051422119140625,
-0.0159912109375,
0.0229949951171875,
-0.04400634765625,
0.057464599609375,
-0.0543212890625,
-0.0246429443359375,
-0.0030384063720703125,
-0.015838623046875,
-0.05206298828125,
0.0238494873046875,
0.00970458984375,
0.05657958984375,
-0.0406494140625,
0.02984619140625,
0.052154541015625,
-0.040435791015625,
-0.07586669921875,
-0.0259552001953125,
0.0341796875,
-0.04742431640625,
0.032012939453125,
0.006320953369140625,
0.01324462890625,
0.007564544677734375,
-0.056304931640625,
-0.0731201171875,
0.093505859375,
0.03173828125,
-0.0426025390625,
0.01491546630859375,
-0.008331298828125,
0.0209503173828125,
-0.031280517578125,
0.030303955078125,
0.01129150390625,
0.03179931640625,
0.00864410400390625,
-0.0428466796875,
0.00988006591796875,
-0.018890380859375,
-0.00533294677734375,
-0.0070648193359375,
-0.06744384765625,
0.07659912109375,
-0.03521728515625,
-0.01007080078125,
0.0121917724609375,
0.047027587890625,
0.053131103515625,
0.01617431640625,
0.049102783203125,
0.08184814453125,
0.028717041015625,
-0.0014352798461914062,
0.08831787109375,
-0.0277557373046875,
0.056671142578125,
0.045989990234375,
-0.007282257080078125,
0.06024169921875,
0.0270233154296875,
-0.029571533203125,
0.055145263671875,
0.061492919921875,
-0.0279083251953125,
0.04205322265625,
0.018310546875,
-0.02374267578125,
-0.010162353515625,
0.0194854736328125,
-0.0360107421875,
0.0227813720703125,
0.020111083984375,
-0.025482177734375,
0.004695892333984375,
-0.004322052001953125,
-0.0003402233123779297,
-0.023345947265625,
-0.0222625732421875,
0.0294952392578125,
-0.00011795759201049805,
-0.0227508544921875,
0.06011962890625,
-0.011993408203125,
0.057159423828125,
-0.034637451171875,
0.004840850830078125,
-0.0013246536254882812,
0.0204010009765625,
-0.022674560546875,
-0.046142578125,
0.01250457763671875,
-0.005756378173828125,
-0.0137176513671875,
0.01012420654296875,
0.040863037109375,
0.0112762451171875,
-0.058685302734375,
0.016448974609375,
0.0174560546875,
0.030609130859375,
0.0016613006591796875,
-0.0721435546875,
0.023712158203125,
0.00844573974609375,
-0.026458740234375,
0.0005655288696289062,
0.00920867919921875,
0.035369873046875,
0.0528564453125,
0.055023193359375,
0.005046844482421875,
0.000995635986328125,
-0.01496124267578125,
0.043060302734375,
-0.043121337890625,
-0.049285888671875,
-0.058990478515625,
0.0611572265625,
-0.01458740234375,
-0.0291748046875,
0.0455322265625,
0.06793212890625,
0.07122802734375,
-0.04888916015625,
0.0635986328125,
-0.0197906494140625,
0.040771484375,
-0.023345947265625,
0.066650390625,
-0.06341552734375,
0.003711700439453125,
-0.03533935546875,
-0.047210693359375,
-0.0184173583984375,
0.03533935546875,
-0.0016012191772460938,
0.00531768798828125,
0.0362548828125,
0.057708740234375,
-0.0309600830078125,
-0.00830841064453125,
0.01021575927734375,
0.02069091796875,
0.0137481689453125,
0.032440185546875,
0.034210205078125,
-0.04541015625,
0.044677734375,
-0.046661376953125,
-0.018035888671875,
-0.0141448974609375,
-0.05706787109375,
-0.060089111328125,
-0.0232391357421875,
-0.042724609375,
-0.044403076171875,
-0.00481414794921875,
0.0535888671875,
0.0743408203125,
-0.046478271484375,
-0.0207366943359375,
-0.0029506683349609375,
0.0048065185546875,
-0.034912109375,
-0.0217132568359375,
0.00518798828125,
0.02008056640625,
-0.0791015625,
0.0104827880859375,
0.0093841552734375,
0.0281219482421875,
-0.00707244873046875,
0.0095062255859375,
-0.0006189346313476562,
0.004276275634765625,
0.02392578125,
0.03228759765625,
-0.064697265625,
-0.0071868896484375,
-0.01557159423828125,
0.011932373046875,
0.0164031982421875,
0.0220489501953125,
-0.05023193359375,
0.02276611328125,
0.042633056640625,
0.014373779296875,
0.047332763671875,
-0.00789642333984375,
0.0173797607421875,
-0.03045654296875,
0.03314208984375,
0.0024738311767578125,
0.0479736328125,
0.01026153564453125,
-0.03778076171875,
0.0312347412109375,
0.049560546875,
-0.02996826171875,
-0.06243896484375,
0.00872802734375,
-0.09539794921875,
-0.037384033203125,
0.0673828125,
-0.0198516845703125,
-0.05218505859375,
0.0123138427734375,
-0.0153350830078125,
0.018890380859375,
-0.0224151611328125,
0.046356201171875,
0.035736083984375,
-0.022674560546875,
-0.0175018310546875,
-0.064453125,
0.007358551025390625,
0.01026153564453125,
-0.059173583984375,
-0.01238250732421875,
0.03302001953125,
0.04736328125,
0.040283203125,
0.0235137939453125,
-0.03387451171875,
0.02349853515625,
0.031646728515625,
0.038055419921875,
0.00567626953125,
0.025146484375,
-0.0097808837890625,
0.00921630859375,
-0.0283355712890625,
-0.0215911865234375
]
] |
timm/vit_small_patch16_224.dino | 2023-05-06T03:21:04.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2104.14294",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/vit_small_patch16_224.dino | 0 | 42,340 | timm | 2022-12-22T07:54:20 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
---
# Model card for vit_small_patch16_224.dino
A Vision Transformer (ViT) image feature model. Trained with Self-Supervised DINO method.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 21.7
- GMACs: 4.3
- Activations (M): 8.2
- Image size: 224 x 224
- **Papers:**
- Emerging Properties in Self-Supervised Vision Transformers: https://arxiv.org/abs/2104.14294
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Pretrain Dataset:** ImageNet-1k
- **Original:** https://github.com/facebookresearch/dino
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_small_patch16_224.dino', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_small_patch16_224.dino',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 384) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@inproceedings{caron2021emerging,
title={Emerging properties in self-supervised vision transformers},
author={Caron, Mathilde and Touvron, Hugo and Misra, Ishan and J{'e}gou, Herv{'e} and Mairal, Julien and Bojanowski, Piotr and Joulin, Armand},
booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
pages={9650--9660},
year={2021}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 3,679 | [
[
-0.04266357421875,
-0.0229949951171875,
0.006877899169921875,
0.00916290283203125,
-0.025787353515625,
-0.026214599609375,
-0.0202178955078125,
-0.039520263671875,
0.0243072509765625,
0.024261474609375,
-0.037750244140625,
-0.036102294921875,
-0.048797607421875,
0.00305938720703125,
-0.0164642333984375,
0.07171630859375,
-0.00621795654296875,
-0.01641845703125,
-0.0181427001953125,
-0.036712646484375,
-0.0076141357421875,
-0.02056884765625,
-0.03814697265625,
-0.025543212890625,
0.0287933349609375,
0.004238128662109375,
0.0482177734375,
0.063720703125,
0.047882080078125,
0.036376953125,
-0.003368377685546875,
0.006443023681640625,
-0.00978851318359375,
-0.018768310546875,
0.0133514404296875,
-0.039825439453125,
-0.03271484375,
0.0230255126953125,
0.05560302734375,
0.0278167724609375,
0.0040740966796875,
0.0293121337890625,
0.01393890380859375,
0.03619384765625,
-0.02105712890625,
0.01898193359375,
-0.035736083984375,
0.0171966552734375,
-0.00823211669921875,
0.0037059783935546875,
-0.01485443115234375,
-0.0179443359375,
0.012725830078125,
-0.039459228515625,
0.0426025390625,
-0.004913330078125,
0.0966796875,
0.021453857421875,
-0.00557708740234375,
0.00641632080078125,
-0.027984619140625,
0.0601806640625,
-0.0501708984375,
0.0243377685546875,
0.0094451904296875,
0.0127716064453125,
-0.0007543563842773438,
-0.075439453125,
-0.05303955078125,
-0.0019330978393554688,
-0.0221710205078125,
0.0025177001953125,
-0.0294952392578125,
0.0032596588134765625,
0.0196380615234375,
0.0389404296875,
-0.025360107421875,
0.005870819091796875,
-0.04327392578125,
-0.0272979736328125,
0.046600341796875,
-0.003154754638671875,
0.0140838623046875,
-0.029388427734375,
-0.043670654296875,
-0.0439453125,
-0.02362060546875,
0.0193939208984375,
0.0225067138671875,
0.01116180419921875,
-0.03839111328125,
0.04150390625,
0.005771636962890625,
0.041839599609375,
0.019805908203125,
-0.021942138671875,
0.04681396484375,
-0.015289306640625,
-0.0210418701171875,
-0.015655517578125,
0.089599609375,
0.032470703125,
0.0231781005859375,
0.00562286376953125,
-0.009979248046875,
-0.01483154296875,
-0.00386810302734375,
-0.082275390625,
-0.032257080078125,
0.00969696044921875,
-0.043487548828125,
-0.0276947021484375,
0.01094818115234375,
-0.0631103515625,
-0.00852203369140625,
-0.0055389404296875,
0.05596923828125,
-0.029937744140625,
-0.02764892578125,
-0.001987457275390625,
-0.00920867919921875,
0.03216552734375,
0.01264190673828125,
-0.055023193359375,
0.00820159912109375,
0.01438140869140625,
0.0767822265625,
-0.001247406005859375,
-0.0419921875,
-0.00995635986328125,
-0.0251312255859375,
-0.0213775634765625,
0.048431396484375,
-0.0033626556396484375,
-0.022186279296875,
-0.0220489501953125,
0.0284271240234375,
-0.0184173583984375,
-0.0472412109375,
0.019073486328125,
-0.006687164306640625,
0.02520751953125,
0.01110076904296875,
-0.00949859619140625,
-0.0216827392578125,
0.01494598388671875,
-0.032470703125,
0.0970458984375,
0.0304718017578125,
-0.0611572265625,
0.03271484375,
-0.033477783203125,
-0.00952911376953125,
-0.01480865478515625,
-0.0045623779296875,
-0.0853271484375,
-0.0016832351684570312,
0.026031494140625,
0.0465087890625,
-0.01558685302734375,
0.001926422119140625,
-0.04241943359375,
-0.00946807861328125,
0.0268707275390625,
-0.016448974609375,
0.0665283203125,
0.01081085205078125,
-0.034881591796875,
0.02105712890625,
-0.049530029296875,
0.00691986083984375,
0.034088134765625,
-0.0171966552734375,
-0.00296783447265625,
-0.043609619140625,
0.003734588623046875,
0.027557373046875,
0.0242462158203125,
-0.045440673828125,
0.029632568359375,
-0.0157928466796875,
0.034942626953125,
0.05401611328125,
-0.0178680419921875,
0.029571533203125,
-0.022430419921875,
0.025634765625,
0.0214385986328125,
0.0303802490234375,
-0.009918212890625,
-0.04620361328125,
-0.066650390625,
-0.045318603515625,
0.0276641845703125,
0.0231781005859375,
-0.04046630859375,
0.04345703125,
-0.0239410400390625,
-0.0545654296875,
-0.048004150390625,
0.01343536376953125,
0.035308837890625,
0.040985107421875,
0.03900146484375,
-0.037445068359375,
-0.034088134765625,
-0.073974609375,
-0.00434112548828125,
-0.00665283203125,
-0.0040435791015625,
0.033966064453125,
0.0467529296875,
-0.0179901123046875,
0.06793212890625,
-0.033447265625,
-0.034698486328125,
-0.00971221923828125,
0.01113128662109375,
0.027374267578125,
0.051513671875,
0.0626220703125,
-0.047821044921875,
-0.033447265625,
-0.018463134765625,
-0.0654296875,
0.0082550048828125,
0.0005412101745605469,
-0.00357818603515625,
0.0246734619140625,
0.01387786865234375,
-0.058685302734375,
0.049530029296875,
0.024261474609375,
-0.030792236328125,
0.032684326171875,
-0.0257110595703125,
0.0053863525390625,
-0.08758544921875,
0.0021305084228515625,
0.0291900634765625,
-0.01087188720703125,
-0.0272216796875,
-0.003173828125,
0.01003265380859375,
0.0013885498046875,
-0.032196044921875,
0.046142578125,
-0.044647216796875,
-0.021270751953125,
-0.0030307769775390625,
-0.01540374755859375,
0.0021495819091796875,
0.052978515625,
-0.002002716064453125,
0.0447998046875,
0.05718994140625,
-0.037353515625,
0.03900146484375,
0.03399658203125,
-0.0168304443359375,
0.040435791015625,
-0.048675537109375,
0.007965087890625,
0.0062255859375,
0.01202392578125,
-0.07672119140625,
-0.012908935546875,
0.0222930908203125,
-0.04541015625,
0.048309326171875,
-0.039886474609375,
-0.033599853515625,
-0.0528564453125,
-0.034515380859375,
0.036590576171875,
0.048919677734375,
-0.0634765625,
0.047210693359375,
0.01556396484375,
0.0181884765625,
-0.038787841796875,
-0.062744140625,
-0.01140594482421875,
-0.032470703125,
-0.051727294921875,
0.037261962890625,
0.0003643035888671875,
0.016632080078125,
0.00888824462890625,
-0.001575469970703125,
0.0017766952514648438,
-0.01514434814453125,
0.0283050537109375,
0.0296173095703125,
-0.0180206298828125,
-0.0043182373046875,
-0.02056884765625,
-0.01393890380859375,
0.0099029541015625,
-0.027008056640625,
0.03900146484375,
-0.0252838134765625,
-0.005390167236328125,
-0.052642822265625,
-0.016998291015625,
0.04180908203125,
-0.0201568603515625,
0.04998779296875,
0.0810546875,
-0.0268707275390625,
-0.00021469593048095703,
-0.036895751953125,
-0.02587890625,
-0.040069580078125,
0.0291595458984375,
-0.03240966796875,
-0.036041259765625,
0.0665283203125,
0.0079803466796875,
-0.01158905029296875,
0.07110595703125,
0.0323486328125,
-0.0080413818359375,
0.0618896484375,
0.049102783203125,
0.01161956787109375,
0.053680419921875,
-0.07147216796875,
-0.0024089813232421875,
-0.07086181640625,
-0.037139892578125,
-0.0177764892578125,
-0.034027099609375,
-0.0650634765625,
-0.036102294921875,
0.033172607421875,
0.00414276123046875,
-0.0121917724609375,
0.045257568359375,
-0.06939697265625,
-0.0005831718444824219,
0.06060791015625,
0.033172607421875,
-0.01221466064453125,
0.0215606689453125,
-0.0225982666015625,
-0.006805419921875,
-0.052001953125,
-0.0028743743896484375,
0.0853271484375,
0.0296478271484375,
0.058624267578125,
-0.0134124755859375,
0.053863525390625,
-0.0111083984375,
0.0184326171875,
-0.0543212890625,
0.048187255859375,
-0.0016317367553710938,
-0.03900146484375,
-0.0260009765625,
-0.02984619140625,
-0.083984375,
0.0128631591796875,
-0.0224151611328125,
-0.05706787109375,
0.034027099609375,
0.01617431640625,
-0.022064208984375,
0.0523681640625,
-0.05352783203125,
0.07366943359375,
-0.00894927978515625,
-0.03302001953125,
0.0040130615234375,
-0.047882080078125,
0.0132904052734375,
0.0054931640625,
-0.0159759521484375,
-0.005687713623046875,
0.015625,
0.069091796875,
-0.0443115234375,
0.06585693359375,
-0.026947021484375,
0.01514434814453125,
0.0419921875,
-0.0109710693359375,
0.0217742919921875,
-0.004932403564453125,
0.007076263427734375,
0.034515380859375,
0.01016998291015625,
-0.0246734619140625,
-0.03790283203125,
0.04290771484375,
-0.07757568359375,
-0.040740966796875,
-0.03985595703125,
-0.034210205078125,
0.016082763671875,
0.0147705078125,
0.04437255859375,
0.04302978515625,
0.0240478515625,
0.02392578125,
0.0426025390625,
-0.0204315185546875,
0.045074462890625,
0.00547027587890625,
-0.0183868408203125,
-0.0400390625,
0.06927490234375,
0.021881103515625,
0.01006317138671875,
0.0036106109619140625,
0.0225982666015625,
-0.033477783203125,
-0.0379638671875,
-0.031219482421875,
0.0338134765625,
-0.046844482421875,
-0.0401611328125,
-0.045135498046875,
-0.03924560546875,
-0.036773681640625,
0.0063323974609375,
-0.0418701171875,
-0.031982421875,
-0.035675048828125,
0.01041412353515625,
0.056304931640625,
0.038970947265625,
-0.0244293212890625,
0.030517578125,
-0.038177490234375,
0.0162353515625,
0.036895751953125,
0.0396728515625,
-0.0196533203125,
-0.07501220703125,
-0.0192718505859375,
-0.003902435302734375,
-0.034454345703125,
-0.047332763671875,
0.0435791015625,
0.0171051025390625,
0.0394287109375,
0.0227813720703125,
-0.01137542724609375,
0.056488037109375,
-0.0052490234375,
0.042510986328125,
0.0243072509765625,
-0.04833984375,
0.047149658203125,
-0.01470947265625,
0.01041412353515625,
0.007381439208984375,
0.015899658203125,
-0.013397216796875,
-0.00199127197265625,
-0.0802001953125,
-0.05133056640625,
0.055694580078125,
0.0150909423828125,
0.00766754150390625,
0.02239990234375,
0.04742431640625,
-0.007740020751953125,
0.003215789794921875,
-0.06890869140625,
-0.0306854248046875,
-0.036407470703125,
-0.0250396728515625,
-0.004764556884765625,
-0.007709503173828125,
-0.0026416778564453125,
-0.054718017578125,
0.042449951171875,
-0.0233001708984375,
0.06341552734375,
0.03558349609375,
-0.00337982177734375,
-0.00982666015625,
-0.022491455078125,
0.0272979736328125,
0.0202178955078125,
-0.023101806640625,
0.00665283203125,
0.01529693603515625,
-0.042327880859375,
-0.0012044906616210938,
0.0298309326171875,
0.00130462646484375,
-0.004512786865234375,
0.0279998779296875,
0.063232421875,
0.001678466796875,
0.007686614990234375,
0.044036865234375,
-0.002399444580078125,
-0.0325927734375,
-0.0222930908203125,
0.0124359130859375,
-0.01331329345703125,
0.033660888671875,
0.031158447265625,
0.0260467529296875,
-0.00286102294921875,
-0.024688720703125,
0.017913818359375,
0.042236328125,
-0.03369140625,
-0.035797119140625,
0.05218505859375,
-0.01763916015625,
-0.00521087646484375,
0.0572509765625,
-0.00704193115234375,
-0.037872314453125,
0.07366943359375,
0.033905029296875,
0.069091796875,
-0.01910400390625,
0.004695892333984375,
0.054229736328125,
0.0169525146484375,
-0.0011625289916992188,
0.0095977783203125,
0.0009489059448242188,
-0.064697265625,
0.0037689208984375,
-0.047882080078125,
-0.00044083595275878906,
0.01922607421875,
-0.038787841796875,
0.027984619140625,
-0.04156494140625,
-0.03240966796875,
0.02099609375,
0.01485443115234375,
-0.06988525390625,
0.0257568359375,
0.004589080810546875,
0.04974365234375,
-0.054229736328125,
0.0631103515625,
0.054534912109375,
-0.048187255859375,
-0.07061767578125,
-0.0133209228515625,
-0.005290985107421875,
-0.071044921875,
0.0399169921875,
0.0306396484375,
0.0003879070281982422,
0.0194244384765625,
-0.056610107421875,
-0.0625,
0.10577392578125,
0.0343017578125,
-0.006381988525390625,
0.00909423828125,
0.00142669677734375,
0.0284576416015625,
-0.029449462890625,
0.028106689453125,
0.0196075439453125,
0.0267486572265625,
0.0198516845703125,
-0.06060791015625,
0.0097198486328125,
-0.0233612060546875,
0.00794219970703125,
0.016448974609375,
-0.07501220703125,
0.06585693359375,
-0.037139892578125,
-0.01131439208984375,
0.0133209228515625,
0.05340576171875,
0.01568603515625,
0.00946044921875,
0.04388427734375,
0.0625,
0.031097412109375,
-0.0274810791015625,
0.06512451171875,
-0.017852783203125,
0.058013916015625,
0.041656494140625,
0.033447265625,
0.038421630859375,
0.031036376953125,
-0.033538818359375,
0.034210205078125,
0.07098388671875,
-0.044677734375,
0.0288543701171875,
0.00554656982421875,
0.004009246826171875,
-0.0188751220703125,
0.0022068023681640625,
-0.031005859375,
0.045562744140625,
0.01343536376953125,
-0.0452880859375,
-0.003337860107421875,
0.00624847412109375,
-0.00847625732421875,
-0.021881103515625,
-0.01442718505859375,
0.039398193359375,
0.0060882568359375,
-0.03271484375,
0.05340576171875,
-0.00493621826171875,
0.06243896484375,
-0.0224456787109375,
0.004123687744140625,
-0.0211639404296875,
0.029632568359375,
-0.02349853515625,
-0.0718994140625,
0.0175933837890625,
-0.0265045166015625,
-0.00449371337890625,
-0.002582550048828125,
0.05633544921875,
-0.023529052734375,
-0.0457763671875,
0.0210418701171875,
0.0196075439453125,
0.0249786376953125,
-0.00026798248291015625,
-0.079833984375,
-0.00870513916015625,
-0.005893707275390625,
-0.0433349609375,
0.0186309814453125,
0.03741455078125,
0.007236480712890625,
0.058563232421875,
0.04638671875,
-0.00914764404296875,
0.0173187255859375,
-0.0184173583984375,
0.07147216796875,
-0.043487548828125,
-0.0253448486328125,
-0.058319091796875,
0.04022216796875,
-0.007190704345703125,
-0.04327392578125,
0.04876708984375,
0.044342041015625,
0.0640869140625,
-0.00394439697265625,
0.0248565673828125,
-0.0128631591796875,
0.00377655029296875,
-0.0231781005859375,
0.04840087890625,
-0.05084228515625,
-0.004558563232421875,
-0.016448974609375,
-0.06732177734375,
-0.02630615234375,
0.05987548828125,
-0.0227813720703125,
0.0411376953125,
0.03546142578125,
0.06951904296875,
-0.026275634765625,
-0.035980224609375,
0.020050048828125,
0.016510009765625,
0.006771087646484375,
0.020782470703125,
0.036163330078125,
-0.059967041015625,
0.04327392578125,
-0.045684814453125,
-0.007598876953125,
-0.01331329345703125,
-0.049774169921875,
-0.0780029296875,
-0.0655517578125,
-0.047821044921875,
-0.048187255859375,
-0.0203399658203125,
0.057769775390625,
0.078857421875,
-0.04901123046875,
-0.00023376941680908203,
-0.0020122528076171875,
0.004299163818359375,
-0.017303466796875,
-0.0178070068359375,
0.046600341796875,
-0.00450897216796875,
-0.05804443359375,
-0.0211639404296875,
0.006313323974609375,
0.0408935546875,
-0.0212249755859375,
-0.01128387451171875,
-0.00623321533203125,
-0.0157470703125,
0.0151519775390625,
0.02978515625,
-0.056976318359375,
-0.0206756591796875,
-0.00910186767578125,
-0.00978851318359375,
0.04534912109375,
0.0246429443359375,
-0.058319091796875,
0.035675048828125,
0.026947021484375,
0.016937255859375,
0.07403564453125,
-0.0225677490234375,
0.004955291748046875,
-0.0540771484375,
0.033477783203125,
-0.01200103759765625,
0.0416259765625,
0.04052734375,
-0.02838134765625,
0.042877197265625,
0.0465087890625,
-0.032135009765625,
-0.05224609375,
-0.00605010986328125,
-0.07861328125,
0.0014657974243164062,
0.06842041015625,
-0.0273895263671875,
-0.0399169921875,
0.034088134765625,
0.0012121200561523438,
0.047882080078125,
-0.005290985107421875,
0.05023193359375,
0.0155792236328125,
-0.0011758804321289062,
-0.053466796875,
-0.0225372314453125,
0.036773681640625,
0.0102386474609375,
-0.048492431640625,
-0.0287017822265625,
0.00345611572265625,
0.049530029296875,
0.035491943359375,
0.0267486572265625,
-0.0197906494140625,
0.00780487060546875,
0.0009531974792480469,
0.04046630859375,
-0.0195770263671875,
-0.0151519775390625,
-0.031494140625,
-0.00959014892578125,
-0.01016998291015625,
-0.036834716796875
]
] |
ostris/ikea-instructions-lora-sdxl | 2023-09-29T11:55:15.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"lora",
"style",
"styles",
"instruction_manual",
"ikea",
"license:other",
"has_space",
"region:us"
] | text-to-image | ostris | null | null | ostris/ikea-instructions-lora-sdxl | 151 | 42,287 | diffusers | 2023-09-29T11:55:12 | ---
license: other
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- style
- styles
- instruction_manual
- ikea
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt:
widget:
- text: "where is waldo "
- text: "sleep"
- text: "hamburger,, lettuce, mayo, lettuce, no tomato "
- text: "barbie and ken "
- text: "back to the future "
- text: "the dude, form the movie the big lebowski, drinking, rug wet, bowling ball "
- text: "hippie "
- text: " fat man, eat pizza, eat hamburgers, drink beer"
- text: " dayman, fighter of the night man, champion of the sun"
- text: " nightman, pay troll toll to get into that boys hole"
---
# Ikea Instructions - LoRA - SDXL
> where is waldo
<p>No trigger word needed. Weight of 1.0 works well on the SDXL 1.0 base. Negatives are usually not needed, but "blurry" and "low quality" seem to help. You can use simple prompts such as "hamburger" or describe steps you want it to show. SDXL does a pretty good job of figuring out the steps to make it.</p>
## Image examples for the model:
> sleep
> hamburger,, lettuce, mayo, lettuce, no tomato
> barbie and ken
> back to the future
> the dude, form the movie the big lebowski, drinking, rug wet, bowling ball
> hippie
> fat man, eat pizza, eat hamburgers, drink beer
> dayman, fighter of the night man, champion of the sun
> nightman, pay troll toll to get into that boys hole
| 1,674 | [
[
-0.038360595703125,
-0.047515869140625,
0.061737060546875,
0.0159149169921875,
-0.040283203125,
-0.00615692138671875,
0.050933837890625,
-0.01233673095703125,
0.053863525390625,
0.048858642578125,
-0.07177734375,
-0.046356201171875,
-0.028106689453125,
0.00031685829162597656,
-0.02825927734375,
0.06781005859375,
-0.0169219970703125,
0.00888824462890625,
0.0193023681640625,
-0.005573272705078125,
-0.032562255859375,
0.0027866363525390625,
-0.0286712646484375,
-0.0132598876953125,
0.040679931640625,
0.02716064453125,
0.06561279296875,
0.0548095703125,
0.017578125,
0.0243377685546875,
-0.0130157470703125,
-0.0155181884765625,
-0.0311279296875,
-0.010589599609375,
-0.0298919677734375,
-0.030609130859375,
-0.04779052734375,
-0.003437042236328125,
0.04364013671875,
0.032623291015625,
-0.01021575927734375,
0.016326904296875,
-0.0163116455078125,
0.0684814453125,
-0.02850341796875,
0.0170745849609375,
-0.01348876953125,
0.030487060546875,
0.0079803466796875,
0.0144500732421875,
0.00763702392578125,
-0.039825439453125,
-0.03668212890625,
-0.045806884765625,
-0.00737762451171875,
0.01131439208984375,
0.09368896484375,
0.034423828125,
-0.0300750732421875,
-0.03680419921875,
-0.0458984375,
0.062347412109375,
-0.062347412109375,
0.0269775390625,
0.03314208984375,
0.0301361083984375,
-0.0099029541015625,
-0.014434814453125,
-0.053497314453125,
0.01116180419921875,
0.00412750244140625,
0.00566864013671875,
-0.01535797119140625,
-0.020843505859375,
0.04058837890625,
0.007495880126953125,
-0.044281005859375,
0.002658843994140625,
-0.056610107421875,
0.0333251953125,
0.05755615234375,
0.0197601318359375,
0.00673675537109375,
-0.036468505859375,
-0.06097412109375,
-0.01727294921875,
-0.038482666015625,
-0.0238037109375,
0.01250457763671875,
0.0007948875427246094,
-0.0264129638671875,
0.06890869140625,
-0.004558563232421875,
0.0240936279296875,
0.01885986328125,
-0.018035888671875,
0.0264129638671875,
-0.02008056640625,
-0.002239227294921875,
0.01059722900390625,
0.030517578125,
0.06378173828125,
-0.0261077880859375,
0.019989013671875,
-0.038238525390625,
0.004119873046875,
0.02398681640625,
-0.042694091796875,
-0.006076812744140625,
0.02716064453125,
-0.03515625,
-0.0035915374755859375,
-0.0111846923828125,
-0.0751953125,
-0.0204010009765625,
-0.0254669189453125,
0.0540771484375,
-0.01149749755859375,
0.0109405517578125,
-0.0016202926635742188,
-0.01036834716796875,
0.06915283203125,
0.0239410400390625,
-0.04034423828125,
0.0287322998046875,
0.0254364013671875,
0.0287322998046875,
0.004791259765625,
0.001983642578125,
-0.0462646484375,
0.035980224609375,
-0.041351318359375,
0.045806884765625,
0.001552581787109375,
-0.0256500244140625,
-0.00008022785186767578,
0.0149078369140625,
0.0211181640625,
-0.021026611328125,
0.052490234375,
-0.05078125,
0.01328277587890625,
-0.04266357421875,
-0.031341552734375,
-0.0305938720703125,
0.0151519775390625,
-0.06964111328125,
0.040130615234375,
0.0199737548828125,
-0.018829345703125,
0.0229949951171875,
-0.06707763671875,
-0.041595458984375,
-0.00406646728515625,
-0.0311737060546875,
-0.019927978515625,
0.0279541015625,
0.0166473388671875,
0.0263671875,
-0.0028553009033203125,
-0.035247802734375,
-0.00099945068359375,
-0.027740478515625,
-0.0003695487976074219,
0.01239776611328125,
0.07403564453125,
0.01861572265625,
-0.0274505615234375,
0.00925445556640625,
-0.068115234375,
0.0008549690246582031,
0.0377197265625,
-0.039581298828125,
0.01331329345703125,
0.001041412353515625,
-0.0167236328125,
0.020751953125,
0.025848388671875,
-0.029937744140625,
0.009552001953125,
-0.014678955078125,
0.00017249584197998047,
0.064208984375,
0.0037364959716796875,
0.0222320556640625,
-0.03155517578125,
0.053466796875,
-0.00908660888671875,
0.01557159423828125,
0.0021114349365234375,
-0.031982421875,
-0.07977294921875,
-0.004131317138671875,
-0.00830841064453125,
0.0379638671875,
-0.0703125,
0.049163818359375,
0.01161956787109375,
-0.0210723876953125,
-0.0181427001953125,
0.0160675048828125,
0.0311279296875,
0.005062103271484375,
0.0204315185546875,
-0.0180206298828125,
-0.06451416015625,
-0.053863525390625,
0.042388916015625,
0.00666046142578125,
-0.01049041748046875,
0.0190277099609375,
0.049163818359375,
-0.0123748779296875,
0.043609619140625,
-0.07177734375,
-0.03887939453125,
-0.020843505859375,
-0.0093536376953125,
0.06298828125,
0.0311737060546875,
0.035736083984375,
-0.044281005859375,
-0.03045654296875,
-0.0187835693359375,
-0.0595703125,
0.0271453857421875,
0.005764007568359375,
-0.00008159875869750977,
0.0126495361328125,
0.040283203125,
-0.051483154296875,
0.033172607421875,
0.0248870849609375,
-0.048583984375,
0.03875732421875,
-0.02239990234375,
0.003910064697265625,
-0.08392333984375,
-0.0169219970703125,
-0.01262664794921875,
-0.01233673095703125,
-0.0192413330078125,
0.02740478515625,
-0.0204315185546875,
-0.027496337890625,
-0.050872802734375,
0.0355224609375,
-0.032196044921875,
-0.029388427734375,
0.0026988983154296875,
0.009124755859375,
0.01020050048828125,
0.05157470703125,
-0.017333984375,
0.034698486328125,
0.03729248046875,
-0.050537109375,
0.038482666015625,
0.02703857421875,
-0.032135009765625,
0.06427001953125,
-0.06103515625,
0.012451171875,
-0.0290374755859375,
0.005886077880859375,
-0.0859375,
-0.0171661376953125,
0.02716064453125,
-0.0007748603820800781,
0.0039520263671875,
0.0017566680908203125,
-0.03460693359375,
-0.0268402099609375,
-0.037017822265625,
-0.00028395652770996094,
0.06561279296875,
-0.03851318359375,
0.05548095703125,
0.039825439453125,
0.013336181640625,
-0.0205230712890625,
-0.03314208984375,
-0.01116943359375,
-0.0158843994140625,
-0.0149688720703125,
0.011566162109375,
-0.02703857421875,
-0.0312042236328125,
-0.00786590576171875,
-0.0078582763671875,
-0.0267791748046875,
-0.0231170654296875,
0.0391845703125,
0.0257415771484375,
-0.0264739990234375,
-0.017822265625,
0.004199981689453125,
-0.010162353515625,
0.02325439453125,
0.0203399658203125,
0.036285400390625,
-0.01422882080078125,
-0.0225372314453125,
-0.035614013671875,
0.04510498046875,
0.045379638671875,
0.0272979736328125,
0.0310821533203125,
0.05548095703125,
-0.043182373046875,
-0.0021915435791015625,
-0.030975341796875,
-0.0250091552734375,
-0.038055419921875,
0.0216827392578125,
-0.03009033203125,
0.00858306884765625,
0.041473388671875,
0.019195556640625,
0.0131988525390625,
0.034576416015625,
0.0166168212890625,
-0.043060302734375,
0.09100341796875,
0.039581298828125,
0.03662109375,
0.0232391357421875,
-0.048583984375,
0.0042877197265625,
-0.06964111328125,
-0.0224761962890625,
-0.03717041015625,
-0.047576904296875,
0.006877899169921875,
-0.05206298828125,
0.01514434814453125,
0.031707763671875,
-0.031402587890625,
0.0657958984375,
-0.007442474365234375,
0.07415771484375,
0.0187835693359375,
0.0175018310546875,
0.00762939453125,
-0.00348663330078125,
-0.0205535888671875,
-0.0218658447265625,
-0.033538818359375,
-0.0263214111328125,
0.039703369140625,
0.0343017578125,
0.0955810546875,
0.0230560302734375,
0.07476806640625,
0.01294708251953125,
-0.006580352783203125,
-0.0408935546875,
0.077392578125,
-0.0291290283203125,
-0.053558349609375,
-0.0266265869140625,
-0.0034656524658203125,
-0.06634521484375,
-0.00785064697265625,
-0.0182342529296875,
-0.042388916015625,
0.024200439453125,
-0.013336181640625,
-0.03985595703125,
0.0180816650390625,
-0.052825927734375,
0.03973388671875,
-0.04473876953125,
-0.0179443359375,
-0.0025463104248046875,
-0.0293121337890625,
0.030609130859375,
0.007205963134765625,
0.033599853515625,
-0.019287109375,
-0.0171966552734375,
0.0673828125,
-0.039825439453125,
0.056365966796875,
-0.02197265625,
-0.0357666015625,
0.007183074951171875,
0.009796142578125,
0.0595703125,
0.00939178466796875,
-0.00400543212890625,
0.01258087158203125,
-0.0010967254638671875,
-0.018829345703125,
-0.04290771484375,
0.064453125,
-0.054901123046875,
-0.03826904296875,
-0.0335693359375,
-0.0302581787109375,
0.0185699462890625,
0.016204833984375,
0.0169677734375,
-0.00585174560546875,
-0.0003695487976074219,
0.01084136962890625,
0.06256103515625,
-0.01318359375,
0.0377197265625,
0.040252685546875,
-0.064453125,
-0.041778564453125,
0.055755615234375,
0.022552490234375,
-0.0012083053588867188,
0.0226287841796875,
0.0126953125,
-0.04217529296875,
-0.00917816162109375,
-0.04205322265625,
0.0301971435546875,
-0.07666015625,
-0.0102691650390625,
-0.027984619140625,
-0.0153045654296875,
0.01222991943359375,
-0.050750732421875,
-0.036346435546875,
-0.0272979736328125,
-0.040130615234375,
-0.0025386810302734375,
0.0256805419921875,
0.0819091796875,
-0.0023670196533203125,
0.020233154296875,
-0.032928466796875,
0.055389404296875,
0.05548095703125,
0.0174713134765625,
-0.0077056884765625,
-0.0197906494140625,
-0.00396728515625,
-0.0074005126953125,
-0.01200103759765625,
-0.05908203125,
0.02301025390625,
-0.0162506103515625,
0.035003662109375,
0.03668212890625,
0.01412200927734375,
0.05902099609375,
-0.055145263671875,
0.0648193359375,
0.05517578125,
-0.053802490234375,
0.04754638671875,
-0.01959228515625,
0.0333251953125,
0.0119171142578125,
0.044677734375,
-0.00286102294921875,
0.00919342041015625,
-0.052276611328125,
-0.053253173828125,
0.038177490234375,
0.00505828857421875,
0.0196990966796875,
-0.002044677734375,
-0.012847900390625,
0.01184844970703125,
0.005229949951171875,
-0.0709228515625,
-0.0166778564453125,
-0.0157928466796875,
0.0190277099609375,
-0.00005036592483520508,
-0.00885772705078125,
-0.03375244140625,
-0.031494140625,
0.0546875,
0.0095977783203125,
0.0225830078125,
-0.00450897216796875,
0.005306243896484375,
-0.03729248046875,
0.020477294921875,
0.061981201171875,
0.0704345703125,
-0.042449951171875,
-0.010345458984375,
0.0208282470703125,
-0.0203399658203125,
0.01035308837890625,
-0.005931854248046875,
-0.0029430389404296875,
0.034332275390625,
0.005939483642578125,
0.056396484375,
0.03717041015625,
-0.039215087890625,
0.01190948486328125,
-0.012969970703125,
-0.0233612060546875,
-0.0360107421875,
0.0284423828125,
0.011505126953125,
0.03753662109375,
0.02703857421875,
-0.0143585205078125,
-0.0222320556640625,
-0.05548095703125,
0.005741119384765625,
0.034271240234375,
-0.0341796875,
-0.00472259521484375,
0.059295654296875,
0.008270263671875,
-0.0592041015625,
0.0293426513671875,
-0.036468505859375,
-0.0193328857421875,
0.051666259765625,
0.0533447265625,
0.052154541015625,
-0.010009765625,
0.029541015625,
0.050262451171875,
0.0200347900390625,
0.0184326171875,
0.07354736328125,
0.0090484619140625,
-0.0269012451171875,
-0.0037689208984375,
-0.0689697265625,
-0.026519775390625,
0.02490234375,
-0.038665771484375,
0.034515380859375,
-0.063720703125,
0.025299072265625,
0.006175994873046875,
0.006465911865234375,
-0.0572509765625,
0.01079559326171875,
-0.0048065185546875,
0.05810546875,
-0.057952880859375,
0.04571533203125,
0.034332275390625,
-0.0389404296875,
-0.04949951171875,
-0.0216064453125,
0.0038852691650390625,
-0.08551025390625,
0.060516357421875,
0.00670623779296875,
0.01019287109375,
-0.0048370361328125,
-0.047698974609375,
-0.07525634765625,
0.081298828125,
-0.0005846023559570312,
-0.05670166015625,
-0.021026611328125,
-0.002407073974609375,
0.021240234375,
-0.031951904296875,
-0.0244293212890625,
0.0180816650390625,
0.038177490234375,
0.0369873046875,
-0.035552978515625,
0.01441192626953125,
-0.0020351409912109375,
0.00994110107421875,
0.00792694091796875,
-0.0115509033203125,
0.089111328125,
-0.054290771484375,
-0.0161285400390625,
0.0187835693359375,
0.032684326171875,
0.023284912109375,
0.0017271041870117188,
0.056304931640625,
0.0584716796875,
0.0221099853515625,
0.005420684814453125,
0.0673828125,
0.005779266357421875,
0.019500732421875,
0.1005859375,
-0.0489501953125,
0.07073974609375,
0.04327392578125,
-0.05462646484375,
0.04510498046875,
0.0267333984375,
-0.0141754150390625,
0.034454345703125,
0.0270843505859375,
0.004180908203125,
0.00598907470703125,
-0.003353118896484375,
-0.045440673828125,
0.02899169921875,
0.034149169921875,
-0.036865234375,
-0.049072265625,
0.01551055908203125,
-0.003871917724609375,
-0.00937652587890625,
-0.041290283203125,
0.064697265625,
0.0051422119140625,
-0.0168914794921875,
0.07342529296875,
-0.0274505615234375,
0.01535797119140625,
-0.052520751953125,
-0.041473388671875,
-0.01849365234375,
0.015380859375,
-0.0201568603515625,
-0.08514404296875,
0.018646240234375,
-0.0076141357421875,
-0.025390625,
-0.002185821533203125,
0.016326904296875,
-0.00910186767578125,
-0.0584716796875,
0.005771636962890625,
0.017425537109375,
0.048980712890625,
0.029937744140625,
-0.0653076171875,
0.04351806640625,
0.0028514862060546875,
0.00838470458984375,
0.007808685302734375,
-0.00362396240234375,
0.0229034423828125,
0.026885986328125,
0.0321044921875,
-0.0198822021484375,
-0.00150299072265625,
-0.0215606689453125,
0.05499267578125,
-0.05743408203125,
-0.029541015625,
-0.03009033203125,
0.048095703125,
0.00450897216796875,
-0.01617431640625,
0.057342529296875,
0.03271484375,
0.05462646484375,
-0.049530029296875,
0.002918243408203125,
-0.02587890625,
0.022186279296875,
-0.0723876953125,
0.06103515625,
-0.0504150390625,
0.0234222412109375,
-0.0255279541015625,
-0.093994140625,
-0.005558013916015625,
0.07318115234375,
-0.0080108642578125,
-0.0002868175506591797,
0.053192138671875,
0.053192138671875,
0.00018072128295898438,
-0.0159912109375,
0.0303955078125,
0.0333251953125,
0.011474609375,
0.031280517578125,
0.033447265625,
-0.0518798828125,
0.03717041015625,
-0.0308685302734375,
-0.00571441650390625,
-0.02337646484375,
-0.07379150390625,
-0.052276611328125,
-0.041015625,
-0.0278472900390625,
-0.042755126953125,
0.01105499267578125,
0.05712890625,
0.07196044921875,
-0.0606689453125,
-0.033599853515625,
0.015960693359375,
0.04132080078125,
-0.026641845703125,
-0.01522064208984375,
0.033966064453125,
0.0102996826171875,
-0.0479736328125,
0.04022216796875,
0.01316070556640625,
0.0281982421875,
-0.038177490234375,
-0.030487060546875,
-0.052581787109375,
0.01345062255859375,
0.0521240234375,
0.03814697265625,
-0.05010986328125,
-0.0110931396484375,
-0.022705078125,
0.00637054443359375,
0.0106048583984375,
0.006168365478515625,
-0.049285888671875,
0.01357269287109375,
0.0305633544921875,
0.0011682510375976562,
0.0276336669921875,
-0.01543426513671875,
0.017578125,
-0.05517578125,
-0.0218353271484375,
0.0190887451171875,
0.036773681640625,
0.0000966191291809082,
-0.0206451416015625,
0.044921875,
-0.01068878173828125,
-0.034210205078125,
-0.04998779296875,
0.016998291015625,
-0.08673095703125,
-0.026519775390625,
0.0692138671875,
0.01214599609375,
-0.045257568359375,
-0.00421905517578125,
-0.048583984375,
-0.0202484130859375,
-0.0289764404296875,
0.06317138671875,
0.043487548828125,
-0.00839996337890625,
-0.0201568603515625,
-0.04736328125,
0.019195556640625,
0.004848480224609375,
-0.07696533203125,
-0.0158843994140625,
0.030517578125,
0.0186614990234375,
0.0616455078125,
0.018829345703125,
-0.016845703125,
0.0257110595703125,
0.0201263427734375,
0.0021152496337890625,
0.0167236328125,
-0.01371002197265625,
-0.02093505859375,
-0.00469207763671875,
-0.0260009765625,
-0.03826904296875
]
] |
EleutherAI/gpt-neox-20b | 2023-06-21T14:34:00.000Z | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"en",
"dataset:EleutherAI/pile",
"arxiv:2204.06745",
"arxiv:2101.00027",
"arxiv:2201.07311",
"arxiv:2104.09864",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | EleutherAI | null | null | EleutherAI/gpt-neox-20b | 442 | 42,268 | transformers | 2022-04-07T20:28:29 | ---
language:
- en
tags:
- pytorch
- causal-lm
license: apache-2.0
datasets:
- EleutherAI/pile
---
GPT-NeoX-20B is a 20 billion parameter autoregressive language model trained
on [the Pile](https://pile.eleuther.ai/) using the [GPT-NeoX
library](https://github.com/EleutherAI/gpt-neox). Its architecture intentionally
resembles that of GPT-3, and is almost identical to that of [GPT-J-
6B](https://huggingface.co/EleutherAI/gpt-j-6B). Its training dataset contains
a multitude of English-language texts, reflecting the general-purpose nature
of this model. See the [accompanying paper](https://arxiv.org/abs/2204.06745)
for details about model architecture (including how it differs from GPT-3),
training procedure, and additional evaluations.
### Model details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [GPT-NeoX-20B: An Open-Source Autoregressive Language
Model](https://arxiv.org/abs/2204.06745). For details about the training dataset,
see [the Pile paper](https://arxiv.org/abs/2101.00027), and [its data
sheet](https://arxiv.org/abs/2201.07311).
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing GPT-NeoX-20B documentation before asking about the model
on Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure style="width:30em">
| Hyperparameter | Value |
| ---------------------- | ----------- |
| n<sub>parameters</sub> | 20554567680 |
| n<sub>layers</sub> | 44 |
| d<sub>model</sub> | 6144 |
| n<sub>heads</sub> | 64 |
| d<sub>head</sub> | 96 |
| n<sub>vocab</sub> | 50257 |
| Sequence Length | 2048 |
| Learning Rate | 0.97 x 10<sup>-5</sup> |
| Positional Encoding | [Rotary Position Embedding (RoPE)](https://arxiv.org/abs/2104.09864) |
</figure>
### Uses and limitations
#### Intended use
GPT-NeoX-20B was developed primarily for research purposes. It learns an inner
representation of the English language that can be used to extract features
useful for downstream tasks.
In addition to scientific uses, you may also further fine-tune and adapt
GPT-NeoX-20B for deployment, as long as your use is in accordance with the
Apache 2.0 license. This model works with the [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained GPT-NeoX-20B as a basis for your fine-tuned model, please note that
you need to conduct your own risk and bias assessment.
#### Out-of-scope use
GPT-NeoX-20B is **not** intended for deployment as-is. It is not a product
and cannot be used for human-facing interactions without supervision.
GPT-NeoX-20B has not been fine-tuned for downstream tasks for which language
models are commonly deployed, such as writing genre prose, or commercial
chatbots. This means GPT-NeoX-20B will likely **not** respond to a given prompt
the way products such as ChatGPT do. This is because, unlike GPT-NeoX-20B,
ChatGPT was fine-tuned using methods such as Reinforcement Learning from Human
Feedback (RLHF) to better “understand” human instructions and dialogue.
This model is English-language only, and thus cannot be used for translation
or generating text in other languages.
#### Limitations and biases
The core functionality of GPT-NeoX-20B is to take a string of text and predict
the next token. Remember that the statistically most likely next token need
not result in the most “accurate” text. Never rely on GPT-NeoX-20B to produce
factually accurate output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
GPT-NeoX-20B may produce socially unacceptable or undesirable text, *even if*
the prompt itself does not include anything explicitly offensive.
We recommend curating the outputs of this model before presenting it to a human
reader. Please inform your audience that you are using artificially generated
text.
#### How to use
If you simply want to try out some prompts, check out [this
playground](https://20b.eleuther.ai/).
GPT-NeoX-20B can be loaded using the `AutoModelForCausalLM` functionality:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/gpt-neox-20b")
```
### Training
#### Training dataset
The Pile is a 825GiB general-purpose dataset in English. It was created by
EleutherAI specifically for training large language models. It contains texts
from 22 diverse sources, roughly broken down into five categories: academic
writing (e.g. arXiv), internet (e.g. CommonCrawl), prose (e.g. Project
Gutenberg), dialogue (e.g. YouTube subtitles), and miscellaneous (e.g. GitHub,
Enron Emails). See [the Pile paper](https://arxiv.org/abs/2101.00027) for
a breakdown of all data sources, methodology, and a discussion of ethical
implications. Consult [the datasheet](https://arxiv.org/abs/2201.07311) for
more detailed documentation about the Pile and its component datasets. The
Pile can be downloaded from the [official website](https://pile.eleuther.ai/),
or from a [community mirror](https://the-eye.eu/public/AI/pile/).
The Pile was **not** deduplicated before being used to train GPT-NeoX-20B.
#### Training procedure
GPT-NeoX-20B was trained with a batch size of approximately 3.15M tokens
(1538 sequences of 2048 tokens each), for a total of 150,000 steps. Tensor
parallelism and pipeline parallelism were used to distribute the model across
GPUs. Additional details about the training procedure are in [Section 3 of
the accompanying paper](https://arxiv.org/abs/2204.06745).
### Evaluations
<figure style="width:55em">
| Model | OpenAI’s LAMBADA | SciQ | PIQA | TriviaQA | ARC (Challenge) |
| ------------- | :--------------: | :-----------: | :-----------: | :-----------: | :-------------: |
| GPT-J-6B | 0.683 ± 0.006 | 0.910 ± 0.009 | 0.752 ± 0.010 | 0.170 ± 0.004 | 0.340 ± 0.014 |
| FairSeq 6.7B | 0.673 ± 0.007 | 0.895 ± 0.010 | 0.762 ± 0.010 | 0.221 ± 0.004 | 0.329 ± 0.014 |
| GPT-3 Curie | 0.693 ± 0.006 | 0.918 ± 0.009 | 0.767 ± 0.010 | 0.196 ± 0.004 | 0.334 ± 0.014 |
| FairSeq 13B | 0.709 ± 0.006 | 0.910 ± 0.009 | 0.769 ± 0.010 | 0.270 ± 0.004 | 0.345 ± 0.014 |
| GPT-NeoX-20B | 0.720 ± 0.006 | 0.928 ± 0.008 | 0.779 ± 0.010 | 0.259 ± 0.004 | 0.380 ± 0.014 |
| GPT-3 DaVinci | 0.752 ± 0.006 | 0.949 ± 0.007 | 0.791 ± 0.009 | 0.409 ± 0.005 | 0.435 ± 0.014 |
<figcaption>Zero-shot performance on selected natural language tasks.</figcaption>
</figure>
This is a heavily abridged version of the evaluation results. Appendix D of the
[GPT-NeoX-20B paper](https://arxiv.org/abs/2204.06745) compares more model
sizes, and contains additional evaluations, including on: zero and five-shot
natural language tasks, zero and five-shot Basic Arithmetic and MATH,
and zero-shot Hendrycks tasks.
### BibTeX
To cite the GPT-NeoX-20B paper:
```
@misc{https://doi.org/10.48550/arxiv.2204.06745,
doi = {10.48550/ARXIV.2204.06745},
url = {https://arxiv.org/abs/2204.06745},
author = {Black, Sid and Biderman, Stella and Hallahan, Eric and Anthony, Quentin and Gao, Leo and Golding, Laurence and He, Horace and Leahy, Connor and McDonell, Kyle and Phang, Jason and Pieler, Michael and Prashanth, USVSN Sai and Purohit, Shivanshu and Reynolds, Laria and Tow, Jonathan and Wang, Ben and Weinbach, Samuel},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {GPT-NeoX-20B: An Open-Source Autoregressive Language Model},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
``` | 8,275 | [
[
-0.0360107421875,
-0.073486328125,
0.0279541015625,
0.005397796630859375,
-0.0200347900390625,
-0.0009608268737792969,
-0.01129913330078125,
-0.0478515625,
0.00881195068359375,
0.0199737548828125,
-0.02978515625,
-0.035980224609375,
-0.049102783203125,
0.01343536376953125,
-0.041748046875,
0.09649658203125,
0.004638671875,
-0.028533935546875,
-0.00209808349609375,
0.007068634033203125,
-0.0019893646240234375,
-0.0413818359375,
-0.0626220703125,
-0.0172576904296875,
0.024322509765625,
-0.011016845703125,
0.05279541015625,
0.0604248046875,
0.0203094482421875,
0.0216522216796875,
-0.01177978515625,
-0.00827789306640625,
-0.0260467529296875,
-0.0271148681640625,
0.0009331703186035156,
-0.01329803466796875,
-0.04833984375,
0.006046295166015625,
0.042083740234375,
0.03875732421875,
-0.018310546875,
0.0107421875,
0.00785064697265625,
0.0240325927734375,
-0.02349853515625,
0.005939483642578125,
-0.02886962890625,
-0.01503753662109375,
-0.0011568069458007812,
0.00823974609375,
-0.017913818359375,
-0.01194000244140625,
0.00792694091796875,
-0.05645751953125,
0.01715087890625,
0.0003833770751953125,
0.091796875,
0.01343536376953125,
-0.0175933837890625,
-0.0160369873046875,
-0.0584716796875,
0.05657958984375,
-0.062286376953125,
0.0252838134765625,
0.03204345703125,
0.004398345947265625,
0.01885986328125,
-0.056549072265625,
-0.0440673828125,
-0.015594482421875,
-0.0092010498046875,
0.0275421142578125,
-0.032440185546875,
-0.00789642333984375,
0.03192138671875,
0.024078369140625,
-0.07440185546875,
0.01004791259765625,
-0.0213623046875,
-0.0147857666015625,
0.040496826171875,
0.018463134765625,
0.020538330078125,
-0.02886962890625,
-0.031341552734375,
-0.039764404296875,
-0.039154052734375,
0.0009636878967285156,
0.041900634765625,
0.012237548828125,
-0.038360595703125,
0.0275726318359375,
-0.0033893585205078125,
0.053924560546875,
0.0037899017333984375,
0.0006895065307617188,
0.0298614501953125,
-0.045166015625,
-0.0207061767578125,
-0.0220947265625,
0.1038818359375,
0.007007598876953125,
0.015472412109375,
-0.0016498565673828125,
-0.0202484130859375,
0.0147857666015625,
0.01549530029296875,
-0.0738525390625,
-0.014617919921875,
0.02093505859375,
-0.014190673828125,
-0.0138702392578125,
0.0056304931640625,
-0.043731689453125,
0.0021038055419921875,
-0.0230255126953125,
0.031585693359375,
-0.0491943359375,
-0.02801513671875,
0.007411956787109375,
-0.0139923095703125,
0.01666259765625,
0.022430419921875,
-0.057647705078125,
0.0450439453125,
0.04827880859375,
0.06103515625,
-0.00007265806198120117,
-0.0249786376953125,
-0.01506805419921875,
-0.0115509033203125,
-0.0184326171875,
0.053680419921875,
-0.03399658203125,
-0.0209503173828125,
-0.0196685791015625,
0.0111846923828125,
-0.02215576171875,
-0.0258941650390625,
0.032318115234375,
-0.01153564453125,
0.05902099609375,
0.006420135498046875,
-0.033355712890625,
-0.01384735107421875,
0.0245513916015625,
-0.03662109375,
0.09039306640625,
0.0308837890625,
-0.0665283203125,
0.020172119140625,
-0.0419921875,
-0.004886627197265625,
0.0088958740234375,
-0.01080322265625,
-0.0389404296875,
-0.022186279296875,
0.0242919921875,
0.0215301513671875,
-0.029022216796875,
0.024139404296875,
-0.011627197265625,
-0.034515380859375,
-0.00433349609375,
-0.030548095703125,
0.0736083984375,
0.0117950439453125,
-0.0533447265625,
0.0014019012451171875,
-0.058135986328125,
-0.003566741943359375,
0.0234375,
-0.01093292236328125,
-0.0220947265625,
-0.022247314453125,
0.0099639892578125,
0.027740478515625,
0.0157623291015625,
-0.040008544921875,
0.01983642578125,
-0.033294677734375,
0.043609619140625,
0.043304443359375,
-0.012115478515625,
0.029632568359375,
-0.02154541015625,
0.0523681640625,
-0.01361846923828125,
0.0164642333984375,
-0.0084991455078125,
-0.04864501953125,
-0.04327392578125,
-0.0209808349609375,
0.028717041015625,
0.0599365234375,
-0.0465087890625,
0.026519775390625,
-0.02020263671875,
-0.048675537109375,
-0.032196044921875,
-0.00945281982421875,
0.037384033203125,
0.029541015625,
0.036102294921875,
-0.0177154541015625,
-0.0382080078125,
-0.0599365234375,
0.003360748291015625,
-0.0240631103515625,
-0.00965118408203125,
0.034515380859375,
0.051788330078125,
-0.032623291015625,
0.056854248046875,
-0.0230255126953125,
0.005115509033203125,
-0.0132293701171875,
0.034912109375,
0.0367431640625,
0.0282440185546875,
0.044158935546875,
-0.036163330078125,
-0.050750732421875,
0.01238250732421875,
-0.04754638671875,
0.0013837814331054688,
-0.00997161865234375,
0.00885772705078125,
0.0288848876953125,
0.032501220703125,
-0.057464599609375,
0.02667236328125,
0.04876708984375,
-0.0347900390625,
0.05743408203125,
-0.0236663818359375,
-0.0093841552734375,
-0.08740234375,
0.0275421142578125,
0.0035114288330078125,
-0.016357421875,
-0.031341552734375,
-0.0118408203125,
0.002002716064453125,
-0.01226043701171875,
-0.03289794921875,
0.06402587890625,
-0.03375244140625,
0.00911712646484375,
-0.0203094482421875,
0.01038360595703125,
-0.007312774658203125,
0.043914794921875,
0.0204925537109375,
0.056884765625,
0.046875,
-0.047119140625,
0.0090789794921875,
0.007587432861328125,
-0.005107879638671875,
0.034576416015625,
-0.07452392578125,
0.028350830078125,
-0.005023956298828125,
0.012298583984375,
-0.056365966796875,
0.0099945068359375,
0.02703857421875,
-0.042938232421875,
0.0223846435546875,
-0.01503753662109375,
-0.027496337890625,
-0.040771484375,
-0.0196533203125,
0.0229949951171875,
0.045654296875,
-0.0103759765625,
0.03753662109375,
0.0137939453125,
-0.0200958251953125,
-0.06195068359375,
-0.0302581787109375,
0.00799560546875,
-0.0228729248046875,
-0.03460693359375,
0.0377197265625,
-0.005863189697265625,
-0.00908660888671875,
0.0185546875,
0.01517486572265625,
0.01296234130859375,
-0.005641937255859375,
0.01280975341796875,
0.0200042724609375,
-0.0003497600555419922,
-0.0159454345703125,
-0.0186614990234375,
-0.0282745361328125,
0.0016450881958007812,
-0.03021240234375,
0.06109619140625,
-0.0251922607421875,
0.004795074462890625,
-0.028717041015625,
0.0183868408203125,
0.037994384765625,
-0.000007033348083496094,
0.051788330078125,
0.0792236328125,
-0.026031494140625,
0.0013561248779296875,
-0.02484130859375,
-0.0273590087890625,
-0.032684326171875,
0.04400634765625,
-0.0172576904296875,
-0.069580078125,
0.0423583984375,
0.026519775390625,
0.0080108642578125,
0.0550537109375,
0.037109375,
0.00276947021484375,
0.0841064453125,
0.057891845703125,
-0.01049041748046875,
0.0355224609375,
-0.04620361328125,
0.006099700927734375,
-0.07403564453125,
-0.0008130073547363281,
-0.045135498046875,
-0.0114898681640625,
-0.0693359375,
-0.03289794921875,
0.01654052734375,
-0.004833221435546875,
-0.044281005859375,
0.05804443359375,
-0.0472412109375,
0.006336212158203125,
0.050537109375,
-0.01268768310546875,
0.0099334716796875,
-0.004657745361328125,
-0.0231475830078125,
0.00469970703125,
-0.06658935546875,
-0.0360107421875,
0.0843505859375,
0.0275726318359375,
0.045684814453125,
-0.00809478759765625,
0.052520751953125,
0.0021915435791015625,
0.0238494873046875,
-0.043487548828125,
0.041259765625,
-0.0175018310546875,
-0.05029296875,
-0.0321044921875,
-0.061309814453125,
-0.09942626953125,
0.0124664306640625,
-0.007244110107421875,
-0.06292724609375,
0.016448974609375,
-0.003192901611328125,
-0.032257080078125,
0.0196075439453125,
-0.045135498046875,
0.07183837890625,
-0.0229339599609375,
-0.027740478515625,
-0.01068878173828125,
-0.04150390625,
0.0105438232421875,
0.001857757568359375,
0.0240631103515625,
0.0142669677734375,
-0.00534820556640625,
0.0684814453125,
-0.03326416015625,
0.063232421875,
-0.004390716552734375,
-0.0014123916625976562,
0.02569580078125,
-0.0005326271057128906,
0.052886962890625,
0.004764556884765625,
0.00856781005859375,
0.0233612060546875,
0.00362396240234375,
-0.026153564453125,
-0.02813720703125,
0.037261962890625,
-0.0841064453125,
-0.026092529296875,
-0.052886962890625,
-0.040069580078125,
0.011962890625,
0.0225830078125,
0.025054931640625,
0.0341796875,
-0.0189971923828125,
0.01194000244140625,
0.0293426513671875,
-0.042388916015625,
0.045989990234375,
0.035980224609375,
-0.018463134765625,
-0.046783447265625,
0.07537841796875,
0.0138092041015625,
0.021087646484375,
0.034332275390625,
0.02471923828125,
-0.03558349609375,
-0.03656005859375,
-0.0367431640625,
0.045745849609375,
-0.0257568359375,
0.004726409912109375,
-0.06878662109375,
-0.0186767578125,
-0.03607177734375,
0.0027484893798828125,
-0.034912109375,
-0.0310516357421875,
-0.0067138671875,
-0.00580596923828125,
0.0263824462890625,
0.0523681640625,
-0.004360198974609375,
0.020751953125,
-0.041473388671875,
0.01496124267578125,
0.030914306640625,
0.01020050048828125,
-0.01885986328125,
-0.056060791015625,
-0.01947021484375,
0.0090789794921875,
-0.0196685791015625,
-0.0423583984375,
0.049957275390625,
0.005107879638671875,
0.036224365234375,
0.0221710205078125,
-0.010650634765625,
0.0380859375,
-0.027069091796875,
0.061126708984375,
0.00977325439453125,
-0.058868408203125,
0.032867431640625,
-0.052734375,
0.03289794921875,
0.0190887451171875,
0.051788330078125,
-0.05499267578125,
-0.02923583984375,
-0.08837890625,
-0.08099365234375,
0.0567626953125,
0.016510009765625,
0.005992889404296875,
-0.00942230224609375,
0.0178985595703125,
0.0017910003662109375,
0.01297760009765625,
-0.06536865234375,
-0.01366424560546875,
-0.0249786376953125,
-0.002796173095703125,
-0.02117919921875,
-0.00374603271484375,
-0.005462646484375,
-0.02130126953125,
0.057891845703125,
-0.01361083984375,
0.054840087890625,
0.006107330322265625,
-0.0031871795654296875,
0.00476837158203125,
0.0133819580078125,
0.0421142578125,
0.050537109375,
-0.0297393798828125,
0.0014705657958984375,
0.0089569091796875,
-0.0618896484375,
-0.0033435821533203125,
0.0311279296875,
-0.0325927734375,
-0.00904083251953125,
0.0237579345703125,
0.08013916015625,
-0.001323699951171875,
-0.03515625,
0.02374267578125,
-0.0161590576171875,
-0.03839111328125,
-0.017547607421875,
-0.0053253173828125,
0.009521484375,
-0.002567291259765625,
0.01128387451171875,
-0.0081939697265625,
-0.002307891845703125,
-0.045166015625,
0.01837158203125,
0.031768798828125,
-0.03851318359375,
-0.038818359375,
0.055877685546875,
0.00026535987854003906,
-0.021240234375,
0.06573486328125,
-0.030609130859375,
-0.035491943359375,
0.042755126953125,
0.044158935546875,
0.067626953125,
-0.016632080078125,
0.04071044921875,
0.05914306640625,
0.04217529296875,
0.00339508056640625,
0.0121002197265625,
0.0107269287109375,
-0.050262451171875,
-0.0474853515625,
-0.047393798828125,
-0.03558349609375,
0.0256195068359375,
-0.0302581787109375,
0.014984130859375,
-0.035369873046875,
-0.0193328857421875,
-0.020538330078125,
0.0178375244140625,
-0.0540771484375,
0.0248870849609375,
0.015777587890625,
0.04766845703125,
-0.06573486328125,
0.051727294921875,
0.06402587890625,
-0.031982421875,
-0.065673828125,
-0.0182342529296875,
-0.005985260009765625,
-0.0640869140625,
0.02838134765625,
0.007183074951171875,
0.01023101806640625,
0.0116119384765625,
-0.029632568359375,
-0.06939697265625,
0.08154296875,
0.0280303955078125,
-0.040985107421875,
0.0015649795532226562,
0.031341552734375,
0.04840087890625,
-0.007709503173828125,
0.07244873046875,
0.0225830078125,
0.037109375,
-0.01256561279296875,
-0.0853271484375,
0.01482391357421875,
-0.04656982421875,
-0.01200103759765625,
0.0194854736328125,
-0.053863525390625,
0.08026123046875,
-0.00017654895782470703,
-0.0141754150390625,
-0.0130615234375,
0.021087646484375,
0.021331787109375,
0.0019092559814453125,
0.043701171875,
0.076171875,
0.05511474609375,
-0.022857666015625,
0.104248046875,
-0.0309906005859375,
0.03466796875,
0.066162109375,
0.01177215576171875,
0.050689697265625,
0.01363372802734375,
-0.03253173828125,
0.055328369140625,
0.051910400390625,
0.01049041748046875,
0.0204620361328125,
-0.0007886886596679688,
0.0017385482788085938,
-0.01372528076171875,
0.001354217529296875,
-0.040985107421875,
0.0194854736328125,
0.02447509765625,
-0.0225372314453125,
-0.01317596435546875,
-0.01177978515625,
0.022705078125,
-0.0193939208984375,
0.0023174285888671875,
0.056243896484375,
0.01496124267578125,
-0.0494384765625,
0.071533203125,
0.00252532958984375,
0.05377197265625,
-0.054229736328125,
0.00678253173828125,
-0.01197052001953125,
0.01418304443359375,
-0.005016326904296875,
-0.052093505859375,
0.0190887451171875,
0.002292633056640625,
0.0023632049560546875,
-0.0284271240234375,
0.035400390625,
-0.01216888427734375,
-0.041351318359375,
0.0306549072265625,
0.044677734375,
0.0176544189453125,
-0.0272979736328125,
-0.08258056640625,
-0.004486083984375,
-0.0130462646484375,
-0.033935546875,
0.0367431640625,
0.037109375,
-0.01036834716796875,
0.04473876953125,
0.056488037109375,
0.0011587142944335938,
-0.01396942138671875,
0.0151824951171875,
0.0643310546875,
-0.055633544921875,
-0.039764404296875,
-0.060272216796875,
0.044952392578125,
-0.005474090576171875,
-0.045166015625,
0.06085205078125,
0.043365478515625,
0.06982421875,
0.0110931396484375,
0.059295654296875,
-0.0252685546875,
0.031768798828125,
-0.01464080810546875,
0.0308837890625,
-0.033203125,
0.004833221435546875,
-0.043701171875,
-0.08935546875,
-0.004848480224609375,
0.053924560546875,
-0.03741455078125,
0.0257568359375,
0.06890869140625,
0.055389404296875,
0.00447845458984375,
-0.010467529296875,
0.01090240478515625,
0.0230255126953125,
0.024566650390625,
0.061676025390625,
0.05474853515625,
-0.0494384765625,
0.04766845703125,
-0.040252685546875,
-0.02484130859375,
-0.00018668174743652344,
-0.0635986328125,
-0.06365966796875,
-0.033111572265625,
-0.037750244140625,
-0.0263519287109375,
0.00872802734375,
0.046142578125,
0.0589599609375,
-0.049072265625,
-0.033660888671875,
-0.0252685546875,
-0.01019287109375,
-0.049346923828125,
-0.01788330078125,
0.0389404296875,
-0.003734588623046875,
-0.07281494140625,
0.0168914794921875,
0.01123809814453125,
0.005947113037109375,
-0.01442718505859375,
-0.020599365234375,
-0.023651123046875,
-0.00634765625,
0.0357666015625,
0.0247955322265625,
-0.02886962890625,
-0.016448974609375,
0.03582763671875,
-0.004932403564453125,
0.002838134765625,
0.03155517578125,
-0.064208984375,
0.013671875,
0.04058837890625,
0.029571533203125,
0.061767578125,
0.00836944580078125,
0.03997802734375,
-0.03192138671875,
0.0105743408203125,
0.027374267578125,
0.0196380615234375,
0.0229339599609375,
-0.0244903564453125,
0.0501708984375,
0.039215087890625,
-0.050048828125,
-0.049896240234375,
-0.0029201507568359375,
-0.08184814453125,
-0.01433563232421875,
0.09808349609375,
-0.0001823902130126953,
-0.024688720703125,
-0.01092529296875,
-0.01053619384765625,
0.01491546630859375,
-0.028656005859375,
0.047576904296875,
0.049713134765625,
-0.00485992431640625,
-0.035125732421875,
-0.04937744140625,
0.0269622802734375,
0.036865234375,
-0.061126708984375,
0.0028247833251953125,
0.01287841796875,
0.020599365234375,
0.0231475830078125,
0.045379638671875,
-0.0236358642578125,
0.0161895751953125,
0.006359100341796875,
0.0210723876953125,
-0.0101470947265625,
-0.0134124755859375,
-0.01393890380859375,
-0.00017535686492919922,
-0.0192413330078125,
0.01462554931640625
]
] |
cross-encoder/stsb-roberta-base | 2021-08-05T08:41:58.000Z | [
"transformers",
"pytorch",
"jax",
"roberta",
"text-classification",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | cross-encoder | null | null | cross-encoder/stsb-roberta-base | 2 | 41,512 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
---
# Cross-Encoder for Quora Duplicate Questions Detection
This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class.
## Training Data
This model was trained on the [STS benchmark dataset](http://ixa2.si.ehu.eus/stswiki/index.php/STSbenchmark). The model will predict a score between 0 and 1 how for the semantic similarity of two sentences.
## Usage and Performance
Pre-trained models can be used like this:
```
from sentence_transformers import CrossEncoder
model = CrossEncoder('model_name')
scores = model.predict([('Sentence 1', 'Sentence 2'), ('Sentence 3', 'Sentence 4')])
```
The model will predict scores for the pairs `('Sentence 1', 'Sentence 2')` and `('Sentence 3', 'Sentence 4')`.
You can use this model also without sentence_transformers and by just using Transformers ``AutoModel`` class | 941 | [
[
-0.01690673828125,
-0.060394287109375,
0.01953125,
0.01727294921875,
-0.02838134765625,
-0.0025272369384765625,
0.012176513671875,
-0.01287078857421875,
0.00896453857421875,
0.0518798828125,
-0.051177978515625,
-0.031982421875,
-0.034912109375,
0.03314208984375,
-0.06365966796875,
0.0767822265625,
-0.01123046875,
0.0297698974609375,
-0.052093505859375,
-0.0252227783203125,
-0.0271148681640625,
-0.032196044921875,
-0.03619384765625,
-0.0186614990234375,
0.00988006591796875,
0.025970458984375,
0.028564453125,
0.0086822509765625,
0.0244903564453125,
0.0301513671875,
-0.0011472702026367188,
0.00782012939453125,
-0.017791748046875,
0.00536346435546875,
-0.023223876953125,
-0.0455322265625,
0.01268768310546875,
-0.013153076171875,
0.0279388427734375,
0.018524169921875,
-0.01024627685546875,
0.035064697265625,
0.0027942657470703125,
0.0221099853515625,
-0.010772705078125,
-0.01508331298828125,
-0.052947998046875,
0.0147857666015625,
0.005443572998046875,
-0.0208740234375,
-0.0042724609375,
-0.0465087890625,
-0.00510406494140625,
-0.041900634765625,
0.0287017822265625,
0.0009074211120605469,
0.0823974609375,
0.025970458984375,
-0.0367431640625,
-0.0160980224609375,
-0.0311126708984375,
0.0611572265625,
-0.038787841796875,
0.01366424560546875,
0.0271148681640625,
0.0240325927734375,
0.0067596435546875,
-0.0626220703125,
-0.07562255859375,
0.00891876220703125,
-0.016510009765625,
0.0089569091796875,
-0.0325927734375,
-0.0399169921875,
0.020751953125,
0.026214599609375,
-0.07452392578125,
-0.003803253173828125,
-0.057098388671875,
-0.02667236328125,
0.029296875,
0.033355712890625,
0.01898193359375,
-0.043304443359375,
-0.056396484375,
-0.0145721435546875,
-0.0093994140625,
0.018646240234375,
0.0263824462890625,
-0.002849578857421875,
-0.00745391845703125,
0.04461669921875,
-0.0308380126953125,
0.03997802734375,
0.0158843994140625,
0.0167388916015625,
0.05511474609375,
-0.039337158203125,
-0.0010204315185546875,
-0.0193023681640625,
0.07879638671875,
0.019195556640625,
0.036285400390625,
0.004261016845703125,
0.00012743473052978516,
0.0129852294921875,
0.03143310546875,
-0.044708251953125,
-0.006351470947265625,
0.0201568603515625,
-0.0298919677734375,
-0.031890869140625,
0.01039886474609375,
-0.034576416015625,
0.0103607177734375,
-0.0157318115234375,
0.059051513671875,
-0.038299560546875,
0.0010938644409179688,
0.02777099609375,
-0.02850341796875,
0.030914306640625,
-0.0014791488647460938,
-0.03070068359375,
0.0340576171875,
0.042022705078125,
0.045074462890625,
-0.01184844970703125,
-0.04815673828125,
-0.0256805419921875,
-0.02459716796875,
0.0090484619140625,
0.0718994140625,
-0.0287322998046875,
-0.01282501220703125,
-0.0121917724609375,
0.0218658447265625,
-0.01149749755859375,
-0.03912353515625,
0.045074462890625,
-0.0423583984375,
0.0694580078125,
-0.022430419921875,
-0.050750732421875,
-0.035064697265625,
0.043304443359375,
-0.0560302734375,
0.09112548828125,
0.0227203369140625,
-0.06787109375,
0.0123748779296875,
-0.02899169921875,
-0.035308837890625,
0.006237030029296875,
-0.01055908203125,
-0.05194091796875,
-0.01708984375,
0.0209808349609375,
0.01349639892578125,
-0.0240631103515625,
0.00923919677734375,
-0.006282806396484375,
-0.03009033203125,
0.0279693603515625,
-0.019744873046875,
0.060516357421875,
0.003299713134765625,
-0.0214691162109375,
0.007781982421875,
-0.048828125,
0.0283966064453125,
0.01476287841796875,
-0.021453857421875,
-0.02032470703125,
-0.034912109375,
0.0216522216796875,
0.0293731689453125,
0.027557373046875,
-0.05657958984375,
-0.0171966552734375,
-0.0162811279296875,
0.0216217041015625,
0.03546142578125,
0.01374053955078125,
0.013916015625,
-0.03472900390625,
0.068115234375,
0.020599365234375,
0.01322174072265625,
0.011383056640625,
-0.041961669921875,
-0.0526123046875,
0.02398681640625,
0.0236053466796875,
0.06494140625,
-0.059844970703125,
0.060333251953125,
-0.010986328125,
-0.04150390625,
-0.05859375,
0.0190582275390625,
0.023101806640625,
0.025146484375,
0.04925537109375,
-0.0167083740234375,
-0.054962158203125,
-0.07318115234375,
-0.03826904296875,
0.0024700164794921875,
0.0010662078857421875,
0.0009412765502929688,
0.06756591796875,
-0.0078582763671875,
0.07763671875,
-0.03466796875,
-0.0159912109375,
-0.028167724609375,
0.0110931396484375,
0.0040435791015625,
0.050048828125,
0.03399658203125,
-0.07745361328125,
-0.049102783203125,
-0.0280914306640625,
-0.05645751953125,
0.0031986236572265625,
0.00010073184967041016,
-0.01279449462890625,
0.00687408447265625,
0.0309600830078125,
-0.054962158203125,
0.0307769775390625,
0.03167724609375,
-0.0174102783203125,
0.0283355712890625,
0.0009832382202148438,
0.0248565673828125,
-0.10723876953125,
-0.0008969306945800781,
-0.01042938232421875,
-0.0255279541015625,
-0.029754638671875,
0.005725860595703125,
0.0022754669189453125,
-0.003299713134765625,
-0.031646728515625,
0.035552978515625,
-0.007411956787109375,
0.00952911376953125,
-0.0147247314453125,
0.0082244873046875,
0.0233306884765625,
0.0408935546875,
0.0016021728515625,
0.0516357421875,
0.035003662109375,
-0.037933349609375,
0.040557861328125,
0.050537109375,
-0.05169677734375,
0.03521728515625,
-0.07879638671875,
0.0258636474609375,
-0.003376007080078125,
0.02325439453125,
-0.0732421875,
0.01270294189453125,
0.02752685546875,
-0.0526123046875,
-0.034393310546875,
0.0085906982421875,
-0.04119873046875,
-0.05438232421875,
-0.026947021484375,
0.04815673828125,
0.03619384765625,
-0.0465087890625,
0.04461669921875,
0.01654052734375,
-0.004543304443359375,
-0.053466796875,
-0.0704345703125,
-0.027191162109375,
-0.0023784637451171875,
-0.043853759765625,
0.01111602783203125,
-0.01409912109375,
0.020233154296875,
0.0191802978515625,
0.0037403106689453125,
-0.01568603515625,
-0.0064697265625,
0.0216522216796875,
0.0080413818359375,
-0.023468017578125,
0.01519012451171875,
0.011566162109375,
-0.0113525390625,
0.007778167724609375,
-0.02362060546875,
0.06439208984375,
-0.00852203369140625,
-0.023468017578125,
-0.03375244140625,
0.034820556640625,
0.0267333984375,
-0.0228271484375,
0.051605224609375,
0.049713134765625,
-0.02880859375,
-0.0171051025390625,
-0.04852294921875,
-0.0034122467041015625,
-0.03533935546875,
0.03607177734375,
-0.03326416015625,
-0.07122802734375,
0.03729248046875,
0.0235748291015625,
-0.03271484375,
0.038604736328125,
0.031463623046875,
0.006084442138671875,
0.055938720703125,
0.0357666015625,
-0.01468658447265625,
0.0178680419921875,
-0.01500701904296875,
0.0155487060546875,
-0.036285400390625,
-0.033416748046875,
-0.0341796875,
-0.0155181884765625,
-0.036865234375,
-0.04461669921875,
0.012725830078125,
-0.00030303001403808594,
-0.0102996826171875,
0.048370361328125,
-0.04901123046875,
0.05194091796875,
0.05230712890625,
0.01284027099609375,
0.0084686279296875,
0.015960693359375,
0.007114410400390625,
0.007068634033203125,
-0.052215576171875,
-0.020111083984375,
0.0751953125,
-0.00211334228515625,
0.04571533203125,
-0.0208740234375,
0.04864501953125,
0.01434326171875,
-0.017242431640625,
-0.03265380859375,
0.0518798828125,
-0.021697998046875,
-0.042938232421875,
-0.0196685791015625,
-0.04376220703125,
-0.08331298828125,
0.022064208984375,
-0.012054443359375,
-0.013885498046875,
0.005100250244140625,
-0.0166473388671875,
-0.03924560546875,
0.0191650390625,
-0.021728515625,
0.08660888671875,
-0.023345947265625,
0.004146575927734375,
-0.0254058837890625,
-0.038604736328125,
0.020782470703125,
-0.013336181640625,
-0.006053924560546875,
0.0025043487548828125,
-0.00223541259765625,
0.06402587890625,
-0.0276641845703125,
0.044677734375,
0.0059814453125,
0.014556884765625,
0.02838134765625,
-0.01326751708984375,
0.0085906982421875,
-0.003665924072265625,
-0.0036334991455078125,
0.0161590576171875,
0.00782012939453125,
-0.031036376953125,
-0.022979736328125,
0.05767822265625,
-0.07061767578125,
-0.027313232421875,
-0.02703857421875,
-0.0264129638671875,
0.0078887939453125,
0.01322174072265625,
0.04541015625,
0.0229949951171875,
-0.03009033203125,
0.004299163818359375,
0.0286865234375,
-0.022796630859375,
0.007076263427734375,
0.045318603515625,
-0.0106964111328125,
-0.041900634765625,
0.041748046875,
-0.003246307373046875,
0.012969970703125,
0.04376220703125,
0.00434112548828125,
-0.0286865234375,
-0.0137176513671875,
-0.01222991943359375,
0.012908935546875,
-0.057830810546875,
-0.029632568359375,
-0.07684326171875,
-0.04559326171875,
-0.0426025390625,
0.02276611328125,
-0.00875091552734375,
-0.044036865234375,
-0.0228271484375,
-0.019378662109375,
0.054351806640625,
0.04400634765625,
-0.0095977783203125,
0.015106201171875,
-0.06329345703125,
0.051361083984375,
0.0308990478515625,
0.0083160400390625,
-0.005870819091796875,
-0.06121826171875,
-0.01074981689453125,
-0.006061553955078125,
-0.020233154296875,
-0.04156494140625,
0.03265380859375,
-0.004604339599609375,
0.0404052734375,
0.0010309219360351562,
0.0041046142578125,
0.039276123046875,
-0.0244598388671875,
0.054656982421875,
0.01207733154296875,
-0.073974609375,
0.0438232421875,
0.01241302490234375,
0.03387451171875,
0.0555419921875,
0.05413818359375,
-0.04541015625,
-0.0267333984375,
-0.0457763671875,
-0.05645751953125,
0.054443359375,
0.02032470703125,
0.0308837890625,
-0.00708770751953125,
0.01343536376953125,
0.037506103515625,
0.00931549072265625,
-0.07666015625,
-0.017120361328125,
-0.038330078125,
-0.0312347412109375,
-0.0013523101806640625,
-0.0110931396484375,
0.01026153564453125,
-0.037872314453125,
0.047760009765625,
0.00907135009765625,
-0.003955841064453125,
0.01467132568359375,
-0.0188140869140625,
-0.006519317626953125,
0.023101806640625,
0.02142333984375,
0.022003173828125,
-0.0017576217651367188,
-0.016845703125,
0.0301666259765625,
-0.0250091552734375,
0.0013113021850585938,
0.01947021484375,
-0.0278472900390625,
0.0219268798828125,
0.0218048095703125,
0.06488037109375,
0.007236480712890625,
-0.03668212890625,
0.050445556640625,
-0.01306915283203125,
-0.0227813720703125,
-0.0633544921875,
-0.0039043426513671875,
0.00504302978515625,
0.034210205078125,
0.00945281982421875,
0.0175628662109375,
0.006305694580078125,
-0.035919189453125,
0.02935791015625,
0.01380157470703125,
-0.0228271484375,
-0.0142364501953125,
0.05010986328125,
0.0080718994140625,
-0.046844482421875,
0.05889892578125,
-0.01071929931640625,
-0.084228515625,
0.050750732421875,
0.0218658447265625,
0.05572509765625,
-0.00637054443359375,
0.0276641845703125,
0.050811767578125,
0.01525115966796875,
-0.02215576171875,
0.050750732421875,
-0.01146697998046875,
-0.072509765625,
0.0028781890869140625,
-0.042938232421875,
-0.0252532958984375,
0.02105712890625,
-0.07586669921875,
0.0250244140625,
-0.0223236083984375,
-0.00931549072265625,
-0.0006556510925292969,
-0.0103302001953125,
-0.0604248046875,
0.0189971923828125,
-0.0015802383422851562,
0.058135986328125,
-0.0687255859375,
0.055206298828125,
0.044281005859375,
-0.06109619140625,
-0.0545654296875,
-0.0033588409423828125,
-0.01136016845703125,
-0.06396484375,
0.049591064453125,
0.0269622802734375,
0.007167816162109375,
-0.01145172119140625,
-0.043487548828125,
-0.05889892578125,
0.07757568359375,
-0.01220703125,
-0.036590576171875,
-0.0007829666137695312,
0.03765869140625,
0.047393798828125,
-0.0235137939453125,
0.027862548828125,
0.036956787109375,
0.0175018310546875,
-0.0172576904296875,
-0.06365966796875,
0.010894775390625,
-0.051361083984375,
-0.01494598388671875,
0.00322723388671875,
-0.04608154296875,
0.08843994140625,
0.0015163421630859375,
-0.0029697418212890625,
0.045135498046875,
0.037322998046875,
0.0270538330078125,
0.0234527587890625,
0.04693603515625,
0.055419921875,
0.042388916015625,
0.006374359130859375,
0.0740966796875,
-0.0195465087890625,
0.034820556640625,
0.08966064453125,
-0.0241851806640625,
0.07159423828125,
0.022979736328125,
-0.0107574462890625,
0.0709228515625,
0.0258636474609375,
-0.045745849609375,
0.034515380859375,
0.0177764892578125,
0.01256561279296875,
-0.033935546875,
0.014739990234375,
-0.04150390625,
0.039306640625,
-0.005779266357421875,
-0.024688720703125,
-0.00322723388671875,
0.0168914794921875,
-0.02850341796875,
0.0311431884765625,
0.0007719993591308594,
0.043487548828125,
0.0016431808471679688,
-0.051971435546875,
0.036468505859375,
-0.00693511962890625,
0.0665283203125,
-0.0582275390625,
0.00177001953125,
-0.0232391357421875,
0.02587890625,
-0.00225067138671875,
-0.07183837890625,
0.013702392578125,
-0.00244140625,
-0.0303192138671875,
-0.0005140304565429688,
0.059112548828125,
-0.050750732421875,
-0.052093505859375,
0.043121337890625,
0.046295166015625,
0.016571044921875,
-0.01421356201171875,
-0.07666015625,
-0.0217437744140625,
0.004558563232421875,
0.002410888671875,
-0.0009260177612304688,
0.043548583984375,
0.00617218017578125,
0.049835205078125,
0.04425048828125,
-0.01959228515625,
0.0120391845703125,
0.0304718017578125,
0.05950927734375,
-0.07623291015625,
-0.0482177734375,
-0.04022216796875,
0.01436614990234375,
-0.0247344970703125,
-0.0487060546875,
0.0689697265625,
0.07122802734375,
0.0780029296875,
-0.0271453857421875,
0.054840087890625,
0.013763427734375,
0.0689697265625,
-0.028564453125,
0.046173095703125,
-0.053009033203125,
0.00937652587890625,
-0.0012750625610351562,
-0.04534912109375,
0.01044464111328125,
0.038604736328125,
-0.0182647705078125,
0.00384521484375,
0.07159423828125,
0.07391357421875,
-0.0119476318359375,
0.0189208984375,
0.001956939697265625,
0.0125579833984375,
-0.027191162109375,
0.057159423828125,
0.08154296875,
-0.0682373046875,
0.07550048828125,
-0.0224761962890625,
0.032073974609375,
0.004795074462890625,
-0.00936126708984375,
-0.07501220703125,
-0.038665771484375,
-0.032806396484375,
-0.034210205078125,
-0.0084228515625,
0.046783447265625,
0.03466796875,
-0.0831298828125,
-0.00562286376953125,
0.004703521728515625,
0.01043701171875,
-0.0128936767578125,
-0.02020263671875,
0.0168609619140625,
0.00113677978515625,
-0.04290771484375,
0.00830078125,
-0.004543304443359375,
-0.003444671630859375,
-0.00494384765625,
0.00238037109375,
-0.037506103515625,
0.01346588134765625,
0.0244903564453125,
0.008819580078125,
-0.052825927734375,
-0.0218963623046875,
0.0003209114074707031,
-0.0295562744140625,
0.0027408599853515625,
0.039886474609375,
-0.080322265625,
-0.0025482177734375,
0.05963134765625,
0.0362548828125,
0.0509033203125,
0.0175933837890625,
0.0290985107421875,
-0.033111572265625,
0.00243377685546875,
0.017333984375,
0.0276031494140625,
0.038970947265625,
-0.020172119140625,
0.0396728515625,
0.0252532958984375,
-0.03228759765625,
-0.04541015625,
-0.002655029296875,
-0.08258056640625,
-0.0290985107421875,
0.079833984375,
-0.005649566650390625,
-0.019439697265625,
-0.01312255859375,
-0.0099945068359375,
0.0229034423828125,
-0.014251708984375,
0.053985595703125,
0.032073974609375,
0.01380157470703125,
-0.00867462158203125,
-0.005649566650390625,
0.008636474609375,
0.0556640625,
-0.0694580078125,
-0.03515625,
0.003910064697265625,
0.064453125,
0.01279449462890625,
0.033294677734375,
-0.00518798828125,
0.037933349609375,
0.01143646240234375,
0.00768280029296875,
-0.0023288726806640625,
0.0134735107421875,
-0.0303802490234375,
0.01381683349609375,
-0.04815673828125,
-0.044158935546875
]
] |
facebook/mbart-large-50-many-to-many-mmt | 2023-09-28T16:42:59.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"safetensors",
"mbart",
"text2text-generation",
"mbart-50",
"translation",
"multilingual",
"ar",
"cs",
"de",
"en",
"es",
"et",
"fi",
"fr",
"gu",
"hi",
"it",
"ja",
"kk",
"ko",
"lt",
"lv",
"my",
"ne",
"nl",
"ro",
"ru",
"si",
"tr",
"vi",
"zh",
"af",
"az",
"bn",
"fa",
"he",
"hr",
"id",
"ka",
"km",
"mk",
"ml",
"mn",
"mr",
"pl",
"ps",
"pt",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"uk",
"ur",
"xh",
"gl",
"sl",
"arxiv:2008.00401",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | translation | facebook | null | null | facebook/mbart-large-50-many-to-many-mmt | 90 | 41,358 | transformers | 2022-03-02T23:29:05 | ---
language:
- multilingual
- ar
- cs
- de
- en
- es
- et
- fi
- fr
- gu
- hi
- it
- ja
- kk
- ko
- lt
- lv
- my
- ne
- nl
- ro
- ru
- si
- tr
- vi
- zh
- af
- az
- bn
- fa
- he
- hr
- id
- ka
- km
- mk
- ml
- mn
- mr
- pl
- ps
- pt
- sv
- sw
- ta
- te
- th
- tl
- uk
- ur
- xh
- gl
- sl
tags:
- mbart-50
pipeline_tag: translation
---
# mBART-50 many to many multilingual machine translation
This model is a fine-tuned checkpoint of [mBART-large-50](https://huggingface.co/facebook/mbart-large-50). `mbart-large-50-many-to-many-mmt` is fine-tuned for multilingual machine translation. It was introduced in [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) paper.
The model can translate directly between any pair of 50 languages. To translate into a target language, the target language id is forced as the first generated token. To force the target language id as the first generated token, pass the `forced_bos_token_id` parameter to the `generate` method.
```python
from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
article_hi = "संयुक्त राष्ट्र के प्रमुख का कहना है कि सीरिया में कोई सैन्य समाधान नहीं है"
article_ar = "الأمين العام للأمم المتحدة يقول إنه لا يوجد حل عسكري في سوريا."
model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
# translate Hindi to French
tokenizer.src_lang = "hi_IN"
encoded_hi = tokenizer(article_hi, return_tensors="pt")
generated_tokens = model.generate(
**encoded_hi,
forced_bos_token_id=tokenizer.lang_code_to_id["fr_XX"]
)
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
# => "Le chef de l 'ONU affirme qu 'il n 'y a pas de solution militaire dans la Syrie."
# translate Arabic to English
tokenizer.src_lang = "ar_AR"
encoded_ar = tokenizer(article_ar, return_tensors="pt")
generated_tokens = model.generate(
**encoded_ar,
forced_bos_token_id=tokenizer.lang_code_to_id["en_XX"]
)
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
# => "The Secretary-General of the United Nations says there is no military solution in Syria."
```
See the [model hub](https://huggingface.co/models?filter=mbart-50) to look for more fine-tuned versions.
## Languages covered
Arabic (ar_AR), Czech (cs_CZ), German (de_DE), English (en_XX), Spanish (es_XX), Estonian (et_EE), Finnish (fi_FI), French (fr_XX), Gujarati (gu_IN), Hindi (hi_IN), Italian (it_IT), Japanese (ja_XX), Kazakh (kk_KZ), Korean (ko_KR), Lithuanian (lt_LT), Latvian (lv_LV), Burmese (my_MM), Nepali (ne_NP), Dutch (nl_XX), Romanian (ro_RO), Russian (ru_RU), Sinhala (si_LK), Turkish (tr_TR), Vietnamese (vi_VN), Chinese (zh_CN), Afrikaans (af_ZA), Azerbaijani (az_AZ), Bengali (bn_IN), Persian (fa_IR), Hebrew (he_IL), Croatian (hr_HR), Indonesian (id_ID), Georgian (ka_GE), Khmer (km_KH), Macedonian (mk_MK), Malayalam (ml_IN), Mongolian (mn_MN), Marathi (mr_IN), Polish (pl_PL), Pashto (ps_AF), Portuguese (pt_XX), Swedish (sv_SE), Swahili (sw_KE), Tamil (ta_IN), Telugu (te_IN), Thai (th_TH), Tagalog (tl_XX), Ukrainian (uk_UA), Urdu (ur_PK), Xhosa (xh_ZA), Galician (gl_ES), Slovene (sl_SI)
## BibTeX entry and citation info
```
@article{tang2020multilingual,
title={Multilingual Translation with Extensible Multilingual Pretraining and Finetuning},
author={Yuqing Tang and Chau Tran and Xian Li and Peng-Jen Chen and Naman Goyal and Vishrav Chaudhary and Jiatao Gu and Angela Fan},
year={2020},
eprint={2008.00401},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
| 3,684 | [
[
-0.042144775390625,
-0.035003662109375,
0.0083770751953125,
0.0292510986328125,
-0.017669677734375,
0.0057525634765625,
-0.0252532958984375,
-0.0224761962890625,
0.0170745849609375,
0.01380157470703125,
-0.04229736328125,
-0.045440673828125,
-0.0479736328125,
0.0179901123046875,
-0.007904052734375,
0.08160400390625,
-0.021270751953125,
0.020904541015625,
0.0163726806640625,
-0.0274810791015625,
-0.0146484375,
-0.038360595703125,
-0.0307769775390625,
-0.007205963134765625,
0.01806640625,
0.032318115234375,
0.031951904296875,
0.0267333984375,
0.049896240234375,
0.0281982421875,
-0.019805908203125,
0.01470947265625,
-0.013763427734375,
-0.0199737548828125,
-0.0142059326171875,
-0.0217742919921875,
-0.057769775390625,
-0.0137176513671875,
0.053070068359375,
0.038787841796875,
0.002429962158203125,
0.037841796875,
0.004795074462890625,
0.052947998046875,
-0.03167724609375,
0.005344390869140625,
-0.019805908203125,
0.003826141357421875,
-0.022064208984375,
0.01263427734375,
-0.0247802734375,
-0.02117919921875,
-0.01471710205078125,
-0.029632568359375,
0.001251220703125,
-0.00542449951171875,
0.07659912109375,
-0.00850677490234375,
-0.049530029296875,
-0.00811767578125,
-0.044586181640625,
0.066650390625,
-0.06365966796875,
0.039581298828125,
0.0301361083984375,
0.0266571044921875,
-0.01947021484375,
-0.052947998046875,
-0.051361083984375,
-0.004673004150390625,
-0.00440216064453125,
0.0287628173828125,
-0.014862060546875,
-0.01337432861328125,
0.0217742919921875,
0.02734375,
-0.058502197265625,
-0.014373779296875,
-0.042755126953125,
-0.0029201507568359375,
0.03387451171875,
0.0006866455078125,
0.025634765625,
-0.032470703125,
-0.0416259765625,
-0.0010251998901367188,
-0.036468505859375,
0.0305328369140625,
0.007778167724609375,
0.02410888671875,
-0.04425048828125,
0.0633544921875,
-0.030426025390625,
0.054656982421875,
0.004665374755859375,
-0.0202789306640625,
0.042144775390625,
-0.05029296875,
-0.0141754150390625,
-0.014923095703125,
0.07879638671875,
0.0281829833984375,
0.022003173828125,
0.004436492919921875,
-0.004604339599609375,
-0.00797271728515625,
-0.009735107421875,
-0.061553955078125,
0.00832366943359375,
0.017974853515625,
-0.03790283203125,
0.006561279296875,
0.022186279296875,
-0.058074951171875,
0.017730712890625,
0.0003962516784667969,
0.021026611328125,
-0.04864501953125,
-0.0252685546875,
-0.00110626220703125,
0.00267791748046875,
0.0253753662109375,
0.00989532470703125,
-0.05670166015625,
-0.0008754730224609375,
0.0287017822265625,
0.0672607421875,
0.01287078857421875,
-0.04058837890625,
-0.02520751953125,
0.0268096923828125,
-0.02410888671875,
0.04290771484375,
-0.0281524658203125,
-0.034332275390625,
-0.00859832763671875,
0.027587890625,
-0.008453369140625,
-0.025360107421875,
0.04779052734375,
-0.00952911376953125,
0.016815185546875,
-0.039581298828125,
-0.00943756103515625,
-0.0261688232421875,
0.031951904296875,
-0.045745849609375,
0.083251953125,
0.0186309814453125,
-0.048065185546875,
0.02288818359375,
-0.051666259765625,
-0.03692626953125,
-0.006092071533203125,
-0.0028743743896484375,
-0.041290283203125,
-0.004016876220703125,
0.0253753662109375,
0.038360595703125,
-0.0285491943359375,
0.0272216796875,
-0.01312255859375,
-0.01416778564453125,
0.0056915283203125,
-0.016632080078125,
0.07427978515625,
0.0374755859375,
-0.032318115234375,
0.011627197265625,
-0.05389404296875,
0.005130767822265625,
0.0191192626953125,
-0.038482666015625,
-0.0033435821533203125,
-0.026092529296875,
0.005096435546875,
0.053924560546875,
0.0127410888671875,
-0.04376220703125,
0.017669677734375,
-0.0310821533203125,
0.02764892578125,
0.040191650390625,
-0.0016269683837890625,
0.0238494873046875,
-0.03594970703125,
0.047027587890625,
0.0231781005859375,
0.0164947509765625,
-0.010833740234375,
-0.04534912109375,
-0.056304931640625,
-0.03656005859375,
0.01013946533203125,
0.04754638671875,
-0.0545654296875,
0.024810791015625,
-0.034027099609375,
-0.0421142578125,
-0.04644775390625,
0.01751708984375,
0.04205322265625,
0.0170135498046875,
0.03363037109375,
-0.0261688232421875,
-0.03936767578125,
-0.05462646484375,
-0.0171356201171875,
-0.01027679443359375,
0.01262664794921875,
0.023773193359375,
0.057373046875,
-0.0233001708984375,
0.05133056640625,
-0.015777587890625,
-0.0241546630859375,
-0.018829345703125,
-0.00170135498046875,
0.0247344970703125,
0.0509033203125,
0.052459716796875,
-0.0684814453125,
-0.061065673828125,
0.0257110595703125,
-0.0482177734375,
0.0233001708984375,
0.0019102096557617188,
-0.023834228515625,
0.0296478271484375,
0.0284423828125,
-0.0479736328125,
0.0263519287109375,
0.054443359375,
-0.0303497314453125,
0.047149658203125,
-0.0031719207763671875,
0.0298919677734375,
-0.1182861328125,
0.02685546875,
-0.00743865966796875,
-0.006404876708984375,
-0.040802001953125,
-0.0021533966064453125,
0.00972747802734375,
-0.0081939697265625,
-0.051483154296875,
0.05853271484375,
-0.04376220703125,
0.024871826171875,
0.0120086669921875,
-0.00030612945556640625,
-0.00634002685546875,
0.03814697265625,
-0.012176513671875,
0.04986572265625,
0.031829833984375,
-0.03466796875,
0.032867431640625,
0.0276031494140625,
-0.0173797607421875,
0.058349609375,
-0.037750244140625,
-0.0137176513671875,
-0.007701873779296875,
0.02276611328125,
-0.08258056640625,
-0.0170745849609375,
0.032073974609375,
-0.053131103515625,
0.0202178955078125,
-0.016082763671875,
-0.03961181640625,
-0.050933837890625,
-0.018798828125,
0.03424072265625,
0.01560211181640625,
-0.0227813720703125,
0.038360595703125,
0.0008702278137207031,
-0.01338958740234375,
-0.0543212890625,
-0.0787353515625,
0.01052093505859375,
-0.00908660888671875,
-0.047882080078125,
0.01551055908203125,
-0.01332855224609375,
0.0011301040649414062,
0.015838623046875,
-0.0021076202392578125,
-0.0039005279541015625,
-0.00140380859375,
0.01983642578125,
0.0218963623046875,
-0.0292510986328125,
0.00859832763671875,
0.0015096664428710938,
-0.000881195068359375,
-0.0179443359375,
-0.02008056640625,
0.054168701171875,
-0.0213623046875,
-0.029388427734375,
-0.029296875,
0.03631591796875,
0.052947998046875,
-0.067626953125,
0.08544921875,
0.085205078125,
-0.0244903564453125,
0.0173492431640625,
-0.039764404296875,
0.003185272216796875,
-0.032196044921875,
0.04595947265625,
-0.0625,
-0.061370849609375,
0.05810546875,
-0.0173797607421875,
0.005077362060546875,
0.0626220703125,
0.07086181640625,
0.0164642333984375,
0.067138671875,
0.04156494140625,
-0.0100860595703125,
0.034912109375,
-0.038848876953125,
0.006389617919921875,
-0.059722900390625,
-0.032989501953125,
-0.042633056640625,
-0.00771331787109375,
-0.071533203125,
-0.040557861328125,
0.01416015625,
0.0027866363525390625,
-0.033447265625,
0.02301025390625,
-0.032196044921875,
0.0079803466796875,
0.04571533203125,
0.004169464111328125,
0.00864410400390625,
0.0022430419921875,
-0.037139892578125,
-0.00208282470703125,
-0.04998779296875,
-0.03759765625,
0.0850830078125,
0.01114654541015625,
0.032073974609375,
0.040252685546875,
0.058837890625,
-0.01395416259765625,
0.0170745849609375,
-0.0439453125,
0.0404052734375,
-0.025360107421875,
-0.07623291015625,
-0.014312744140625,
-0.0418701171875,
-0.06964111328125,
0.00981903076171875,
-0.0146026611328125,
-0.04931640625,
0.022796630859375,
-0.01384735107421875,
-0.02685546875,
0.0245819091796875,
-0.060546875,
0.07269287109375,
-0.0294189453125,
-0.020965576171875,
-0.0035991668701171875,
-0.058074951171875,
0.038543701171875,
-0.013580322265625,
0.027801513671875,
-0.01500701904296875,
0.0006303787231445312,
0.059814453125,
-0.018096923828125,
0.04595947265625,
-0.0015697479248046875,
0.00624847412109375,
0.01413726806640625,
-0.00859832763671875,
0.03167724609375,
0.0013608932495117188,
-0.01482391357421875,
0.01441192626953125,
0.00579071044921875,
-0.05389404296875,
-0.0167694091796875,
0.05267333984375,
-0.0654296875,
-0.0355224609375,
-0.04449462890625,
-0.0423583984375,
0.006183624267578125,
0.048187255859375,
0.03314208984375,
0.0074920654296875,
-0.01439666748046875,
0.017059326171875,
0.0187835693359375,
-0.0298004150390625,
0.03546142578125,
0.03125,
-0.0167999267578125,
-0.05059814453125,
0.06976318359375,
0.02020263671875,
0.028167724609375,
0.0244598388671875,
0.0022735595703125,
-0.00569915771484375,
-0.0124359130859375,
-0.042327880859375,
0.043060302734375,
-0.03765869140625,
-0.0160369873046875,
-0.0487060546875,
-0.01499176025390625,
-0.061553955078125,
-0.015869140625,
-0.0364990234375,
-0.025665283203125,
-0.012054443359375,
0.0063934326171875,
0.019927978515625,
0.038482666015625,
-0.005107879638671875,
0.024871826171875,
-0.061279296875,
0.04107666015625,
-0.00020384788513183594,
0.019195556640625,
-0.0029811859130859375,
-0.04583740234375,
-0.044342041015625,
0.0161590576171875,
-0.03143310546875,
-0.0692138671875,
0.037933349609375,
0.021240234375,
0.043243408203125,
0.0350341796875,
0.0071563720703125,
0.06256103515625,
-0.0367431640625,
0.0572509765625,
0.02850341796875,
-0.0703125,
0.0377197265625,
-0.024993896484375,
0.04931640625,
0.038848876953125,
0.055511474609375,
-0.061309814453125,
-0.029541015625,
-0.032257080078125,
-0.078857421875,
0.053131103515625,
0.002864837646484375,
0.017791748046875,
0.00299835205078125,
0.00637054443359375,
-0.00998687744140625,
0.01293182373046875,
-0.06982421875,
-0.0443115234375,
-0.02008056640625,
-0.018585205078125,
-0.024658203125,
-0.031524658203125,
-0.0193328857421875,
-0.036468505859375,
0.05731201171875,
0.01232147216796875,
0.03204345703125,
0.01386260986328125,
0.0034084320068359375,
-0.016845703125,
0.03387451171875,
0.061920166015625,
0.048187255859375,
-0.013153076171875,
0.0083160400390625,
0.0201873779296875,
-0.04412841796875,
0.022064208984375,
0.0217437744140625,
0.0035190582275390625,
0.01117706298828125,
0.0304412841796875,
0.055572509765625,
-0.003368377685546875,
-0.026031494140625,
0.030853271484375,
0.0012121200561523438,
-0.018585205078125,
-0.0248870849609375,
-0.0238494873046875,
0.0196380615234375,
0.030487060546875,
0.0300140380859375,
0.00006628036499023438,
-0.01287078857421875,
-0.04998779296875,
0.016754150390625,
0.039337158203125,
-0.018951416015625,
-0.0281219482421875,
0.051910400390625,
0.0068817138671875,
-0.01019287109375,
0.044830322265625,
-0.0302886962890625,
-0.057098388671875,
0.028411865234375,
0.04248046875,
0.0546875,
-0.05218505859375,
0.016937255859375,
0.05230712890625,
0.04241943359375,
-0.005191802978515625,
0.0352783203125,
0.010040283203125,
-0.0333251953125,
-0.029144287109375,
-0.057098388671875,
-0.0022869110107421875,
0.00109100341796875,
-0.05133056640625,
0.028961181640625,
-0.0146026611328125,
-0.034698486328125,
-0.010589599609375,
0.01337432861328125,
-0.053802490234375,
0.0160675048828125,
-0.005435943603515625,
0.052398681640625,
-0.0743408203125,
0.07904052734375,
0.07696533203125,
-0.04290771484375,
-0.0692138671875,
-0.0022144317626953125,
-0.00537872314453125,
-0.043487548828125,
0.0513916015625,
0.0014514923095703125,
0.013580322265625,
0.00737762451171875,
-0.0193634033203125,
-0.0689697265625,
0.07464599609375,
0.0313720703125,
-0.033294677734375,
0.00608062744140625,
0.0285491943359375,
0.0311431884765625,
-0.005298614501953125,
0.00850677490234375,
0.0177001953125,
0.051605224609375,
0.015045166015625,
-0.0875244140625,
0.0186004638671875,
-0.0401611328125,
-0.01493072509765625,
0.01526641845703125,
-0.0697021484375,
0.0850830078125,
-0.0277557373046875,
0.0012054443359375,
0.0038585662841796875,
0.041046142578125,
0.0265655517578125,
0.02386474609375,
0.007843017578125,
0.048309326171875,
0.0364990234375,
-0.0028209686279296875,
0.06536865234375,
-0.02984619140625,
0.037322998046875,
0.062744140625,
0.00954437255859375,
0.0635986328125,
0.04583740234375,
-0.0282745361328125,
0.020416259765625,
0.043701171875,
-0.00853729248046875,
0.0287017822265625,
-0.006183624267578125,
-0.0184478759765625,
-0.00998687744140625,
-0.0218658447265625,
-0.048736572265625,
0.041839599609375,
0.0015411376953125,
-0.03857421875,
-0.005718231201171875,
0.00992584228515625,
0.038726806640625,
-0.02386474609375,
-0.011444091796875,
0.037841796875,
0.021484375,
-0.045928955078125,
0.0673828125,
0.0207061767578125,
0.04620361328125,
-0.047882080078125,
0.006847381591796875,
-0.017852783203125,
0.0210723876953125,
-0.01898193359375,
-0.04193115234375,
0.0101318359375,
0.0055694580078125,
-0.01983642578125,
-0.0025005340576171875,
0.0162353515625,
-0.046966552734375,
-0.0762939453125,
0.022369384765625,
0.050140380859375,
0.01198577880859375,
0.0035037994384765625,
-0.0625,
-0.006439208984375,
0.01551055908203125,
-0.04193115234375,
0.02301025390625,
0.0499267578125,
-0.0107879638671875,
0.0423583984375,
0.051727294921875,
0.0193023681640625,
0.0164031982421875,
-0.021026611328125,
0.06585693359375,
-0.053314208984375,
-0.0247344970703125,
-0.080322265625,
0.0445556640625,
0.01837158203125,
-0.030426025390625,
0.09027099609375,
0.05609130859375,
0.07232666015625,
-0.0063018798828125,
0.0521240234375,
-0.01482391357421875,
0.0248870849609375,
-0.0220947265625,
0.06451416015625,
-0.07073974609375,
-0.012481689453125,
-0.0421142578125,
-0.061553955078125,
-0.0285491943359375,
0.038787841796875,
-0.0309295654296875,
0.0309295654296875,
0.047454833984375,
0.04742431640625,
-0.00806427001953125,
-0.040985107421875,
0.0188446044921875,
0.02606201171875,
0.0224609375,
0.052703857421875,
0.029541015625,
-0.0303497314453125,
0.051605224609375,
-0.0304412841796875,
-0.003082275390625,
-0.021820068359375,
-0.040374755859375,
-0.05902099609375,
-0.053802490234375,
-0.00550079345703125,
-0.032623291015625,
-0.0011758804321289062,
0.0743408203125,
0.046356201171875,
-0.0703125,
-0.0312042236328125,
0.02349853515625,
0.0026187896728515625,
-0.026275634765625,
-0.008880615234375,
0.042816162109375,
0.0037479400634765625,
-0.05987548828125,
-0.0007395744323730469,
0.0028820037841796875,
0.0216522216796875,
-0.002605438232421875,
-0.0232696533203125,
-0.049530029296875,
-0.00238037109375,
0.052703857421875,
0.0208740234375,
-0.049224853515625,
0.01198577880859375,
0.0084075927734375,
-0.02423095703125,
0.008331298828125,
0.01439666748046875,
-0.01788330078125,
0.039337158203125,
0.030242919921875,
0.0204315185546875,
0.04754638671875,
0.00035881996154785156,
0.021514892578125,
-0.042877197265625,
0.0333251953125,
0.00310516357421875,
0.023773193359375,
0.024078369140625,
-0.0090789794921875,
0.0367431640625,
0.0226287841796875,
-0.03253173828125,
-0.07696533203125,
0.00415802001953125,
-0.0771484375,
-0.0164031982421875,
0.09442138671875,
-0.033905029296875,
-0.0234832763671875,
0.0027256011962890625,
-0.01132965087890625,
0.054290771484375,
-0.026947021484375,
0.0301055908203125,
0.0560302734375,
0.010009765625,
-0.0131683349609375,
-0.0596923828125,
0.017730712890625,
0.0399169921875,
-0.05657958984375,
-0.014923095703125,
0.00762176513671875,
0.01361083984375,
0.017364501953125,
0.04241943359375,
-0.01108551025390625,
0.0277862548828125,
-0.012847900390625,
0.0301055908203125,
-0.0032939910888671875,
-0.00897216796875,
-0.0152587890625,
-0.00656890869140625,
0.0114288330078125,
-0.0258331298828125
]
] |
sbcBI/sentiment_analysis_model | 2022-05-16T18:37:13.000Z | [
"transformers",
"pytorch",
"distilbert",
"text-classification",
"exbert",
"en",
"dataset:Confidential",
"arxiv:1810.04805",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | sbcBI | null | null | sbcBI/sentiment_analysis_model | 3 | 41,296 | transformers | 2022-05-04T05:33:05 | ---
language: en
tags:
- exbert
license: apache-2.0
datasets:
- Confidential
---
# BERT base model (uncased)
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
[this paper](https://arxiv.org/abs/1810.04805) and first released in
[this repository](https://github.com/google-research/bert). This model is uncased: it does not make a difference
between english and English.
## Model description
BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Next sentence prediction (NSP): the models concatenates two masked sentences as inputs during pretraining. Sometimes
they correspond to sentences that were next to each other in the original text, sometimes not. The model then has to
predict if the two sentences were following each other or not.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the BERT model as inputs.
## Model description [sbcBI/sentiment_analysis]
This is a fine-tuned downstream version of the bert-base-uncased model for sentiment analysis, this model is not intended for
further downstream fine-tuning for any other tasks. This model is trained on a classified dataset for text-classification. | 2,215 | [
[
-0.02984619140625,
-0.04779052734375,
0.01396942138671875,
0.02398681640625,
-0.025299072265625,
0.004138946533203125,
-0.024505615234375,
-0.03662109375,
0.016693115234375,
0.05706787109375,
-0.057952880859375,
-0.02490234375,
-0.04669189453125,
-0.0017137527465820312,
-0.023712158203125,
0.099609375,
0.01110076904296875,
0.01328277587890625,
-0.0123748779296875,
0.023468017578125,
-0.032012939453125,
-0.069580078125,
-0.027130126953125,
-0.034759521484375,
0.02398681640625,
0.0020809173583984375,
0.0372314453125,
0.0168304443359375,
0.03704833984375,
0.0244293212890625,
-0.00432586669921875,
-0.00885772705078125,
-0.028564453125,
-0.005260467529296875,
0.002574920654296875,
-0.0271759033203125,
-0.0157470703125,
0.0216827392578125,
0.04229736328125,
0.0614013671875,
0.01102447509765625,
-0.00018930435180664062,
0.020111083984375,
0.049713134765625,
-0.04217529296875,
0.01806640625,
-0.052978515625,
0.00978851318359375,
-0.005954742431640625,
0.0016345977783203125,
-0.037261962890625,
-0.0163116455078125,
0.03662109375,
0.0017957687377929688,
0.020111083984375,
-0.00788116455078125,
0.0819091796875,
0.00357818603515625,
-0.0245208740234375,
-0.027801513671875,
-0.044189453125,
0.0689697265625,
-0.064208984375,
0.0272979736328125,
0.0232696533203125,
0.004550933837890625,
-0.00727081298828125,
-0.06585693359375,
-0.03436279296875,
-0.0235443115234375,
-0.0272216796875,
0.01690673828125,
-0.01422119140625,
0.0203399658203125,
0.00266265869140625,
0.01458740234375,
-0.042816162109375,
0.004184722900390625,
-0.0361328125,
-0.01361846923828125,
0.0445556640625,
-0.0234527587890625,
0.00859832763671875,
-0.024810791015625,
-0.050567626953125,
0.00905609130859375,
-0.046539306640625,
0.016998291015625,
0.0291290283203125,
0.0360107421875,
-0.004047393798828125,
0.042205810546875,
0.00799560546875,
0.04681396484375,
0.0107574462890625,
0.002635955810546875,
0.031829833984375,
-0.0002770423889160156,
-0.0311431884765625,
0.01113128662109375,
0.051666259765625,
0.00800323486328125,
0.045074462890625,
-0.021514892578125,
-0.0307159423828125,
-0.001598358154296875,
0.0307464599609375,
-0.052978515625,
-0.0134124755859375,
0.0087127685546875,
-0.047576904296875,
-0.03118896484375,
0.0093841552734375,
-0.019744873046875,
0.01438140869140625,
-0.017242431640625,
0.054718017578125,
-0.025665283203125,
-0.0038280487060546875,
0.0007004737854003906,
0.003559112548828125,
0.018402099609375,
-0.00531768798828125,
-0.0692138671875,
0.026947021484375,
0.046234130859375,
0.046539306640625,
-0.020721435546875,
-0.01386260986328125,
0.005767822265625,
-0.00629425048828125,
-0.0159912109375,
0.041900634765625,
-0.0296173095703125,
-0.01104736328125,
0.015777587890625,
0.0231475830078125,
-0.00951385498046875,
-0.01085662841796875,
0.03387451171875,
-0.045135498046875,
0.0352783203125,
-0.00765228271484375,
-0.050048828125,
-0.030792236328125,
0.0100860595703125,
-0.034271240234375,
0.084716796875,
-0.00931549072265625,
-0.05548095703125,
0.0225067138671875,
-0.048309326171875,
-0.041107177734375,
0.0021381378173828125,
0.0118560791015625,
-0.028106689453125,
0.0141754150390625,
0.0160369873046875,
0.05023193359375,
0.0086212158203125,
0.03753662109375,
-0.0023059844970703125,
-0.02838134765625,
0.0217132568359375,
-0.03680419921875,
0.0745849609375,
0.005435943603515625,
-0.03497314453125,
0.0001417398452758789,
-0.0523681640625,
0.01617431640625,
0.0007901191711425781,
-0.0207366943359375,
-0.0234222412109375,
0.01047515869140625,
0.008544921875,
0.022369384765625,
0.0340576171875,
-0.043914794921875,
-0.002872467041015625,
-0.0467529296875,
0.027008056640625,
0.06683349609375,
-0.0088043212890625,
0.026885986328125,
-0.0124053955078125,
0.0247344970703125,
-0.00890350341796875,
0.0083465576171875,
-0.0197296142578125,
-0.053863525390625,
-0.0679931640625,
-0.019287109375,
0.0494384765625,
0.053253173828125,
-0.026885986328125,
0.0694580078125,
0.00496673583984375,
-0.02117919921875,
-0.05499267578125,
0.005779266357421875,
0.03656005859375,
0.032867431640625,
0.0250701904296875,
-0.03570556640625,
-0.0645751953125,
-0.0877685546875,
0.0087432861328125,
-0.0041656494140625,
-0.0017108917236328125,
-0.0007677078247070312,
0.044219970703125,
-0.0303802490234375,
0.07366943359375,
-0.0219268798828125,
-0.026397705078125,
-0.04144287109375,
0.0290374755859375,
0.0182342529296875,
0.046417236328125,
0.038299560546875,
-0.046295166015625,
-0.04315185546875,
-0.0196990966796875,
-0.04498291015625,
-0.01361846923828125,
-0.00579071044921875,
-0.008697509765625,
0.0287628173828125,
0.030792236328125,
-0.042083740234375,
0.03985595703125,
0.05474853515625,
0.002689361572265625,
0.032257080078125,
-0.0174102783203125,
-0.019287109375,
-0.0875244140625,
-0.006206512451171875,
-0.016357421875,
-0.01568603515625,
-0.054290771484375,
-0.008087158203125,
0.0016422271728515625,
-0.00930023193359375,
-0.033111572265625,
0.024932861328125,
-0.046142578125,
-0.00894927978515625,
-0.0291748046875,
-0.0122833251953125,
-0.0013036727905273438,
0.061798095703125,
0.031829833984375,
0.04742431640625,
0.046173095703125,
-0.038116455078125,
0.01039886474609375,
0.01189422607421875,
-0.036712646484375,
-0.00353240966796875,
-0.060150146484375,
0.01361083984375,
-0.0143585205078125,
0.00946807861328125,
-0.08782958984375,
0.01641845703125,
-0.005268096923828125,
-0.048797607421875,
0.037353515625,
0.01390838623046875,
-0.02581787109375,
-0.03558349609375,
-0.016693115234375,
0.004367828369140625,
0.058868408203125,
-0.0305328369140625,
0.038787841796875,
0.0309600830078125,
-0.021240234375,
-0.0633544921875,
-0.071533203125,
-0.004428863525390625,
0.01374053955078125,
-0.041290283203125,
0.0287628173828125,
-0.009979248046875,
-0.003070831298828125,
0.01058197021484375,
0.0016841888427734375,
-0.0198516845703125,
0.0012111663818359375,
0.024688720703125,
0.027984619140625,
-0.022125244140625,
0.01250457763671875,
0.005828857421875,
-0.0095672607421875,
0.01360321044921875,
-0.01190948486328125,
0.04315185546875,
-0.01116180419921875,
-0.010284423828125,
-0.0265960693359375,
0.0421142578125,
0.0088348388671875,
-0.01219940185546875,
0.06787109375,
0.0498046875,
-0.03387451171875,
-0.0219268798828125,
-0.051025390625,
-0.0225372314453125,
-0.03631591796875,
0.03179931640625,
-0.0265960693359375,
-0.06890869140625,
0.0313720703125,
0.02301025390625,
0.0074920654296875,
0.036285400390625,
0.05377197265625,
-0.04107666015625,
0.07342529296875,
0.07666015625,
-0.012603759765625,
0.0267181396484375,
-0.0048065185546875,
0.02960205078125,
-0.046630859375,
-0.0238800048828125,
-0.0295257568359375,
-0.0264129638671875,
-0.044281005859375,
-0.00820159912109375,
-0.002105712890625,
0.0123291015625,
-0.006317138671875,
0.034820556640625,
-0.0455322265625,
0.033843994140625,
0.0701904296875,
0.006481170654296875,
-0.00016999244689941406,
0.00910186767578125,
-0.022735595703125,
-0.023590087890625,
-0.040924072265625,
-0.040008544921875,
0.0892333984375,
0.038055419921875,
0.050323486328125,
-0.0125885009765625,
0.051910400390625,
0.037017822265625,
0.023773193359375,
-0.056488037109375,
0.046722412109375,
-0.0216827392578125,
-0.0709228515625,
-0.005741119384765625,
-0.005268096923828125,
-0.0775146484375,
0.014862060546875,
-0.029327392578125,
-0.051116943359375,
0.010101318359375,
-0.0021877288818359375,
-0.004428863525390625,
0.0211029052734375,
-0.06988525390625,
0.04962158203125,
-0.0333251953125,
0.00695037841796875,
0.011993408203125,
-0.0687255859375,
0.0196380615234375,
-0.01409912109375,
-0.00589752197265625,
0.00907135009765625,
0.0205078125,
0.06561279296875,
-0.0289154052734375,
0.08575439453125,
-0.0093841552734375,
0.00856781005859375,
0.01556396484375,
-0.01708984375,
0.02618408203125,
-0.0293121337890625,
0.016571044921875,
0.0323486328125,
-0.015106201171875,
-0.026275634765625,
-0.0307464599609375,
0.031463623046875,
-0.0675048828125,
-0.043365478515625,
-0.04376220703125,
-0.036834716796875,
-0.0225677490234375,
0.024169921875,
0.035552978515625,
0.0170135498046875,
-0.0199432373046875,
0.0307769775390625,
0.05816650390625,
-0.0254669189453125,
0.0439453125,
0.041900634765625,
-0.00965118408203125,
-0.0107421875,
0.03668212890625,
0.004032135009765625,
0.025299072265625,
0.0498046875,
0.0024013519287109375,
-0.031646728515625,
-0.045135498046875,
0.004848480224609375,
0.01995849609375,
-0.0467529296875,
-0.0021038055419921875,
-0.065185546875,
-0.05657958984375,
-0.053863525390625,
-0.02178955078125,
-0.024810791015625,
-0.024871826171875,
-0.0157928466796875,
-0.020965576171875,
0.00945281982421875,
0.054443359375,
-0.021270751953125,
0.030364990234375,
-0.046905517578125,
0.0204010009765625,
0.035491943359375,
0.01273345947265625,
-0.0151519775390625,
-0.042877197265625,
-0.018890380859375,
0.016082763671875,
-0.0140533447265625,
-0.065185546875,
0.040313720703125,
0.004352569580078125,
0.053497314453125,
0.03546142578125,
-0.00495147705078125,
0.04022216796875,
-0.05419921875,
0.053680419921875,
0.016082763671875,
-0.0743408203125,
0.044525146484375,
-0.0009484291076660156,
0.01113128662109375,
0.036834716796875,
0.03765869140625,
-0.0206451416015625,
-0.032928466796875,
-0.04180908203125,
-0.06927490234375,
0.048797607421875,
0.0269775390625,
0.033966064453125,
-0.006252288818359375,
0.0082244873046875,
0.01488494873046875,
0.040740966796875,
-0.10040283203125,
-0.0316162109375,
-0.023529052734375,
-0.0122833251953125,
-0.021484375,
-0.048583984375,
0.0085601806640625,
-0.029693603515625,
0.061309814453125,
0.0231475830078125,
0.04931640625,
0.0009851455688476562,
-0.0211029052734375,
0.01207733154296875,
0.0196990966796875,
0.040618896484375,
0.026275634765625,
-0.053924560546875,
-0.00380706787109375,
-0.0026874542236328125,
-0.051025390625,
-0.01104736328125,
0.013824462890625,
-0.0204010009765625,
0.0289154052734375,
0.035491943359375,
0.07427978515625,
0.0171051025390625,
-0.044921875,
0.046356201171875,
0.0197601318359375,
-0.02703857421875,
-0.040069580078125,
-0.0132598876953125,
-0.002437591552734375,
0.01031494140625,
0.039154052734375,
0.0006508827209472656,
-0.00276947021484375,
-0.05230712890625,
0.030487060546875,
0.044097900390625,
-0.0423583984375,
-0.0143585205078125,
0.03680419921875,
0.0181732177734375,
-0.022216796875,
0.045806884765625,
-0.00257110595703125,
-0.057037353515625,
0.04534912109375,
0.057525634765625,
0.08148193359375,
-0.0164947509765625,
0.02642822265625,
0.00836944580078125,
0.0595703125,
0.0091400146484375,
0.01131439208984375,
0.0016851425170898438,
-0.0748291015625,
-0.038787841796875,
-0.05279541015625,
-0.020904541015625,
0.03314208984375,
-0.057037353515625,
0.00437164306640625,
-0.02801513671875,
-0.0078277587890625,
0.003448486328125,
0.004108428955078125,
-0.044586181640625,
0.042816162109375,
0.01462554931640625,
0.058074951171875,
-0.07012939453125,
0.0762939453125,
0.03839111328125,
-0.0276336669921875,
-0.05792236328125,
-0.00574493408203125,
-0.022125244140625,
-0.07879638671875,
0.0689697265625,
0.0234222412109375,
0.0093841552734375,
-0.0033931732177734375,
-0.04852294921875,
-0.057098388671875,
0.05224609375,
0.00907135009765625,
-0.0307464599609375,
-0.0186004638671875,
0.0167388916015625,
0.04693603515625,
-0.0523681640625,
0.0193634033203125,
0.0159912109375,
0.0211029052734375,
0.00904083251953125,
-0.05804443359375,
-0.01947021484375,
-0.025634765625,
0.0132598876953125,
0.0035266876220703125,
-0.01788330078125,
0.084716796875,
-0.0028076171875,
-0.0027256011962890625,
0.0009264945983886719,
0.042144775390625,
-0.0040130615234375,
-0.0055694580078125,
0.0290374755859375,
0.0401611328125,
0.034820556640625,
-0.0176239013671875,
0.07000732421875,
-0.0182037353515625,
0.0311737060546875,
0.087158203125,
-0.0187225341796875,
0.0740966796875,
0.0247344970703125,
-0.00618743896484375,
0.054473876953125,
0.055511474609375,
-0.011505126953125,
0.07122802734375,
0.006870269775390625,
-0.0033359527587890625,
-0.0060577392578125,
0.01110076904296875,
-0.04376220703125,
0.033355712890625,
0.01506805419921875,
-0.05352783203125,
-0.01360321044921875,
0.0148468017578125,
0.004276275634765625,
-0.00827789306640625,
-0.029998779296875,
0.05377197265625,
-0.002330780029296875,
-0.044586181640625,
0.0311737060546875,
0.0078582763671875,
0.07037353515625,
-0.0701904296875,
0.01369476318359375,
-0.0092315673828125,
0.007213592529296875,
-0.0052947998046875,
-0.048309326171875,
0.024658203125,
0.001953125,
-0.030426025390625,
-0.035888671875,
0.06903076171875,
-0.04376220703125,
-0.055633544921875,
0.019866943359375,
0.0298614501953125,
0.0233154296875,
-0.003971099853515625,
-0.072265625,
-0.0171661376953125,
0.007686614990234375,
-0.031524658203125,
0.0203399658203125,
0.021881103515625,
0.0096282958984375,
0.04827880859375,
0.050445556640625,
0.007572174072265625,
0.01175689697265625,
0.005489349365234375,
0.0528564453125,
-0.048065185546875,
-0.04437255859375,
-0.05108642578125,
0.049346923828125,
0.0002856254577636719,
-0.00589752197265625,
0.05694580078125,
0.034210205078125,
0.06097412109375,
-0.028350830078125,
0.060760498046875,
0.0018873214721679688,
0.049713134765625,
-0.0435791015625,
0.053436279296875,
-0.033111572265625,
-0.0003509521484375,
-0.0294342041015625,
-0.07623291015625,
-0.0114898681640625,
0.0740966796875,
-0.01116180419921875,
0.0200042724609375,
0.06500244140625,
0.05108642578125,
0.00804901123046875,
-0.00791168212890625,
0.0293426513671875,
0.0230712890625,
-0.0146484375,
0.0307769775390625,
0.039459228515625,
-0.024078369140625,
0.03131103515625,
-0.0275115966796875,
-0.01102447509765625,
-0.00402069091796875,
-0.0655517578125,
-0.10247802734375,
-0.048126220703125,
-0.0187225341796875,
-0.025543212890625,
0.0153656005859375,
0.05426025390625,
0.06695556640625,
-0.08221435546875,
-0.0167083740234375,
-0.010223388671875,
-0.004222869873046875,
-0.00914764404296875,
-0.021392822265625,
0.024932861328125,
-0.035980224609375,
-0.05670166015625,
0.0135650634765625,
0.0182037353515625,
0.01297760009765625,
-0.0367431640625,
0.01320648193359375,
-0.040863037109375,
0.0257720947265625,
0.054412841796875,
0.006038665771484375,
-0.048980712890625,
-0.017181396484375,
-0.0001455545425415039,
-0.01488494873046875,
-0.0005517005920410156,
0.0504150390625,
-0.05712890625,
0.033355712890625,
0.0199432373046875,
0.052642822265625,
0.03973388671875,
-0.01561737060546875,
0.047607421875,
-0.084716796875,
0.0302581787109375,
0.0260009765625,
0.023712158203125,
0.01271820068359375,
-0.02960205078125,
0.025299072265625,
0.0165252685546875,
-0.0301361083984375,
-0.0625,
0.01387786865234375,
-0.07781982421875,
-0.03363037109375,
0.07421875,
-0.019317626953125,
-0.0100860595703125,
-0.00894927978515625,
-0.0103607177734375,
0.00797271728515625,
-0.0156402587890625,
0.058074951171875,
0.0728759765625,
0.01617431640625,
-0.0250244140625,
-0.03192138671875,
0.0369873046875,
0.035308837890625,
-0.0389404296875,
-0.03582763671875,
0.0130615234375,
0.0165252685546875,
0.009918212890625,
0.050018310546875,
0.00439453125,
-0.0032405853271484375,
-0.0234222412109375,
0.037017822265625,
0.002948760986328125,
-0.022735595703125,
-0.01036834716796875,
0.01514434814453125,
-0.0298614501953125,
-0.041595458984375
]
] |
CAMeL-Lab/bert-base-arabic-camelbert-mix-pos-glf | 2021-10-18T10:16:30.000Z | [
"transformers",
"pytorch",
"tf",
"bert",
"token-classification",
"ar",
"arxiv:2103.06678",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | CAMeL-Lab | null | null | CAMeL-Lab/bert-base-arabic-camelbert-mix-pos-glf | 1 | 41,135 | transformers | 2022-03-02T23:29:04 | ---
language:
- ar
license: apache-2.0
widget:
- text: 'شلونك ؟ شخبارك ؟'
---
# CAMeLBERT-Mix POS-GLF Model
## Model description
**CAMeLBERT-Mix POS-GLF Model** is a Gulf Arabic POS tagging model that was built by fine-tuning the [CAMeLBERT-Mix](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-mix/) model.
For the fine-tuning, we used the [Gumar](https://camel.abudhabi.nyu.edu/annotated-gumar-corpus/) dataset .
Our fine-tuning procedure and the hyperparameters we used can be found in our paper *"[The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models](https://arxiv.org/abs/2103.06678)."* Our fine-tuning code can be found [here](https://github.com/CAMeL-Lab/CAMeLBERT).
## Intended uses
You can use the CAMeLBERT-Mix POS-GLF model as part of the transformers pipeline.
This model will also be available in [CAMeL Tools](https://github.com/CAMeL-Lab/camel_tools) soon.
#### How to use
To use the model with a transformers pipeline:
```python
>>> from transformers import pipeline
>>> pos = pipeline('token-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-pos-glf')
>>> text = 'شلونك ؟ شخبارك ؟'
>>> pos(text)
[{'entity': 'pron_interrog', 'score': 0.82657206, 'index': 1, 'word': 'شلون', 'start': 0, 'end': 4}, {'entity': 'prep', 'score': 0.9771731, 'index': 2, 'word': '##ك', 'start': 4, 'end': 5}, {'entity': 'punc', 'score': 0.9999568, 'index': 3, 'word': '؟', 'start': 6, 'end': 7}, {'entity': 'noun', 'score': 0.9977217, 'index': 4, 'word': 'ش', 'start': 8, 'end': 9}, {'entity': 'noun', 'score': 0.99993783, 'index': 5, 'word': '##خبار', 'start': 9, 'end': 13}, {'entity': 'prep', 'score': 0.5309442, 'index': 6, 'word': '##ك', 'start': 13, 'end': 14}, {'entity': 'punc', 'score': 0.9999575, 'index': 7, 'word': '؟', 'start': 15, 'end': 16}]
```
*Note*: to download our models, you would need `transformers>=3.5.0`.
Otherwise, you could download the models manually.
## Citation
```bibtex
@inproceedings{inoue-etal-2021-interplay,
title = "The Interplay of Variant, Size, and Task Type in {A}rabic Pre-trained Language Models",
author = "Inoue, Go and
Alhafni, Bashar and
Baimukan, Nurpeiis and
Bouamor, Houda and
Habash, Nizar",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Online)",
publisher = "Association for Computational Linguistics",
abstract = "In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicly available models by fine-tuning them on five NLP tasks spanning 12 datasets. Our results suggest that the variant proximity of pre-training data to fine-tuning data is more important than the pre-training data size. We exploit this insight in defining an optimized system selection model for the studied tasks.",
}
``` | 3,399 | [
[
-0.0467529296875,
-0.044586181640625,
0.002559661865234375,
0.009246826171875,
-0.024627685546875,
-0.00391387939453125,
-0.0233154296875,
-0.037811279296875,
0.0054168701171875,
0.0298614501953125,
-0.0276031494140625,
-0.057159423828125,
-0.06756591796875,
0.00469207763671875,
-0.02569580078125,
0.09979248046875,
-0.020660400390625,
-0.0044403076171875,
0.0168304443359375,
-0.0220489501953125,
-0.0123443603515625,
-0.046356201171875,
-0.03497314453125,
-0.0171356201171875,
0.038330078125,
0.0238494873046875,
0.08538818359375,
0.038604736328125,
0.036163330078125,
0.018951416015625,
-0.00782012939453125,
0.0139617919921875,
-0.01641845703125,
-0.006191253662109375,
-0.009918212890625,
-0.007198333740234375,
-0.02545166015625,
0.00757598876953125,
0.057586669921875,
0.049774169921875,
-0.01367950439453125,
0.031829833984375,
-0.0027675628662109375,
0.0443115234375,
-0.050933837890625,
0.0056304931640625,
-0.04351806640625,
-0.0210113525390625,
-0.0296630859375,
0.01329803466796875,
-0.002796173095703125,
-0.0001862049102783203,
0.016815185546875,
-0.02386474609375,
0.01201629638671875,
0.0085601806640625,
0.10870361328125,
0.025146484375,
-0.0258331298828125,
-0.0263671875,
-0.05303955078125,
0.07177734375,
-0.06890869140625,
0.01708984375,
0.048919677734375,
0.0131072998046875,
-0.018310546875,
-0.051116943359375,
-0.05096435546875,
-0.0238037109375,
-0.02423095703125,
-0.01708984375,
-0.01062774658203125,
0.004901885986328125,
0.018585205078125,
0.0303955078125,
-0.038970947265625,
-0.0043182373046875,
-0.005397796630859375,
-0.0176239013671875,
0.0413818359375,
-0.000060617923736572266,
0.030364990234375,
-0.0010509490966796875,
-0.0012598037719726562,
-0.006633758544921875,
-0.05584716796875,
0.0152130126953125,
0.038818359375,
0.0279388427734375,
-0.0209197998046875,
0.0487060546875,
-0.021148681640625,
0.0771484375,
-0.007541656494140625,
-0.0101318359375,
0.0266265869140625,
-0.03472900390625,
-0.0193328857421875,
-0.008148193359375,
0.0611572265625,
-0.004116058349609375,
0.0115509033203125,
0.0036907196044921875,
-0.0289459228515625,
0.002864837646484375,
0.007282257080078125,
-0.07135009765625,
-0.016693115234375,
0.0113525390625,
-0.0362548828125,
0.0030612945556640625,
-0.01044464111328125,
-0.0233154296875,
-0.0067291259765625,
-0.0229949951171875,
0.045684814453125,
-0.05047607421875,
-0.0098724365234375,
0.03192138671875,
0.0116424560546875,
0.0155029296875,
0.01031494140625,
-0.06707763671875,
0.0164794921875,
0.021728515625,
0.055389404296875,
-0.0000034570693969726562,
-0.02520751953125,
-0.0208587646484375,
0.01129150390625,
-0.0017671585083007812,
0.041107177734375,
-0.055572509765625,
-0.035614013671875,
0.0070648193359375,
-0.01580810546875,
-0.0126190185546875,
-0.042144775390625,
0.05126953125,
-0.037841796875,
0.01483154296875,
-0.00875091552734375,
-0.040740966796875,
-0.01520538330078125,
0.01104736328125,
-0.051361083984375,
0.0906982421875,
0.0210113525390625,
-0.07989501953125,
0.027130126953125,
-0.0537109375,
-0.03668212890625,
0.0027256011962890625,
-0.019073486328125,
-0.050079345703125,
-0.01042938232421875,
0.018829345703125,
0.0257568359375,
-0.03399658203125,
0.01486968994140625,
-0.0010852813720703125,
-0.03021240234375,
0.0181121826171875,
-0.007015228271484375,
0.053192138671875,
0.0238037109375,
-0.031646728515625,
0.0175933837890625,
-0.066162109375,
-0.000002562999725341797,
0.0025424957275390625,
-0.040557861328125,
-0.0152130126953125,
0.0123291015625,
0.0216064453125,
0.029266357421875,
0.03192138671875,
-0.03460693359375,
0.021148681640625,
-0.0386962890625,
0.027099609375,
0.0213775634765625,
-0.01476287841796875,
0.0238494873046875,
-0.052947998046875,
0.03759765625,
0.0092620849609375,
0.007785797119140625,
0.0166168212890625,
-0.036712646484375,
-0.06396484375,
-0.046783447265625,
0.049102783203125,
0.02789306640625,
-0.04888916015625,
0.051422119140625,
-0.018035888671875,
-0.06671142578125,
-0.06719970703125,
-0.0033626556396484375,
0.0262908935546875,
0.02587890625,
0.043060302734375,
-0.03240966796875,
-0.03875732421875,
-0.07977294921875,
-0.034088134765625,
0.003936767578125,
0.0069427490234375,
0.0185699462890625,
0.043212890625,
-0.036468505859375,
0.08209228515625,
-0.0246734619140625,
-0.0240325927734375,
-0.026947021484375,
0.030670166015625,
0.034454345703125,
0.051361083984375,
0.05426025390625,
-0.04864501953125,
-0.04498291015625,
-0.0026073455810546875,
-0.01065826416015625,
0.0075225830078125,
0.01430511474609375,
-0.01137542724609375,
0.0292510986328125,
0.01453399658203125,
-0.061676025390625,
0.0474853515625,
0.040863037109375,
-0.030120849609375,
0.053253173828125,
-0.0162353515625,
0.003490447998046875,
-0.0675048828125,
0.007617950439453125,
-0.00672149658203125,
0.006656646728515625,
-0.055572509765625,
0.00463104248046875,
-0.005367279052734375,
0.020263671875,
-0.029541015625,
0.042755126953125,
-0.02886962890625,
0.00679779052734375,
-0.015289306640625,
-0.0208282470703125,
-0.01287841796875,
0.041778564453125,
-0.0004131793975830078,
0.06768798828125,
0.048980712890625,
-0.044677734375,
-0.0116424560546875,
0.01293182373046875,
-0.05426025390625,
-0.00904083251953125,
-0.05517578125,
-0.002765655517578125,
-0.01222991943359375,
0.0124969482421875,
-0.0821533203125,
-0.00811004638671875,
0.033172607421875,
-0.025634765625,
0.024627685546875,
-0.0027637481689453125,
-0.061737060546875,
-0.01007080078125,
-0.01441192626953125,
0.049072265625,
0.03338623046875,
-0.008514404296875,
0.06585693359375,
0.0167083740234375,
-0.00640869140625,
-0.05206298828125,
-0.031494140625,
-0.0159149169921875,
-0.016204833984375,
-0.0360107421875,
0.04681396484375,
-0.0187225341796875,
0.00203704833984375,
0.0036602020263671875,
-0.0027980804443359375,
-0.0005688667297363281,
0.0179290771484375,
0.0224761962890625,
0.0188446044921875,
-0.00785064697265625,
0.0120697021484375,
0.00913238525390625,
0.0094757080078125,
-0.014495849609375,
-0.0163421630859375,
0.0706787109375,
-0.01287841796875,
-0.017120361328125,
-0.027984619140625,
0.0325927734375,
0.022979736328125,
-0.050079345703125,
0.09906005859375,
0.06378173828125,
-0.03399658203125,
0.0059967041015625,
-0.030487060546875,
0.007205963134765625,
-0.035675048828125,
0.0323486328125,
-0.041473388671875,
-0.07415771484375,
0.03509521484375,
0.01004791259765625,
0.01171875,
0.0538330078125,
0.060028076171875,
0.005947113037109375,
0.089111328125,
0.042877197265625,
-0.0253753662109375,
0.044464111328125,
-0.0218048095703125,
0.0223388671875,
-0.041748046875,
-0.0019273757934570312,
-0.06353759765625,
-0.0285186767578125,
-0.053955078125,
-0.0263214111328125,
0.01439666748046875,
0.0235595703125,
-0.048858642578125,
0.01428985595703125,
-0.030914306640625,
0.0160980224609375,
0.04962158203125,
-0.01026153564453125,
0.007640838623046875,
0.0162200927734375,
-0.0186309814453125,
0.0017995834350585938,
-0.04345703125,
-0.05047607421875,
0.0848388671875,
0.0124359130859375,
0.043365478515625,
0.0271759033203125,
0.061767578125,
0.0186004638671875,
0.0294952392578125,
-0.050262451171875,
0.0279998779296875,
-0.0022640228271484375,
-0.04718017578125,
-0.032470703125,
-0.01061248779296875,
-0.0853271484375,
0.020172119140625,
-0.0212249755859375,
-0.060882568359375,
-0.0011396408081054688,
0.0037059783935546875,
-0.0251617431640625,
0.0037288665771484375,
-0.04473876953125,
0.061981201171875,
0.002796173095703125,
0.00020003318786621094,
-0.0167694091796875,
-0.04937744140625,
0.003162384033203125,
-0.006572723388671875,
0.0247650146484375,
-0.0200653076171875,
-0.0028781890869140625,
0.0701904296875,
-0.043060302734375,
0.0518798828125,
0.00473785400390625,
-0.01073455810546875,
0.027862548828125,
0.004436492919921875,
0.04052734375,
-0.005008697509765625,
-0.00861358642578125,
0.026824951171875,
0.01044464111328125,
-0.0518798828125,
-0.0264892578125,
0.036224365234375,
-0.10028076171875,
-0.049163818359375,
-0.041046142578125,
-0.056549072265625,
-0.0182037353515625,
0.01555633544921875,
0.03790283203125,
0.0274658203125,
0.0103912353515625,
-0.0031681060791015625,
0.0178375244140625,
-0.0148162841796875,
0.031280517578125,
0.04541015625,
-0.016632080078125,
-0.01322174072265625,
0.061676025390625,
0.0199127197265625,
0.0098114013671875,
0.032501220703125,
-0.00159454345703125,
-0.00923919677734375,
-0.063720703125,
-0.0265350341796875,
0.035675048828125,
-0.038360595703125,
-0.01471710205078125,
-0.04833984375,
-0.02740478515625,
-0.0338134765625,
0.009613037109375,
-0.0142822265625,
-0.0253448486328125,
-0.038604736328125,
0.0091705322265625,
0.035247802734375,
0.052337646484375,
0.0172271728515625,
0.03985595703125,
-0.06573486328125,
0.0007715225219726562,
0.005802154541015625,
0.0208282470703125,
-0.00043845176696777344,
-0.0621337890625,
-0.043731689453125,
0.0221710205078125,
-0.01641845703125,
-0.06903076171875,
0.03424072265625,
0.022491455078125,
0.032562255859375,
0.01812744140625,
-0.0111846923828125,
0.03900146484375,
-0.038604736328125,
0.06341552734375,
0.0003218650817871094,
-0.08038330078125,
0.0294189453125,
-0.034759521484375,
0.029876708984375,
0.034423828125,
0.0589599609375,
-0.045654296875,
-0.0247955322265625,
-0.043914794921875,
-0.07293701171875,
0.06402587890625,
0.034759521484375,
-0.003070831298828125,
-0.004215240478515625,
0.016998291015625,
0.0112762451171875,
0.0288543701171875,
-0.045196533203125,
-0.053955078125,
-0.011077880859375,
-0.038818359375,
-0.0184478759765625,
-0.02630615234375,
-0.01010894775390625,
-0.039215087890625,
0.07110595703125,
0.0079345703125,
0.0182647705078125,
0.004344940185546875,
-0.0230865478515625,
0.00624847412109375,
0.0245208740234375,
0.04559326171875,
0.041717529296875,
-0.019866943359375,
0.00390625,
0.0022945404052734375,
-0.041839599609375,
0.00012022256851196289,
0.0347900390625,
-0.0159454345703125,
0.011016845703125,
0.022369384765625,
0.064208984375,
0.00009721517562866211,
-0.0645751953125,
0.0240325927734375,
0.0005068778991699219,
-0.01523590087890625,
-0.00981903076171875,
0.00350189208984375,
0.00908660888671875,
0.007015228271484375,
0.023590087890625,
0.0030002593994140625,
0.00930023193359375,
-0.0264434814453125,
-0.0023670196533203125,
0.032073974609375,
-0.01416015625,
-0.019683837890625,
0.0249176025390625,
-0.020721435546875,
-0.03131103515625,
0.026214599609375,
-0.03143310546875,
-0.035308837890625,
0.041961669921875,
0.033721923828125,
0.034881591796875,
-0.024627685546875,
0.0246734619140625,
0.0205535888671875,
0.0186004638671875,
0.00385284423828125,
0.03546142578125,
-0.00039505958557128906,
-0.070068359375,
-0.02484130859375,
-0.07269287109375,
-0.0089874267578125,
0.0186920166015625,
-0.0325927734375,
0.01403045654296875,
-0.031646728515625,
-0.01812744140625,
0.00711822509765625,
0.01329803466796875,
-0.07452392578125,
0.024200439453125,
0.007694244384765625,
0.053558349609375,
-0.043670654296875,
0.087646484375,
0.07501220703125,
-0.042236328125,
-0.0858154296875,
-0.00888824462890625,
-0.030914306640625,
-0.053955078125,
0.055389404296875,
0.01190185546875,
-0.00481414794921875,
0.01041412353515625,
-0.0421142578125,
-0.10699462890625,
0.05975341796875,
0.01395416259765625,
-0.0323486328125,
0.00594329833984375,
0.028045654296875,
0.046417236328125,
-0.03411865234375,
0.03668212890625,
0.0621337890625,
0.025604248046875,
-0.00397491455078125,
-0.07830810546875,
0.01013946533203125,
-0.0266265869140625,
0.004001617431640625,
0.0268707275390625,
-0.04388427734375,
0.0924072265625,
0.007232666015625,
-0.0155487060546875,
0.022918701171875,
0.05389404296875,
0.00988006591796875,
-0.0139312744140625,
0.03326416015625,
0.049560546875,
0.045501708984375,
-0.00141143798828125,
0.0701904296875,
-0.0384521484375,
0.039947509765625,
0.0894775390625,
-0.011077880859375,
0.0679931640625,
0.032073974609375,
-0.031494140625,
0.062255859375,
0.057708740234375,
0.0129241943359375,
0.038604736328125,
0.0267333984375,
-0.0239715576171875,
-0.0199432373046875,
-0.0233612060546875,
-0.042724609375,
0.041473388671875,
0.036712646484375,
-0.0224609375,
-0.0196075439453125,
-0.01036834716796875,
0.01220703125,
-0.0045318603515625,
-0.0142822265625,
0.031524658203125,
-0.015625,
-0.0496826171875,
0.07342529296875,
0.033660888671875,
0.0574951171875,
-0.052337646484375,
0.01007843017578125,
0.0002281665802001953,
-0.0017194747924804688,
-0.009246826171875,
-0.033660888671875,
0.0017595291137695312,
-0.0173797607421875,
-0.01418304443359375,
0.01204681396484375,
0.045501708984375,
-0.044769287109375,
-0.038238525390625,
0.01519775390625,
0.04168701171875,
0.004077911376953125,
-0.01318359375,
-0.06427001953125,
0.00951385498046875,
0.002056121826171875,
-0.0293121337890625,
0.033935546875,
0.0206298828125,
-0.00909423828125,
0.0355224609375,
0.039459228515625,
0.008880615234375,
0.01123046875,
0.00909423828125,
0.07342529296875,
-0.051116943359375,
-0.0264892578125,
-0.06707763671875,
0.032257080078125,
0.01113128662109375,
-0.033447265625,
0.045257568359375,
0.03460693359375,
0.066650390625,
-0.00832366943359375,
0.056976318359375,
-0.00782012939453125,
0.03875732421875,
-0.021087646484375,
0.0521240234375,
-0.049530029296875,
0.001987457275390625,
-0.0137939453125,
-0.058990478515625,
-0.0156402587890625,
0.044525146484375,
-0.035308837890625,
0.017974853515625,
0.04217529296875,
0.07135009765625,
0.01422119140625,
-0.003376007080078125,
0.0030002593994140625,
0.0168304443359375,
0.0178070068359375,
0.04241943359375,
0.0506591796875,
-0.0293731689453125,
0.031402587890625,
-0.0079498291015625,
-0.00992584228515625,
-0.0241241455078125,
-0.05023193359375,
-0.0745849609375,
-0.056121826171875,
-0.01788330078125,
-0.0213165283203125,
-0.0103302001953125,
0.08984375,
0.037689208984375,
-0.06658935546875,
-0.02276611328125,
0.0016813278198242188,
0.00296783447265625,
-0.015960693359375,
-0.0147552490234375,
0.04412841796875,
-0.02728271484375,
-0.053802490234375,
-0.00424957275390625,
0.00324249267578125,
0.0226287841796875,
0.0034389495849609375,
-0.01181793212890625,
-0.05267333984375,
0.0157012939453125,
0.029296875,
0.01453399658203125,
-0.05743408203125,
-0.0282745361328125,
-0.027191162109375,
-0.0195770263671875,
0.0022296905517578125,
0.039581298828125,
-0.0565185546875,
0.00449371337890625,
0.0160675048828125,
0.04986572265625,
0.035552978515625,
-0.016876220703125,
0.0200653076171875,
-0.052978515625,
0.0255279541015625,
0.01235198974609375,
0.0360107421875,
0.022003173828125,
-0.01136016845703125,
0.018707275390625,
0.003429412841796875,
-0.039642333984375,
-0.043914794921875,
0.030975341796875,
-0.061767578125,
-0.020782470703125,
0.085693359375,
-0.01499176025390625,
-0.0084228515625,
-0.01219940185546875,
-0.040802001953125,
0.038818359375,
-0.03363037109375,
0.058746337890625,
0.08148193359375,
0.0069427490234375,
0.0273590087890625,
-0.01412200927734375,
0.062408447265625,
0.065185546875,
-0.04193115234375,
-0.0244293212890625,
0.0157318115234375,
0.019287109375,
0.01354217529296875,
0.043670654296875,
0.0134124755859375,
0.0110931396484375,
-0.02374267578125,
0.01580810546875,
0.00647735595703125,
-0.006317138671875,
-0.013641357421875,
0.004947662353515625,
0.0262908935546875,
-0.01261138916015625
]
] |
timpal0l/mdeberta-v3-base-squad2 | 2023-04-05T16:28:16.000Z | [
"transformers",
"pytorch",
"safetensors",
"deberta-v2",
"question-answering",
"deberta",
"deberta-v3",
"mdeberta",
"multilingual",
"af",
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ug",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"zh",
"dataset:squad_v2",
"arxiv:2006.03654",
"arxiv:2111.09543",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | question-answering | timpal0l | null | null | timpal0l/mdeberta-v3-base-squad2 | 84 | 41,132 | transformers | 2022-11-30T11:34:54 | ---
datasets:
- squad_v2
language:
- multilingual
- af
- am
- ar
- as
- az
- be
- bg
- bn
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- no
- om
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- th
- tl
- tr
- ug
- uk
- ur
- uz
- vi
- xh
- yi
- zh
tags:
- deberta
- deberta-v3
- mdeberta
- question-answering
thumbnail: https://huggingface.co/front/thumbnails/microsoft.png
license: mit
---
## This model can be used for Extractive QA
It has been finetuned for 3 epochs on [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/).
## Evaluation on SQuAD2.0 dev set
```
{
"epoch": 3.0,
"eval_HasAns_exact": 79.65587044534414,
"eval_HasAns_f1": 85.91387795001529,
"eval_HasAns_total": 5928,
"eval_NoAns_exact": 82.10260723296888,
"eval_NoAns_f1": 82.10260723296888,
"eval_NoAns_total": 5945,
"eval_best_exact": 80.8809904826076,
"eval_best_exact_thresh": 0.0,
"eval_best_f1": 84.00551406448994,
"eval_best_f1_thresh": 0.0,
"eval_exact": 80.8809904826076,
"eval_f1": 84.00551406449004,
"eval_samples": 12508,
"eval_total": 11873,
"train_loss": 0.7729689576483615,
"train_runtime": 9118.953,
"train_samples": 134891,
"train_samples_per_second": 44.377,
"train_steps_per_second": 0.925
}
```
## DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
[DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data.
In [DeBERTa V3](https://arxiv.org/abs/2111.09543), we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our [paper](https://arxiv.org/abs/2111.09543).
Please check the [official repository](https://github.com/microsoft/DeBERTa) for more implementation details and updates.
mDeBERTa is multilingual version of DeBERTa which use the same structure as DeBERTa and was trained with CC100 multilingual data.
The mDeBERTa V3 base model comes with 12 layers and a hidden size of 768. It has 86M backbone parameters with a vocabulary containing 250K tokens which introduces 190M parameters in the Embedding layer. This model was trained using the 2.5T CC100 data as XLM-R.
| 2,810 | [
[
-0.0186614990234375,
-0.065673828125,
0.02606201171875,
0.0369873046875,
-0.024627685546875,
0.0143585205078125,
0.00691986083984375,
-0.045440673828125,
0.0152740478515625,
0.00746917724609375,
-0.0391845703125,
-0.046478271484375,
-0.05218505859375,
0.004497528076171875,
-0.019256591796875,
0.0504150390625,
-0.0016889572143554688,
0.01654052734375,
0.015716552734375,
-0.0184478759765625,
-0.0477294921875,
-0.033477783203125,
-0.053009033203125,
-0.0036106109619140625,
0.029541015625,
0.014923095703125,
0.032073974609375,
0.0233306884765625,
0.03399658203125,
0.0239410400390625,
-0.022125244140625,
0.01556396484375,
-0.04107666015625,
0.0023040771484375,
0.00041794776916503906,
-0.039031982421875,
-0.056854248046875,
0.007205963134765625,
0.0386962890625,
0.0060577392578125,
-0.0089263916015625,
0.027099609375,
-0.0009059906005859375,
0.07318115234375,
-0.049652099609375,
0.026092529296875,
-0.045806884765625,
-0.0022602081298828125,
0.005016326904296875,
0.0018720626831054688,
-0.0205078125,
-0.01401519775390625,
0.02008056640625,
-0.0291595458984375,
0.00461578369140625,
-0.013275146484375,
0.09466552734375,
0.0214080810546875,
-0.0248870849609375,
0.0004591941833496094,
-0.040313720703125,
0.07037353515625,
-0.059356689453125,
0.031951904296875,
0.026153564453125,
0.037109375,
0.003986358642578125,
-0.0555419921875,
-0.04339599609375,
0.0107574462890625,
0.0102996826171875,
0.020904541015625,
-0.03466796875,
-0.01873779296875,
0.0146636962890625,
0.024871826171875,
-0.03948974609375,
0.0188446044921875,
-0.04364013671875,
0.005268096923828125,
0.059814453125,
0.011138916015625,
0.0055694580078125,
-0.01334381103515625,
-0.0338134765625,
-0.01995849609375,
-0.056549072265625,
0.0171661376953125,
0.035064697265625,
0.003162384033203125,
-0.008331298828125,
0.026153564453125,
-0.031707763671875,
0.03997802734375,
0.006839752197265625,
0.019378662109375,
0.047149658203125,
-0.0160980224609375,
-0.026641845703125,
-0.00995635986328125,
0.057037353515625,
0.0240936279296875,
-0.0108489990234375,
-0.00009250640869140625,
-0.00849151611328125,
-0.00696563720703125,
0.0161895751953125,
-0.07464599609375,
-0.0338134765625,
0.03900146484375,
-0.035888671875,
-0.0259552001953125,
0.00370025634765625,
-0.0672607421875,
-0.0001226663589477539,
-0.019622802734375,
0.031829833984375,
-0.047393798828125,
-0.03265380859375,
0.02362060546875,
-0.001651763916015625,
0.03167724609375,
0.03326416015625,
-0.064208984375,
0.00870513916015625,
0.0328369140625,
0.06805419921875,
-0.0120849609375,
-0.0190887451171875,
-0.029754638671875,
-0.0137939453125,
-0.003116607666015625,
0.041839599609375,
-0.0045928955078125,
-0.006366729736328125,
-0.01277923583984375,
0.0215606689453125,
-0.01421356201171875,
-0.032379150390625,
0.0231475830078125,
-0.065673828125,
0.00585174560546875,
-0.00738525390625,
-0.027984619140625,
-0.0394287109375,
0.0230560302734375,
-0.0638427734375,
0.07867431640625,
0.02728271484375,
-0.03131103515625,
0.029205322265625,
-0.0587158203125,
0.00262451171875,
0.0026874542236328125,
0.00730133056640625,
-0.048828125,
-0.01629638671875,
0.0322265625,
0.029632568359375,
-0.0068817138671875,
0.019073486328125,
-0.025360107421875,
-0.0303192138671875,
0.0235748291015625,
-0.03057861328125,
0.093994140625,
0.0269927978515625,
-0.03912353515625,
-0.006072998046875,
-0.056365966796875,
0.0239105224609375,
0.0174102783203125,
-0.0183258056640625,
-0.00336456298828125,
-0.0102691650390625,
0.00872039794921875,
0.025360107421875,
0.030670166015625,
-0.04278564453125,
0.0198974609375,
-0.02374267578125,
0.04827880859375,
0.048431396484375,
0.0022869110107421875,
0.0257720947265625,
-0.01418304443359375,
0.0465087890625,
0.01690673828125,
0.032318115234375,
0.0203399658203125,
-0.042510986328125,
-0.042449951171875,
-0.057037353515625,
0.04638671875,
0.04010009765625,
-0.039520263671875,
0.049041748046875,
-0.01097869873046875,
-0.059417724609375,
-0.0589599609375,
0.0098724365234375,
0.025665283203125,
0.00568389892578125,
0.04388427734375,
-0.0019178390502929688,
-0.058502197265625,
-0.07269287109375,
0.017486572265625,
-0.00656890869140625,
-0.0028839111328125,
0.00399017333984375,
0.05462646484375,
-0.0291595458984375,
0.0654296875,
-0.045928955078125,
-0.0298309326171875,
-0.02435302734375,
0.0004432201385498047,
0.025970458984375,
0.05145263671875,
0.06719970703125,
-0.0601806640625,
-0.0333251953125,
-0.02935791015625,
-0.06170654296875,
0.0247039794921875,
0.01490020751953125,
-0.02606201171875,
0.024505615234375,
0.0025501251220703125,
-0.04248046875,
0.026153564453125,
0.054779052734375,
-0.0168609619140625,
0.0161895751953125,
-0.0029926300048828125,
0.0184326171875,
-0.1016845703125,
0.01214599609375,
-0.00823974609375,
-0.0131683349609375,
-0.0286712646484375,
0.0232086181640625,
0.021240234375,
0.0100250244140625,
-0.0531005859375,
0.021087646484375,
-0.041839599609375,
0.0162353515625,
-0.0009965896606445312,
0.01666259765625,
0.0173797607421875,
0.051422119140625,
-0.002307891845703125,
0.057830810546875,
0.046875,
-0.031005859375,
0.01428985595703125,
0.03277587890625,
-0.0367431640625,
0.01525115966796875,
-0.06732177734375,
0.021270751953125,
-0.0013303756713867188,
0.0186767578125,
-0.06427001953125,
0.0037708282470703125,
0.0203857421875,
-0.039154052734375,
0.021728515625,
-0.0191650390625,
-0.04339599609375,
-0.02471923828125,
-0.04376220703125,
0.027679443359375,
0.0496826171875,
-0.04827880859375,
0.0265960693359375,
0.035797119140625,
0.005336761474609375,
-0.051177978515625,
-0.0494384765625,
-0.00927734375,
-0.0311737060546875,
-0.041412353515625,
0.0308685302734375,
-0.0171966552734375,
-0.006092071533203125,
-0.0076141357421875,
0.0030803680419921875,
-0.0207366943359375,
0.0180206298828125,
0.0211639404296875,
0.042724609375,
-0.0054931640625,
0.004543304443359375,
0.0121917724609375,
0.00839996337890625,
-0.00800323486328125,
0.00363922119140625,
0.046478271484375,
-0.031585693359375,
-0.0017795562744140625,
-0.038177490234375,
0.026519775390625,
0.02911376953125,
-0.036163330078125,
0.06866455078125,
0.059417724609375,
-0.027557373046875,
-0.0025730133056640625,
-0.035125732421875,
-0.00983428955078125,
-0.036651611328125,
0.0379638671875,
-0.030914306640625,
-0.054473876953125,
0.0545654296875,
0.0231170654296875,
0.0019855499267578125,
0.055999755859375,
0.031280517578125,
-0.001361846923828125,
0.089111328125,
0.029541015625,
-0.01117706298828125,
0.036651611328125,
-0.074951171875,
0.01050567626953125,
-0.09271240234375,
-0.035491943359375,
-0.03338623046875,
-0.027801513671875,
-0.044219970703125,
-0.0199127197265625,
0.0186767578125,
0.04339599609375,
-0.0100250244140625,
0.04296875,
-0.04547119140625,
0.01873779296875,
0.031219482421875,
0.0440673828125,
0.00995635986328125,
-0.0025482177734375,
0.0276336669921875,
-0.0033740997314453125,
-0.039764404296875,
-0.039642333984375,
0.0885009765625,
0.04052734375,
0.040802001953125,
0.045318603515625,
0.056640625,
0.0180206298828125,
0.002864837646484375,
-0.053009033203125,
0.031646728515625,
0.01367950439453125,
-0.06256103515625,
-0.0168304443359375,
-0.0253448486328125,
-0.07781982421875,
0.0251922607421875,
-0.01165771484375,
-0.07806396484375,
0.027435302734375,
0.006626129150390625,
-0.0286712646484375,
0.01058197021484375,
-0.05328369140625,
0.056793212890625,
-0.00514984130859375,
-0.0364990234375,
-0.01351165771484375,
-0.04248046875,
0.02471923828125,
-0.0017299652099609375,
-0.0205078125,
-0.011871337890625,
0.00855255126953125,
0.0679931640625,
-0.016082763671875,
0.045074462890625,
-0.0259246826171875,
-0.007061004638671875,
0.03759765625,
-0.0010976791381835938,
0.03900146484375,
0.036651611328125,
-0.01035308837890625,
0.0357666015625,
0.0257110595703125,
-0.03912353515625,
-0.041961669921875,
0.06365966796875,
-0.0684814453125,
-0.0352783203125,
-0.0335693359375,
-0.03973388671875,
-0.00542449951171875,
0.01358795166015625,
0.01485443115234375,
0.040313720703125,
-0.0036449432373046875,
0.036651611328125,
0.051544189453125,
0.006389617919921875,
0.032379150390625,
0.0633544921875,
-0.01006317138671875,
-0.025360107421875,
0.056243896484375,
0.01033782958984375,
0.01035308837890625,
0.0308685302734375,
-0.0172882080078125,
-0.043975830078125,
-0.05743408203125,
-0.045166015625,
0.006671905517578125,
-0.04681396484375,
-0.04107666015625,
-0.0811767578125,
-0.015716552734375,
-0.033111572265625,
0.021392822265625,
-0.033782958984375,
-0.044891357421875,
-0.045135498046875,
-0.0214691162109375,
0.04632568359375,
0.032745361328125,
0.002170562744140625,
0.016632080078125,
-0.072265625,
0.0006818771362304688,
0.016998291015625,
0.00901031494140625,
-0.0015859603881835938,
-0.040313720703125,
-0.03009033203125,
0.0211334228515625,
-0.039581298828125,
-0.07806396484375,
0.041107177734375,
-0.00417327880859375,
0.040771484375,
0.01222991943359375,
-0.0002474784851074219,
0.0504150390625,
-0.017486572265625,
0.07537841796875,
-0.00884246826171875,
-0.06890869140625,
0.040313720703125,
-0.018707275390625,
0.008087158203125,
0.05621337890625,
0.03143310546875,
0.0192718505859375,
-0.01358795166015625,
-0.0601806640625,
-0.0762939453125,
0.05120849609375,
0.0280303955078125,
-0.0089263916015625,
-0.0025634765625,
0.01071929931640625,
-0.0021305084228515625,
0.0142364501953125,
-0.042724609375,
-0.024322509765625,
-0.0153961181640625,
-0.014678955078125,
-0.00498199462890625,
-0.022918701171875,
-0.00988006591796875,
-0.031402587890625,
0.0643310546875,
-0.004772186279296875,
0.03533935546875,
0.0247802734375,
-0.0214080810546875,
0.0178985595703125,
0.013946533203125,
0.0469970703125,
0.058502197265625,
-0.05615234375,
-0.0098114013671875,
0.0204925537109375,
-0.0290069580078125,
0.01300811767578125,
0.031036376953125,
0.0006561279296875,
-0.0005965232849121094,
0.0169219970703125,
0.0546875,
-0.00504302978515625,
-0.045166015625,
0.038665771484375,
-0.00909423828125,
-0.016876220703125,
-0.031951904296875,
0.0013895034790039062,
-0.00923919677734375,
0.04583740234375,
0.0281219482421875,
0.0025501251220703125,
0.0291595458984375,
-0.03253173828125,
0.005680084228515625,
0.027740478515625,
-0.0288848876953125,
-0.0289459228515625,
0.046783447265625,
0.0018224716186523438,
-0.00412750244140625,
0.044677734375,
-0.0225677490234375,
-0.0396728515625,
0.0582275390625,
0.04052734375,
0.06842041015625,
-0.0156707763671875,
0.0213165283203125,
0.041259765625,
0.016448974609375,
-0.00626373291015625,
0.044097900390625,
0.0023860931396484375,
-0.038909912109375,
-0.01617431640625,
-0.0440673828125,
-0.00975799560546875,
0.0153961181640625,
-0.07421875,
0.002643585205078125,
-0.001373291015625,
-0.01210784912109375,
-0.00344085693359375,
0.0203399658203125,
-0.072265625,
0.00331878662109375,
-0.031402587890625,
0.07391357421875,
-0.05279541015625,
0.071533203125,
0.04437255859375,
-0.04986572265625,
-0.07183837890625,
-0.0238189697265625,
-0.0159759521484375,
-0.059906005859375,
0.0587158203125,
0.01535797119140625,
-0.0011615753173828125,
0.011810302734375,
-0.03790283203125,
-0.0645751953125,
0.1201171875,
0.00891876220703125,
-0.053466796875,
0.0002868175506591797,
-0.012420654296875,
0.047149658203125,
-0.02728271484375,
0.0243377685546875,
0.039825439453125,
0.01806640625,
-0.01134490966796875,
-0.047882080078125,
0.009307861328125,
-0.03216552734375,
0.0055694580078125,
0.004772186279296875,
-0.051910400390625,
0.07708740234375,
-0.01175689697265625,
-0.0084228515625,
0.02239990234375,
0.04046630859375,
0.0276336669921875,
0.0104217529296875,
0.0287628173828125,
0.045745849609375,
0.046875,
-0.01250457763671875,
0.0699462890625,
-0.0166168212890625,
0.049285888671875,
0.08087158203125,
-0.016510009765625,
0.07342529296875,
0.035430908203125,
-0.02655029296875,
0.045928955078125,
0.046600341796875,
-0.0086212158203125,
0.060791015625,
0.005950927734375,
-0.0089111328125,
0.00688934326171875,
0.0110931396484375,
-0.04278564453125,
0.03741455078125,
0.01165008544921875,
-0.0330810546875,
-0.0012998580932617188,
-0.0016126632690429688,
0.0054473876953125,
-0.01763916015625,
0.0035762786865234375,
0.05108642578125,
-0.01297760009765625,
-0.033935546875,
0.061859130859375,
-0.0042877197265625,
0.03790283203125,
-0.041168212890625,
-0.0179443359375,
-0.0156402587890625,
0.0268707275390625,
-0.00717926025390625,
-0.048065185546875,
0.003231048583984375,
-0.0047760009765625,
-0.01284027099609375,
0.0019140243530273438,
0.0280303955078125,
-0.0264434814453125,
-0.0357666015625,
0.025848388671875,
0.04010009765625,
0.006130218505859375,
-0.0153961181640625,
-0.05792236328125,
0.0196685791015625,
0.0017299652099609375,
-0.02886962890625,
0.020233154296875,
0.0189056396484375,
0.0159759521484375,
0.038177490234375,
0.036041259765625,
-0.0094146728515625,
0.0079193115234375,
-0.01145172119140625,
0.07342529296875,
-0.04095458984375,
-0.01959228515625,
-0.05511474609375,
0.046142578125,
-0.016510009765625,
-0.0272369384765625,
0.06170654296875,
0.052398681640625,
0.0556640625,
-0.0172271728515625,
0.035888671875,
-0.0201416015625,
0.0210418701171875,
-0.05859375,
0.045166015625,
-0.04388427734375,
0.01459503173828125,
-0.0186767578125,
-0.076171875,
-0.006450653076171875,
0.0377197265625,
-0.0015392303466796875,
0.00299072265625,
0.05047607421875,
0.06903076171875,
0.0003807544708251953,
0.004505157470703125,
0.00899505615234375,
0.00469970703125,
0.044464111328125,
0.054534912109375,
0.05517578125,
-0.07281494140625,
0.0288848876953125,
-0.0305023193359375,
-0.0209808349609375,
-0.0110626220703125,
-0.046783447265625,
-0.0692138671875,
-0.048736572265625,
-0.02197265625,
-0.034088134765625,
0.013702392578125,
0.07049560546875,
0.0592041015625,
-0.05029296875,
0.0105438232421875,
-0.005462646484375,
-0.007007598876953125,
-0.041778564453125,
-0.0225677490234375,
0.047393798828125,
-0.0048980712890625,
-0.08868408203125,
0.036834716796875,
-0.0115814208984375,
0.0121307373046875,
-0.026641845703125,
-0.00882720947265625,
-0.04412841796875,
-0.01522064208984375,
0.04949951171875,
0.0034999847412109375,
-0.031890869140625,
-0.0230712890625,
0.0089263916015625,
-0.00408172607421875,
0.003635406494140625,
0.0161590576171875,
-0.05328369140625,
0.02362060546875,
0.03826904296875,
0.02886962890625,
0.052154541015625,
-0.01031494140625,
0.02227783203125,
-0.03997802734375,
0.0246429443359375,
0.0185546875,
0.035247802734375,
0.01000213623046875,
-0.03472900390625,
0.055755615234375,
-0.01165771484375,
-0.0462646484375,
-0.06231689453125,
0.002552032470703125,
-0.0985107421875,
-0.007038116455078125,
0.07708740234375,
-0.035003662109375,
-0.021484375,
0.0107269287109375,
-0.0242156982421875,
0.01837158203125,
-0.049560546875,
0.07366943359375,
0.034912109375,
0.01019287109375,
-0.00861358642578125,
-0.0447998046875,
0.031951904296875,
0.0341796875,
-0.06329345703125,
-0.028228759765625,
0.03289794921875,
0.02301025390625,
0.01220703125,
0.03839111328125,
-0.029510498046875,
0.020599365234375,
-0.01219940185546875,
-0.0014963150024414062,
-0.0288238525390625,
-0.03533935546875,
-0.02935791015625,
0.0021839141845703125,
-0.003719329833984375,
-0.05157470703125
]
] |
tuner007/pegasus_paraphrase | 2021-03-22T21:11:33.000Z | [
"transformers",
"pytorch",
"pegasus",
"text2text-generation",
"paraphrasing",
"seq2seq",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | text2text-generation | tuner007 | null | null | tuner007/pegasus_paraphrase | 154 | 41,106 | transformers | 2022-03-02T23:29:05 | ---
language: en
license: apache-2.0
tags:
- pegasus
- paraphrasing
- seq2seq
---
## Model description
[PEGASUS](https://github.com/google-research/pegasus) fine-tuned for paraphrasing
## Model in Action 🚀
```
import torch
from transformers import PegasusForConditionalGeneration, PegasusTokenizer
model_name = 'tuner007/pegasus_paraphrase'
torch_device = 'cuda' if torch.cuda.is_available() else 'cpu'
tokenizer = PegasusTokenizer.from_pretrained(model_name)
model = PegasusForConditionalGeneration.from_pretrained(model_name).to(torch_device)
def get_response(input_text,num_return_sequences,num_beams):
batch = tokenizer([input_text],truncation=True,padding='longest',max_length=60, return_tensors="pt").to(torch_device)
translated = model.generate(**batch,max_length=60,num_beams=num_beams, num_return_sequences=num_return_sequences, temperature=1.5)
tgt_text = tokenizer.batch_decode(translated, skip_special_tokens=True)
return tgt_text
```
#### Example:
```
num_beams = 10
num_return_sequences = 10
context = "The ultimate test of your knowledge is your capacity to convey it to another."
get_response(context,num_return_sequences,num_beams)
# output:
['The test of your knowledge is your ability to convey it.',
'The ability to convey your knowledge is the ultimate test of your knowledge.',
'The ability to convey your knowledge is the most important test of your knowledge.',
'Your capacity to convey your knowledge is the ultimate test of it.',
'The test of your knowledge is your ability to communicate it.',
'Your capacity to convey your knowledge is the ultimate test of your knowledge.',
'Your capacity to convey your knowledge to another is the ultimate test of your knowledge.',
'Your capacity to convey your knowledge is the most important test of your knowledge.',
'The test of your knowledge is how well you can convey it.',
'Your capacity to convey your knowledge is the ultimate test.']
```
> Created by [Arpit Rajauria](https://twitter.com/arpit_rajauria)
[](https://twitter.com/arpit_rajauria)
| 2,129 | [
[
-0.0267791748046875,
-0.058258056640625,
0.01358795166015625,
0.0291290283203125,
-0.03057861328125,
-0.01806640625,
-0.0160064697265625,
-0.0132904052734375,
0.01183319091796875,
0.03167724609375,
-0.03143310546875,
-0.032440185546875,
-0.051422119140625,
0.004505157470703125,
-0.038726806640625,
0.07879638671875,
-0.01403045654296875,
-0.007152557373046875,
0.005290985107421875,
-0.006282806396484375,
-0.03631591796875,
-0.0214385986328125,
-0.06341552734375,
-0.0299224853515625,
0.0192108154296875,
0.0254669189453125,
0.0279998779296875,
0.037933349609375,
0.0382080078125,
0.02801513671875,
-0.004817962646484375,
0.0134124755859375,
-0.012542724609375,
0.00888824462890625,
-0.0149993896484375,
-0.0205078125,
-0.018402099609375,
-0.00998687744140625,
0.05023193359375,
0.037261962890625,
0.0057830810546875,
0.04351806640625,
0.0195159912109375,
0.0131378173828125,
-0.034393310546875,
0.034393310546875,
-0.041015625,
-0.01201629638671875,
-0.00910186767578125,
-0.0226898193359375,
-0.01904296875,
-0.0197906494140625,
-0.01177978515625,
-0.05865478515625,
0.0199432373046875,
0.00004667043685913086,
0.09405517578125,
0.0213623046875,
-0.0280914306640625,
-0.01526641845703125,
-0.0297088623046875,
0.06890869140625,
-0.054443359375,
0.0127716064453125,
0.0247344970703125,
0.0322265625,
0.0109100341796875,
-0.09747314453125,
-0.05682373046875,
-0.016265869140625,
-0.01092529296875,
0.01873779296875,
0.0024433135986328125,
-0.007274627685546875,
0.0232086181640625,
0.0251312255859375,
-0.02783203125,
-0.0212249755859375,
-0.042449951171875,
-0.0206146240234375,
0.036102294921875,
0.03265380859375,
0.023834228515625,
-0.00814056396484375,
-0.02008056640625,
-0.0207366943359375,
-0.020294189453125,
0.00724029541015625,
0.0064239501953125,
0.01812744140625,
-0.0158843994140625,
0.045806884765625,
-0.0294647216796875,
0.058746337890625,
0.0198211669921875,
-0.00710296630859375,
0.0171051025390625,
-0.027374267578125,
-0.0200653076171875,
-0.0100555419921875,
0.07708740234375,
0.020416259765625,
0.0096282958984375,
-0.016632080078125,
-0.00418853759765625,
-0.011444091796875,
0.0151214599609375,
-0.0576171875,
-0.01312255859375,
0.01348114013671875,
-0.0252685546875,
-0.0302581787109375,
0.006214141845703125,
-0.06683349609375,
-0.01409149169921875,
0.009033203125,
0.06201171875,
-0.04656982421875,
-0.0105133056640625,
0.0130462646484375,
-0.02740478515625,
0.0290374755859375,
-0.007442474365234375,
-0.0977783203125,
0.0223236083984375,
0.044219970703125,
0.062408447265625,
0.022796630859375,
-0.05194091796875,
-0.0222320556640625,
0.01739501953125,
-0.01285552978515625,
0.03265380859375,
-0.02166748046875,
-0.017730712890625,
-0.019775390625,
0.0000565648078918457,
-0.03131103515625,
-0.018707275390625,
0.0625,
-0.017364501953125,
0.037384033203125,
-0.04150390625,
-0.052337646484375,
-0.017730712890625,
-0.0017404556274414062,
-0.0276031494140625,
0.0709228515625,
0.01485443115234375,
-0.07568359375,
0.0139312744140625,
-0.0653076171875,
-0.027099609375,
0.00792694091796875,
-0.020233154296875,
-0.032684326171875,
-0.0029773712158203125,
0.0191802978515625,
0.038604736328125,
-0.0277252197265625,
0.0010099411010742188,
-0.01371002197265625,
-0.0201263427734375,
0.0243988037109375,
-0.017852783203125,
0.07073974609375,
0.018035888671875,
-0.0638427734375,
0.015899658203125,
-0.04248046875,
0.01512908935546875,
0.01502227783203125,
-0.021331787109375,
0.01342010498046875,
-0.0034656524658203125,
0.005313873291015625,
0.01233673095703125,
0.0218658447265625,
-0.034942626953125,
0.00750732421875,
-0.0438232421875,
0.045989990234375,
0.053070068359375,
0.013031005859375,
0.01532745361328125,
-0.0469970703125,
0.0232086181640625,
0.00167083740234375,
0.00464630126953125,
0.008087158203125,
-0.0389404296875,
-0.07879638671875,
-0.0005350112915039062,
-0.0018320083618164062,
0.0413818359375,
-0.06561279296875,
0.03558349609375,
-0.0298309326171875,
-0.06146240234375,
-0.043182373046875,
0.005126953125,
0.033599853515625,
0.073486328125,
0.034393310546875,
0.005527496337890625,
-0.0418701171875,
-0.06488037109375,
-0.0297088623046875,
-0.0266571044921875,
0.0038166046142578125,
0.00008863210678100586,
0.054412841796875,
0.0111846923828125,
0.0283966064453125,
-0.040985107421875,
-0.0055389404296875,
-0.0305633544921875,
0.0094757080078125,
0.0309906005859375,
0.04302978515625,
0.039337158203125,
-0.05694580078125,
-0.03302001953125,
0.0013914108276367188,
-0.06304931640625,
-0.00946807861328125,
-0.01239013671875,
-0.0221405029296875,
-0.0015592575073242188,
0.01342010498046875,
-0.06512451171875,
0.0298919677734375,
0.006580352783203125,
-0.054351806640625,
0.055267333984375,
-0.007518768310546875,
0.0289154052734375,
-0.10235595703125,
0.01617431640625,
-0.01190948486328125,
0.01397705078125,
-0.03790283203125,
0.03204345703125,
-0.0011301040649414062,
0.0141143798828125,
-0.038360595703125,
0.07135009765625,
-0.02301025390625,
0.03594970703125,
-0.0060882568359375,
-0.0016298294067382812,
-0.0027942657470703125,
0.02301025390625,
-0.01374053955078125,
0.05975341796875,
0.056549072265625,
-0.062744140625,
0.0675048828125,
0.0394287109375,
-0.02923583984375,
0.022796630859375,
-0.064453125,
-0.006011962890625,
0.00498199462890625,
-0.0105438232421875,
-0.09014892578125,
-0.0247344970703125,
0.034576416015625,
-0.05975341796875,
0.004547119140625,
0.0228271484375,
-0.042236328125,
-0.049041748046875,
-0.0223236083984375,
0.01375579833984375,
0.04583740234375,
-0.038116455078125,
0.038604736328125,
0.0014019012451171875,
0.0004496574401855469,
-0.055206298828125,
-0.066162109375,
-0.0022029876708984375,
-0.045806884765625,
-0.054534912109375,
0.040252685546875,
-0.0095672607421875,
0.0010356903076171875,
-0.02496337890625,
0.00714111328125,
-0.0195465087890625,
0.004245758056640625,
0.026519775390625,
0.021331787109375,
-0.0175323486328125,
0.003902435302734375,
-0.005298614501953125,
0.0043487548828125,
0.0248260498046875,
-0.033233642578125,
0.04766845703125,
-0.032440185546875,
-0.016937255859375,
-0.044647216796875,
0.0007543563842773438,
0.041961669921875,
-0.004016876220703125,
0.0770263671875,
0.08087158203125,
-0.0229949951171875,
-0.00009566545486450195,
-0.03955078125,
-0.0174713134765625,
-0.03826904296875,
0.0312042236328125,
-0.03985595703125,
-0.0330810546875,
0.056610107421875,
0.0219879150390625,
0.0102081298828125,
0.060333251953125,
0.05029296875,
0.005245208740234375,
0.06439208984375,
0.0312042236328125,
0.0009541511535644531,
0.0176849365234375,
-0.04730224609375,
0.0093994140625,
-0.055206298828125,
-0.024139404296875,
-0.027862548828125,
-0.01453399658203125,
-0.022369384765625,
-0.01078033447265625,
0.013458251953125,
0.01386260986328125,
-0.038330078125,
0.035369873046875,
-0.051513671875,
0.0091705322265625,
0.055938720703125,
0.0122833251953125,
0.00394439697265625,
-0.005603790283203125,
-0.032196044921875,
-0.009063720703125,
-0.039703369140625,
-0.05780029296875,
0.0826416015625,
0.01300811767578125,
0.034698486328125,
0.0070037841796875,
0.045989990234375,
-0.005161285400390625,
0.01220703125,
-0.04473876953125,
0.0576171875,
0.00724029541015625,
-0.06396484375,
-0.028350830078125,
-0.0322265625,
-0.06146240234375,
0.01184844970703125,
-0.003261566162109375,
-0.061553955078125,
-0.032867431640625,
0.00028586387634277344,
-0.03125,
0.039337158203125,
-0.0465087890625,
0.07073974609375,
-0.01216888427734375,
-0.0238800048828125,
0.0097808837890625,
-0.037506103515625,
0.030914306640625,
-0.0010204315185546875,
-0.00460052490234375,
0.010467529296875,
-0.0131378173828125,
0.08746337890625,
-0.037445068359375,
0.05908203125,
0.0016078948974609375,
0.0222625732421875,
0.0308990478515625,
-0.01763916015625,
0.017730712890625,
0.006061553955078125,
-0.017303466796875,
-0.02581787109375,
0.01788330078125,
-0.046905517578125,
-0.0296783447265625,
0.044891357421875,
-0.06890869140625,
-0.044403076171875,
-0.0247802734375,
-0.02886962890625,
-0.00118255615234375,
0.02130126953125,
0.06231689453125,
0.034271240234375,
-0.01004791259765625,
0.003131866455078125,
0.0283050537109375,
-0.01406097412109375,
0.042266845703125,
0.01190948486328125,
-0.010498046875,
-0.037384033203125,
0.0682373046875,
0.004383087158203125,
0.0069732666015625,
0.031005859375,
0.01136016845703125,
-0.04034423828125,
-0.0287933349609375,
-0.0205078125,
0.0330810546875,
-0.0640869140625,
-0.0084686279296875,
-0.0531005859375,
-0.0287017822265625,
-0.064453125,
-0.0007467269897460938,
-0.0084686279296875,
-0.0418701171875,
-0.03472900390625,
-0.0119781494140625,
0.0323486328125,
0.0374755859375,
-0.00634002685546875,
0.044952392578125,
-0.04302978515625,
0.0302581787109375,
0.02996826171875,
0.0023040771484375,
0.0032405853271484375,
-0.060882568359375,
-0.0109100341796875,
0.006465911865234375,
-0.056549072265625,
-0.06842041015625,
0.046966552734375,
0.00847625732421875,
0.05908203125,
0.0305938720703125,
0.0067596435546875,
0.049224853515625,
-0.012908935546875,
0.06512451171875,
0.0134429931640625,
-0.08587646484375,
0.038665771484375,
-0.01654052734375,
0.009033203125,
0.029876708984375,
0.020660400390625,
-0.047393798828125,
-0.03546142578125,
-0.06744384765625,
-0.064453125,
0.040313720703125,
0.033172607421875,
0.0259552001953125,
-0.01352691650390625,
0.034637451171875,
-0.001323699951171875,
0.01171112060546875,
-0.060333251953125,
-0.044036865234375,
-0.0303802490234375,
-0.02642822265625,
-0.0011205673217773438,
-0.00264739990234375,
-0.01357269287109375,
-0.04345703125,
0.0615234375,
0.0090179443359375,
0.040985107421875,
0.0118408203125,
0.004932403564453125,
0.01220703125,
0.01556396484375,
0.05279541015625,
0.060272216796875,
-0.0163421630859375,
0.0182647705078125,
0.0362548828125,
-0.042510986328125,
0.006252288818359375,
0.01177978515625,
-0.002838134765625,
0.01329803466796875,
0.04632568359375,
0.0714111328125,
-0.01326751708984375,
-0.0211029052734375,
0.0275115966796875,
-0.00400543212890625,
-0.0218963623046875,
-0.03131103515625,
0.01361846923828125,
0.0179443359375,
0.01259613037109375,
0.028228759765625,
-0.006328582763671875,
0.0025196075439453125,
-0.017730712890625,
0.020263671875,
0.01023101806640625,
-0.0188140869140625,
-0.021026611328125,
0.08587646484375,
0.0035266876220703125,
-0.0140838623046875,
0.039642333984375,
-0.01132965087890625,
-0.049652099609375,
0.06298828125,
0.03466796875,
0.05816650390625,
-0.0097198486328125,
0.0272979736328125,
0.039703369140625,
0.022369384765625,
-0.01192474365234375,
0.036376953125,
-0.006786346435546875,
-0.034576416015625,
-0.0196533203125,
-0.04779052734375,
-0.01306915283203125,
0.0286865234375,
-0.04730224609375,
0.025909423828125,
-0.04345703125,
-0.0229949951171875,
0.01849365234375,
0.01390838623046875,
-0.04766845703125,
0.03131103515625,
-0.006633758544921875,
0.072998046875,
-0.0574951171875,
0.05706787109375,
0.05816650390625,
-0.051177978515625,
-0.08966064453125,
-0.0103607177734375,
-0.027069091796875,
-0.06402587890625,
0.06829833984375,
0.007747650146484375,
0.0205230712890625,
0.0197906494140625,
-0.03692626953125,
-0.052642822265625,
0.0853271484375,
0.0186309814453125,
0.0015134811401367188,
-0.01186370849609375,
0.0206756591796875,
0.034210205078125,
-0.02044677734375,
0.047698974609375,
0.0279693603515625,
0.04815673828125,
0.016876220703125,
-0.06597900390625,
0.02490234375,
-0.02685546875,
-0.0104217529296875,
0.00434112548828125,
-0.04931640625,
0.08538818359375,
-0.0209503173828125,
-0.006381988525390625,
0.0258331298828125,
0.06488037109375,
0.0279541015625,
0.0217742919921875,
0.01444244384765625,
0.045745849609375,
0.040191650390625,
-0.0164947509765625,
0.0684814453125,
-0.0322265625,
0.04864501953125,
0.06439208984375,
0.0255889892578125,
0.050994873046875,
0.040252685546875,
0.002552032470703125,
0.0263824462890625,
0.05072021484375,
-0.007152557373046875,
0.0389404296875,
0.0184326171875,
-0.0223236083984375,
-0.00489044189453125,
0.01103973388671875,
-0.049102783203125,
0.021209716796875,
0.0243377685546875,
-0.03790283203125,
-0.01508331298828125,
0.006549835205078125,
0.01325225830078125,
-0.004718780517578125,
-0.01224517822265625,
0.0271453857421875,
-0.0012035369873046875,
-0.055694580078125,
0.078369140625,
0.006771087646484375,
0.05914306640625,
-0.036407470703125,
0.0078887939453125,
-0.007358551025390625,
0.023590087890625,
-0.0006995201110839844,
-0.06396484375,
0.0284576416015625,
-0.01509857177734375,
0.00150299072265625,
-0.01200103759765625,
0.034271240234375,
-0.0249176025390625,
-0.05230712890625,
0.0189361572265625,
0.0238494873046875,
0.029876708984375,
-0.01171875,
-0.06646728515625,
-0.01611328125,
0.00595855712890625,
-0.0303192138671875,
-0.00888824462890625,
0.03265380859375,
0.0222320556640625,
0.056396484375,
0.0252838134765625,
0.0172882080078125,
0.032440185546875,
-0.007343292236328125,
0.056121826171875,
-0.061431884765625,
-0.0233154296875,
-0.0775146484375,
0.0251617431640625,
-0.0120391845703125,
-0.0460205078125,
0.0635986328125,
0.03997802734375,
0.04595947265625,
-0.02197265625,
0.06390380859375,
-0.022369384765625,
0.033599853515625,
-0.03228759765625,
0.0625,
-0.03192138671875,
0.006069183349609375,
-0.0155181884765625,
-0.051422119140625,
0.00009685754776000977,
0.048919677734375,
-0.034210205078125,
0.0166473388671875,
0.06622314453125,
0.0526123046875,
-0.0031681060791015625,
-0.007450103759765625,
0.02587890625,
0.026214599609375,
0.028167724609375,
0.06402587890625,
0.059417724609375,
-0.06854248046875,
0.062744140625,
-0.052734375,
0.0015172958374023438,
-0.0049591064453125,
-0.040618896484375,
-0.0830078125,
-0.07769775390625,
-0.0286407470703125,
-0.05084228515625,
-0.006954193115234375,
0.0439453125,
0.0526123046875,
-0.05645751953125,
-0.0198822021484375,
-0.0189666748046875,
0.0111541748046875,
-0.025482177734375,
-0.0241546630859375,
0.035888671875,
-0.030120849609375,
-0.051605224609375,
-0.0025920867919921875,
-0.01493072509765625,
0.022430419921875,
0.01274871826171875,
-0.0007014274597167969,
-0.0134429931640625,
0.00884246826171875,
0.0222625732421875,
0.021026611328125,
-0.054901123046875,
-0.025848388671875,
0.003444671630859375,
-0.0252685546875,
-0.0189666748046875,
0.019622802734375,
-0.03826904296875,
0.01141357421875,
0.043853759765625,
0.0301971435546875,
0.03558349609375,
-0.009735107421875,
0.02423095703125,
-0.0338134765625,
0.0059967041015625,
0.0154571533203125,
0.033203125,
0.0148468017578125,
-0.033233642578125,
0.03350830078125,
0.0237274169921875,
-0.03997802734375,
-0.052581787109375,
-0.0013246536254882812,
-0.0733642578125,
-0.0177001953125,
0.076904296875,
-0.01396942138671875,
-0.0241851806640625,
0.0026950836181640625,
-0.0253753662109375,
0.06158447265625,
-0.0157470703125,
0.072265625,
0.0634765625,
-0.005199432373046875,
0.0011644363403320312,
-0.051239013671875,
0.032806396484375,
0.047760009765625,
-0.05389404296875,
-0.014251708984375,
-0.0034656524658203125,
0.040313720703125,
0.0213165283203125,
0.042205810546875,
0.007747650146484375,
0.0159149169921875,
0.006591796875,
0.0016126632690429688,
-0.01031494140625,
0.00803375244140625,
0.0009074211120605469,
0.0111083984375,
-0.006801605224609375,
-0.051513671875
]
] |
prithivida/grammar_error_correcter_v1 | 2021-07-04T10:44:31.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text2text-generation | prithivida | null | null | prithivida/grammar_error_correcter_v1 | 30 | 41,003 | transformers | 2022-03-02T23:29:05 | **This model is part of the Gramformer library** please refer to https://github.com/PrithivirajDamodaran/Gramformer/
| 118 | [
[
0.01442718505859375,
-0.051727294921875,
0.0222930908203125,
0.005573272705078125,
-0.01085662841796875,
0.004547119140625,
0.0275726318359375,
-0.00656890869140625,
0.0169219970703125,
0.057525634765625,
-0.04681396484375,
-0.030487060546875,
-0.02886962890625,
-0.0237884521484375,
-0.0286865234375,
0.055419921875,
0.0013933181762695312,
0.035491943359375,
-0.0301971435546875,
0.017181396484375,
-0.003902435302734375,
-0.011444091796875,
-0.0291748046875,
-0.03631591796875,
0.0276031494140625,
0.0295867919921875,
0.0298309326171875,
0.015289306640625,
0.047210693359375,
0.0178985595703125,
-0.0345458984375,
-0.0283966064453125,
-0.0172576904296875,
0.003269195556640625,
-0.007526397705078125,
-0.0457763671875,
-0.0908203125,
0.0006532669067382812,
0.04815673828125,
0.025177001953125,
-0.0198974609375,
0.04443359375,
-0.0205230712890625,
0.0557861328125,
-0.04290771484375,
0.02081298828125,
0.0023899078369140625,
0.0089874267578125,
-0.035797119140625,
0.0167083740234375,
-0.0229034423828125,
-0.0390625,
-0.0198822021484375,
-0.033416748046875,
0.01546478271484375,
-0.003101348876953125,
0.08087158203125,
0.0078277587890625,
-0.0318603515625,
0.00505828857421875,
-0.054779052734375,
0.00878143310546875,
-0.0438232421875,
0.037261962890625,
0.0213470458984375,
0.06964111328125,
0.009429931640625,
-0.070068359375,
-0.021881103515625,
-0.02691650390625,
-0.004199981689453125,
0.0153350830078125,
-0.0064697265625,
0.0179290771484375,
0.0210723876953125,
0.05279541015625,
-0.059478759765625,
-0.035064697265625,
-0.08660888671875,
-0.01535797119140625,
0.01019287109375,
0.0026264190673828125,
0.03436279296875,
-0.048126220703125,
-0.01184844970703125,
0.0086822509765625,
-0.0199432373046875,
0.016326904296875,
0.0241851806640625,
0.005016326904296875,
-0.034942626953125,
0.06317138671875,
-0.01136016845703125,
0.06781005859375,
0.00982666015625,
-0.00885009765625,
0.020538330078125,
0.002208709716796875,
-0.0305633544921875,
0.000720977783203125,
0.026824951171875,
-0.004222869873046875,
0.031341552734375,
0.007427215576171875,
-0.0088043212890625,
-0.0033588409423828125,
0.036712646484375,
-0.054931640625,
-0.060943603515625,
0.00362396240234375,
-0.054290771484375,
-0.027862548828125,
0.02618408203125,
-0.050506591796875,
0.01003265380859375,
-0.01053619384765625,
0.018768310546875,
-0.0096588134765625,
-0.048828125,
-0.007171630859375,
0.0003924369812011719,
-0.00801849365234375,
-0.007457733154296875,
-0.057708740234375,
0.047332763671875,
0.03802490234375,
0.056243896484375,
0.0362548828125,
-0.00862884521484375,
-0.0241546630859375,
0.01294708251953125,
0.011962890625,
0.068115234375,
-0.033905029296875,
-0.05615234375,
0.00464630126953125,
0.0173492431640625,
-0.00661468505859375,
-0.02386474609375,
0.09100341796875,
-0.048858642578125,
0.005748748779296875,
0.0303955078125,
-0.04071044921875,
-0.037353515625,
0.0246734619140625,
-0.07366943359375,
0.059051513671875,
0.0262603759765625,
-0.053497314453125,
0.004985809326171875,
-0.0775146484375,
-0.007190704345703125,
0.038604736328125,
0.0018491744995117188,
-0.046142578125,
0.0135955810546875,
-0.013031005859375,
0.01053619384765625,
-0.004367828369140625,
0.042388916015625,
-0.022369384765625,
0.0017547607421875,
0.00508880615234375,
0.0109710693359375,
0.06365966796875,
0.03900146484375,
0.0297393798828125,
0.057342529296875,
-0.09796142578125,
0.00469207763671875,
0.00647735595703125,
-0.0006761550903320312,
-0.033172607421875,
-0.036102294921875,
0.045318603515625,
-0.0007572174072265625,
0.0360107421875,
-0.0247955322265625,
0.037567138671875,
-0.004322052001953125,
0.027557373046875,
0.036834716796875,
-0.0110015869140625,
0.043365478515625,
-0.0400390625,
0.0738525390625,
-0.010009765625,
0.04498291015625,
0.004314422607421875,
-0.020965576171875,
-0.05438232421875,
-0.0248565673828125,
0.040191650390625,
0.034698486328125,
-0.0185546875,
0.0300750732421875,
0.002773284912109375,
-0.07470703125,
-0.0094757080078125,
-0.02154541015625,
0.0292816162109375,
0.0226287841796875,
0.0018129348754882812,
-0.0233612060546875,
-0.0550537109375,
-0.0684814453125,
0.0074005126953125,
-0.030120849609375,
0.021697998046875,
-0.00887298583984375,
0.05145263671875,
-0.01494598388671875,
0.07843017578125,
-0.048797607421875,
0.0001742839813232422,
-0.0234832763671875,
0.01380157470703125,
0.03076171875,
0.04608154296875,
0.0501708984375,
-0.06103515625,
-0.0193328857421875,
-0.0428466796875,
-0.0294647216796875,
-0.043182373046875,
0.02685546875,
-0.032379150390625,
-0.01172637939453125,
0.0194854736328125,
-0.036163330078125,
0.039093017578125,
0.0687255859375,
-0.058746337890625,
0.052825927734375,
-0.007251739501953125,
-0.01320648193359375,
-0.09893798828125,
0.01904296875,
-0.0125732421875,
-0.04071044921875,
-0.0294647216796875,
0.0208892822265625,
0.033935546875,
-0.0100860595703125,
-0.024505615234375,
0.035919189453125,
-0.0496826171875,
-0.0068206787109375,
-0.020599365234375,
-0.033905029296875,
0.0104827880859375,
0.002285003662109375,
-0.01346588134765625,
0.045135498046875,
0.060943603515625,
-0.0195159912109375,
0.034698486328125,
0.037628173828125,
-0.0189208984375,
0.02044677734375,
-0.0675048828125,
-0.0122833251953125,
-0.00594329833984375,
0.01385498046875,
-0.047576904296875,
-0.0308074951171875,
0.043914794921875,
-0.01201629638671875,
0.022064208984375,
-0.0258941650390625,
-0.02313232421875,
-0.03350830078125,
-0.004352569580078125,
0.034759521484375,
0.040252685546875,
-0.005413055419921875,
0.06365966796875,
0.04058837890625,
-0.0247650146484375,
0.002285003662109375,
-0.0408935546875,
-0.0273895263671875,
0.000644683837890625,
-0.043212890625,
0.0008120536804199219,
-0.0235595703125,
-0.037689208984375,
0.00933837890625,
0.01343536376953125,
-0.0303955078125,
-0.009674072265625,
0.05755615234375,
0.039306640625,
-0.01328277587890625,
0.005710601806640625,
0.00043129920959472656,
-0.02978515625,
-0.0085601806640625,
-0.0168609619140625,
0.0272369384765625,
-0.005001068115234375,
-0.03363037109375,
-0.03228759765625,
0.0213165283203125,
0.041259765625,
-0.0190582275390625,
0.037933349609375,
0.037841796875,
-0.035400390625,
0.00864410400390625,
-0.03765869140625,
0.0036602020263671875,
-0.0250396728515625,
0.0174102783203125,
-0.038665771484375,
-0.0408935546875,
0.03204345703125,
-0.0020046234130859375,
-0.04644775390625,
0.05267333984375,
0.038818359375,
0.042633056640625,
0.0295562744140625,
0.07080078125,
0.00228118896484375,
0.054595947265625,
-0.0213775634765625,
0.008392333984375,
-0.06646728515625,
-0.02447509765625,
-0.045867919921875,
0.022430419921875,
-0.04241943359375,
-0.0120391845703125,
0.0026302337646484375,
0.029937744140625,
-0.042999267578125,
0.036346435546875,
-0.053131103515625,
0.0297393798828125,
0.05438232421875,
-0.004791259765625,
0.038360595703125,
-0.0199432373046875,
-0.01517486572265625,
-0.0004525184631347656,
-0.03741455078125,
-0.046417236328125,
0.056610107421875,
0.03875732421875,
0.0679931640625,
0.016510009765625,
0.0384521484375,
-0.01468658447265625,
0.0232696533203125,
-0.040618896484375,
0.0271453857421875,
-0.00879669189453125,
-0.056793212890625,
0.0130767822265625,
-0.0020847320556640625,
-0.0245819091796875,
0.01114654541015625,
-0.01209259033203125,
-0.03363037109375,
0.0037822723388671875,
-0.00658416748046875,
-0.03131103515625,
0.0170745849609375,
-0.038909912109375,
0.08807373046875,
-0.0047149658203125,
0.016143798828125,
0.0200653076171875,
-0.00959014892578125,
0.04571533203125,
0.022674560546875,
0.0306549072265625,
-0.0028362274169921875,
0.0185546875,
0.04864501953125,
-0.024871826171875,
0.0631103515625,
-0.0004248619079589844,
0.0050506591796875,
0.00699615478515625,
0.0098876953125,
0.0272064208984375,
0.01690673828125,
0.00603485107421875,
-0.004505157470703125,
-0.01108551025390625,
-0.0255584716796875,
-0.0037288665771484375,
0.048583984375,
-0.048431396484375,
-0.0036258697509765625,
-0.04412841796875,
-0.0318603515625,
0.02593994140625,
0.031494140625,
0.018890380859375,
0.052520751953125,
-0.0250396728515625,
-0.006317138671875,
0.045257568359375,
0.030517578125,
0.013336181640625,
0.027191162109375,
-0.0672607421875,
-0.033294677734375,
0.026824951171875,
0.0111846923828125,
-0.0032596588134765625,
0.0283355712890625,
0.0282745361328125,
-0.006519317626953125,
-0.044403076171875,
-0.0306549072265625,
0.0202484130859375,
-0.0533447265625,
-0.0010318756103515625,
-0.047210693359375,
-0.034820556640625,
-0.050018310546875,
0.0127716064453125,
-0.01812744140625,
-0.0362548828125,
-0.022491455078125,
-0.0131988525390625,
0.041046142578125,
0.0638427734375,
-0.01137542724609375,
0.040771484375,
-0.08050537109375,
0.028594970703125,
0.0296478271484375,
0.04132080078125,
-0.01198577880859375,
-0.053558349609375,
-0.0213623046875,
-0.03131103515625,
-0.04156494140625,
-0.037567138671875,
0.034942626953125,
-0.009368896484375,
0.044036865234375,
0.0174407958984375,
-0.022491455078125,
0.039520263671875,
-0.04498291015625,
0.0634765625,
0.01544189453125,
-0.058380126953125,
0.0469970703125,
-0.0265655517578125,
0.05242919921875,
0.058441162109375,
0.02142333984375,
-0.0267486572265625,
-0.008575439453125,
-0.056549072265625,
-0.07318115234375,
0.0283966064453125,
0.018310546875,
-0.0105438232421875,
0.02630615234375,
0.01062774658203125,
0.0054473876953125,
0.00966644287109375,
-0.08123779296875,
-0.014617919921875,
-0.02532958984375,
-0.012420654296875,
0.0199737548828125,
-0.05865478515625,
-0.00630950927734375,
-0.01212310791015625,
0.058929443359375,
0.0295562744140625,
-0.0020847320556640625,
-0.01155853271484375,
-0.01087188720703125,
-0.03594970703125,
0.022674560546875,
0.064697265625,
0.06768798828125,
-0.04205322265625,
-0.0038967132568359375,
-0.0396728515625,
-0.05584716796875,
-0.0130157470703125,
0.0305328369140625,
-0.0233154296875,
0.005901336669921875,
0.024078369140625,
0.06256103515625,
0.009796142578125,
0.0024261474609375,
0.01406097412109375,
-0.0081329345703125,
-0.0112152099609375,
-0.0849609375,
0.0035419464111328125,
0.0081024169921875,
0.038848876953125,
0.01479339599609375,
0.027557373046875,
0.044891357421875,
-0.024078369140625,
0.0021381378173828125,
-0.01033782958984375,
-0.042144775390625,
-0.0267333984375,
0.060882568359375,
0.0210113525390625,
-0.049591064453125,
0.01438140869140625,
-0.0233612060546875,
-0.038543701171875,
0.0214080810546875,
0.04254150390625,
0.087890625,
-0.0230255126953125,
0.0109405517578125,
0.03790283203125,
-0.0019969940185546875,
-0.010162353515625,
0.047698974609375,
0.007770538330078125,
-0.00591278076171875,
-0.0199737548828125,
-0.061859130859375,
-0.0276641845703125,
0.00010865926742553711,
-0.03338623046875,
0.0264434814453125,
-0.018707275390625,
-0.005794525146484375,
0.0023746490478515625,
-0.0239105224609375,
-0.01244354248046875,
-0.0036830902099609375,
0.0266265869140625,
0.09375,
-0.05548095703125,
0.07647705078125,
0.07952880859375,
-0.06878662109375,
-0.056915283203125,
-0.0014753341674804688,
0.0185546875,
-0.0228424072265625,
0.076904296875,
0.009857177734375,
-0.022674560546875,
-0.0184478759765625,
-0.03466796875,
-0.058929443359375,
0.073974609375,
0.0001556873321533203,
-0.05816650390625,
-0.024658203125,
-0.0264434814453125,
0.024383544921875,
-0.025909423828125,
0.034332275390625,
0.00214385986328125,
0.046661376953125,
0.00522613525390625,
-0.07379150390625,
-0.0112457275390625,
-0.051239013671875,
0.0400390625,
0.0189971923828125,
-0.03387451171875,
0.093994140625,
0.03094482421875,
0.01035308837890625,
0.04583740234375,
0.05206298828125,
0.0175323486328125,
-0.007595062255859375,
0.034912109375,
0.038818359375,
0.040435791015625,
0.01369476318359375,
0.060699462890625,
-0.027862548828125,
0.06390380859375,
0.0831298828125,
-0.007076263427734375,
0.033935546875,
0.02374267578125,
-0.00820159912109375,
0.04339599609375,
0.028533935546875,
-0.0149383544921875,
0.023101806640625,
0.03369140625,
-0.00794219970703125,
-0.01194000244140625,
0.0011730194091796875,
-0.04010009765625,
0.0284423828125,
-0.0012388229370117188,
-0.036376953125,
-0.02374267578125,
-0.00505828857421875,
0.0012874603271484375,
0.021636962890625,
-0.04034423828125,
0.036712646484375,
-0.0121612548828125,
-0.01454925537109375,
0.0218353271484375,
-0.0169830322265625,
0.049560546875,
-0.06201171875,
-0.024932861328125,
0.01177215576171875,
0.02337646484375,
-0.02532958984375,
-0.0458984375,
0.04046630859375,
-0.0167083740234375,
-0.0390625,
-0.01123809814453125,
0.07904052734375,
-0.03564453125,
-0.07623291015625,
0.019561767578125,
0.0205841064453125,
0.007778167724609375,
-0.0032329559326171875,
-0.057373046875,
0.01068115234375,
-0.01416778564453125,
-0.02264404296875,
-0.01097869873046875,
-0.0013685226440429688,
-0.01366424560546875,
0.039794921875,
0.030059814453125,
0.022003173828125,
-0.007843017578125,
0.036834716796875,
0.04827880859375,
-0.05633544921875,
-0.03802490234375,
-0.037139892578125,
0.056060791015625,
-0.0263519287109375,
-0.0235137939453125,
0.032806396484375,
0.060302734375,
0.06903076171875,
-0.058929443359375,
0.0498046875,
-0.01381683349609375,
0.055694580078125,
-0.045440673828125,
0.0806884765625,
-0.0149383544921875,
-0.03265380859375,
-0.0201263427734375,
-0.0653076171875,
-0.04949951171875,
0.05419921875,
-0.0285186767578125,
-0.01380157470703125,
0.048614501953125,
0.0670166015625,
-0.022491455078125,
0.00531768798828125,
0.031768798828125,
0.01250457763671875,
0.00926971435546875,
0.004505157470703125,
0.04302978515625,
-0.0360107421875,
0.02630615234375,
-0.0157318115234375,
-0.0299224853515625,
-0.0278167724609375,
-0.06781005859375,
-0.06402587890625,
-0.0509033203125,
-0.018707275390625,
-0.0131683349609375,
0.005298614501953125,
0.0740966796875,
0.0533447265625,
-0.0618896484375,
-0.036376953125,
-0.0146636962890625,
-0.0027713775634765625,
0.01546478271484375,
-0.01556396484375,
0.02447509765625,
-0.0006937980651855469,
-0.0684814453125,
0.0024166107177734375,
0.0014801025390625,
0.0270538330078125,
-0.039031982421875,
-0.00014674663543701172,
-0.035125732421875,
-0.00913238525390625,
0.016998291015625,
0.001537322998046875,
-0.04754638671875,
-0.00139617919921875,
-0.0244903564453125,
-0.0288543701171875,
0.015838623046875,
0.05096435546875,
-0.0247344970703125,
0.0301055908203125,
0.0565185546875,
-0.00933074951171875,
0.0282745361328125,
-0.01384735107421875,
0.0210113525390625,
-0.01200103759765625,
0.0189361572265625,
-0.01390838623046875,
0.053497314453125,
0.021453857421875,
-0.035614013671875,
0.047332763671875,
0.018463134765625,
-0.05029296875,
-0.03265380859375,
0.0230712890625,
-0.103759765625,
-0.00785064697265625,
0.05780029296875,
-0.006107330322265625,
-0.054290771484375,
0.018280029296875,
-0.055877685546875,
0.052703857421875,
-0.041900634765625,
0.0384521484375,
0.046630859375,
0.01230621337890625,
-0.034576416015625,
-0.05889892578125,
0.0169219970703125,
-0.0263519287109375,
-0.049072265625,
-0.0177459716796875,
0.033355712890625,
0.0188140869140625,
0.04736328125,
0.043548583984375,
-0.035186767578125,
0.010894775390625,
0.0013799667358398438,
0.051727294921875,
-0.04510498046875,
-0.028594970703125,
-0.0240631103515625,
0.01383209228515625,
0.00861358642578125,
-0.022430419921875
]
] |
timm/mixer_b16_224.goog_in21k_ft_in1k | 2023-03-27T23:03:14.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-21k",
"arxiv:2105.01601",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/mixer_b16_224.goog_in21k_ft_in1k | 1 | 40,802 | timm | 2023-03-27T23:02:23 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-21k
---
# Model card for mixer_b16_224.goog_in21k_ft_in1k
A MLP-Mixer image classification model. Pretrained on ImageNet-21k and fine-tuned on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 59.9
- GMACs: 12.6
- Activations (M): 14.5
- Image size: 224 x 224
- **Papers:**
- MLP-Mixer: An all-MLP Architecture for Vision: https://arxiv.org/abs/2105.01601
- **Original:** https://github.com/google-research/vision_transformers
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-21k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('mixer_b16_224.goog_in21k_ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'mixer_b16_224.goog_in21k_ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 196, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{tolstikhin2021mixer,
title={MLP-Mixer: An all-MLP Architecture for Vision},
author={Tolstikhin, Ilya and Houlsby, Neil and Kolesnikov, Alexander and Beyer, Lucas and Zhai, Xiaohua and Unterthiner, Thomas and Yung, Jessica and Steiner, Andreas and Keysers, Daniel and Uszkoreit, Jakob and Lucic, Mario and Dosovitskiy, Alexey},
journal={arXiv preprint arXiv:2105.01601},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 3,276 | [
[
-0.05157470703125,
-0.023651123046875,
0.0129852294921875,
0.0174407958984375,
-0.0208587646484375,
-0.0305938720703125,
-0.00818634033203125,
-0.033782958984375,
0.022186279296875,
0.0232696533203125,
-0.04388427734375,
-0.0386962890625,
-0.057098388671875,
-0.01342010498046875,
-0.0193939208984375,
0.0718994140625,
-0.00824737548828125,
0.005725860595703125,
-0.019073486328125,
-0.027191162109375,
-0.0184326171875,
-0.0233154296875,
-0.052001953125,
-0.0389404296875,
0.0266265869140625,
0.007320404052734375,
0.044830322265625,
0.03411865234375,
0.04290771484375,
0.032135009765625,
-0.01336669921875,
-0.0048675537109375,
-0.01496124267578125,
-0.0118560791015625,
0.02069091796875,
-0.040985107421875,
-0.05352783203125,
0.03082275390625,
0.058013916015625,
0.04718017578125,
0.0008077621459960938,
0.03802490234375,
0.02044677734375,
0.040130615234375,
-0.03131103515625,
0.0083770751953125,
-0.042083740234375,
0.034637451171875,
-0.00891876220703125,
-0.006244659423828125,
-0.0304718017578125,
-0.0055999755859375,
0.003448486328125,
-0.039794921875,
0.0294342041015625,
-0.00848388671875,
0.09246826171875,
0.0192413330078125,
-0.00472259521484375,
0.0117645263671875,
-0.03570556640625,
0.051116943359375,
-0.051025390625,
0.0380859375,
0.01372528076171875,
0.0262451171875,
-0.0166168212890625,
-0.0850830078125,
-0.0474853515625,
0.00783538818359375,
0.002048492431640625,
0.0186004638671875,
-0.0196685791015625,
0.00957489013671875,
0.0207061767578125,
0.02337646484375,
-0.033538818359375,
0.0011205673217773438,
-0.0325927734375,
-0.01236724853515625,
0.03802490234375,
0.00449371337890625,
0.01296234130859375,
-0.0015583038330078125,
-0.039306640625,
-0.037628173828125,
-0.0212554931640625,
0.0201873779296875,
0.0192108154296875,
0.003879547119140625,
-0.045501708984375,
0.041595458984375,
0.013031005859375,
0.048797607421875,
0.0206298828125,
-0.024139404296875,
0.044036865234375,
-0.0073089599609375,
-0.036346435546875,
-0.0110626220703125,
0.0869140625,
0.04443359375,
0.01317596435546875,
0.0036220550537109375,
-0.0124053955078125,
-0.003498077392578125,
-0.0080413818359375,
-0.0902099609375,
-0.0291290283203125,
0.026397705078125,
-0.041656494140625,
-0.0251312255859375,
0.014617919921875,
-0.04937744140625,
-0.002361297607421875,
-0.00841522216796875,
0.05755615234375,
-0.0136871337890625,
-0.0247344970703125,
-0.000949859619140625,
-0.017913818359375,
0.0240936279296875,
0.01073455810546875,
-0.045684814453125,
0.0162353515625,
0.03106689453125,
0.07818603515625,
0.00002378225326538086,
-0.034576416015625,
-0.0243988037109375,
-0.026458740234375,
-0.0292510986328125,
0.0270538330078125,
0.0009794235229492188,
-0.01531219482421875,
-0.0250396728515625,
0.022430419921875,
-0.0223236083984375,
-0.059326171875,
0.0298614501953125,
-0.0158538818359375,
0.021697998046875,
0.009429931640625,
-0.027618408203125,
-0.0176849365234375,
0.005603790283203125,
-0.0267486572265625,
0.0853271484375,
0.01451873779296875,
-0.05908203125,
0.039337158203125,
-0.03265380859375,
-0.00678253173828125,
-0.01177215576171875,
-0.01363372802734375,
-0.08319091796875,
-0.007740020751953125,
0.01255035400390625,
0.05535888671875,
-0.0087432861328125,
0.0203094482421875,
-0.058929443359375,
-0.0250396728515625,
0.026397705078125,
-0.0181732177734375,
0.0782470703125,
0.015869140625,
-0.0292816162109375,
0.0296630859375,
-0.053070068359375,
0.003265380859375,
0.02685546875,
-0.0225677490234375,
0.0199432373046875,
-0.03912353515625,
0.021728515625,
0.034820556640625,
0.002895355224609375,
-0.0396728515625,
0.00848388671875,
-0.01284027099609375,
0.02606201171875,
0.050537109375,
-0.0124359130859375,
0.03314208984375,
-0.03369140625,
0.0286407470703125,
0.0293121337890625,
0.032958984375,
-0.00151824951171875,
-0.064697265625,
-0.0667724609375,
-0.03485107421875,
0.0271453857421875,
0.027252197265625,
-0.040252685546875,
0.0469970703125,
-0.0160980224609375,
-0.047088623046875,
-0.054168701171875,
0.00971221923828125,
0.02423095703125,
0.044464111328125,
0.026123046875,
-0.045501708984375,
-0.048248291015625,
-0.063720703125,
0.003231048583984375,
0.0136566162109375,
-0.01361846923828125,
0.0193023681640625,
0.044891357421875,
-0.016082763671875,
0.0592041015625,
-0.0184478759765625,
-0.0255279541015625,
-0.014678955078125,
-0.002559661865234375,
0.04931640625,
0.059539794921875,
0.070068359375,
-0.04150390625,
-0.044708251953125,
-0.01430511474609375,
-0.06903076171875,
0.0034637451171875,
0.00603485107421875,
-0.0249786376953125,
0.0220947265625,
0.006587982177734375,
-0.061859130859375,
0.050811767578125,
0.031280517578125,
-0.0310516357421875,
0.041961669921875,
-0.0010919570922851562,
0.007564544677734375,
-0.0867919921875,
0.006336212158203125,
0.022125244140625,
-0.0148162841796875,
-0.039581298828125,
0.0010442733764648438,
0.0054473876953125,
-0.0084991455078125,
-0.049407958984375,
0.048614501953125,
-0.032501220703125,
-0.0212554931640625,
-0.0173492431640625,
-0.01213836669921875,
0.00609588623046875,
0.05419921875,
-0.006061553955078125,
0.028778076171875,
0.06732177734375,
-0.0455322265625,
0.034515380859375,
0.0205230712890625,
-0.017974853515625,
0.039581298828125,
-0.051025390625,
0.0002040863037109375,
0.0020694732666015625,
0.024810791015625,
-0.0782470703125,
-0.01248931884765625,
0.03924560546875,
-0.052337646484375,
0.0457763671875,
-0.048614501953125,
-0.032470703125,
-0.034576416015625,
-0.0305633544921875,
0.030364990234375,
0.055419921875,
-0.060394287109375,
0.05224609375,
0.0198822021484375,
0.0243377685546875,
-0.04437255859375,
-0.063720703125,
-0.01824951171875,
-0.024505615234375,
-0.059478759765625,
0.032012939453125,
-0.0029430389404296875,
0.00762176513671875,
0.0028018951416015625,
-0.0205535888671875,
0.0020389556884765625,
-0.0101470947265625,
0.04144287109375,
0.03753662109375,
-0.018707275390625,
-0.024078369140625,
-0.018157958984375,
-0.01120758056640625,
0.0160675048828125,
-0.0255584716796875,
0.050018310546875,
-0.00656890869140625,
-0.01233673095703125,
-0.0682373046875,
-0.0086822509765625,
0.043182373046875,
-0.0009055137634277344,
0.06585693359375,
0.08673095703125,
-0.0290679931640625,
-0.0019893646240234375,
-0.03363037109375,
-0.0238800048828125,
-0.04052734375,
0.03411865234375,
-0.035491943359375,
-0.0213623046875,
0.07421875,
0.01898193359375,
0.01233673095703125,
0.044708251953125,
0.033203125,
-0.0180206298828125,
0.070556640625,
0.02691650390625,
0.0142364501953125,
0.04901123046875,
-0.064453125,
-0.0113067626953125,
-0.06396484375,
-0.023590087890625,
-0.0260162353515625,
-0.04345703125,
-0.04974365234375,
-0.035491943359375,
0.0328369140625,
0.0130462646484375,
-0.0289764404296875,
0.0217132568359375,
-0.052459716796875,
0.00881195068359375,
0.05157470703125,
0.028778076171875,
-0.0157012939453125,
0.017974853515625,
-0.03363037109375,
-0.0004105567932128906,
-0.0645751953125,
-0.00902557373046875,
0.084716796875,
0.035247802734375,
0.04925537109375,
-0.0128326416015625,
0.051910400390625,
-0.029937744140625,
0.0214385986328125,
-0.05242919921875,
0.052581787109375,
-0.0008020401000976562,
-0.03802490234375,
0.00428009033203125,
-0.036895751953125,
-0.07293701171875,
0.0330810546875,
-0.02899169921875,
-0.054412841796875,
0.01549530029296875,
0.0200653076171875,
-0.000039577484130859375,
0.057281494140625,
-0.05731201171875,
0.07403564453125,
-0.002117156982421875,
-0.035888671875,
0.0231170654296875,
-0.049652099609375,
0.0216064453125,
0.0159912109375,
0.0003478527069091797,
-0.0008401870727539062,
0.026885986328125,
0.078125,
-0.03857421875,
0.06353759765625,
-0.037017822265625,
0.01438140869140625,
0.031982421875,
0.0007395744323730469,
0.0158233642578125,
-0.00799560546875,
0.0083160400390625,
0.0316162109375,
0.007221221923828125,
-0.024932861328125,
-0.040802001953125,
0.0517578125,
-0.0750732421875,
-0.0242767333984375,
-0.021514892578125,
-0.037017822265625,
0.004085540771484375,
0.00421142578125,
0.042999267578125,
0.04046630859375,
0.0287017822265625,
0.0272064208984375,
0.03717041015625,
-0.0137786865234375,
0.041534423828125,
-0.00275421142578125,
-0.039520263671875,
-0.037017822265625,
0.0557861328125,
0.0153961181640625,
0.0204925537109375,
0.006046295166015625,
0.01067352294921875,
-0.0230865478515625,
-0.025634765625,
-0.035614013671875,
0.01904296875,
-0.06011962890625,
-0.0240631103515625,
-0.0484619140625,
-0.032989501953125,
-0.0321044921875,
-0.0015773773193359375,
-0.04998779296875,
-0.033416748046875,
-0.031524658203125,
0.01727294921875,
0.03155517578125,
0.019287109375,
-0.0107421875,
0.0301361083984375,
-0.0458984375,
0.01328277587890625,
0.0132598876953125,
0.049468994140625,
0.0052032470703125,
-0.07427978515625,
-0.01216888427734375,
0.001743316650390625,
-0.04296875,
-0.06494140625,
0.03271484375,
0.015960693359375,
0.0433349609375,
0.0316162109375,
-0.01910400390625,
0.06494140625,
-0.0070037841796875,
0.041046142578125,
0.03192138671875,
-0.051361083984375,
0.042388916015625,
-0.006664276123046875,
0.020660400390625,
0.004787445068359375,
0.027099609375,
-0.018463134765625,
-0.0114288330078125,
-0.0673828125,
-0.0672607421875,
0.06280517578125,
0.02032470703125,
-0.00730133056640625,
0.03143310546875,
0.0394287109375,
-0.007152557373046875,
0.00955963134765625,
-0.07781982421875,
-0.0406494140625,
-0.0293121337890625,
-0.022247314453125,
-0.00691986083984375,
0.0037326812744140625,
-0.01143646240234375,
-0.0587158203125,
0.061859130859375,
-0.0018854141235351562,
0.0576171875,
0.01523590087890625,
0.004985809326171875,
-0.02301025390625,
-0.0202178955078125,
0.02288818359375,
0.0260009765625,
-0.0312042236328125,
0.006580352783203125,
0.007480621337890625,
-0.0467529296875,
0.003833770751953125,
0.012451171875,
-0.00279998779296875,
0.006435394287109375,
0.0255889892578125,
0.07672119140625,
0.00860595703125,
-0.00177001953125,
0.037811279296875,
-0.005859375,
-0.044097900390625,
-0.0247802734375,
0.01311492919921875,
0.007328033447265625,
0.0311431884765625,
0.0276641845703125,
0.0298614501953125,
-0.006679534912109375,
-0.0197906494140625,
0.0157318115234375,
0.04534912109375,
-0.025909423828125,
-0.0274200439453125,
0.07086181640625,
-0.01531219482421875,
-0.0058441162109375,
0.052154541015625,
-0.006137847900390625,
-0.0239715576171875,
0.06884765625,
0.0367431640625,
0.0682373046875,
-0.00388336181640625,
-0.005100250244140625,
0.0498046875,
0.0097808837890625,
0.006504058837890625,
0.0126190185546875,
-0.0021495819091796875,
-0.065185546875,
-0.00995635986328125,
-0.05682373046875,
-0.003948211669921875,
0.0292816162109375,
-0.047119140625,
0.02911376953125,
-0.04840087890625,
-0.037445068359375,
0.0233154296875,
0.01000213623046875,
-0.070068359375,
0.00727081298828125,
0.006988525390625,
0.05084228515625,
-0.058013916015625,
0.058685302734375,
0.06695556640625,
-0.031646728515625,
-0.07330322265625,
-0.022308349609375,
0.00494384765625,
-0.0506591796875,
0.038238525390625,
0.031707763671875,
0.00472259521484375,
0.00600433349609375,
-0.059661865234375,
-0.044891357421875,
0.09881591796875,
0.0284423828125,
-0.0236053466796875,
0.0232086181640625,
0.0013418197631835938,
0.018768310546875,
-0.03155517578125,
0.0300445556640625,
0.01311492919921875,
0.028350830078125,
0.038665771484375,
-0.06915283203125,
0.0017461776733398438,
-0.0302581787109375,
0.00577545166015625,
0.0168914794921875,
-0.0404052734375,
0.07232666015625,
-0.0259552001953125,
-0.0082244873046875,
0.0034637451171875,
0.04425048828125,
0.033935546875,
0.0212249755859375,
0.03857421875,
0.068359375,
0.016937255859375,
-0.02935791015625,
0.056610107421875,
-0.01335906982421875,
0.05169677734375,
0.056915283203125,
0.0125274658203125,
0.04168701171875,
0.043426513671875,
-0.032623291015625,
0.01324462890625,
0.0662841796875,
-0.02783203125,
0.0261383056640625,
0.00453948974609375,
-0.0008745193481445312,
-0.01422119140625,
0.0126800537109375,
-0.038177490234375,
0.03741455078125,
0.01107025146484375,
-0.04290771484375,
-0.00447845458984375,
0.01105499267578125,
0.0001785755157470703,
-0.03607177734375,
-0.0168304443359375,
0.03472900390625,
0.004016876220703125,
-0.033447265625,
0.0626220703125,
-0.00044226646423339844,
0.07220458984375,
-0.0207061767578125,
-0.0008869171142578125,
-0.016448974609375,
0.0274658203125,
-0.0255279541015625,
-0.068359375,
0.01279449462890625,
-0.0274505615234375,
-0.0010519027709960938,
0.005123138427734375,
0.046051025390625,
-0.02532958984375,
-0.0357666015625,
0.0272979736328125,
0.0169525146484375,
0.029083251953125,
0.000988006591796875,
-0.077880859375,
0.0162353515625,
-0.00460052490234375,
-0.041900634765625,
0.03253173828125,
0.0160064697265625,
0.022735595703125,
0.053558349609375,
0.04718017578125,
-0.00946807861328125,
0.0251617431640625,
-0.0026683807373046875,
0.059906005859375,
-0.0323486328125,
-0.033477783203125,
-0.05438232421875,
0.048675537109375,
0.005725860595703125,
-0.0286865234375,
0.040191650390625,
0.04119873046875,
0.080078125,
-0.01201629638671875,
0.02069091796875,
-0.00791168212890625,
-0.00292205810546875,
-0.0293121337890625,
0.056915283203125,
-0.056304931640625,
0.004878997802734375,
-0.0275726318359375,
-0.0745849609375,
-0.02532958984375,
0.059051513671875,
-0.004131317138671875,
0.042877197265625,
0.0230560302734375,
0.0673828125,
-0.03631591796875,
-0.0196685791015625,
0.022125244140625,
0.0163116455078125,
0.01110076904296875,
0.026092529296875,
0.035369873046875,
-0.06231689453125,
0.02996826171875,
-0.05438232421875,
-0.01172637939453125,
-0.0168304443359375,
-0.044403076171875,
-0.06817626953125,
-0.0609130859375,
-0.041259765625,
-0.043731689453125,
-0.0196075439453125,
0.06591796875,
0.0823974609375,
-0.0450439453125,
-0.0225372314453125,
0.0021724700927734375,
-0.0049591064453125,
-0.0224151611328125,
-0.02117919921875,
0.0245513916015625,
-0.00525665283203125,
-0.06329345703125,
-0.01255035400390625,
0.0006756782531738281,
0.04046630859375,
-0.004726409912109375,
-0.01934814453125,
-0.018218994140625,
-0.0216827392578125,
0.030426025390625,
0.0160675048828125,
-0.05084228515625,
-0.0013952255249023438,
-0.0230865478515625,
0.0017328262329101562,
0.0341796875,
0.013458251953125,
-0.041046142578125,
0.031402587890625,
0.028900146484375,
0.01480865478515625,
0.0703125,
-0.0323486328125,
0.0034236907958984375,
-0.0684814453125,
0.04254150390625,
-0.00812530517578125,
0.046875,
0.0199432373046875,
-0.0138702392578125,
0.034637451171875,
0.03546142578125,
-0.036712646484375,
-0.066650390625,
-0.0109100341796875,
-0.08917236328125,
-0.007427215576171875,
0.055572509765625,
-0.018707275390625,
-0.03558349609375,
0.0304107666015625,
0.005390167236328125,
0.048126220703125,
-0.006771087646484375,
0.03656005859375,
0.01824951171875,
-0.0099945068359375,
-0.04742431640625,
-0.047027587890625,
0.026702880859375,
0.020843505859375,
-0.03924560546875,
-0.042266845703125,
0.01277923583984375,
0.05438232421875,
0.0181121826171875,
0.038665771484375,
-0.0228424072265625,
0.0196533203125,
0.011688232421875,
0.0433349609375,
-0.0224456787109375,
-0.02569580078125,
-0.018585205078125,
0.00823211669921875,
-0.011932373046875,
-0.04583740234375
]
] |
albert-base-v1 | 2023-04-06T13:42:57.000Z | [
"transformers",
"pytorch",
"tf",
"safetensors",
"albert",
"fill-mask",
"exbert",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1909.11942",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | null | null | null | albert-base-v1 | 3 | 40,725 | transformers | 2022-03-02T23:29:04 | ---
tags:
- exbert
language: en
license: apache-2.0
datasets:
- bookcorpus
- wikipedia
---
# ALBERT Base v1
Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in
[this paper](https://arxiv.org/abs/1909.11942) and first released in
[this repository](https://github.com/google-research/albert). This model, as all ALBERT models, is uncased: it does not make a difference
between english and English.
Disclaimer: The team releasing ALBERT did not write a model card for this model so this model card has been written by
the Hugging Face team.
## Model description
ALBERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
- Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
- Sentence Ordering Prediction (SOP): ALBERT uses a pretraining loss based on predicting the ordering of two consecutive segments of text.
This way, the model learns an inner representation of the English language that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the ALBERT model as inputs.
ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.
This is the first version of the base model. Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training. It has better results in nearly all downstream tasks.
This model has the following configuration:
- 12 repeating layers
- 128 embedding dimension
- 768 hidden dimension
- 12 attention heads
- 11M parameters
## Intended uses & limitations
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=albert) to look for
fine-tuned versions on a task that interests you.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
generation you should look at model like GPT2.
### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='albert-base-v1')
>>> unmasker("Hello I'm a [MASK] model.")
[
{
"sequence":"[CLS] hello i'm a modeling model.[SEP]",
"score":0.05816134437918663,
"token":12807,
"token_str":"▁modeling"
},
{
"sequence":"[CLS] hello i'm a modelling model.[SEP]",
"score":0.03748830780386925,
"token":23089,
"token_str":"▁modelling"
},
{
"sequence":"[CLS] hello i'm a model model.[SEP]",
"score":0.033725276589393616,
"token":1061,
"token_str":"▁model"
},
{
"sequence":"[CLS] hello i'm a runway model.[SEP]",
"score":0.017313428223133087,
"token":8014,
"token_str":"▁runway"
},
{
"sequence":"[CLS] hello i'm a lingerie model.[SEP]",
"score":0.014405295252799988,
"token":29104,
"token_str":"▁lingerie"
}
]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import AlbertTokenizer, AlbertModel
tokenizer = AlbertTokenizer.from_pretrained('albert-base-v1')
model = AlbertModel.from_pretrained("albert-base-v1")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
and in TensorFlow:
```python
from transformers import AlbertTokenizer, TFAlbertModel
tokenizer = AlbertTokenizer.from_pretrained('albert-base-v1')
model = TFAlbertModel.from_pretrained("albert-base-v1")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)
```
### Limitations and bias
Even if the training data used for this model could be characterized as fairly neutral, this model can have biased
predictions:
```python
>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='albert-base-v1')
>>> unmasker("The man worked as a [MASK].")
[
{
"sequence":"[CLS] the man worked as a chauffeur.[SEP]",
"score":0.029577180743217468,
"token":28744,
"token_str":"▁chauffeur"
},
{
"sequence":"[CLS] the man worked as a janitor.[SEP]",
"score":0.028865724802017212,
"token":29477,
"token_str":"▁janitor"
},
{
"sequence":"[CLS] the man worked as a shoemaker.[SEP]",
"score":0.02581118606030941,
"token":29024,
"token_str":"▁shoemaker"
},
{
"sequence":"[CLS] the man worked as a blacksmith.[SEP]",
"score":0.01849772222340107,
"token":21238,
"token_str":"▁blacksmith"
},
{
"sequence":"[CLS] the man worked as a lawyer.[SEP]",
"score":0.01820771023631096,
"token":3672,
"token_str":"▁lawyer"
}
]
>>> unmasker("The woman worked as a [MASK].")
[
{
"sequence":"[CLS] the woman worked as a receptionist.[SEP]",
"score":0.04604868218302727,
"token":25331,
"token_str":"▁receptionist"
},
{
"sequence":"[CLS] the woman worked as a janitor.[SEP]",
"score":0.028220869600772858,
"token":29477,
"token_str":"▁janitor"
},
{
"sequence":"[CLS] the woman worked as a paramedic.[SEP]",
"score":0.0261906236410141,
"token":23386,
"token_str":"▁paramedic"
},
{
"sequence":"[CLS] the woman worked as a chauffeur.[SEP]",
"score":0.024797942489385605,
"token":28744,
"token_str":"▁chauffeur"
},
{
"sequence":"[CLS] the woman worked as a waitress.[SEP]",
"score":0.024124596267938614,
"token":13678,
"token_str":"▁waitress"
}
]
```
This bias will also affect all fine-tuned versions of this model.
## Training data
The ALBERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038
unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and
headers).
## Training procedure
### Preprocessing
The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 30,000. The inputs of the model are
then of the form:
```
[CLS] Sentence A [SEP] Sentence B [SEP]
```
### Training
The ALBERT procedure follows the BERT setup.
The details of the masking procedure for each sentence are the following:
- 15% of the tokens are masked.
- In 80% of the cases, the masked tokens are replaced by `[MASK]`.
- In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
- In the 10% remaining cases, the masked tokens are left as is.
## Evaluation results
When fine-tuned on downstream tasks, the ALBERT models achieve the following results:
| | Average | SQuAD1.1 | SQuAD2.0 | MNLI | SST-2 | RACE |
|----------------|----------|----------|----------|----------|----------|----------|
|V2 |
|ALBERT-base |82.3 |90.2/83.2 |82.1/79.3 |84.6 |92.9 |66.8 |
|ALBERT-large |85.7 |91.8/85.2 |84.9/81.8 |86.5 |94.9 |75.2 |
|ALBERT-xlarge |87.9 |92.9/86.4 |87.9/84.1 |87.9 |95.4 |80.7 |
|ALBERT-xxlarge |90.9 |94.6/89.1 |89.8/86.9 |90.6 |96.8 |86.8 |
|V1 |
|ALBERT-base |80.1 |89.3/82.3 | 80.0/77.1|81.6 |90.3 | 64.0 |
|ALBERT-large |82.4 |90.6/83.9 | 82.3/79.4|83.5 |91.7 | 68.5 |
|ALBERT-xlarge |85.5 |92.5/86.1 | 86.1/83.1|86.4 |92.4 | 74.8 |
|ALBERT-xxlarge |91.0 |94.8/89.3 | 90.2/87.4|90.8 |96.9 | 86.5 |
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-1909-11942,
author = {Zhenzhong Lan and
Mingda Chen and
Sebastian Goodman and
Kevin Gimpel and
Piyush Sharma and
Radu Soricut},
title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language
Representations},
journal = {CoRR},
volume = {abs/1909.11942},
year = {2019},
url = {http://arxiv.org/abs/1909.11942},
archivePrefix = {arXiv},
eprint = {1909.11942},
timestamp = {Fri, 27 Sep 2019 13:04:21 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
<a href="https://huggingface.co/exbert/?model=albert-base-v1">
<img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png">
</a>
| 9,881 | [
[
-0.00881195068359375,
-0.03839111328125,
0.01390838623046875,
0.025909423828125,
-0.0355224609375,
0.0013017654418945312,
0.007328033447265625,
-0.0111236572265625,
0.025360107421875,
0.0460205078125,
-0.03955078125,
-0.037139892578125,
-0.06097412109375,
0.00922393798828125,
-0.037109375,
0.08782958984375,
0.00540924072265625,
0.0260162353515625,
-0.0008072853088378906,
0.00902557373046875,
-0.027587890625,
-0.0479736328125,
-0.05963134765625,
-0.0218048095703125,
0.0341796875,
0.025115966796875,
0.044769287109375,
0.0526123046875,
0.040557861328125,
0.02978515625,
-0.0008330345153808594,
-0.01465606689453125,
-0.0241851806640625,
0.0028629302978515625,
-0.002475738525390625,
-0.04876708984375,
-0.03546142578125,
0.00708770751953125,
0.04736328125,
0.06268310546875,
-0.0037021636962890625,
0.0244903564453125,
-0.00798797607421875,
0.043121337890625,
-0.0268096923828125,
0.0209503173828125,
-0.0285186767578125,
0.00738525390625,
-0.0197296142578125,
0.005588531494140625,
-0.023040771484375,
-0.0099945068359375,
0.008880615234375,
-0.048309326171875,
0.0165557861328125,
0.0250701904296875,
0.08489990234375,
0.007503509521484375,
-0.0137939453125,
-0.010711669921875,
-0.040557861328125,
0.06341552734375,
-0.050323486328125,
0.0146942138671875,
0.039215087890625,
0.0196685791015625,
-0.0014190673828125,
-0.07366943359375,
-0.0240936279296875,
-0.0063629150390625,
-0.0176849365234375,
-0.001373291015625,
-0.0020046234130859375,
-0.008819580078125,
0.03253173828125,
0.03167724609375,
-0.03436279296875,
-0.000823974609375,
-0.055511474609375,
-0.02313232421875,
0.049560546875,
0.01812744140625,
0.0197296142578125,
-0.020751953125,
-0.025360107421875,
-0.0234832763671875,
-0.0279541015625,
0.00738525390625,
0.0386962890625,
0.0270843505859375,
-0.01824951171875,
0.050933837890625,
-0.0281219482421875,
0.036468505859375,
-0.002002716064453125,
-0.0015325546264648438,
0.036102294921875,
-0.00482940673828125,
-0.034027099609375,
0.0014295578002929688,
0.08135986328125,
0.01788330078125,
0.026885986328125,
-0.006786346435546875,
-0.031982421875,
-0.0031757354736328125,
0.0202484130859375,
-0.05389404296875,
-0.0255889892578125,
0.011016845703125,
-0.035858154296875,
-0.03216552734375,
0.0374755859375,
-0.04840087890625,
-0.00322723388671875,
-0.005886077880859375,
0.0364990234375,
-0.0216522216796875,
-0.016021728515625,
0.01513671875,
-0.0303192138671875,
0.00826263427734375,
0.00734710693359375,
-0.07049560546875,
0.0170440673828125,
0.044189453125,
0.06353759765625,
0.026580810546875,
-0.01557159423828125,
-0.0284576416015625,
-0.01061248779296875,
-0.027435302734375,
0.035980224609375,
-0.0239105224609375,
-0.039276123046875,
0.0028285980224609375,
0.0161285400390625,
-0.0024394989013671875,
-0.0282745361328125,
0.04534912109375,
-0.045013427734375,
0.03790283203125,
-0.00257110595703125,
-0.031280517578125,
-0.01499176025390625,
0.0041961669921875,
-0.056365966796875,
0.080810546875,
0.030670166015625,
-0.051483154296875,
0.022003173828125,
-0.0682373046875,
-0.040313720703125,
0.0182647705078125,
0.007198333740234375,
-0.036224365234375,
0.00917816162109375,
0.01035308837890625,
0.0287933349609375,
-0.00875091552734375,
0.014801025390625,
-0.01412200927734375,
-0.0311126708984375,
0.0241851806640625,
-0.0146484375,
0.08160400390625,
0.0169525146484375,
-0.01806640625,
0.004474639892578125,
-0.0648193359375,
-0.0035572052001953125,
0.0212860107421875,
-0.0228118896484375,
-0.01812744140625,
-0.020050048828125,
0.022674560546875,
0.00870513916015625,
0.0305328369140625,
-0.040313720703125,
0.019683837890625,
-0.0447998046875,
0.03582763671875,
0.05615234375,
-0.005031585693359375,
0.0304718017578125,
-0.032012939453125,
0.044586181640625,
0.0038623809814453125,
-0.006450653076171875,
-0.02142333984375,
-0.044525146484375,
-0.0653076171875,
-0.0231781005859375,
0.039154052734375,
0.055877685546875,
-0.034423828125,
0.04730224609375,
-0.00994110107421875,
-0.0467529296875,
-0.049652099609375,
-0.003383636474609375,
0.0303192138671875,
0.0318603515625,
0.02471923828125,
-0.03167724609375,
-0.0650634765625,
-0.064208984375,
-0.0223388671875,
-0.01480865478515625,
-0.0240631103515625,
-0.0017843246459960938,
0.058929443359375,
-0.0226287841796875,
0.05682373046875,
-0.05047607421875,
-0.027374267578125,
-0.0091400146484375,
0.0244293212890625,
0.038299560546875,
0.059051513671875,
0.0272979736328125,
-0.046356201171875,
-0.0338134765625,
-0.021087646484375,
-0.05633544921875,
-0.0010929107666015625,
-0.00453948974609375,
-0.0189971923828125,
-0.0017309188842773438,
0.035552978515625,
-0.056121826171875,
0.04052734375,
0.0157928466796875,
-0.038818359375,
0.04913330078125,
-0.017913818359375,
0.00603485107421875,
-0.08917236328125,
0.013092041015625,
-0.006351470947265625,
-0.023406982421875,
-0.05548095703125,
-0.00197601318359375,
-0.0095672607421875,
-0.0001728534698486328,
-0.0452880859375,
0.04217529296875,
-0.038299560546875,
0.004520416259765625,
-0.003765106201171875,
-0.01111602783203125,
0.01255035400390625,
0.032257080078125,
-0.0011682510375976562,
0.042724609375,
0.050872802734375,
-0.045623779296875,
0.041412353515625,
0.035552978515625,
-0.047149658203125,
0.018829345703125,
-0.06390380859375,
0.0198974609375,
-0.0033435821533203125,
-0.007232666015625,
-0.0780029296875,
-0.0231170654296875,
0.02850341796875,
-0.039154052734375,
0.0268096923828125,
-0.004192352294921875,
-0.050811767578125,
-0.0364990234375,
-0.01541900634765625,
0.038604736328125,
0.03900146484375,
-0.016876220703125,
0.03265380859375,
0.0246124267578125,
-0.00998687744140625,
-0.048370361328125,
-0.0557861328125,
0.0070037841796875,
-0.01922607421875,
-0.039794921875,
0.0245819091796875,
-0.0010166168212890625,
-0.0196685791015625,
-0.019805908203125,
0.005657196044921875,
-0.00420379638671875,
0.007110595703125,
0.0211181640625,
0.036712646484375,
-0.0216827392578125,
-0.0198211669921875,
-0.0078582763671875,
-0.01462554931640625,
0.02398681640625,
-0.0027103424072265625,
0.053619384765625,
-0.00264739990234375,
-0.01012420654296875,
-0.033233642578125,
0.032989501953125,
0.04791259765625,
-0.00550079345703125,
0.060882568359375,
0.05743408203125,
-0.04266357421875,
0.00592803955078125,
-0.0197601318359375,
-0.013458251953125,
-0.039764404296875,
0.045867919921875,
-0.04217529296875,
-0.062469482421875,
0.055328369140625,
0.0208587646484375,
-0.01285552978515625,
0.052459716796875,
0.0452880859375,
-0.01203155517578125,
0.088623046875,
0.034423828125,
-0.00725555419921875,
0.036163330078125,
-0.01824951171875,
0.02410888671875,
-0.06524658203125,
-0.03594970703125,
-0.035675048828125,
-0.0143585205078125,
-0.033843994140625,
-0.0060882568359375,
0.0151824951171875,
0.02978515625,
-0.039398193359375,
0.0496826171875,
-0.046600341796875,
0.02880859375,
0.06805419921875,
0.0134429931640625,
-0.00893402099609375,
-0.0184783935546875,
-0.005584716796875,
0.00211334228515625,
-0.0318603515625,
-0.03955078125,
0.07763671875,
0.043670654296875,
0.05511474609375,
0.004886627197265625,
0.047119140625,
0.017791748046875,
0.01430511474609375,
-0.040618896484375,
0.044647216796875,
-0.0072479248046875,
-0.06689453125,
-0.024932861328125,
-0.0124664306640625,
-0.0758056640625,
0.01238250732421875,
-0.02020263671875,
-0.07000732421875,
-0.00884246826171875,
-0.0103912353515625,
-0.0299835205078125,
0.00884246826171875,
-0.051971435546875,
0.0836181640625,
-0.0242919921875,
-0.01019287109375,
0.01528167724609375,
-0.06524658203125,
0.0216522216796875,
0.00589752197265625,
0.0135498046875,
-0.011016845703125,
0.013458251953125,
0.0865478515625,
-0.03399658203125,
0.061279296875,
-0.01061248779296875,
0.0165557861328125,
0.0034198760986328125,
0.005504608154296875,
0.0238037109375,
0.00917816162109375,
0.0089874267578125,
0.03131103515625,
0.007785797119140625,
-0.032958984375,
-0.0186920166015625,
0.032623291015625,
-0.06390380859375,
-0.041961669921875,
-0.045867919921875,
-0.040771484375,
0.0166778564453125,
0.03515625,
0.046722412109375,
0.037322998046875,
-0.01526641845703125,
0.0135955810546875,
0.0281829833984375,
-0.01361846923828125,
0.047515869140625,
0.0297088623046875,
-0.02642822265625,
-0.040985107421875,
0.046905517578125,
0.0021076202392578125,
0.0003600120544433594,
0.043121337890625,
0.007633209228515625,
-0.040435791015625,
-0.0175018310546875,
-0.033966064453125,
0.0149993896484375,
-0.04913330078125,
-0.025604248046875,
-0.0479736328125,
-0.0290374755859375,
-0.05145263671875,
-0.00746917724609375,
-0.017730712890625,
-0.0261383056640625,
-0.052642822265625,
-0.0137939453125,
0.0234527587890625,
0.0506591796875,
-0.00553131103515625,
0.046234130859375,
-0.06036376953125,
0.018524169921875,
0.017120361328125,
0.032318115234375,
-0.0216522216796875,
-0.058929443359375,
-0.03851318359375,
0.0022220611572265625,
-0.013824462890625,
-0.061798095703125,
0.051849365234375,
0.007694244384765625,
0.032928466796875,
0.048187255859375,
-0.005558013916015625,
0.046173095703125,
-0.044647216796875,
0.06951904296875,
0.0206451416015625,
-0.0791015625,
0.043670654296875,
-0.0233001708984375,
0.0181884765625,
0.030975341796875,
0.0207061767578125,
-0.0390625,
-0.0281219482421875,
-0.061004638671875,
-0.0731201171875,
0.06964111328125,
0.0196075439453125,
0.022216796875,
0.0012636184692382812,
0.0160980224609375,
0.00745391845703125,
0.032958984375,
-0.06634521484375,
-0.0504150390625,
-0.03460693359375,
-0.0216522216796875,
-0.00905609130859375,
-0.0205841064453125,
-0.00868988037109375,
-0.036834716796875,
0.057891845703125,
0.018157958984375,
0.0401611328125,
0.0006947517395019531,
-0.00908660888671875,
-0.00490570068359375,
0.01320648193359375,
0.05926513671875,
0.0384521484375,
-0.03741455078125,
0.0030689239501953125,
0.0017480850219726562,
-0.041717529296875,
0.00514984130859375,
0.0107269287109375,
-0.0032291412353515625,
0.018280029296875,
0.04217529296875,
0.075439453125,
0.011505126953125,
-0.03741455078125,
0.041778564453125,
0.00881195068359375,
-0.0184478759765625,
-0.045623779296875,
0.01329803466796875,
-0.00798797607421875,
0.00739288330078125,
0.0352783203125,
0.01470947265625,
0.0106201171875,
-0.033477783203125,
0.0273590087890625,
0.02874755859375,
-0.03582763671875,
-0.0212554931640625,
0.07489013671875,
0.0006957054138183594,
-0.0638427734375,
0.055084228515625,
-0.01534271240234375,
-0.0506591796875,
0.051361083984375,
0.05059814453125,
0.0697021484375,
-0.0196075439453125,
0.0121917724609375,
0.043701171875,
0.0244293212890625,
-0.02490234375,
0.01551055908203125,
0.0208892822265625,
-0.06298828125,
-0.0237884521484375,
-0.058685302734375,
-0.018218994140625,
0.01873779296875,
-0.06414794921875,
0.028411865234375,
-0.037322998046875,
-0.00986480712890625,
0.01047515869140625,
-0.006763458251953125,
-0.058013916015625,
0.038665771484375,
0.007843017578125,
0.07379150390625,
-0.0758056640625,
0.06536865234375,
0.059234619140625,
-0.052520751953125,
-0.06500244140625,
-0.0333251953125,
-0.0240936279296875,
-0.08160400390625,
0.053253173828125,
0.03204345703125,
0.0232086181640625,
0.004604339599609375,
-0.048553466796875,
-0.05743408203125,
0.06793212890625,
0.01436614990234375,
-0.037445068359375,
-0.0133514404296875,
0.0155792236328125,
0.03759765625,
-0.04534912109375,
0.046417236328125,
0.04180908203125,
0.0297698974609375,
-0.005001068115234375,
-0.05743408203125,
0.00099945068359375,
-0.0361328125,
0.00439453125,
0.006771087646484375,
-0.031890869140625,
0.08306884765625,
-0.004852294921875,
-0.0027561187744140625,
0.0158538818359375,
0.04925537109375,
0.004993438720703125,
0.016998291015625,
0.035003662109375,
0.049041748046875,
0.046722412109375,
-0.0211639404296875,
0.06451416015625,
-0.016876220703125,
0.044464111328125,
0.059783935546875,
0.0036640167236328125,
0.051055908203125,
0.0311431884765625,
-0.02520751953125,
0.07275390625,
0.059173583984375,
-0.0201263427734375,
0.057830810546875,
0.0093536376953125,
-0.00811767578125,
-0.00568389892578125,
0.0091400146484375,
-0.01910400390625,
0.035430908203125,
0.015045166015625,
-0.041900634765625,
0.0038890838623046875,
0.0004901885986328125,
0.014556884765625,
-0.01485443115234375,
-0.036834716796875,
0.051971435546875,
0.0170440673828125,
-0.051788330078125,
0.0257568359375,
0.016265869140625,
0.04510498046875,
-0.040771484375,
-0.0009441375732421875,
-0.005451202392578125,
0.014984130859375,
-0.0099029541015625,
-0.060546875,
0.016326904296875,
-0.01122283935546875,
-0.031158447265625,
-0.0246124267578125,
0.0440673828125,
-0.0372314453125,
-0.05322265625,
-0.0015687942504882812,
0.0208892822265625,
0.0250396728515625,
-0.01319122314453125,
-0.060394287109375,
-0.01197052001953125,
0.0019159317016601562,
-0.02398681640625,
0.016571044921875,
0.0236053466796875,
0.01203155517578125,
0.041595458984375,
0.054351806640625,
-0.0073699951171875,
0.000621795654296875,
0.003772735595703125,
0.0533447265625,
-0.06878662109375,
-0.061553955078125,
-0.07958984375,
0.05859375,
-0.00738525390625,
-0.042449951171875,
0.050262451171875,
0.05938720703125,
0.0633544921875,
-0.03057861328125,
0.044647216796875,
-0.01129150390625,
0.04437255859375,
-0.02679443359375,
0.058624267578125,
-0.031402587890625,
0.006084442138671875,
-0.026611328125,
-0.061798095703125,
-0.0263824462890625,
0.0672607421875,
-0.00774383544921875,
0.006938934326171875,
0.05316162109375,
0.0599365234375,
0.004138946533203125,
-0.00969696044921875,
0.0205078125,
0.0060577392578125,
0.00615692138671875,
0.029815673828125,
0.046630859375,
-0.0614013671875,
0.029052734375,
-0.021728515625,
-0.0051116943359375,
-0.0270843505859375,
-0.057586669921875,
-0.0792236328125,
-0.044891357421875,
-0.02532958984375,
-0.05303955078125,
-0.0202789306640625,
0.0699462890625,
0.05572509765625,
-0.0758056640625,
-0.0198974609375,
-0.0081329345703125,
0.007068634033203125,
-0.0142364501953125,
-0.0214080810546875,
0.030487060546875,
-0.007686614990234375,
-0.0638427734375,
0.016754150390625,
0.0035858154296875,
0.00540924072265625,
-0.0164794921875,
-0.005725860595703125,
-0.0211334228515625,
-0.0013990402221679688,
0.0257415771484375,
0.01030731201171875,
-0.049041748046875,
-0.033233642578125,
0.00733184814453125,
-0.0225372314453125,
0.0150299072265625,
0.03851318359375,
-0.039947509765625,
0.0272979736328125,
0.02978515625,
0.0211334228515625,
0.04815673828125,
0.00765228271484375,
0.04522705078125,
-0.07354736328125,
0.0206756591796875,
0.019775390625,
0.03973388671875,
0.033721923828125,
-0.031036376953125,
0.0321044921875,
0.03790283203125,
-0.04156494140625,
-0.0684814453125,
-0.00045371055603027344,
-0.07391357421875,
-0.006084442138671875,
0.072998046875,
-0.0093994140625,
-0.02679443359375,
-0.006366729736328125,
-0.0265960693359375,
0.0364990234375,
-0.028533935546875,
0.05181884765625,
0.058837890625,
0.007091522216796875,
-0.019317626953125,
-0.02899169921875,
0.03131103515625,
0.0292510986328125,
-0.03179931640625,
-0.03460693359375,
0.0016050338745117188,
0.03338623046875,
0.0247802734375,
0.0487060546875,
0.000009894371032714844,
0.01111602783203125,
0.020538330078125,
0.0200042724609375,
-0.006969451904296875,
-0.01189422607421875,
-0.0186614990234375,
0.0112457275390625,
-0.00801849365234375,
-0.051788330078125
]
] |
DeepPavlov/rubert-base-cased-sentence | 2021-05-18T18:18:43.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"feature-extraction",
"ru",
"arxiv:1508.05326",
"arxiv:1809.05053",
"arxiv:1908.10084",
"endpoints_compatible",
"has_space",
"region:us"
] | feature-extraction | DeepPavlov | null | null | DeepPavlov/rubert-base-cased-sentence | 14 | 40,665 | transformers | 2022-03-02T23:29:04 | ---
language:
- ru
---
# rubert-base-cased-sentence
Sentence RuBERT \(Russian, cased, 12-layer, 768-hidden, 12-heads, 180M parameters\) is a representation‑based sentence encoder for Russian. It is initialized with RuBERT and fine‑tuned on SNLI\[1\] google-translated to russian and on russian part of XNLI dev set\[2\]. Sentence representations are mean pooled token embeddings in the same manner as in Sentence‑BERT\[3\].
\[1\]: S. R. Bowman, G. Angeli, C. Potts, and C. D. Manning. \(2015\) A large annotated corpus for learning natural language inference. arXiv preprint [arXiv:1508.05326](https://arxiv.org/abs/1508.05326)
\[2\]: Williams A., Bowman S. \(2018\) XNLI: Evaluating Cross-lingual Sentence Representations. arXiv preprint [arXiv:1809.05053](https://arxiv.org/abs/1809.05053)
\[3\]: N. Reimers, I. Gurevych \(2019\) Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv preprint [arXiv:1908.10084](https://arxiv.org/abs/1908.10084)
| 970 | [
[
-0.003078460693359375,
-0.06536865234375,
0.0200958251953125,
0.01534271240234375,
-0.0157623291015625,
0.0038661956787109375,
-0.0384521484375,
0.004852294921875,
0.021728515625,
0.0243377685546875,
-0.0347900390625,
-0.025360107421875,
-0.034454345703125,
0.004848480224609375,
-0.0205535888671875,
0.11492919921875,
-0.0002624988555908203,
0.035247802734375,
-0.00994873046875,
0.00884246826171875,
-0.0175323486328125,
-0.0294189453125,
-0.0061798095703125,
-0.026611328125,
0.028564453125,
0.0389404296875,
0.06500244140625,
0.0302734375,
0.038604736328125,
0.0220947265625,
-0.01116180419921875,
-0.0251922607421875,
-0.0271148681640625,
0.00864410400390625,
-0.0049896240234375,
-0.05023193359375,
-0.0190582275390625,
-0.0024585723876953125,
0.057647705078125,
0.045013427734375,
-0.034088134765625,
-0.005977630615234375,
-0.0288848876953125,
0.05194091796875,
-0.036865234375,
-0.007472991943359375,
-0.043182373046875,
0.02783203125,
-0.023834228515625,
-0.0023670196533203125,
-0.05023193359375,
-0.0137939453125,
0.0098114013671875,
-0.05035400390625,
0.010955810546875,
0.029327392578125,
0.09039306640625,
-0.01373291015625,
-0.0238494873046875,
-0.031585693359375,
-0.0193023681640625,
0.0689697265625,
-0.040191650390625,
0.019561767578125,
0.0166778564453125,
0.0311279296875,
-0.03228759765625,
-0.0572509765625,
-0.0567626953125,
-0.029571533203125,
-0.037322998046875,
0.0067291259765625,
-0.00868988037109375,
0.004474639892578125,
0.0189971923828125,
0.040283203125,
-0.0750732421875,
-0.02392578125,
-0.0243377685546875,
-0.006542205810546875,
0.0222625732421875,
-0.0019683837890625,
0.0145111083984375,
-0.039703369140625,
-0.046112060546875,
-0.0213623046875,
-0.0340576171875,
0.0005612373352050781,
0.035308837890625,
0.012481689453125,
-0.01511383056640625,
0.05926513671875,
-0.0163421630859375,
0.038726806640625,
0.006023406982421875,
0.00803375244140625,
0.037872314453125,
-0.01062774658203125,
-0.024627685546875,
-0.01580810546875,
0.06878662109375,
-0.0034580230712890625,
0.030853271484375,
-0.022125244140625,
-0.0166015625,
0.007568359375,
0.020233154296875,
-0.030548095703125,
-0.032196044921875,
0.016998291015625,
-0.0233306884765625,
-0.0212249755859375,
0.02667236328125,
-0.063720703125,
-0.008819580078125,
0.00418853759765625,
0.0335693359375,
-0.04193115234375,
0.006679534912109375,
0.0216064453125,
-0.0169677734375,
0.04052734375,
0.00958251953125,
-0.050445556640625,
0.044097900390625,
0.05926513671875,
0.035369873046875,
-0.0107269287109375,
-0.020294189453125,
-0.04974365234375,
-0.015869140625,
-0.00907135009765625,
0.05987548828125,
-0.041473388671875,
-0.00865936279296875,
0.02008056640625,
0.00887298583984375,
0.00787353515625,
-0.0218658447265625,
0.053314208984375,
-0.046905517578125,
0.06207275390625,
0.00846099853515625,
-0.0401611328125,
-0.007419586181640625,
0.029693603515625,
-0.035614013671875,
0.08746337890625,
0.00926971435546875,
-0.0538330078125,
0.03375244140625,
-0.05291748046875,
-0.044677734375,
0.00624847412109375,
-0.0013132095336914062,
-0.051513671875,
-0.00373077392578125,
0.0103759765625,
0.038787841796875,
-0.0185546875,
0.031646728515625,
0.00785064697265625,
0.0007872581481933594,
0.05224609375,
0.0079193115234375,
0.06988525390625,
0.019439697265625,
-0.0188751220703125,
0.017181396484375,
-0.056060791015625,
0.01355743408203125,
0.00760650634765625,
-0.027587890625,
-0.01271820068359375,
-0.0122222900390625,
0.03436279296875,
-0.0008912086486816406,
0.006317138671875,
-0.04998779296875,
0.019012451171875,
-0.0256195068359375,
0.0306396484375,
0.04827880859375,
-0.00965118408203125,
0.052520751953125,
-0.023162841796875,
0.04193115234375,
0.011688232421875,
0.0026340484619140625,
-0.027374267578125,
-0.03594970703125,
-0.078369140625,
-0.0120391845703125,
0.037567138671875,
0.057952880859375,
-0.0709228515625,
0.035614013671875,
-0.03668212890625,
-0.0189971923828125,
-0.030426025390625,
-0.0022602081298828125,
0.040496826171875,
0.004009246826171875,
0.018096923828125,
-0.00019085407257080078,
-0.043548583984375,
-0.07818603515625,
-0.027923583984375,
-0.0004565715789794922,
0.0192108154296875,
-0.004711151123046875,
0.06842041015625,
-0.0000730752944946289,
0.0572509765625,
-0.03167724609375,
-0.0213165283203125,
-0.0416259765625,
0.020263671875,
0.03265380859375,
0.049774169921875,
0.029937744140625,
-0.058837890625,
-0.072509765625,
0.02056884765625,
-0.0276641845703125,
0.0037097930908203125,
-0.0302276611328125,
-0.027435302734375,
0.033294677734375,
0.0132598876953125,
-0.06085205078125,
0.038421630859375,
0.038909912109375,
-0.0577392578125,
0.029571533203125,
-0.0090179443359375,
0.0149383544921875,
-0.085205078125,
0.005992889404296875,
-0.004978179931640625,
-0.03826904296875,
-0.060455322265625,
0.0206756591796875,
0.01190185546875,
-0.00499725341796875,
-0.0294342041015625,
0.0216064453125,
-0.054534912109375,
0.005718231201171875,
0.0084228515625,
0.02581787109375,
-0.0015745162963867188,
0.054718017578125,
-0.01166534423828125,
0.054046630859375,
0.048858642578125,
-0.016326904296875,
0.0276336669921875,
0.0289154052734375,
-0.040618896484375,
0.043609619140625,
-0.044647216796875,
0.00676727294921875,
0.002391815185546875,
0.01287841796875,
-0.06890869140625,
-0.00595855712890625,
0.037384033203125,
-0.045318603515625,
0.0236968994140625,
0.0037784576416015625,
-0.0501708984375,
-0.00440216064453125,
-0.03741455078125,
0.02386474609375,
0.049163818359375,
-0.0237579345703125,
0.033294677734375,
0.0245208740234375,
-0.0007114410400390625,
-0.05853271484375,
-0.07904052734375,
0.0204925537109375,
-0.0016107559204101562,
-0.0478515625,
0.02947998046875,
-0.002094268798828125,
-0.02227783203125,
0.01239013671875,
0.0189971923828125,
-0.016265869140625,
-0.026763916015625,
0.0002701282501220703,
0.005329132080078125,
-0.02337646484375,
0.0125274658203125,
-0.005268096923828125,
-0.0058441162109375,
-0.01061248779296875,
0.0162353515625,
0.04119873046875,
-0.017608642578125,
-0.0022373199462890625,
-0.027313232421875,
0.03900146484375,
0.0271148681640625,
-0.0045928955078125,
0.05242919921875,
0.04461669921875,
-0.01055145263671875,
-0.031341552734375,
-0.04180908203125,
-0.00629425048828125,
-0.0338134765625,
0.016571044921875,
-0.0264129638671875,
-0.06829833984375,
0.051239013671875,
0.02130126953125,
-0.026611328125,
0.02984619140625,
0.03857421875,
0.0054931640625,
0.02496337890625,
0.03497314453125,
-0.00531768798828125,
0.03997802734375,
-0.0282135009765625,
0.0147857666015625,
-0.05322265625,
-0.019287109375,
-0.042938232421875,
-0.01210784912109375,
-0.04705810546875,
-0.043731689453125,
0.01511383056640625,
-0.02105712890625,
-0.01067352294921875,
0.03662109375,
-0.0291900634765625,
0.037811279296875,
0.047271728515625,
0.004604339599609375,
0.00539398193359375,
0.0088958740234375,
-0.0160675048828125,
-0.0136871337890625,
-0.0648193359375,
-0.0257720947265625,
0.059295654296875,
0.016387939453125,
0.06378173828125,
0.0229034423828125,
0.033660888671875,
0.03546142578125,
-0.0017862319946289062,
-0.0614013671875,
0.058349609375,
-0.002605438232421875,
-0.0689697265625,
-0.0157470703125,
-0.02667236328125,
-0.08807373046875,
0.022369384765625,
-0.03515625,
-0.04986572265625,
0.00788116455078125,
-0.0166473388671875,
0.0027923583984375,
0.01153564453125,
-0.05633544921875,
0.06982421875,
-0.0014553070068359375,
-0.017333984375,
-0.0278167724609375,
-0.05694580078125,
0.01226043701171875,
0.038482666015625,
0.002471923828125,
0.0013456344604492188,
0.0027713775634765625,
0.054718017578125,
-0.0308837890625,
0.054534912109375,
-0.0053558349609375,
0.01641845703125,
0.019500732421875,
0.01490020751953125,
0.039093017578125,
0.01091766357421875,
0.00145721435546875,
-0.0009074211120605469,
-0.01078033447265625,
-0.03509521484375,
-0.0560302734375,
0.04754638671875,
-0.050384521484375,
-0.045196533203125,
-0.07183837890625,
-0.033355712890625,
0.0173492431640625,
0.0184478759765625,
-0.00555419921875,
0.0263824462890625,
-0.0296783447265625,
0.033966064453125,
0.031341552734375,
-0.0195465087890625,
0.03851318359375,
0.033843994140625,
-0.01641845703125,
-0.05230712890625,
0.0467529296875,
-0.01264190673828125,
0.00783538818359375,
0.06390380859375,
0.01230621337890625,
0.01039886474609375,
-0.0142822265625,
-0.0282745361328125,
0.03289794921875,
-0.0640869140625,
-0.027130126953125,
-0.040435791015625,
-0.00981903076171875,
-0.023223876953125,
-0.0221099853515625,
-0.003879547119140625,
-0.050567626953125,
-0.024627685546875,
-0.00482177734375,
0.040924072265625,
0.0474853515625,
-0.001949310302734375,
0.038177490234375,
-0.032989501953125,
0.0281829833984375,
0.0009531974792480469,
0.0226287841796875,
-0.032989501953125,
-0.04644775390625,
-0.037322998046875,
-0.011688232421875,
-0.013458251953125,
-0.05859375,
0.04144287109375,
0.0286712646484375,
0.05535888671875,
0.0118408203125,
0.007709503173828125,
0.0416259765625,
-0.052642822265625,
0.07904052734375,
0.0141143798828125,
-0.0863037109375,
0.047454833984375,
-0.01873779296875,
0.020660400390625,
0.0264129638671875,
0.00952911376953125,
-0.058990478515625,
-0.0247802734375,
-0.048065185546875,
-0.048980712890625,
0.06689453125,
0.024932861328125,
0.0243377685546875,
-0.01702880859375,
0.0235748291015625,
0.0216064453125,
0.007843017578125,
-0.09027099609375,
-0.032928466796875,
-0.015594482421875,
-0.0221099853515625,
-0.0012636184692382812,
-0.043243408203125,
-0.0232086181640625,
-0.01338958740234375,
0.05462646484375,
0.00705718994140625,
0.049072265625,
0.0273590087890625,
-0.03472900390625,
-0.01043701171875,
0.038360595703125,
0.06829833984375,
0.022552490234375,
-0.0009164810180664062,
0.0136566162109375,
0.01241302490234375,
-0.036865234375,
-0.00328826904296875,
-0.006557464599609375,
0.00164794921875,
0.0131072998046875,
0.03204345703125,
0.06689453125,
0.0107574462890625,
-0.049774169921875,
0.0655517578125,
0.00580596923828125,
-0.0194091796875,
-0.048980712890625,
-0.015869140625,
-0.036590576171875,
0.0152435302734375,
0.0360107421875,
-0.0028781890869140625,
0.01178741455078125,
-0.043548583984375,
0.0227203369140625,
0.035125732421875,
-0.027679443359375,
-0.02862548828125,
0.0207977294921875,
0.005840301513671875,
-0.0282745361328125,
0.029266357421875,
-0.0244293212890625,
-0.05572509765625,
0.025970458984375,
0.031982421875,
0.0732421875,
0.00853729248046875,
0.036468505859375,
0.0171966552734375,
0.03375244140625,
0.007537841796875,
0.034210205078125,
0.002704620361328125,
-0.061248779296875,
-0.036895751953125,
-0.0176849365234375,
-0.02569580078125,
-0.010223388671875,
-0.056640625,
0.0214080810546875,
-0.0274658203125,
0.0021228790283203125,
-0.01468658447265625,
-0.00508880615234375,
-0.0244293212890625,
0.006656646728515625,
-0.01226043701171875,
0.058746337890625,
-0.054412841796875,
0.0601806640625,
0.074462890625,
-0.01409149169921875,
-0.021331787109375,
-0.006595611572265625,
-0.018585205078125,
-0.056121826171875,
0.06719970703125,
-0.01140594482421875,
0.018890380859375,
-0.028778076171875,
-0.042510986328125,
-0.05694580078125,
0.07098388671875,
0.01416015625,
-0.00762176513671875,
0.0340576171875,
0.0214385986328125,
0.050079345703125,
-0.03314208984375,
0.01226043701171875,
0.0156707763671875,
0.0404052734375,
-0.0128173828125,
-0.064208984375,
0.00983428955078125,
-0.041351318359375,
0.01129913330078125,
0.02197265625,
-0.042938232421875,
0.07342529296875,
-0.0082244873046875,
-0.0219573974609375,
0.01763916015625,
0.0462646484375,
-0.0034961700439453125,
-0.0034465789794921875,
0.0257568359375,
0.06207275390625,
0.030426025390625,
-0.020294189453125,
0.0765380859375,
-0.019989013671875,
0.04302978515625,
0.059295654296875,
0.0045623779296875,
0.0732421875,
0.056549072265625,
-0.028289794921875,
0.08282470703125,
0.0223541259765625,
-0.0015621185302734375,
0.057586669921875,
0.024932861328125,
-0.004085540771484375,
-0.005764007568359375,
0.0230712890625,
-0.01235198974609375,
0.02716064453125,
0.0211944580078125,
-0.0286712646484375,
-0.0008101463317871094,
0.01194000244140625,
0.0252685546875,
0.01554107666015625,
-0.0003001689910888672,
0.047454833984375,
-0.01445770263671875,
-0.05108642578125,
0.03228759765625,
-0.00276947021484375,
0.043670654296875,
-0.03717041015625,
-0.0126190185546875,
-0.0086212158203125,
0.0165252685546875,
-0.0086517333984375,
-0.069580078125,
0.007625579833984375,
-0.0052032470703125,
-0.0166778564453125,
-0.028778076171875,
0.040496826171875,
-0.049072265625,
-0.042510986328125,
-0.0011453628540039062,
0.0298309326171875,
0.00904083251953125,
0.03558349609375,
-0.0555419921875,
-0.005641937255859375,
0.003871917724609375,
-0.046630859375,
0.01139068603515625,
0.061676025390625,
0.01253509521484375,
0.056549072265625,
0.034149169921875,
0.002223968505859375,
0.01360321044921875,
-0.004421234130859375,
0.07879638671875,
-0.0623779296875,
-0.043914794921875,
-0.04876708984375,
0.07373046875,
-0.0094757080078125,
-0.042205810546875,
0.05047607421875,
0.044952392578125,
0.05206298828125,
-0.03631591796875,
0.040191650390625,
-0.0288238525390625,
0.036712646484375,
-0.05181884765625,
0.042236328125,
-0.034881591796875,
-0.0023040771484375,
-0.007781982421875,
-0.057464599609375,
-0.061248779296875,
0.075927734375,
-0.026275634765625,
-0.00021827220916748047,
0.088623046875,
0.07061767578125,
-0.0021533966064453125,
-0.023773193359375,
0.033233642578125,
0.0208892822265625,
0.005603790283203125,
0.0278167724609375,
0.0479736328125,
-0.052642822265625,
0.053863525390625,
-0.0181427001953125,
-0.0022983551025390625,
-0.026763916015625,
-0.0635986328125,
-0.08563232421875,
-0.050567626953125,
-0.034881591796875,
-0.0231475830078125,
0.0160980224609375,
0.059051513671875,
0.0377197265625,
-0.08282470703125,
-0.03515625,
-0.025146484375,
0.01221466064453125,
-0.0073089599609375,
-0.02142333984375,
0.0215301513671875,
-0.037872314453125,
-0.0445556640625,
0.012451171875,
0.0098724365234375,
-0.01486968994140625,
-0.019439697265625,
-0.01313018798828125,
-0.047454833984375,
-0.007293701171875,
0.0310821533203125,
0.0008816719055175781,
-0.07220458984375,
-0.038787841796875,
0.01519012451171875,
-0.0183258056640625,
0.024871826171875,
0.06195068359375,
-0.052001953125,
0.03466796875,
0.042938232421875,
0.0222930908203125,
0.037811279296875,
-0.02001953125,
0.050262451171875,
-0.061676025390625,
0.03350830078125,
0.017974853515625,
0.044952392578125,
0.031280517578125,
-0.0217437744140625,
0.041656494140625,
0.0199737548828125,
-0.05572509765625,
-0.058746337890625,
0.00952911376953125,
-0.10552978515625,
-0.007053375244140625,
0.10247802734375,
-0.0228271484375,
-0.028717041015625,
-0.0008573532104492188,
-0.035400390625,
-0.0031490325927734375,
-0.05194091796875,
0.042449951171875,
0.056640625,
0.01434326171875,
-0.047515869140625,
-0.0254364013671875,
0.030792236328125,
0.0484619140625,
-0.03973388671875,
-0.009857177734375,
0.0174407958984375,
0.000720977783203125,
0.0310516357421875,
0.0135345458984375,
-0.0019235610961914062,
0.025634765625,
0.007106781005859375,
0.040313720703125,
0.0196380615234375,
-0.0020122528076171875,
-0.0207672119140625,
0.00791168212890625,
-0.01367950439453125,
-0.01267242431640625
]
] |
timm/resmlp_12_224.fb_in1k | 2023-03-27T23:12:17.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2105.03404",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/resmlp_12_224.fb_in1k | 0 | 40,637 | timm | 2023-03-27T23:12:04 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for resmlp_12_224.fb_in1k
A ResMLP image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 15.4
- GMACs: 3.0
- Activations (M): 5.5
- Image size: 224 x 224
- **Papers:**
- ResMLP: Feedforward networks for image classification with data-efficient training: https://arxiv.org/abs/2105.03404
- **Original:** https://github.com/facebookresearch/deit
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('resmlp_12_224.fb_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'resmlp_12_224.fb_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 196, 384) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{touvron2021resmlp,
title={ResMLP: Feedforward networks for image classification with data-efficient training},
author={Hugo Touvron and Piotr Bojanowski and Mathilde Caron and Matthieu Cord and Alaaeldin El-Nouby and Edouard Grave and Gautier Izacard and Armand Joulin and Gabriel Synnaeve and Jakob Verbeek and Herv'e J'egou},
journal={arXiv preprint arXiv:2105.03404},
year={2021},
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 3,178 | [
[
-0.031005859375,
-0.019775390625,
-0.0024433135986328125,
0.01149749755859375,
-0.0254669189453125,
-0.0299530029296875,
-0.0154266357421875,
-0.032318115234375,
0.016998291015625,
0.02484130859375,
-0.04730224609375,
-0.048797607421875,
-0.049468994140625,
-0.0016260147094726562,
-0.0166778564453125,
0.07635498046875,
-0.0054168701171875,
0.005031585693359375,
-0.0217742919921875,
-0.039031982421875,
-0.0113525390625,
-0.02313232421875,
-0.07037353515625,
-0.03631591796875,
0.0430908203125,
0.0101165771484375,
0.041046142578125,
0.04693603515625,
0.0458984375,
0.033843994140625,
-0.008453369140625,
0.007213592529296875,
-0.0256805419921875,
-0.016387939453125,
0.0184173583984375,
-0.040740966796875,
-0.0258636474609375,
0.0247802734375,
0.053436279296875,
0.034820556640625,
-0.003326416015625,
0.032470703125,
0.0085296630859375,
0.044647216796875,
-0.0217742919921875,
0.017181396484375,
-0.0296783447265625,
0.02734375,
-0.00714111328125,
0.00930023193359375,
-0.029693603515625,
-0.037078857421875,
0.01422119140625,
-0.036834716796875,
0.032623291015625,
0.002155303955078125,
0.09527587890625,
0.01229095458984375,
0.0010137557983398438,
0.004238128662109375,
-0.01358795166015625,
0.049072265625,
-0.06524658203125,
0.034210205078125,
0.0230255126953125,
0.01214599609375,
-0.00455474853515625,
-0.085205078125,
-0.044219970703125,
-0.006793975830078125,
-0.0169830322265625,
-0.006031036376953125,
-0.0198516845703125,
0.00588226318359375,
0.0187225341796875,
0.0229339599609375,
-0.037872314453125,
0.00859832763671875,
-0.03692626953125,
-0.0128173828125,
0.047088623046875,
0.00286102294921875,
0.00804901123046875,
-0.01482391357421875,
-0.0384521484375,
-0.03497314453125,
-0.02166748046875,
0.02288818359375,
0.0271148681640625,
0.024383544921875,
-0.035919189453125,
0.0193328857421875,
0.002231597900390625,
0.048095703125,
0.01224517822265625,
-0.0252838134765625,
0.04925537109375,
0.00010007619857788086,
-0.03179931640625,
-0.011993408203125,
0.08111572265625,
0.0303497314453125,
0.016143798828125,
-0.0032787322998046875,
-0.0120849609375,
-0.0244598388671875,
-0.0010328292846679688,
-0.09368896484375,
-0.0290679931640625,
0.0233001708984375,
-0.053863525390625,
-0.039703369140625,
0.02130126953125,
-0.03759765625,
-0.01161956787109375,
-0.0062103271484375,
0.039337158203125,
-0.026519775390625,
-0.0286102294921875,
-0.0019359588623046875,
-0.00778961181640625,
0.022430419921875,
0.01465606689453125,
-0.035003662109375,
0.015533447265625,
0.0322265625,
0.0904541015625,
0.006500244140625,
-0.040313720703125,
-0.018341064453125,
-0.035247802734375,
-0.023834228515625,
0.03662109375,
-0.0089569091796875,
-0.005863189697265625,
-0.0146636962890625,
0.037811279296875,
-0.020050048828125,
-0.048126220703125,
0.0236358642578125,
-0.0267181396484375,
0.023193359375,
0.0024394989013671875,
-0.0258941650390625,
-0.0389404296875,
0.02325439453125,
-0.0289154052734375,
0.07635498046875,
0.0226287841796875,
-0.0712890625,
0.0203704833984375,
-0.0233612060546875,
-0.0111083984375,
-0.0213165283203125,
0.005298614501953125,
-0.07989501953125,
-0.00943756103515625,
0.0030117034912109375,
0.06903076171875,
-0.0151214599609375,
0.0118408203125,
-0.049468994140625,
-0.01593017578125,
0.0275115966796875,
-0.0099029541015625,
0.06976318359375,
0.0162200927734375,
-0.01189422607421875,
0.016510009765625,
-0.048858642578125,
0.0175628662109375,
0.04071044921875,
-0.02374267578125,
-0.0046234130859375,
-0.040771484375,
0.0145111083984375,
0.0263824462890625,
0.0042572021484375,
-0.048553466796875,
0.0225830078125,
-0.015838623046875,
0.037139892578125,
0.055084228515625,
-0.00868988037109375,
0.023040771484375,
-0.0310821533203125,
0.02294921875,
0.020050048828125,
0.0253143310546875,
-0.001987457275390625,
-0.044891357421875,
-0.050445556640625,
-0.0301971435546875,
0.033538818359375,
0.026519775390625,
-0.03912353515625,
0.036102294921875,
-0.0128326416015625,
-0.064697265625,
-0.030120849609375,
0.005336761474609375,
0.03955078125,
0.057281494140625,
0.0241241455078125,
-0.03436279296875,
-0.03143310546875,
-0.0648193359375,
0.0038928985595703125,
-0.003925323486328125,
0.009033203125,
0.0245819091796875,
0.044830322265625,
-0.01448822021484375,
0.04931640625,
-0.0390625,
-0.019927978515625,
-0.007904052734375,
-0.0019969940185546875,
0.04278564453125,
0.057342529296875,
0.062347412109375,
-0.04754638671875,
-0.03924560546875,
-0.0101165771484375,
-0.07159423828125,
0.00823211669921875,
-0.0011110305786132812,
-0.0189971923828125,
0.0267181396484375,
0.0096282958984375,
-0.048858642578125,
0.0498046875,
0.0199737548828125,
-0.02984619140625,
0.0350341796875,
-0.01031494140625,
0.006473541259765625,
-0.0797119140625,
0.0075836181640625,
0.0305938720703125,
-0.0130462646484375,
-0.037628173828125,
-0.0030956268310546875,
0.0042572021484375,
-0.006595611572265625,
-0.032745361328125,
0.051422119140625,
-0.033935546875,
-0.0039215087890625,
-0.01186370849609375,
-0.020477294921875,
0.0022411346435546875,
0.058380126953125,
0.0034847259521484375,
0.0147552490234375,
0.054962158203125,
-0.03472900390625,
0.044281005859375,
0.033233642578125,
-0.004543304443359375,
0.03338623046875,
-0.047027587890625,
0.01081085205078125,
-0.003070831298828125,
0.026275634765625,
-0.08538818359375,
-0.0134735107421875,
0.0362548828125,
-0.049468994140625,
0.055999755859375,
-0.041717529296875,
-0.0259857177734375,
-0.049163818359375,
-0.032562255859375,
0.02435302734375,
0.0472412109375,
-0.0672607421875,
0.029998779296875,
0.00566864013671875,
0.0163726806640625,
-0.048736572265625,
-0.0665283203125,
-0.0274505615234375,
-0.026214599609375,
-0.059783935546875,
0.027374267578125,
0.0160064697265625,
0.020294189453125,
0.0175933837890625,
-0.01041412353515625,
-0.005092620849609375,
-0.014434814453125,
0.043365478515625,
0.02392578125,
-0.0214080810546875,
0.0016584396362304688,
-0.01763916015625,
-0.00804901123046875,
0.010223388671875,
-0.032196044921875,
0.03948974609375,
-0.0177001953125,
-0.007350921630859375,
-0.0657958984375,
-0.01342010498046875,
0.030517578125,
-0.006610870361328125,
0.0732421875,
0.06964111328125,
-0.036224365234375,
-0.01029205322265625,
-0.0303497314453125,
-0.0283966064453125,
-0.03680419921875,
0.032989501953125,
-0.017913818359375,
-0.026275634765625,
0.0672607421875,
0.00811004638671875,
0.01390838623046875,
0.043121337890625,
0.00891876220703125,
-0.0015954971313476562,
0.05322265625,
0.03375244140625,
0.00644683837890625,
0.053070068359375,
-0.07183837890625,
-0.01605224609375,
-0.059814453125,
-0.036224365234375,
-0.027252197265625,
-0.04864501953125,
-0.048309326171875,
-0.0213165283203125,
0.015899658203125,
0.006622314453125,
-0.037872314453125,
0.0311431884765625,
-0.06329345703125,
0.004863739013671875,
0.04632568359375,
0.047149658203125,
-0.019012451171875,
0.0244598388671875,
-0.0167236328125,
0.0030727386474609375,
-0.06939697265625,
-0.00865936279296875,
0.084228515625,
0.040863037109375,
0.058135986328125,
-0.01511383056640625,
0.052703857421875,
-0.0167388916015625,
0.038116455078125,
-0.046844482421875,
0.043121337890625,
-0.01580810546875,
-0.031219482421875,
-0.004909515380859375,
-0.037811279296875,
-0.07684326171875,
0.0130615234375,
-0.0222930908203125,
-0.044952392578125,
0.0197296142578125,
0.0159454345703125,
-0.0166168212890625,
0.052978515625,
-0.056121826171875,
0.07550048828125,
-0.0057220458984375,
-0.039886474609375,
0.00885009765625,
-0.05413818359375,
0.017547607421875,
0.01322174072265625,
-0.016510009765625,
0.00203704833984375,
0.016876220703125,
0.08551025390625,
-0.05487060546875,
0.0731201171875,
-0.0479736328125,
0.025146484375,
0.036224365234375,
-0.0116119384765625,
0.02392578125,
-0.002162933349609375,
-0.003444671630859375,
0.032989501953125,
0.006717681884765625,
-0.025787353515625,
-0.03912353515625,
0.049468994140625,
-0.07037353515625,
-0.021209716796875,
-0.033477783203125,
-0.026092529296875,
0.00689697265625,
0.0088958740234375,
0.03900146484375,
0.05706787109375,
0.0237579345703125,
0.0258636474609375,
0.04052734375,
-0.02923583984375,
0.031585693359375,
-0.0026111602783203125,
-0.027740478515625,
-0.04400634765625,
0.06610107421875,
0.0248565673828125,
0.01031494140625,
0.004131317138671875,
0.020294189453125,
-0.03240966796875,
-0.03753662109375,
-0.022003173828125,
0.043853759765625,
-0.056732177734375,
-0.0491943359375,
-0.0439453125,
-0.04052734375,
-0.03240966796875,
-0.003948211669921875,
-0.038848876953125,
-0.0279388427734375,
-0.03143310546875,
0.006870269775390625,
0.052764892578125,
0.03778076171875,
-0.01654052734375,
0.041473388671875,
-0.04583740234375,
0.0009226799011230469,
0.01080322265625,
0.046173095703125,
0.015045166015625,
-0.0767822265625,
-0.01557159423828125,
-0.004276275634765625,
-0.03656005859375,
-0.054290771484375,
0.03460693359375,
0.0217742919921875,
0.04046630859375,
0.039764404296875,
-0.0124969482421875,
0.05413818359375,
-0.00847625732421875,
0.0274505615234375,
0.0279388427734375,
-0.033233642578125,
0.04095458984375,
-0.005069732666015625,
0.0034942626953125,
0.01067352294921875,
0.0386962890625,
-0.02850341796875,
0.006786346435546875,
-0.07757568359375,
-0.048919677734375,
0.072509765625,
0.003936767578125,
0.000560760498046875,
0.0259857177734375,
0.068359375,
0.0010833740234375,
0.007160186767578125,
-0.06256103515625,
-0.026275634765625,
-0.0269012451171875,
-0.024444580078125,
0.001110076904296875,
0.0035572052001953125,
0.002716064453125,
-0.052886962890625,
0.061248779296875,
-0.00812530517578125,
0.054443359375,
0.0261383056640625,
0.0137176513671875,
-0.01032257080078125,
-0.042205810546875,
0.0258636474609375,
0.0225067138671875,
-0.0227508544921875,
-0.0010852813720703125,
0.007221221923828125,
-0.043548583984375,
0.00572967529296875,
0.0249481201171875,
0.0000019073486328125,
-0.00400543212890625,
0.04376220703125,
0.067138671875,
-0.0028553009033203125,
0.007320404052734375,
0.03564453125,
-0.01326751708984375,
-0.034271240234375,
-0.02117919921875,
0.007904052734375,
0.0006628036499023438,
0.0391845703125,
0.0228118896484375,
0.0276641845703125,
-0.0132598876953125,
-0.013946533203125,
0.017730712890625,
0.04046630859375,
-0.0251007080078125,
-0.0294036865234375,
0.048492431640625,
-0.01177978515625,
-0.0092620849609375,
0.073974609375,
-0.00595855712890625,
-0.033447265625,
0.0780029296875,
0.03387451171875,
0.07208251953125,
-0.0115814208984375,
0.0094757080078125,
0.062042236328125,
0.01062774658203125,
-0.004642486572265625,
0.0033740997314453125,
0.01067352294921875,
-0.068359375,
0.005275726318359375,
-0.050567626953125,
0.004558563232421875,
0.03179931640625,
-0.04119873046875,
0.0180816650390625,
-0.059417724609375,
-0.03302001953125,
0.0166168212890625,
0.0200347900390625,
-0.059539794921875,
0.0182342529296875,
0.0029811859130859375,
0.0714111328125,
-0.060699462890625,
0.0518798828125,
0.06842041015625,
-0.0350341796875,
-0.08331298828125,
-0.013885498046875,
-0.00559234619140625,
-0.06463623046875,
0.05120849609375,
0.0430908203125,
0.01325225830078125,
0.0087432861328125,
-0.06878662109375,
-0.0447998046875,
0.10211181640625,
0.02581787109375,
-0.006961822509765625,
0.01552581787109375,
-0.01293182373046875,
0.022186279296875,
-0.0301055908203125,
0.025177001953125,
0.004039764404296875,
0.0237884521484375,
0.0299224853515625,
-0.044342041015625,
0.0171966552734375,
-0.021881103515625,
0.0102081298828125,
0.0162811279296875,
-0.068603515625,
0.06732177734375,
-0.033843994140625,
-0.01032257080078125,
0.00428009033203125,
0.053741455078125,
0.0194244384765625,
0.023223876953125,
0.038726806640625,
0.061187744140625,
0.03741455078125,
-0.02734375,
0.06365966796875,
0.0023021697998046875,
0.05389404296875,
0.04193115234375,
0.0252838134765625,
0.042144775390625,
0.0253143310546875,
-0.0308685302734375,
0.0254669189453125,
0.08441162109375,
-0.024169921875,
0.033355712890625,
0.0177459716796875,
0.0068817138671875,
-0.01053619384765625,
0.010467529296875,
-0.03497314453125,
0.034454345703125,
0.009490966796875,
-0.043609619140625,
-0.01491546630859375,
0.01204681396484375,
0.00745391845703125,
-0.021575927734375,
-0.020751953125,
0.035736083984375,
0.00420379638671875,
-0.031463623046875,
0.06573486328125,
0.0012540817260742188,
0.0675048828125,
-0.033966064453125,
0.00250244140625,
-0.032318115234375,
0.031951904296875,
-0.03521728515625,
-0.062255859375,
0.0217132568359375,
-0.0229949951171875,
-0.0074310302734375,
0.002681732177734375,
0.056365966796875,
-0.027313232421875,
-0.03790283203125,
0.016265869140625,
0.01309967041015625,
0.0308685302734375,
-0.0009102821350097656,
-0.09136962890625,
0.003265380859375,
0.00511932373046875,
-0.05078125,
0.02362060546875,
0.0276336669921875,
0.00894927978515625,
0.062286376953125,
0.04766845703125,
-0.0084075927734375,
0.00835418701171875,
-0.02093505859375,
0.06988525390625,
-0.03094482421875,
-0.02874755859375,
-0.057769775390625,
0.034088134765625,
-0.00417327880859375,
-0.0369873046875,
0.039215087890625,
0.03759765625,
0.07513427734375,
-0.007781982421875,
0.0273590087890625,
-0.0220794677734375,
0.0093231201171875,
-0.0298004150390625,
0.06097412109375,
-0.05718994140625,
-0.01073455810546875,
-0.0199737548828125,
-0.053436279296875,
-0.0242462158203125,
0.06842041015625,
-0.0203399658203125,
0.03839111328125,
0.030029296875,
0.07232666015625,
-0.027984619140625,
-0.00984954833984375,
0.006191253662109375,
0.01361846923828125,
0.005542755126953125,
0.0299224853515625,
0.04046630859375,
-0.058807373046875,
0.01904296875,
-0.058319091796875,
-0.0169830322265625,
-0.0079498291015625,
-0.055938720703125,
-0.077392578125,
-0.0655517578125,
-0.04803466796875,
-0.048675537109375,
-0.01473236083984375,
0.06854248046875,
0.079833984375,
-0.05120849609375,
-0.00785064697265625,
0.0025787353515625,
0.00555419921875,
-0.0185699462890625,
-0.0188751220703125,
0.042327880859375,
-0.0081787109375,
-0.04632568359375,
-0.033538818359375,
-0.010986328125,
0.025634765625,
-0.003662109375,
-0.0234527587890625,
-0.0235443115234375,
-0.028472900390625,
0.0182342529296875,
0.0235137939453125,
-0.043243408203125,
-0.011199951171875,
-0.0158233642578125,
0.00021660327911376953,
0.02099609375,
0.02105712890625,
-0.044769287109375,
0.016815185546875,
0.034027099609375,
0.037200927734375,
0.054229736328125,
-0.00920867919921875,
-0.007137298583984375,
-0.06640625,
0.041259765625,
-0.01097869873046875,
0.031982421875,
0.031646728515625,
-0.032257080078125,
0.0516357421875,
0.04693603515625,
-0.041534423828125,
-0.0682373046875,
-0.0163116455078125,
-0.070556640625,
-0.01299285888671875,
0.064208984375,
-0.0352783203125,
-0.03955078125,
0.04736328125,
0.0007891654968261719,
0.0421142578125,
-0.009613037109375,
0.025726318359375,
0.0224151611328125,
-0.0179290771484375,
-0.045074462890625,
-0.034271240234375,
0.033233642578125,
0.004367828369140625,
-0.04473876953125,
-0.02569580078125,
0.0059051513671875,
0.052764892578125,
0.0188751220703125,
0.03131103515625,
-0.0064849853515625,
0.006626129150390625,
0.000308990478515625,
0.02825927734375,
-0.03778076171875,
-0.01334381103515625,
-0.02703857421875,
-0.0022678375244140625,
-0.010955810546875,
-0.043914794921875
]
] |
megagonlabs/transformers-ud-japanese-electra-base-ginza-510 | 2021-12-05T12:12:12.000Z | [
"transformers",
"pytorch",
"electra",
"feature-extraction",
"PyTorch",
"Transformers",
"spaCy",
"ELECTRA",
"GiNZA",
"mC4",
"UD_Japanese-BCCWJ",
"GSK2014-A",
"ja",
"MIT",
"dataset:mC4",
"dataset:UD_Japanese_BCCWJ r2.8",
"dataset:GSK2014-A(2019)",
"arxiv:1910.10683",
"license:mit",
"endpoints_compatible",
"region:us"
] | feature-extraction | megagonlabs | null | null | megagonlabs/transformers-ud-japanese-electra-base-ginza-510 | 2 | 40,512 | transformers | 2022-03-02T23:29:05 | ---
language:
- ja
thumbnail: "https://raw.githubusercontent.com/megagonlabs/ginza/static/docs/images/GiNZA_logo_4c_s.png"
tags:
- PyTorch
- Transformers
- spaCy
- ELECTRA
- GiNZA
- mC4
- UD_Japanese-BCCWJ
- GSK2014-A
- ja
- MIT
license: "mit"
datasets:
- mC4
- UD_Japanese_BCCWJ r2.8
- GSK2014-A(2019)
metrics:
- UAS
- LAS
- UPOS
---
# transformers-ud-japanese-electra-ginza-510 (sudachitra-wordpiece, mC4 Japanese)
This is an [ELECTRA](https://github.com/google-research/electra) model pretrained on approximately 200M Japanese sentences extracted from the [mC4](https://huggingface.co/datasets/mc4) and finetuned by [spaCy v3](https://spacy.io/usage/v3) on [UD\_Japanese\_BCCWJ r2.8](https://universaldependencies.org/treebanks/ja_bccwj/index.html).
The base pretrain model is [megagonlabs/transformers-ud-japanese-electra-base-discrimininator](https://huggingface.co/megagonlabs/transformers-ud-japanese-electra-base-discriminator).
The entire spaCy v3 model is distributed as a python package named [`ja_ginza_electra`](https://pypi.org/project/ja-ginza-electra/) from PyPI along with [`GiNZA v5`](https://github.com/megagonlabs/ginza) which provides some custom pipeline components to recognize the Japanese bunsetu-phrase structures.
Try running it as below:
```console
$ pip install ginza ja_ginza_electra
$ ginza
```
## Licenses
The models are distributed under the terms of the [MIT License](https://opensource.org/licenses/mit-license.php).
## Acknowledgments
This model is permitted to be published under the `MIT License` under a joint research agreement between NINJAL (National Institute for Japanese Language and Linguistics) and Megagon Labs Tokyo.
## Citations
- [mC4](https://huggingface.co/datasets/mc4)
Contains information from `mC4` which is made available under the [ODC Attribution License](https://opendatacommons.org/licenses/by/1-0/).
```
@article{2019t5,
author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
journal = {arXiv e-prints},
year = {2019},
archivePrefix = {arXiv},
eprint = {1910.10683},
}
```
- [UD\_Japanese\_BCCWJ r2.8](https://universaldependencies.org/treebanks/ja_bccwj/index.html)
```
Asahara, M., Kanayama, H., Tanaka, T., Miyao, Y., Uematsu, S., Mori, S.,
Matsumoto, Y., Omura, M., & Murawaki, Y. (2018).
Universal Dependencies Version 2 for Japanese.
In LREC-2018.
```
- [GSK2014-A(2019)](https://www.gsk.or.jp/catalog/gsk2014-a/)
| 2,618 | [
[
-0.0325927734375,
-0.040863037109375,
0.033966064453125,
0.0085906982421875,
-0.0170745849609375,
-0.00740814208984375,
-0.013946533203125,
-0.0258941650390625,
0.0080413818359375,
0.047027587890625,
-0.05218505859375,
-0.035552978515625,
-0.031768798828125,
0.03826904296875,
-0.01483154296875,
0.0762939453125,
-0.0299530029296875,
-0.01387786865234375,
0.005664825439453125,
-0.00936126708984375,
-0.0233154296875,
-0.0280914306640625,
-0.01270294189453125,
-0.036407470703125,
0.022613525390625,
0.031951904296875,
0.03948974609375,
0.031829833984375,
0.0281524658203125,
0.02325439453125,
-0.0024261474609375,
0.0030364990234375,
-0.01181793212890625,
-0.0180206298828125,
-0.0025272369384765625,
-0.057220458984375,
-0.0242462158203125,
-0.01380157470703125,
0.043212890625,
0.029632568359375,
-0.0006604194641113281,
0.00994110107421875,
-0.01387786865234375,
0.03961181640625,
-0.03619384765625,
0.030792236328125,
-0.05316162109375,
0.00345611572265625,
-0.044830322265625,
0.001239776611328125,
-0.03497314453125,
-0.016815185546875,
0.0009927749633789062,
-0.06439208984375,
0.0292816162109375,
-0.00249481201171875,
0.1162109375,
0.01030731201171875,
-0.01479339599609375,
-0.017578125,
-0.034149169921875,
0.042999267578125,
-0.053314208984375,
0.01824951171875,
0.020599365234375,
0.005794525146484375,
-0.0057220458984375,
-0.060760498046875,
-0.05120849609375,
0.001674652099609375,
-0.00994110107421875,
0.037322998046875,
-0.040618896484375,
-0.01399993896484375,
0.045501708984375,
0.0235443115234375,
-0.043121337890625,
0.0215301513671875,
-0.040283203125,
-0.015380859375,
0.03607177734375,
0.0022335052490234375,
0.033172607421875,
-0.051116943359375,
-0.035552978515625,
-0.021209716796875,
-0.049468994140625,
0.005199432373046875,
0.0467529296875,
0.0308685302734375,
-0.0295867919921875,
0.0418701171875,
0.0003306865692138672,
0.032745361328125,
-0.000009775161743164062,
-0.00373077392578125,
0.04766845703125,
-0.02520751953125,
-0.00106048583984375,
-0.002960205078125,
0.0931396484375,
0.0142822265625,
0.0231475830078125,
-0.012298583984375,
0.020721435546875,
0.01488494873046875,
0.01076507568359375,
-0.058746337890625,
-0.019439697265625,
-0.01090240478515625,
-0.00975799560546875,
-0.0028247833251953125,
0.0153350830078125,
-0.08160400390625,
-0.00027632713317871094,
-0.0135955810546875,
0.026611328125,
-0.048065185546875,
-0.035369873046875,
0.01076507568359375,
-0.00782012939453125,
0.03558349609375,
-0.007465362548828125,
-0.07080078125,
0.00829315185546875,
0.013641357421875,
0.0687255859375,
0.0005369186401367188,
-0.02374267578125,
0.009979248046875,
0.018157958984375,
-0.01229095458984375,
0.06695556640625,
-0.0222015380859375,
-0.033782958984375,
-0.005207061767578125,
0.035308837890625,
-0.0245819091796875,
-0.030731201171875,
0.06793212890625,
-0.02020263671875,
0.025726318359375,
-0.0188446044921875,
-0.0296630859375,
-0.0343017578125,
-0.0191192626953125,
-0.052825927734375,
0.07421875,
0.0220947265625,
-0.0797119140625,
0.0110015869140625,
-0.053955078125,
-0.04144287109375,
0.0144500732421875,
-0.0043182373046875,
-0.0587158203125,
-0.003971099853515625,
0.0202178955078125,
0.0367431640625,
-0.01288604736328125,
0.01526641845703125,
-0.0246734619140625,
-0.0160980224609375,
0.01209259033203125,
-0.031951904296875,
0.07470703125,
0.008148193359375,
-0.044708251953125,
-0.002773284912109375,
-0.06842041015625,
-0.01715087890625,
0.027313232421875,
0.01190185546875,
-0.0294342041015625,
-0.021453857421875,
-0.00434112548828125,
0.007762908935546875,
0.02044677734375,
-0.0462646484375,
0.0215606689453125,
-0.0283355712890625,
0.032958984375,
0.05609130859375,
-0.01232147216796875,
0.02252197265625,
-0.0034275054931640625,
0.050628662109375,
0.0202178955078125,
-0.006763458251953125,
-0.02044677734375,
-0.04095458984375,
-0.07861328125,
-0.00579833984375,
0.0234527587890625,
0.044830322265625,
-0.07525634765625,
0.056304931640625,
-0.03961181640625,
-0.05340576171875,
-0.0460205078125,
-0.02081298828125,
0.01311492919921875,
0.031280517578125,
0.046875,
-0.01020050048828125,
-0.06561279296875,
-0.08026123046875,
0.00028395652770996094,
-0.02044677734375,
0.005535125732421875,
0.00244140625,
0.044921875,
-0.043060302734375,
0.0660400390625,
-0.040435791015625,
-0.0243072509765625,
-0.0299530029296875,
0.00910186767578125,
0.03851318359375,
0.0203094482421875,
0.029296875,
-0.040557861328125,
-0.03509521484375,
0.01430511474609375,
-0.054931640625,
-0.024444580078125,
-0.01490020751953125,
-0.02447509765625,
0.016326904296875,
0.0166778564453125,
-0.05047607421875,
0.025604248046875,
0.0345458984375,
-0.0293731689453125,
0.04412841796875,
-0.005947113037109375,
-0.00287628173828125,
-0.1199951171875,
0.031494140625,
0.018096923828125,
-0.0169830322265625,
-0.045501708984375,
-0.0007104873657226562,
0.02484130859375,
0.0106658935546875,
-0.0258331298828125,
0.026031494140625,
-0.02935791015625,
0.0011758804321289062,
-0.0012083053588867188,
0.0159759521484375,
-0.006954193115234375,
0.051239013671875,
-0.002811431884765625,
0.06634521484375,
0.035430908203125,
-0.04443359375,
0.014923095703125,
0.038848876953125,
-0.0272979736328125,
0.0343017578125,
-0.044403076171875,
-0.00226593017578125,
0.005725860595703125,
0.0235443115234375,
-0.05413818359375,
-0.01451873779296875,
0.035552978515625,
-0.024993896484375,
0.0242767333984375,
-0.002529144287109375,
-0.041656494140625,
-0.04388427734375,
-0.00408935546875,
0.00038933753967285156,
0.044647216796875,
-0.051666259765625,
0.03057861328125,
0.023223876953125,
-0.007778167724609375,
-0.039093017578125,
-0.06036376953125,
-0.0096435546875,
-0.02972412109375,
-0.0234527587890625,
0.03717041015625,
-0.002178192138671875,
0.0189361572265625,
-0.00921630859375,
-0.0056610107421875,
-0.0017757415771484375,
0.0014448165893554688,
0.0074615478515625,
0.04327392578125,
-0.006343841552734375,
-0.018890380859375,
0.0227508544921875,
-0.02947998046875,
0.00431060791015625,
0.0078582763671875,
0.054107666015625,
-0.0217132568359375,
0.003620147705078125,
-0.0419921875,
0.005481719970703125,
0.036865234375,
-0.004261016845703125,
0.047088623046875,
0.07177734375,
-0.01299285888671875,
0.003154754638671875,
-0.0191192626953125,
0.0213165283203125,
-0.03564453125,
0.036773681640625,
-0.0567626953125,
-0.06341552734375,
0.03985595703125,
-0.004421234130859375,
0.007633209228515625,
0.07464599609375,
0.040679931640625,
0.01174163818359375,
0.0777587890625,
0.038360595703125,
-0.005390167236328125,
0.0263519287109375,
-0.048980712890625,
0.00829315185546875,
-0.09600830078125,
-0.016876220703125,
-0.048553466796875,
-0.0010929107666015625,
-0.06591796875,
-0.0174713134765625,
0.00827789306640625,
0.0204620361328125,
-0.021820068359375,
0.07708740234375,
-0.036468505859375,
0.0281829833984375,
0.017425537109375,
0.006938934326171875,
0.027801513671875,
0.00431060791015625,
-0.0233306884765625,
-0.01079559326171875,
-0.0499267578125,
-0.04205322265625,
0.0797119140625,
0.031402587890625,
0.03802490234375,
0.0179901123046875,
0.04840087890625,
-0.0150146484375,
0.021209716796875,
-0.047210693359375,
0.048797607421875,
-0.0258331298828125,
-0.042694091796875,
-0.0018863677978515625,
-0.05609130859375,
-0.10089111328125,
0.0229339599609375,
0.00711822509765625,
-0.06854248046875,
0.00585174560546875,
-0.0247039794921875,
-0.00560760498046875,
0.037841796875,
-0.05548095703125,
0.06298828125,
-0.0006456375122070312,
-0.004161834716796875,
0.00746917724609375,
-0.046112060546875,
0.0394287109375,
-0.00609588623046875,
0.021453857421875,
-0.0192413330078125,
-0.002552032470703125,
0.060760498046875,
-0.01507568359375,
0.0517578125,
-0.00103759765625,
-0.021240234375,
0.004833221435546875,
-0.02166748046875,
0.0252227783203125,
-0.00005823373794555664,
0.0017919540405273438,
0.04193115234375,
-0.00267791748046875,
-0.018218994140625,
-0.02716064453125,
0.041229248046875,
-0.07647705078125,
-0.0278167724609375,
-0.040863037109375,
-0.01459503173828125,
-0.00531768798828125,
0.033599853515625,
0.062103271484375,
0.0235443115234375,
0.005458831787109375,
0.02325439453125,
0.04254150390625,
-0.0175323486328125,
0.047393798828125,
0.037689208984375,
-0.0216522216796875,
-0.028900146484375,
0.05682373046875,
0.0190582275390625,
0.0124664306640625,
0.029144287109375,
0.0165252685546875,
-0.034271240234375,
-0.01511383056640625,
-0.055419921875,
0.0350341796875,
-0.0386962890625,
-0.0250244140625,
-0.05694580078125,
-0.031707763671875,
-0.0233917236328125,
0.005626678466796875,
-0.0288543701171875,
-0.0215301513671875,
-0.042205810546875,
-0.0214385986328125,
0.0369873046875,
0.0269927978515625,
0.004276275634765625,
0.01502227783203125,
-0.0545654296875,
0.029571533203125,
0.0020542144775390625,
0.029998779296875,
0.0004935264587402344,
-0.060760498046875,
-0.020172119140625,
0.0006508827209472656,
-0.03662109375,
-0.0740966796875,
0.04290771484375,
-0.0007195472717285156,
0.049468994140625,
0.0122833251953125,
0.009033203125,
0.06640625,
-0.05035400390625,
0.06256103515625,
0.04034423828125,
-0.06878662109375,
0.037872314453125,
-0.0220947265625,
0.037689208984375,
0.0478515625,
0.05120849609375,
-0.0309600830078125,
-0.02825927734375,
-0.07696533203125,
-0.07501220703125,
0.06103515625,
0.0299224853515625,
0.0130462646484375,
0.00908660888671875,
0.010894775390625,
0.0243988037109375,
-0.00650787353515625,
-0.0823974609375,
-0.038726806640625,
-0.022796630859375,
-0.0316162109375,
-0.007579803466796875,
0.00719451904296875,
0.01026153564453125,
-0.0224609375,
0.07135009765625,
-0.0090789794921875,
0.034454345703125,
0.01824951171875,
-0.016387939453125,
-0.00205230712890625,
0.03076171875,
0.033477783203125,
0.023529052734375,
0.00433349609375,
-0.0086822509765625,
0.020599365234375,
-0.04827880859375,
0.01030731201171875,
0.0275726318359375,
-0.0352783203125,
0.026763916015625,
0.01555633544921875,
0.10247802734375,
0.021392822265625,
-0.031402587890625,
0.02972412109375,
-0.01190948486328125,
-0.022491455078125,
-0.0411376953125,
0.00792694091796875,
-0.004119873046875,
-0.0018100738525390625,
0.0220489501953125,
-0.0003705024719238281,
0.00331878662109375,
-0.031494140625,
0.013092041015625,
0.005126953125,
-0.0242462158203125,
-0.04071044921875,
0.04400634765625,
0.005405426025390625,
-0.01099395751953125,
0.034271240234375,
-0.0193634033203125,
-0.048004150390625,
0.0270538330078125,
0.0579833984375,
0.08135986328125,
-0.0156097412109375,
0.0225982666015625,
0.06390380859375,
0.021453857421875,
-0.00841522216796875,
0.003566741943359375,
0.0055389404296875,
-0.0615234375,
-0.0206146240234375,
-0.05548095703125,
-0.0242156982421875,
0.0299224853515625,
-0.05560302734375,
0.032501220703125,
-0.014923095703125,
-0.010528564453125,
-0.007740020751953125,
0.005863189697265625,
-0.046234130859375,
-0.0048065185546875,
0.005359649658203125,
0.037506103515625,
-0.0654296875,
0.0623779296875,
0.04638671875,
-0.053985595703125,
-0.081298828125,
0.0036334991455078125,
-0.0263214111328125,
-0.047607421875,
0.01934814453125,
0.03692626953125,
0.00908660888671875,
0.0235748291015625,
-0.019622802734375,
-0.06890869140625,
0.0911865234375,
0.02569580078125,
-0.04827880859375,
-0.005077362060546875,
0.0095062255859375,
0.0361328125,
0.0064697265625,
0.03936767578125,
0.06024169921875,
0.041534423828125,
-0.00015354156494140625,
-0.06695556640625,
0.0035228729248046875,
-0.035888671875,
0.0129852294921875,
0.025665283203125,
-0.059326171875,
0.043731689453125,
0.011322021484375,
-0.03680419921875,
0.0254669189453125,
0.057342529296875,
0.037506103515625,
-0.005001068115234375,
0.0277099609375,
0.06842041015625,
0.042816162109375,
-0.028900146484375,
0.06695556640625,
-0.00749969482421875,
0.0386962890625,
0.060760498046875,
-0.003993988037109375,
0.061920166015625,
0.019744873046875,
-0.055145263671875,
0.08441162109375,
0.044891357421875,
-0.0211334228515625,
0.0225982666015625,
-0.0020904541015625,
-0.007537841796875,
0.0110321044921875,
0.004932403564453125,
-0.042694091796875,
0.034271240234375,
0.0264739990234375,
-0.01073455810546875,
-0.005168914794921875,
0.0006437301635742188,
0.02691650390625,
-0.004291534423828125,
-0.0172271728515625,
0.057708740234375,
0.014129638671875,
-0.051788330078125,
0.050628662109375,
-0.004657745361328125,
0.07281494140625,
-0.05926513671875,
0.017333984375,
-0.0178375244140625,
0.01236724853515625,
-0.0152587890625,
-0.051605224609375,
0.015716552734375,
0.02423095703125,
-0.00921630859375,
-0.0018949508666992188,
0.040863037109375,
-0.03143310546875,
-0.05096435546875,
0.0177764892578125,
0.005523681640625,
0.01543426513671875,
0.03509521484375,
-0.056365966796875,
-0.006221771240234375,
0.0188446044921875,
-0.01837158203125,
0.0214996337890625,
0.026123046875,
0.0174407958984375,
0.0286712646484375,
0.04827880859375,
0.002475738525390625,
0.0114898681640625,
0.0179901123046875,
0.039886474609375,
-0.0406494140625,
-0.0440673828125,
-0.0595703125,
0.050445556640625,
-0.0198822021484375,
-0.045440673828125,
0.07135009765625,
0.042816162109375,
0.07733154296875,
-0.0154571533203125,
0.06658935546875,
-0.0157470703125,
0.034393310546875,
-0.04736328125,
0.0460205078125,
-0.039764404296875,
0.0012454986572265625,
-0.04644775390625,
-0.08013916015625,
-0.01442718505859375,
0.05810546875,
-0.0057525634765625,
-0.003566741943359375,
0.0594482421875,
0.049468994140625,
0.0035877227783203125,
0.00827789306640625,
0.008941650390625,
0.02264404296875,
0.0254058837890625,
0.056793212890625,
0.045013427734375,
-0.0655517578125,
0.047210693359375,
-0.03216552734375,
-0.0097198486328125,
0.00415802001953125,
-0.049407958984375,
-0.052947998046875,
-0.058868408203125,
-0.0301513671875,
-0.0204315185546875,
-0.0292816162109375,
0.0433349609375,
0.031402587890625,
-0.057342529296875,
-0.020599365234375,
-0.0416259765625,
-0.00897216796875,
0.0021915435791015625,
-0.0223541259765625,
0.031768798828125,
-0.0164031982421875,
-0.067626953125,
0.0168304443359375,
0.006748199462890625,
0.00728607177734375,
-0.01299285888671875,
-0.0011796951293945312,
-0.0302276611328125,
-0.01294708251953125,
0.0220184326171875,
0.025909423828125,
-0.054595947265625,
-0.0188446044921875,
-0.004878997802734375,
-0.005565643310546875,
0.01192474365234375,
0.033447265625,
-0.035430908203125,
0.028594970703125,
0.03155517578125,
0.04150390625,
0.0482177734375,
-0.01522064208984375,
0.034759521484375,
-0.049835205078125,
0.0124664306640625,
-0.0031757354736328125,
0.04510498046875,
0.0286102294921875,
-0.0081939697265625,
0.051116943359375,
0.0474853515625,
-0.031494140625,
-0.045501708984375,
0.0178375244140625,
-0.08001708984375,
-0.01727294921875,
0.0941162109375,
-0.0168914794921875,
-0.0173797607421875,
0.0108795166015625,
-0.0195770263671875,
0.053314208984375,
-0.0084228515625,
0.0367431640625,
0.050567626953125,
0.01058197021484375,
-0.024322509765625,
-0.02630615234375,
0.01788330078125,
0.016693115234375,
-0.07421875,
-0.001407623291015625,
0.01412200927734375,
0.00853729248046875,
0.0328369140625,
0.0255126953125,
-0.0163421630859375,
0.00438690185546875,
-0.01110076904296875,
0.0211029052734375,
0.005733489990234375,
-0.01080322265625,
-0.0305328369140625,
-0.012298583984375,
-0.03851318359375,
-0.0008196830749511719
]
] |
flair/ner-dutch-large | 2021-05-08T15:36:03.000Z | [
"flair",
"pytorch",
"token-classification",
"sequence-tagger-model",
"nl",
"dataset:conll2003",
"arxiv:2011.06993",
"region:us",
"has_space"
] | token-classification | flair | null | null | flair/ner-dutch-large | 4 | 40,407 | flair | 2022-03-02T23:29:05 | ---
tags:
- flair
- token-classification
- sequence-tagger-model
language: nl
datasets:
- conll2003
widget:
- text: "George Washington ging naar Washington"
---
## Dutch NER in Flair (large model)
This is the large 4-class NER model for Dutch that ships with [Flair](https://github.com/flairNLP/flair/).
F1-Score: **95,25** (CoNLL-03 Dutch)
Predicts 4 tags:
| **tag** | **meaning** |
|---------------------------------|-----------|
| PER | person name |
| LOC | location name |
| ORG | organization name |
| MISC | other name |
Based on document-level XLM-R embeddings and [FLERT](https://arxiv.org/pdf/2011.06993v1.pdf/).
---
### Demo: How to use in Flair
Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
```python
from flair.data import Sentence
from flair.models import SequenceTagger
# load tagger
tagger = SequenceTagger.load("flair/ner-dutch-large")
# make example sentence
sentence = Sentence("George Washington ging naar Washington")
# predict NER tags
tagger.predict(sentence)
# print sentence
print(sentence)
# print predicted NER spans
print('The following NER tags are found:')
# iterate over entities and print
for entity in sentence.get_spans('ner'):
print(entity)
```
This yields the following output:
```
Span [1,2]: "George Washington" [− Labels: PER (1.0)]
Span [5]: "Washington" [− Labels: LOC (1.0)]
```
So, the entities "*George Washington*" (labeled as a **person**) and "*Washington*" (labeled as a **location**) are found in the sentence "*George Washington ging naar Washington*".
---
### Training: Script to train this model
The following Flair script was used to train this model:
```python
import torch
# 1. get the corpus
from flair.datasets import CONLL_03_DUTCH
corpus = CONLL_03_DUTCH()
# 2. what tag do we want to predict?
tag_type = 'ner'
# 3. make the tag dictionary from the corpus
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
# 4. initialize fine-tuneable transformer embeddings WITH document context
from flair.embeddings import TransformerWordEmbeddings
embeddings = TransformerWordEmbeddings(
model='xlm-roberta-large',
layers="-1",
subtoken_pooling="first",
fine_tune=True,
use_context=True,
)
# 5. initialize bare-bones sequence tagger (no CRF, no RNN, no reprojection)
from flair.models import SequenceTagger
tagger = SequenceTagger(
hidden_size=256,
embeddings=embeddings,
tag_dictionary=tag_dictionary,
tag_type='ner',
use_crf=False,
use_rnn=False,
reproject_embeddings=False,
)
# 6. initialize trainer with AdamW optimizer
from flair.trainers import ModelTrainer
trainer = ModelTrainer(tagger, corpus, optimizer=torch.optim.AdamW)
# 7. run training with XLM parameters (20 epochs, small LR)
from torch.optim.lr_scheduler import OneCycleLR
trainer.train('resources/taggers/ner-dutch-large',
learning_rate=5.0e-6,
mini_batch_size=4,
mini_batch_chunk_size=1,
max_epochs=20,
scheduler=OneCycleLR,
embeddings_storage_mode='none',
weight_decay=0.,
)
)
```
---
### Cite
Please cite the following paper when using this model.
```
@misc{schweter2020flert,
title={FLERT: Document-Level Features for Named Entity Recognition},
author={Stefan Schweter and Alan Akbik},
year={2020},
eprint={2011.06993},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
---
### Issues?
The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).
| 3,638 | [
[
-0.03955078125,
-0.04132080078125,
0.014312744140625,
0.00852203369140625,
-0.009735107421875,
-0.013397216796875,
-0.0227508544921875,
-0.039947509765625,
0.038330078125,
0.0299835205078125,
-0.0285797119140625,
-0.044891357421875,
-0.040771484375,
0.0259552001953125,
-0.0110321044921875,
0.07958984375,
-0.00014340877532958984,
0.01427459716796875,
0.00002110004425048828,
0.0011463165283203125,
-0.0236663818359375,
-0.04144287109375,
-0.0552978515625,
-0.0242767333984375,
0.053436279296875,
0.0238189697265625,
0.029571533203125,
0.046722412109375,
0.029876708984375,
0.02081298828125,
-0.0127105712890625,
0.005741119384765625,
-0.0196533203125,
-0.0064697265625,
-0.0029010772705078125,
-0.025909423828125,
-0.052093505859375,
-0.0024967193603515625,
0.04266357421875,
0.029876708984375,
0.011138916015625,
0.00197601318359375,
-0.0023746490478515625,
0.0207977294921875,
-0.026702880859375,
0.02911376953125,
-0.04754638671875,
-0.0115814208984375,
-0.0135498046875,
-0.00409698486328125,
-0.03564453125,
-0.02069091796875,
0.02557373046875,
-0.0430908203125,
0.01406097412109375,
0.01554107666015625,
0.10723876953125,
0.00711822509765625,
-0.0308685302734375,
-0.0132293701171875,
-0.040618896484375,
0.06829833984375,
-0.071044921875,
0.018768310546875,
0.0217437744140625,
0.0016078948974609375,
0.0019817352294921875,
-0.050018310546875,
-0.049468994140625,
-0.0135650634765625,
-0.0017080307006835938,
0.01483154296875,
-0.01751708984375,
-0.00856781005859375,
0.0281524658203125,
0.0030536651611328125,
-0.049102783203125,
0.006069183349609375,
-0.0252838134765625,
-0.01641845703125,
0.048553466796875,
0.01230621337890625,
0.0030384063720703125,
-0.0236968994140625,
-0.03887939453125,
-0.01641845703125,
-0.0250091552734375,
-0.00882720947265625,
0.02044677734375,
0.036834716796875,
-0.014556884765625,
0.03802490234375,
0.004039764404296875,
0.056854248046875,
0.00881195068359375,
-0.01026153564453125,
0.046173095703125,
-0.0007300376892089844,
-0.015350341796875,
0.00786590576171875,
0.0640869140625,
0.026611328125,
0.0205230712890625,
-0.00018727779388427734,
-0.0188751220703125,
0.0019521713256835938,
-0.00629425048828125,
-0.06427001953125,
-0.0321044921875,
0.01165771484375,
-0.02197265625,
-0.02093505859375,
0.0112457275390625,
-0.051513671875,
-0.006320953369140625,
-0.0146331787109375,
0.05401611328125,
-0.048248291015625,
-0.01544952392578125,
0.001708984375,
-0.02130126953125,
0.034423828125,
0.0196380615234375,
-0.059967041015625,
-0.00035071372985839844,
0.0255584716796875,
0.05291748046875,
0.0118865966796875,
-0.020355224609375,
-0.016937255859375,
-0.0060577392578125,
-0.0211334228515625,
0.0460205078125,
-0.0290374755859375,
-0.0155181884765625,
-0.00249481201171875,
0.01056671142578125,
-0.01934814453125,
-0.0171966552734375,
0.0345458984375,
-0.05401611328125,
0.0231475830078125,
-0.0254974365234375,
-0.06280517578125,
-0.036468505859375,
0.0214996337890625,
-0.048370361328125,
0.07275390625,
0.01345062255859375,
-0.08477783203125,
0.039764404296875,
-0.038482666015625,
-0.02197265625,
-0.0010986328125,
-0.00012576580047607422,
-0.0484619140625,
-0.0100250244140625,
0.0102081298828125,
0.055816650390625,
-0.01030731201171875,
0.01175689697265625,
-0.0262603759765625,
-0.002742767333984375,
0.0070953369140625,
0.00141143798828125,
0.0628662109375,
0.00829315185546875,
-0.0249176025390625,
0.005584716796875,
-0.0709228515625,
-0.005157470703125,
0.02459716796875,
-0.0297698974609375,
-0.0171356201171875,
-0.0144500732421875,
0.025726318359375,
0.02252197265625,
0.0183563232421875,
-0.03765869140625,
0.034912109375,
-0.03955078125,
0.0261077880859375,
0.04229736328125,
0.00548553466796875,
0.03167724609375,
-0.029388427734375,
0.032196044921875,
0.0092926025390625,
-0.016021728515625,
-0.002445220947265625,
-0.043853759765625,
-0.063720703125,
-0.0175628662109375,
0.040069580078125,
0.043609619140625,
-0.053192138671875,
0.059722900390625,
-0.0276947021484375,
-0.0589599609375,
-0.01331329345703125,
-0.0183258056640625,
0.0122222900390625,
0.04925537109375,
0.042449951171875,
-0.008087158203125,
-0.0635986328125,
-0.0653076171875,
-0.002704620361328125,
0.00858306884765625,
0.00968170166015625,
0.0186309814453125,
0.07666015625,
-0.0250701904296875,
0.069580078125,
-0.030029296875,
-0.0256195068359375,
-0.03466796875,
0.0153961181640625,
0.0401611328125,
0.045867919921875,
0.043670654296875,
-0.04534912109375,
-0.0556640625,
-0.007274627685546875,
-0.04229736328125,
0.0170440673828125,
-0.0096588134765625,
0.002899169921875,
0.035552978515625,
0.0281219482421875,
-0.03558349609375,
0.036041259765625,
0.022430419921875,
-0.032623291015625,
0.04412841796875,
-0.01200103759765625,
-0.0220184326171875,
-0.097412109375,
0.01953125,
0.014312744140625,
-0.01444244384765625,
-0.03741455078125,
-0.028533935546875,
0.01541900634765625,
0.01358795166015625,
-0.0256805419921875,
0.05670166015625,
-0.040496826171875,
0.00923919677734375,
-0.0123443603515625,
-0.00293731689453125,
0.004840850830078125,
0.027740478515625,
0.0225830078125,
0.0297088623046875,
0.05218505859375,
-0.0472412109375,
0.014068603515625,
0.0335693359375,
-0.033477783203125,
0.013702392578125,
-0.041229248046875,
-0.0044097900390625,
-0.00418853759765625,
0.022430419921875,
-0.060791015625,
-0.0218505859375,
0.01468658447265625,
-0.039306640625,
0.05859375,
-0.0012226104736328125,
-0.03106689453125,
-0.03948974609375,
-0.01806640625,
0.00628662109375,
0.03369140625,
-0.03631591796875,
0.050140380859375,
0.01012420654296875,
0.01059722900390625,
-0.06317138671875,
-0.05303955078125,
-0.0016622543334960938,
-0.016387939453125,
-0.04888916015625,
0.041046142578125,
0.0008645057678222656,
0.00652313232421875,
0.00391387939453125,
-0.006839752197265625,
0.004261016845703125,
0.0024471282958984375,
0.01103973388671875,
0.034912109375,
-0.0164947509765625,
0.0007982254028320312,
-0.019561767578125,
-0.0080108642578125,
0.002895355224609375,
-0.0178680419921875,
0.055084228515625,
-0.007534027099609375,
0.0171356201171875,
-0.035919189453125,
0.005466461181640625,
0.0243988037109375,
-0.01751708984375,
0.0797119140625,
0.0684814453125,
-0.035552978515625,
-0.01494598388671875,
-0.0369873046875,
-0.020294189453125,
-0.028839111328125,
0.046417236328125,
-0.03125,
-0.045806884765625,
0.047210693359375,
0.01308441162109375,
0.01184844970703125,
0.0665283203125,
0.032470703125,
0.00551605224609375,
0.0792236328125,
0.052642822265625,
-0.00445556640625,
0.038970947265625,
-0.059814453125,
0.00997161865234375,
-0.0677490234375,
-0.01519775390625,
-0.0340576171875,
-0.0172576904296875,
-0.050567626953125,
-0.016265869140625,
0.0141143798828125,
0.0200042724609375,
-0.04754638671875,
0.052520751953125,
-0.044891357421875,
0.01282501220703125,
0.044219970703125,
0.0012655258178710938,
-0.007640838623046875,
-0.01448822021484375,
-0.0281524658203125,
-0.0114288330078125,
-0.060882568359375,
-0.046112060546875,
0.08148193359375,
0.02679443359375,
0.056304931640625,
-0.01396942138671875,
0.0679931640625,
-0.0156402587890625,
0.027587890625,
-0.055084228515625,
0.031829833984375,
-0.00016009807586669922,
-0.061309814453125,
-0.008575439453125,
-0.0279388427734375,
-0.07861328125,
0.00829315185546875,
-0.03387451171875,
-0.06195068359375,
0.0233154296875,
0.00579833984375,
-0.03387451171875,
0.04205322265625,
-0.032440185546875,
0.07452392578125,
-0.00901031494140625,
-0.019622802734375,
0.019287109375,
-0.0638427734375,
0.0153656005859375,
-0.0029621124267578125,
0.01056671142578125,
-0.0103607177734375,
-0.0005125999450683594,
0.0802001953125,
-0.02569580078125,
0.061737060546875,
-0.01029205322265625,
0.00647735595703125,
0.00689697265625,
-0.00457763671875,
0.040557861328125,
0.003948211669921875,
-0.01849365234375,
0.01727294921875,
-0.0026035308837890625,
-0.01788330078125,
-0.005092620849609375,
0.054473876953125,
-0.06951904296875,
-0.0237884521484375,
-0.062744140625,
-0.02392578125,
0.006420135498046875,
0.0270233154296875,
0.058563232421875,
0.036712646484375,
-0.004364013671875,
0.01062774658203125,
0.0430908203125,
-0.025726318359375,
0.050689697265625,
0.02191162109375,
-0.0297088623046875,
-0.03887939453125,
0.0572509765625,
0.019073486328125,
0.003086090087890625,
0.037261962890625,
0.00701141357421875,
-0.02362060546875,
-0.0225982666015625,
-0.0157012939453125,
0.0306396484375,
-0.05364990234375,
-0.043731689453125,
-0.06805419921875,
-0.0263671875,
-0.04718017578125,
-0.016998291015625,
-0.02703857421875,
-0.0282745361328125,
-0.054473876953125,
0.0016574859619140625,
0.03570556640625,
0.05352783203125,
-0.0137939453125,
0.0219573974609375,
-0.044036865234375,
-0.00884246826171875,
0.00536346435546875,
0.006317138671875,
0.005535125732421875,
-0.063232421875,
-0.02587890625,
-0.0115203857421875,
-0.031219482421875,
-0.07049560546875,
0.07354736328125,
0.01264190673828125,
0.0276336669921875,
0.0307159423828125,
0.004741668701171875,
0.03466796875,
-0.0377197265625,
0.0556640625,
0.015716552734375,
-0.061065673828125,
0.036895751953125,
-0.0173187255859375,
0.01081085205078125,
0.01253509521484375,
0.04962158203125,
-0.02557373046875,
-0.01081085205078125,
-0.05926513671875,
-0.08343505859375,
0.058074951171875,
0.0010232925415039062,
0.00724029541015625,
-0.0242767333984375,
0.0234527587890625,
-0.0058135986328125,
-0.0013856887817382812,
-0.07794189453125,
-0.042205810546875,
-0.0151519775390625,
-0.0023746490478515625,
-0.01459503173828125,
-0.0165557861328125,
0.01367950439453125,
-0.032379150390625,
0.08868408203125,
0.0013866424560546875,
0.0404052734375,
0.031890869140625,
0.00010180473327636719,
-0.0036373138427734375,
0.00830841064453125,
0.040496826171875,
0.036376953125,
-0.038970947265625,
-0.0082855224609375,
0.0241241455078125,
-0.01641845703125,
-0.0179443359375,
0.0186004638671875,
-0.0024394989013671875,
0.0217132568359375,
0.034088134765625,
0.0640869140625,
0.0196533203125,
-0.0078887939453125,
0.04266357421875,
0.0038051605224609375,
-0.025726318359375,
-0.05364990234375,
-0.003971099853515625,
0.0113372802734375,
0.0116424560546875,
0.0294647216796875,
0.0193939208984375,
-0.01200103759765625,
-0.0252685546875,
0.005695343017578125,
0.036956787109375,
-0.0285186767578125,
-0.029296875,
0.07818603515625,
-0.0017499923706054688,
-0.0052490234375,
0.03680419921875,
-0.03265380859375,
-0.0604248046875,
0.056365966796875,
0.045196533203125,
0.0572509765625,
-0.008453369140625,
-0.007904052734375,
0.06488037109375,
0.01812744140625,
-0.01312255859375,
0.038299560546875,
0.033294677734375,
-0.06427001953125,
-0.0310821533203125,
-0.0634765625,
-0.006618499755859375,
0.0133819580078125,
-0.049835205078125,
0.05029296875,
-0.0241241455078125,
-0.027862548828125,
0.0306549072265625,
0.018951416015625,
-0.077392578125,
0.015106201171875,
0.0261383056640625,
0.0919189453125,
-0.058990478515625,
0.07745361328125,
0.055877685546875,
-0.051910400390625,
-0.07916259765625,
-0.0157623291015625,
-0.01100921630859375,
-0.05413818359375,
0.0653076171875,
0.036590576171875,
0.0279388427734375,
0.01751708984375,
-0.05035400390625,
-0.08843994140625,
0.08856201171875,
0.0012111663818359375,
-0.044769287109375,
-0.0162811279296875,
-0.0278167724609375,
0.023895263671875,
-0.0257415771484375,
0.038330078125,
0.0230865478515625,
0.0460205078125,
0.00347137451171875,
-0.06842041015625,
-0.001434326171875,
-0.00812530517578125,
0.0018825531005859375,
0.0188140869140625,
-0.04290771484375,
0.08538818359375,
-0.019989013671875,
-0.00873565673828125,
0.021942138671875,
0.06060791015625,
0.00336456298828125,
0.00975799560546875,
0.0194854736328125,
0.0626220703125,
0.04571533203125,
-0.0165557861328125,
0.0784912109375,
-0.02862548828125,
0.0576171875,
0.0765380859375,
-0.0167388916015625,
0.06494140625,
0.023193359375,
-0.0063934326171875,
0.048248291015625,
0.05084228515625,
-0.0205535888671875,
0.0369873046875,
0.02191162109375,
-0.0015516281127929688,
-0.021942138671875,
0.011749267578125,
-0.042877197265625,
0.041961669921875,
0.0227813720703125,
-0.039306640625,
-0.0093841552734375,
0.0053863525390625,
0.027923583984375,
-0.0181884765625,
-0.0256500244140625,
0.0518798828125,
0.0029239654541015625,
-0.0284576416015625,
0.050140380859375,
0.0064697265625,
0.0751953125,
-0.03790283203125,
0.002071380615234375,
0.00386810302734375,
0.019927978515625,
-0.0179290771484375,
-0.038482666015625,
0.009979248046875,
-0.01450347900390625,
-0.0154876708984375,
-0.0013265609741210938,
0.04132080078125,
-0.031982421875,
-0.03790283203125,
0.0263671875,
0.03033447265625,
0.013519287109375,
-0.004497528076171875,
-0.055206298828125,
-0.01198577880859375,
0.0007252693176269531,
-0.04473876953125,
0.011810302734375,
0.02606201171875,
0.006000518798828125,
0.032257080078125,
0.03753662109375,
0.00310516357421875,
0.0012407302856445312,
-0.0125579833984375,
0.06292724609375,
-0.06695556640625,
-0.02606201171875,
-0.0634765625,
0.033477783203125,
-0.0066375732421875,
-0.034942626953125,
0.058441162109375,
0.06280517578125,
0.06695556640625,
-0.013336181640625,
0.054962158203125,
-0.030120849609375,
0.046630859375,
-0.0181732177734375,
0.056365966796875,
-0.041717529296875,
0.004364013671875,
-0.0236358642578125,
-0.0750732421875,
-0.036773681640625,
0.063720703125,
-0.036590576171875,
0.0136566162109375,
0.041839599609375,
0.054412841796875,
0.0004546642303466797,
-0.00927734375,
0.019744873046875,
0.0323486328125,
0.01457977294921875,
0.040069580078125,
0.0445556640625,
-0.04412841796875,
0.0316162109375,
-0.04559326171875,
-0.00682830810546875,
-0.0285797119140625,
-0.074951171875,
-0.0760498046875,
-0.04541015625,
-0.03680419921875,
-0.048431396484375,
-0.025238037109375,
0.0919189453125,
0.04937744140625,
-0.072021484375,
-0.0006170272827148438,
-0.00218963623046875,
-0.01306915283203125,
-0.005298614501953125,
-0.022125244140625,
0.046966552734375,
-0.018402099609375,
-0.055267333984375,
0.01027679443359375,
-0.004085540771484375,
0.01393890380859375,
0.009307861328125,
-0.00165557861328125,
-0.041107177734375,
-0.0016641616821289062,
0.031402587890625,
0.0223541259765625,
-0.058074951171875,
-0.0247039794921875,
0.012420654296875,
-0.0230865478515625,
0.01343536376953125,
0.0112762451171875,
-0.05181884765625,
0.0266571044921875,
0.027313232421875,
0.025146484375,
0.04888916015625,
-0.019775390625,
0.018157958984375,
-0.0528564453125,
-0.005794525146484375,
0.031951904296875,
0.05181884765625,
0.021728515625,
-0.01503753662109375,
0.033416748046875,
0.0170745849609375,
-0.0582275390625,
-0.04705810546875,
-0.01184844970703125,
-0.08978271484375,
-0.0164794921875,
0.08489990234375,
-0.0114288330078125,
-0.027435302734375,
0.0022144317626953125,
-0.01512908935546875,
0.0426025390625,
-0.034759521484375,
0.030029296875,
0.0377197265625,
-0.01155853271484375,
0.0027713775634765625,
-0.04620361328125,
0.040771484375,
0.0192718505859375,
-0.03399658203125,
-0.0173492431640625,
0.0172271728515625,
0.04193115234375,
0.02569580078125,
0.024810791015625,
0.00962066650390625,
0.013885498046875,
0.0022335052490234375,
0.042877197265625,
0.0031261444091796875,
-0.004673004150390625,
-0.02825927734375,
-0.01216888427734375,
-0.00930023193359375,
-0.0156707763671875
]
] |
dbmdz/bert-medium-historic-multilingual-cased | 2023-09-06T22:19:02.000Z | [
"transformers",
"pytorch",
"tf",
"tensorboard",
"safetensors",
"bert",
"fill-mask",
"multilingual",
"arxiv:1908.08962",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | dbmdz | null | null | dbmdz/bert-medium-historic-multilingual-cased | 0 | 40,329 | transformers | 2022-03-02T23:29:05 | ---
language: multilingual
license: mit
widget:
- text: "and I cannot conceive the reafon why [MASK] hath"
- text: "Täkäläinen sanomalehdistö [MASK] erit - täin"
- text: "Det vore [MASK] häller nödvändigt att be"
- text: "Comme, à cette époque [MASK] était celle de la"
- text: "In [MASK] an atmosphärischen Nahrungsmitteln"
---
# Historic Language Models (HLMs)
## Languages
Our Historic Language Models Zoo contains support for the following languages - incl. their training data source:
| Language | Training data | Size
| -------- | ------------- | ----
| German | [Europeana](http://www.europeana-newspapers.eu/) | 13-28GB (filtered)
| French | [Europeana](http://www.europeana-newspapers.eu/) | 11-31GB (filtered)
| English | [British Library](https://data.bl.uk/digbks/db14.html) | 24GB (year filtered)
| Finnish | [Europeana](http://www.europeana-newspapers.eu/) | 1.2GB
| Swedish | [Europeana](http://www.europeana-newspapers.eu/) | 1.1GB
## Models
At the moment, the following models are available on the model hub:
| Model identifier | Model Hub link
| --------------------------------------------- | --------------------------------------------------------------------------
| `dbmdz/bert-base-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-base-historic-multilingual-cased)
| `dbmdz/bert-base-historic-english-cased` | [here](https://huggingface.co/dbmdz/bert-base-historic-english-cased)
| `dbmdz/bert-base-finnish-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-finnish-europeana-cased)
| `dbmdz/bert-base-swedish-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-swedish-europeana-cased)
We also released smaller models for the multilingual model:
| Model identifier | Model Hub link
| ----------------------------------------------- | ---------------------------------------------------------------------------
| `dbmdz/bert-tiny-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-tiny-historic-multilingual-cased)
| `dbmdz/bert-mini-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-mini-historic-multilingual-cased)
| `dbmdz/bert-small-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-small-historic-multilingual-cased)
| `dbmdz/bert-medium-historic-multilingual-cased` | [here](https://huggingface.co/dbmdz/bert-base-historic-multilingual-cased)
**Notice**: We have released language models for Historic German and French trained on more noisier data earlier - see
[this repo](https://github.com/stefan-it/europeana-bert) for more information:
| Model identifier | Model Hub link
| --------------------------------------------- | --------------------------------------------------------------------------
| `dbmdz/bert-base-german-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-german-europeana-cased)
| `dbmdz/bert-base-french-europeana-cased` | [here](https://huggingface.co/dbmdz/bert-base-french-europeana-cased)
# Corpora Stats
## German Europeana Corpus
We provide some statistics using different thresholds of ocr confidences, in order to shrink down the corpus size
and use less-noisier data:
| OCR confidence | Size
| -------------- | ----
| **0.60** | 28GB
| 0.65 | 18GB
| 0.70 | 13GB
For the final corpus we use a OCR confidence of 0.6 (28GB). The following plot shows a tokens per year distribution:
## French Europeana Corpus
Like German, we use different ocr confidence thresholds:
| OCR confidence | Size
| -------------- | ----
| 0.60 | 31GB
| 0.65 | 27GB
| **0.70** | 27GB
| 0.75 | 23GB
| 0.80 | 11GB
For the final corpus we use a OCR confidence of 0.7 (27GB). The following plot shows a tokens per year distribution:
## British Library Corpus
Metadata is taken from [here](https://data.bl.uk/digbks/DB21.html). Stats incl. year filtering:
| Years | Size
| ----------------- | ----
| ALL | 24GB
| >= 1800 && < 1900 | 24GB
We use the year filtered variant. The following plot shows a tokens per year distribution:
## Finnish Europeana Corpus
| OCR confidence | Size
| -------------- | ----
| 0.60 | 1.2GB
The following plot shows a tokens per year distribution:
## Swedish Europeana Corpus
| OCR confidence | Size
| -------------- | ----
| 0.60 | 1.1GB
The following plot shows a tokens per year distribution:
## All Corpora
The following plot shows a tokens per year distribution of the complete training corpus:
# Multilingual Vocab generation
For the first attempt, we use the first 10GB of each pretraining corpus. We upsample both Finnish and Swedish to ~10GB.
The following tables shows the exact size that is used for generating a 32k and 64k subword vocabs:
| Language | Size
| -------- | ----
| German | 10GB
| French | 10GB
| English | 10GB
| Finnish | 9.5GB
| Swedish | 9.7GB
We then calculate the subword fertility rate and portion of `[UNK]`s over the following NER corpora:
| Language | NER corpora
| -------- | ------------------
| German | CLEF-HIPE, NewsEye
| French | CLEF-HIPE, NewsEye
| English | CLEF-HIPE
| Finnish | NewsEye
| Swedish | NewsEye
Breakdown of subword fertility rate and unknown portion per language for the 32k vocab:
| Language | Subword fertility | Unknown portion
| -------- | ------------------ | ---------------
| German | 1.43 | 0.0004
| French | 1.25 | 0.0001
| English | 1.25 | 0.0
| Finnish | 1.69 | 0.0007
| Swedish | 1.43 | 0.0
Breakdown of subword fertility rate and unknown portion per language for the 64k vocab:
| Language | Subword fertility | Unknown portion
| -------- | ------------------ | ---------------
| German | 1.31 | 0.0004
| French | 1.16 | 0.0001
| English | 1.17 | 0.0
| Finnish | 1.54 | 0.0007
| Swedish | 1.32 | 0.0
# Final pretraining corpora
We upsample Swedish and Finnish to ~27GB. The final stats for all pretraining corpora can be seen here:
| Language | Size
| -------- | ----
| German | 28GB
| French | 27GB
| English | 24GB
| Finnish | 27GB
| Swedish | 27GB
Total size is 130GB.
# Smaller multilingual models
Inspired by the ["Well-Read Students Learn Better: On the Importance of Pre-training Compact Models"](https://arxiv.org/abs/1908.08962)
paper, we train smaller models (different layers and hidden sizes), and report number of parameters and pre-training costs:
| Model (Layer / Hidden size) | Parameters | Pre-Training time
| --------------------------- | ----------: | ----------------------:
| hmBERT Tiny ( 2/128) | 4.58M | 4.3 sec / 1,000 steps
| hmBERT Mini ( 4/256) | 11.55M | 10.5 sec / 1,000 steps
| hmBERT Small ( 4/512) | 29.52M | 20.7 sec / 1,000 steps
| hmBERT Medium ( 8/512) | 42.13M | 35.0 sec / 1,000 steps
| hmBERT Base (12/768) | 110.62M | 80.0 sec / 1,000 steps
We then perform downstream evaluations on the multilingual [NewsEye](https://zenodo.org/record/4573313#.Ya3oVr-ZNzU) dataset:
# Pretraining
## Multilingual model - hmBERT Base
We train a multilingual BERT model using the 32k vocab with the official BERT implementation
on a v3-32 TPU using the following parameters:
```bash
python3 run_pretraining.py --input_file gs://histolectra/historic-multilingual-tfrecords/*.tfrecord \
--output_dir gs://histolectra/bert-base-historic-multilingual-cased \
--bert_config_file ./config.json \
--max_seq_length=512 \
--max_predictions_per_seq=75 \
--do_train=True \
--train_batch_size=128 \
--num_train_steps=3000000 \
--learning_rate=1e-4 \
--save_checkpoints_steps=100000 \
--keep_checkpoint_max=20 \
--use_tpu=True \
--tpu_name=electra-2 \
--num_tpu_cores=32
```
The following plot shows the pretraining loss curve:
## Smaller multilingual models
We use the same parameters as used for training the base model.
### hmBERT Tiny
The following plot shows the pretraining loss curve for the tiny model:
### hmBERT Mini
The following plot shows the pretraining loss curve for the mini model:
### hmBERT Small
The following plot shows the pretraining loss curve for the small model:
### hmBERT Medium
The following plot shows the pretraining loss curve for the medium model:
## English model
The English BERT model - with texts from British Library corpus - was trained with the Hugging Face
JAX/FLAX implementation for 10 epochs (approx. 1M steps) on a v3-8 TPU, using the following command:
```bash
python3 run_mlm_flax.py --model_type bert \
--config_name /mnt/datasets/bert-base-historic-english-cased/ \
--tokenizer_name /mnt/datasets/bert-base-historic-english-cased/ \
--train_file /mnt/datasets/bl-corpus/bl_1800-1900_extracted.txt \
--validation_file /mnt/datasets/bl-corpus/english_validation.txt \
--max_seq_length 512 \
--per_device_train_batch_size 16 \
--learning_rate 1e-4 \
--num_train_epochs 10 \
--preprocessing_num_workers 96 \
--output_dir /mnt/datasets/bert-base-historic-english-cased-512-noadafactor-10e \
--save_steps 2500 \
--eval_steps 2500 \
--warmup_steps 10000 \
--line_by_line \
--pad_to_max_length
```
The following plot shows the pretraining loss curve:
## Finnish model
The BERT model - with texts from Finnish part of Europeana - was trained with the Hugging Face
JAX/FLAX implementation for 40 epochs (approx. 1M steps) on a v3-8 TPU, using the following command:
```bash
python3 run_mlm_flax.py --model_type bert \
--config_name /mnt/datasets/bert-base-finnish-europeana-cased/ \
--tokenizer_name /mnt/datasets/bert-base-finnish-europeana-cased/ \
--train_file /mnt/datasets/hlms/extracted_content_Finnish_0.6.txt \
--validation_file /mnt/datasets/hlms/finnish_validation.txt \
--max_seq_length 512 \
--per_device_train_batch_size 16 \
--learning_rate 1e-4 \
--num_train_epochs 40 \
--preprocessing_num_workers 96 \
--output_dir /mnt/datasets/bert-base-finnish-europeana-cased-512-dupe1-noadafactor-40e \
--save_steps 2500 \
--eval_steps 2500 \
--warmup_steps 10000 \
--line_by_line \
--pad_to_max_length
```
The following plot shows the pretraining loss curve:
## Swedish model
The BERT model - with texts from Swedish part of Europeana - was trained with the Hugging Face
JAX/FLAX implementation for 40 epochs (approx. 660K steps) on a v3-8 TPU, using the following command:
```bash
python3 run_mlm_flax.py --model_type bert \
--config_name /mnt/datasets/bert-base-swedish-europeana-cased/ \
--tokenizer_name /mnt/datasets/bert-base-swedish-europeana-cased/ \
--train_file /mnt/datasets/hlms/extracted_content_Swedish_0.6.txt \
--validation_file /mnt/datasets/hlms/swedish_validation.txt \
--max_seq_length 512 \
--per_device_train_batch_size 16 \
--learning_rate 1e-4 \
--num_train_epochs 40 \
--preprocessing_num_workers 96 \
--output_dir /mnt/datasets/bert-base-swedish-europeana-cased-512-dupe1-noadafactor-40e \
--save_steps 2500 \
--eval_steps 2500 \
--warmup_steps 10000 \
--line_by_line \
--pad_to_max_length
```
The following plot shows the pretraining loss curve:
# Acknowledgments
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC) program, previously known as
TensorFlow Research Cloud (TFRC). Many thanks for providing access to the TRC ❤️
Thanks to the generous support from the [Hugging Face](https://huggingface.co/) team,
it is possible to download both cased and uncased models from their S3 storage 🤗
| 12,753 | [
[
-0.037200927734375,
-0.037567138671875,
0.013427734375,
0.004138946533203125,
-0.0303802490234375,
-0.01151275634765625,
-0.030426025390625,
-0.03460693359375,
0.0305633544921875,
0.0187530517578125,
-0.04681396484375,
-0.053955078125,
-0.0282440185546875,
0.0168304443359375,
-0.00499725341796875,
0.0660400390625,
-0.0008769035339355469,
0.036773681640625,
0.0011701583862304688,
-0.0201416015625,
-0.0192413330078125,
-0.074462890625,
-0.036834716796875,
-0.01151275634765625,
0.046417236328125,
0.025115966796875,
0.0369873046875,
0.042938232421875,
0.037322998046875,
0.012176513671875,
-0.0155792236328125,
-0.0084075927734375,
-0.0260162353515625,
-0.0101318359375,
0.01412200927734375,
-0.0243072509765625,
-0.03594970703125,
-0.0041351318359375,
0.04705810546875,
0.06451416015625,
-0.00146484375,
0.00850677490234375,
-0.0024471282958984375,
0.053070068359375,
-0.037445068359375,
0.010711669921875,
-0.0274810791015625,
0.005771636962890625,
-0.0255584716796875,
-0.0024318695068359375,
-0.033843994140625,
-0.00860595703125,
0.0003447532653808594,
-0.039703369140625,
0.02337646484375,
-0.00989532470703125,
0.0833740234375,
-0.006267547607421875,
-0.02069091796875,
-0.01885986328125,
-0.031585693359375,
0.0682373046875,
-0.056915283203125,
0.0513916015625,
0.032440185546875,
-0.0022754669189453125,
-0.002918243408203125,
-0.049713134765625,
-0.042999267578125,
-0.0177001953125,
-0.01535797119140625,
0.0128021240234375,
-0.0067138671875,
-0.0112152099609375,
0.01346588134765625,
0.022064208984375,
-0.057586669921875,
0.0099945068359375,
-0.042938232421875,
-0.0301666259765625,
0.059661865234375,
-0.007137298583984375,
0.021087646484375,
-0.0181884765625,
-0.02130126953125,
-0.03851318359375,
-0.049774169921875,
0.0030841827392578125,
0.04412841796875,
0.0391845703125,
-0.03173828125,
0.042724609375,
0.0010433197021484375,
0.037994384765625,
-0.0063629150390625,
-0.02008056640625,
0.05792236328125,
-0.0482177734375,
0.0001952648162841797,
0.0018396377563476562,
0.06915283203125,
0.01033782958984375,
0.022430419921875,
-0.004673004150390625,
-0.0073699951171875,
0.0025348663330078125,
-0.004123687744140625,
-0.057708740234375,
-0.0104522705078125,
0.0088653564453125,
-0.034759521484375,
0.0011491775512695312,
-0.00494384765625,
-0.05126953125,
0.0067596435546875,
-0.01320648193359375,
0.02386474609375,
-0.059539794921875,
-0.02130126953125,
0.0208740234375,
-0.0197296142578125,
0.0207977294921875,
0.0092010498046875,
-0.061431884765625,
0.0066070556640625,
0.0200653076171875,
0.052490234375,
-0.022491455078125,
-0.034515380859375,
-0.005367279052734375,
-0.016632080078125,
-0.034454345703125,
0.033355712890625,
-0.0203704833984375,
-0.033111572265625,
0.00983428955078125,
0.0157928466796875,
-0.01971435546875,
-0.019805908203125,
0.049285888671875,
-0.0258026123046875,
0.04168701171875,
-0.0246124267578125,
-0.0391845703125,
-0.004703521728515625,
0.01386260986328125,
-0.0574951171875,
0.096435546875,
0.01336669921875,
-0.0670166015625,
0.04022216796875,
-0.0306549072265625,
-0.0290374755859375,
-0.0099639892578125,
-0.01317596435546875,
-0.0305938720703125,
-0.0136871337890625,
0.01995849609375,
0.0302734375,
-0.003864288330078125,
0.0117645263671875,
-0.0163726806640625,
-0.0162353515625,
-0.002231597900390625,
-0.029876708984375,
0.0899658203125,
0.02056884765625,
-0.0217132568359375,
-0.00787353515625,
-0.06878662109375,
-0.0057830810546875,
0.0230255126953125,
-0.038330078125,
-0.01555633544921875,
-0.0183868408203125,
0.012542724609375,
0.019378662109375,
0.03173828125,
-0.048431396484375,
0.0160675048828125,
-0.038177490234375,
0.02325439453125,
0.02545166015625,
-0.005615234375,
0.0259857177734375,
-0.0157012939453125,
0.03704833984375,
0.0148162841796875,
0.0191650390625,
-0.0096282958984375,
-0.044281005859375,
-0.06390380859375,
-0.0251617431640625,
0.047698974609375,
0.044036865234375,
-0.05340576171875,
0.0472412109375,
-0.037567138671875,
-0.050445556640625,
-0.040496826171875,
0.00579071044921875,
0.037994384765625,
0.0215911865234375,
0.023345947265625,
-0.034210205078125,
-0.051483154296875,
-0.0753173828125,
0.005527496337890625,
-0.0272674560546875,
0.01309967041015625,
0.00841522216796875,
0.055816650390625,
-0.0081024169921875,
0.057891845703125,
-0.0172576904296875,
-0.020294189453125,
-0.0214691162109375,
0.00647735595703125,
0.02325439453125,
0.036376953125,
0.06591796875,
-0.058258056640625,
-0.036834716796875,
0.0023174285888671875,
-0.037322998046875,
0.02215576171875,
0.01323699951171875,
-0.0107421875,
0.055419921875,
0.038604736328125,
-0.04351806640625,
0.0255584716796875,
0.04327392578125,
-0.028411865234375,
0.046173095703125,
-0.0303802490234375,
-0.015625,
-0.092529296875,
0.0164031982421875,
-0.007114410400390625,
0.005802154541015625,
-0.0391845703125,
-0.0019321441650390625,
0.0146484375,
0.007709503173828125,
-0.05511474609375,
0.061004638671875,
-0.043731689453125,
0.00701904296875,
0.0254974365234375,
0.01210784912109375,
-0.0096588134765625,
0.051483154296875,
0.023040771484375,
0.052947998046875,
0.03607177734375,
-0.043212890625,
-0.003025054931640625,
0.0272216796875,
-0.039093017578125,
0.01009368896484375,
-0.029205322265625,
-0.0038242340087890625,
-0.0028896331787109375,
0.013580322265625,
-0.0709228515625,
-0.01187896728515625,
0.006565093994140625,
-0.05340576171875,
0.0303802490234375,
-0.0087738037109375,
-0.041473388671875,
-0.041473388671875,
-0.0283966064453125,
0.0117950439453125,
0.0440673828125,
-0.034576416015625,
0.040802001953125,
0.02142333984375,
-0.0187225341796875,
-0.06951904296875,
-0.0684814453125,
-0.00403594970703125,
-0.01093292236328125,
-0.048370361328125,
0.0170135498046875,
-0.02001953125,
-0.007236480712890625,
0.00980377197265625,
0.006656646728515625,
-0.01290130615234375,
-0.001434326171875,
-0.0011892318725585938,
0.0347900390625,
-0.0223846435546875,
0.01192474365234375,
-0.01165771484375,
0.00864410400390625,
-0.01898193359375,
-0.0013141632080078125,
0.0653076171875,
-0.01274871826171875,
-0.01140594482421875,
-0.0217742919921875,
0.01151275634765625,
0.032684326171875,
-0.0184783935546875,
0.0718994140625,
0.055419921875,
-0.02410888671875,
0.0120391845703125,
-0.0460205078125,
-0.017852783203125,
-0.0289459228515625,
0.031280517578125,
-0.036895751953125,
-0.06427001953125,
0.05474853515625,
0.032257080078125,
0.0244903564453125,
0.06695556640625,
0.045623779296875,
0.0021724700927734375,
0.07763671875,
0.044677734375,
-0.015869140625,
0.0418701171875,
-0.039703369140625,
-0.00015485286712646484,
-0.037628173828125,
-0.0212554931640625,
-0.045806884765625,
-0.007625579833984375,
-0.05499267578125,
-0.0179443359375,
0.01192474365234375,
0.01453399658203125,
-0.0250396728515625,
0.03326416015625,
-0.0201263427734375,
0.0159759521484375,
0.05023193359375,
-0.00846099853515625,
0.00849151611328125,
0.023773193359375,
-0.039459228515625,
-0.01403045654296875,
-0.06927490234375,
-0.035736083984375,
0.09503173828125,
0.0220794677734375,
0.031890869140625,
0.004215240478515625,
0.065185546875,
0.00408935546875,
0.01377105712890625,
-0.05340576171875,
0.0305633544921875,
-0.0225372314453125,
-0.070068359375,
-0.033782958984375,
-0.031402587890625,
-0.0863037109375,
0.0266265869140625,
-0.0152130126953125,
-0.0504150390625,
0.0318603515625,
0.00415802001953125,
-0.016876220703125,
0.022674560546875,
-0.064208984375,
0.0704345703125,
-0.01515960693359375,
-0.0112762451171875,
-0.00011938810348510742,
-0.04736328125,
0.01091766357421875,
-0.0152130126953125,
0.0362548828125,
-0.0016508102416992188,
0.005245208740234375,
0.07476806640625,
-0.039764404296875,
0.06890869140625,
-0.01045989990234375,
-0.0047149658203125,
0.02001953125,
-0.0067901611328125,
0.032989501953125,
-0.018890380859375,
-0.0124969482421875,
0.02947998046875,
0.0249481201171875,
-0.035491943359375,
-0.007297515869140625,
0.040283203125,
-0.068359375,
-0.0263824462890625,
-0.044403076171875,
-0.03839111328125,
-0.00893402099609375,
0.031341552734375,
0.046875,
0.029876708984375,
-0.022857666015625,
0.030670166015625,
0.03668212890625,
-0.027374267578125,
0.040924072265625,
0.05078125,
-0.01065826416015625,
-0.03326416015625,
0.054534912109375,
0.021759033203125,
0.0161285400390625,
0.02490234375,
0.0157318115234375,
-0.031951904296875,
-0.0438232421875,
-0.03839111328125,
0.038238525390625,
-0.049468994140625,
0.007053375244140625,
-0.0594482421875,
-0.0183868408203125,
-0.058380126953125,
-0.0051727294921875,
-0.02728271484375,
-0.04486083984375,
-0.018463134765625,
-0.0166473388671875,
0.02557373046875,
0.0380859375,
-0.0137176513671875,
0.019439697265625,
-0.04345703125,
-0.002140045166015625,
0.0016117095947265625,
0.01268768310546875,
-0.01058197021484375,
-0.057464599609375,
-0.0244140625,
0.00958251953125,
-0.0099945068359375,
-0.0489501953125,
0.04388427734375,
0.0136871337890625,
0.0428466796875,
0.0269775390625,
0.003143310546875,
0.040924072265625,
-0.046417236328125,
0.0906982421875,
0.0303802490234375,
-0.0465087890625,
0.028076171875,
-0.016448974609375,
0.0148162841796875,
0.046783447265625,
0.04119873046875,
-0.047027587890625,
-0.017669677734375,
-0.06280517578125,
-0.080810546875,
0.07232666015625,
0.007297515869140625,
0.0203704833984375,
-0.01151275634765625,
0.01425933837890625,
0.01525115966796875,
0.00841522216796875,
-0.06378173828125,
-0.04119873046875,
-0.003452301025390625,
-0.0235595703125,
-0.03778076171875,
-0.029632568359375,
-0.006633758544921875,
-0.0382080078125,
0.072998046875,
0.0024623870849609375,
0.01351165771484375,
0.017608642578125,
-0.01348876953125,
0.003009796142578125,
0.022979736328125,
0.048797607421875,
0.05267333984375,
-0.03082275390625,
-0.006465911865234375,
0.0234527587890625,
-0.0626220703125,
0.0022296905517578125,
0.0098724365234375,
-0.0157623291015625,
0.0262451171875,
0.047882080078125,
0.07666015625,
0.01052093505859375,
-0.05224609375,
0.051483154296875,
-0.01236724853515625,
-0.042633056640625,
-0.04681396484375,
-0.01497650146484375,
0.0149383544921875,
-0.0037136077880859375,
0.0215301513671875,
-0.018707275390625,
-0.0126495361328125,
-0.04730224609375,
0.006988525390625,
0.0218658447265625,
-0.036834716796875,
-0.0252227783203125,
0.034423828125,
0.000050187110900878906,
-0.010650634765625,
0.0347900390625,
-0.02130126953125,
-0.03851318359375,
0.04571533203125,
0.032196044921875,
0.046783447265625,
-0.01532745361328125,
0.0167999267578125,
0.05535888671875,
0.0399169921875,
-0.0146026611328125,
0.049102783203125,
0.0194549560546875,
-0.06573486328125,
-0.022674560546875,
-0.065185546875,
-0.01218414306640625,
0.0286865234375,
-0.053070068359375,
0.019805908203125,
-0.0069580078125,
-0.0207366943359375,
0.003814697265625,
0.01824951171875,
-0.0721435546875,
0.02178955078125,
0.0126953125,
0.089599609375,
-0.057708740234375,
0.07769775390625,
0.053253173828125,
-0.05078125,
-0.06488037109375,
-0.023162841796875,
-0.0126953125,
-0.060943603515625,
0.060333251953125,
-0.00016868114471435547,
0.0096893310546875,
-0.0009288787841796875,
-0.0266571044921875,
-0.079833984375,
0.0709228515625,
0.031585693359375,
-0.0518798828125,
0.004314422607421875,
0.017730712890625,
0.057098388671875,
-0.0183563232421875,
0.01158905029296875,
0.0400390625,
0.0396728515625,
0.0036296844482421875,
-0.06536865234375,
-0.0165557861328125,
-0.033233642578125,
-0.00913238525390625,
0.01116180419921875,
-0.038238525390625,
0.0770263671875,
-0.00955963134765625,
-0.0303192138671875,
0.0017547607421875,
0.033233642578125,
0.0206756591796875,
0.00753021240234375,
0.039337158203125,
0.04962158203125,
0.055450439453125,
-0.01204681396484375,
0.0992431640625,
-0.039459228515625,
0.019317626953125,
0.07080078125,
0.00494384765625,
0.07757568359375,
0.03631591796875,
-0.0232391357421875,
0.034210205078125,
0.0665283203125,
0.00582122802734375,
0.0263824462890625,
-0.00849151611328125,
0.003021240234375,
-0.01238250732421875,
-0.0019817352294921875,
-0.039886474609375,
0.0174713134765625,
0.0206146240234375,
-0.0279541015625,
0.0016794204711914062,
0.004772186279296875,
0.0282745361328125,
-0.021881103515625,
-0.01488494873046875,
0.0399169921875,
0.005428314208984375,
-0.045257568359375,
0.06744384765625,
-0.0053253173828125,
0.060638427734375,
-0.061126708984375,
0.0270233154296875,
-0.023529052734375,
0.01267242431640625,
-0.003658294677734375,
-0.048828125,
-0.0006585121154785156,
0.00220489501953125,
-0.0083465576171875,
-0.00931549072265625,
0.0281219482421875,
-0.046783447265625,
-0.05291748046875,
0.041290283203125,
0.052154541015625,
0.029510498046875,
0.0161895751953125,
-0.056915283203125,
0.0031185150146484375,
0.008880615234375,
-0.040863037109375,
0.0178070068359375,
0.029144287109375,
-0.012298583984375,
0.03106689453125,
0.047119140625,
0.0225677490234375,
0.0218048095703125,
0.024658203125,
0.05126953125,
-0.041839599609375,
-0.030853271484375,
-0.050689697265625,
0.03302001953125,
-0.00439453125,
-0.0428466796875,
0.070068359375,
0.05780029296875,
0.09075927734375,
-0.01348876953125,
0.0616455078125,
-0.005268096923828125,
0.04388427734375,
-0.034454345703125,
0.050201416015625,
-0.06439208984375,
-0.0096282958984375,
-0.0085601806640625,
-0.0670166015625,
-0.0241241455078125,
0.036773681640625,
-0.030029296875,
0.0034236907958984375,
0.05804443359375,
0.0455322265625,
0.0024280548095703125,
-0.017913818359375,
0.020599365234375,
0.021240234375,
0.002147674560546875,
0.024383544921875,
0.03125,
-0.036407470703125,
0.055694580078125,
-0.042724609375,
0.0003821849822998047,
-0.0197296142578125,
-0.049224853515625,
-0.07281494140625,
-0.0618896484375,
-0.016143798828125,
-0.027496337890625,
0.000598907470703125,
0.06781005859375,
0.043792724609375,
-0.07159423828125,
-0.029296875,
0.01332855224609375,
-0.0182647705078125,
-0.016510009765625,
-0.0149993896484375,
0.0555419921875,
-0.0202484130859375,
-0.05780029296875,
0.0186920166015625,
-0.00222015380859375,
0.01806640625,
-0.02008056640625,
-0.0224151611328125,
-0.027618408203125,
0.0136260986328125,
0.04180908203125,
0.01959228515625,
-0.045654296875,
-0.01343536376953125,
0.01349639892578125,
-0.02685546875,
0.0137786865234375,
0.032684326171875,
-0.0291900634765625,
0.0299224853515625,
0.0440673828125,
0.019989013671875,
0.05364990234375,
-0.0293426513671875,
0.0207672119140625,
-0.06488037109375,
0.04095458984375,
0.015869140625,
0.046875,
0.0286865234375,
-0.010406494140625,
0.052337646484375,
0.022491455078125,
-0.01303863525390625,
-0.07098388671875,
-0.0024089813232421875,
-0.07568359375,
-0.030853271484375,
0.08538818359375,
-0.00846099853515625,
-0.040252685546875,
-0.00742340087890625,
-0.0126495361328125,
0.0243072509765625,
-0.02685546875,
0.038543701171875,
0.07708740234375,
0.008758544921875,
0.00434112548828125,
-0.043853759765625,
0.039215087890625,
0.033538818359375,
-0.036102294921875,
-0.002513885498046875,
0.03173828125,
0.0265960693359375,
0.034637451171875,
0.0616455078125,
-0.0267486572265625,
0.007152557373046875,
0.01171112060546875,
0.046875,
0.008697509765625,
-0.0205078125,
-0.023712158203125,
-0.00292205810546875,
-0.005870819091796875,
-0.006008148193359375
]
] |
timm/regnety_002.pycls_in1k | 2023-03-21T06:36:53.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2003.13678",
"license:mit",
"region:us"
] | image-classification | timm | null | null | timm/regnety_002.pycls_in1k | 0 | 40,226 | timm | 2023-03-21T06:36:49 | ---
tags:
- image-classification
- timm
library_tag: timm
license: mit
datasets:
- imagenet-1k
---
# Model card for regnety_002.pycls_in1k
A RegNetY-200MF image classification model. Pretrained on ImageNet-1k by paper authors.
The `timm` RegNet implementation includes a number of enhancements not present in other implementations, including:
* stochastic depth
* gradient checkpointing
* layer-wise LR decay
* configurable output stride (dilation)
* configurable activation and norm layers
* option for a pre-activation bottleneck block used in RegNetV variant
* only known RegNetZ model definitions with pretrained weights
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 3.2
- GMACs: 0.2
- Activations (M): 2.2
- Image size: 224 x 224
- **Papers:**
- Designing Network Design Spaces: https://arxiv.org/abs/2003.13678
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/facebookresearch/pycls
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('regnety_002.pycls_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'regnety_002.pycls_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 32, 112, 112])
# torch.Size([1, 24, 56, 56])
# torch.Size([1, 56, 28, 28])
# torch.Size([1, 152, 14, 14])
# torch.Size([1, 368, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'regnety_002.pycls_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 368, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in `timm`.
|model |img_size|top1 |top5 |param_count|gmacs|macts |
|-------------------------|--------|------|------|-----------|-----|------|
|[regnety_1280.swag_ft_in1k](https://huggingface.co/timm/regnety_1280.swag_ft_in1k)|384 |88.228|98.684|644.81 |374.99|210.2 |
|[regnety_320.swag_ft_in1k](https://huggingface.co/timm/regnety_320.swag_ft_in1k)|384 |86.84 |98.364|145.05 |95.0 |88.87 |
|[regnety_160.swag_ft_in1k](https://huggingface.co/timm/regnety_160.swag_ft_in1k)|384 |86.024|98.05 |83.59 |46.87|67.67 |
|[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|288 |86.004|97.83 |83.59 |26.37|38.07 |
|[regnety_1280.swag_lc_in1k](https://huggingface.co/timm/regnety_1280.swag_lc_in1k)|224 |85.996|97.848|644.81 |127.66|71.58 |
|[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|288 |85.982|97.844|83.59 |26.37|38.07 |
|[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|224 |85.574|97.666|83.59 |15.96|23.04 |
|[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|224 |85.564|97.674|83.59 |15.96|23.04 |
|[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|288 |85.398|97.584|51.82 |20.06|35.34 |
|[regnety_2560.seer_ft_in1k](https://huggingface.co/timm/regnety_2560.seer_ft_in1k)|384 |85.15 |97.436|1282.6 |747.83|296.49|
|[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|320 |85.036|97.268|57.7 |15.46|63.94 |
|[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|224 |84.976|97.416|51.82 |12.14|21.38 |
|[regnety_320.swag_lc_in1k](https://huggingface.co/timm/regnety_320.swag_lc_in1k)|224 |84.56 |97.446|145.05 |32.34|30.26 |
|[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|320 |84.496|97.004|28.94 |6.43 |37.94 |
|[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|256 |84.436|97.02 |57.7 |9.91 |40.94 |
|[regnety_1280.seer_ft_in1k](https://huggingface.co/timm/regnety_1280.seer_ft_in1k)|384 |84.432|97.092|644.81 |374.99|210.2 |
|[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|320 |84.246|96.93 |27.12 |6.35 |37.78 |
|[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|320 |84.054|96.992|23.37 |6.19 |37.08 |
|[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|320 |84.038|96.992|23.46 |7.03 |38.92 |
|[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|320 |84.022|96.866|27.58 |9.33 |37.08 |
|[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|288 |83.932|96.888|39.18 |13.22|29.69 |
|[regnety_640.seer_ft_in1k](https://huggingface.co/timm/regnety_640.seer_ft_in1k)|384 |83.912|96.924|281.38 |188.47|124.83|
|[regnety_160.swag_lc_in1k](https://huggingface.co/timm/regnety_160.swag_lc_in1k)|224 |83.778|97.286|83.59 |15.96|23.04 |
|[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|256 |83.776|96.704|28.94 |4.12 |24.29 |
|[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|288 |83.72 |96.75 |30.58 |10.55|27.11 |
|[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|288 |83.718|96.724|30.58 |10.56|27.11 |
|[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|288 |83.69 |96.778|83.59 |26.37|38.07 |
|[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|256 |83.62 |96.704|27.12 |4.06 |24.19 |
|[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|256 |83.438|96.776|23.37 |3.97 |23.74 |
|[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|256 |83.424|96.632|27.58 |5.98 |23.74 |
|[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|256 |83.36 |96.636|23.46 |4.5 |24.92 |
|[regnety_320.seer_ft_in1k](https://huggingface.co/timm/regnety_320.seer_ft_in1k)|384 |83.35 |96.71 |145.05 |95.0 |88.87 |
|[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|288 |83.204|96.66 |20.64 |6.6 |20.3 |
|[regnety_320.tv2_in1k](https://huggingface.co/timm/regnety_320.tv2_in1k)|224 |83.162|96.42 |145.05 |32.34|30.26 |
|[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|224 |83.16 |96.486|39.18 |8.0 |17.97 |
|[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|224 |83.108|96.458|30.58 |6.39 |16.41 |
|[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|288 |83.044|96.5 |20.65 |6.61 |20.3 |
|[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|224 |83.02 |96.292|30.58 |6.39 |16.41 |
|[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|224 |82.974|96.502|83.59 |15.96|23.04 |
|[regnetx_320.tv2_in1k](https://huggingface.co/timm/regnetx_320.tv2_in1k)|224 |82.816|96.208|107.81 |31.81|36.3 |
|[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|288 |82.742|96.418|19.44 |5.29 |18.61 |
|[regnety_160.tv2_in1k](https://huggingface.co/timm/regnety_160.tv2_in1k)|224 |82.634|96.22 |83.59 |15.96|23.04 |
|[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|320 |82.634|96.472|13.49 |3.86 |25.88 |
|[regnety_080_tv.tv2_in1k](https://huggingface.co/timm/regnety_080_tv.tv2_in1k)|224 |82.592|96.246|39.38 |8.51 |19.73 |
|[regnetx_160.tv2_in1k](https://huggingface.co/timm/regnetx_160.tv2_in1k)|224 |82.564|96.052|54.28 |15.99|25.52 |
|[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|320 |82.51 |96.358|13.46 |3.92 |25.88 |
|[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|224 |82.44 |96.198|20.64 |4.0 |12.29 |
|[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|224 |82.304|96.078|20.65 |4.0 |12.29 |
|[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|256 |82.16 |96.048|13.46 |2.51 |16.57 |
|[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|256 |81.936|96.15 |13.49 |2.48 |16.57 |
|[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|224 |81.924|95.988|19.44 |3.2 |11.26 |
|[regnety_032.tv2_in1k](https://huggingface.co/timm/regnety_032.tv2_in1k)|224 |81.77 |95.842|19.44 |3.2 |11.26 |
|[regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k)|224 |81.552|95.544|39.57 |8.02 |14.06 |
|[regnetx_032.tv2_in1k](https://huggingface.co/timm/regnetx_032.tv2_in1k)|224 |80.924|95.27 |15.3 |3.2 |11.37 |
|[regnety_320.pycls_in1k](https://huggingface.co/timm/regnety_320.pycls_in1k)|224 |80.804|95.246|145.05 |32.34|30.26 |
|[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|288 |80.712|95.47 |9.72 |2.39 |16.43 |
|[regnety_016.tv2_in1k](https://huggingface.co/timm/regnety_016.tv2_in1k)|224 |80.66 |95.334|11.2 |1.63 |8.04 |
|[regnety_120.pycls_in1k](https://huggingface.co/timm/regnety_120.pycls_in1k)|224 |80.37 |95.12 |51.82 |12.14|21.38 |
|[regnety_160.pycls_in1k](https://huggingface.co/timm/regnety_160.pycls_in1k)|224 |80.288|94.964|83.59 |15.96|23.04 |
|[regnetx_320.pycls_in1k](https://huggingface.co/timm/regnetx_320.pycls_in1k)|224 |80.246|95.01 |107.81 |31.81|36.3 |
|[regnety_080.pycls_in1k](https://huggingface.co/timm/regnety_080.pycls_in1k)|224 |79.882|94.834|39.18 |8.0 |17.97 |
|[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|224 |79.872|94.974|9.72 |1.45 |9.95 |
|[regnetx_160.pycls_in1k](https://huggingface.co/timm/regnetx_160.pycls_in1k)|224 |79.862|94.828|54.28 |15.99|25.52 |
|[regnety_064.pycls_in1k](https://huggingface.co/timm/regnety_064.pycls_in1k)|224 |79.716|94.772|30.58 |6.39 |16.41 |
|[regnetx_120.pycls_in1k](https://huggingface.co/timm/regnetx_120.pycls_in1k)|224 |79.592|94.738|46.11 |12.13|21.37 |
|[regnetx_016.tv2_in1k](https://huggingface.co/timm/regnetx_016.tv2_in1k)|224 |79.44 |94.772|9.19 |1.62 |7.93 |
|[regnety_040.pycls_in1k](https://huggingface.co/timm/regnety_040.pycls_in1k)|224 |79.23 |94.654|20.65 |4.0 |12.29 |
|[regnetx_080.pycls_in1k](https://huggingface.co/timm/regnetx_080.pycls_in1k)|224 |79.198|94.55 |39.57 |8.02 |14.06 |
|[regnetx_064.pycls_in1k](https://huggingface.co/timm/regnetx_064.pycls_in1k)|224 |79.064|94.454|26.21 |6.49 |16.37 |
|[regnety_032.pycls_in1k](https://huggingface.co/timm/regnety_032.pycls_in1k)|224 |78.884|94.412|19.44 |3.2 |11.26 |
|[regnety_008_tv.tv2_in1k](https://huggingface.co/timm/regnety_008_tv.tv2_in1k)|224 |78.654|94.388|6.43 |0.84 |5.42 |
|[regnetx_040.pycls_in1k](https://huggingface.co/timm/regnetx_040.pycls_in1k)|224 |78.482|94.24 |22.12 |3.99 |12.2 |
|[regnetx_032.pycls_in1k](https://huggingface.co/timm/regnetx_032.pycls_in1k)|224 |78.178|94.08 |15.3 |3.2 |11.37 |
|[regnety_016.pycls_in1k](https://huggingface.co/timm/regnety_016.pycls_in1k)|224 |77.862|93.73 |11.2 |1.63 |8.04 |
|[regnetx_008.tv2_in1k](https://huggingface.co/timm/regnetx_008.tv2_in1k)|224 |77.302|93.672|7.26 |0.81 |5.15 |
|[regnetx_016.pycls_in1k](https://huggingface.co/timm/regnetx_016.pycls_in1k)|224 |76.908|93.418|9.19 |1.62 |7.93 |
|[regnety_008.pycls_in1k](https://huggingface.co/timm/regnety_008.pycls_in1k)|224 |76.296|93.05 |6.26 |0.81 |5.25 |
|[regnety_004.tv2_in1k](https://huggingface.co/timm/regnety_004.tv2_in1k)|224 |75.592|92.712|4.34 |0.41 |3.89 |
|[regnety_006.pycls_in1k](https://huggingface.co/timm/regnety_006.pycls_in1k)|224 |75.244|92.518|6.06 |0.61 |4.33 |
|[regnetx_008.pycls_in1k](https://huggingface.co/timm/regnetx_008.pycls_in1k)|224 |75.042|92.342|7.26 |0.81 |5.15 |
|[regnetx_004_tv.tv2_in1k](https://huggingface.co/timm/regnetx_004_tv.tv2_in1k)|224 |74.57 |92.184|5.5 |0.42 |3.17 |
|[regnety_004.pycls_in1k](https://huggingface.co/timm/regnety_004.pycls_in1k)|224 |74.018|91.764|4.34 |0.41 |3.89 |
|[regnetx_006.pycls_in1k](https://huggingface.co/timm/regnetx_006.pycls_in1k)|224 |73.862|91.67 |6.2 |0.61 |3.98 |
|[regnetx_004.pycls_in1k](https://huggingface.co/timm/regnetx_004.pycls_in1k)|224 |72.38 |90.832|5.16 |0.4 |3.14 |
|[regnety_002.pycls_in1k](https://huggingface.co/timm/regnety_002.pycls_in1k)|224 |70.282|89.534|3.16 |0.2 |2.17 |
|[regnetx_002.pycls_in1k](https://huggingface.co/timm/regnetx_002.pycls_in1k)|224 |68.752|88.556|2.68 |0.2 |2.16 |
## Citation
```bibtex
@InProceedings{Radosavovic2020,
title = {Designing Network Design Spaces},
author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{'a}r},
booktitle = {CVPR},
year = {2020}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 15,490 | [
[
-0.059844970703125,
-0.016876220703125,
-0.011810302734375,
0.037078857421875,
-0.03240966796875,
-0.00746917724609375,
-0.013031005859375,
-0.0390625,
0.07501220703125,
0.00611114501953125,
-0.05145263671875,
-0.03741455078125,
-0.047821044921875,
0.0030689239501953125,
0.0189361572265625,
0.06329345703125,
-0.004344940185546875,
-0.01457977294921875,
0.02227783203125,
-0.0225677490234375,
-0.010528564453125,
-0.02276611328125,
-0.05120849609375,
-0.0263214111328125,
0.0279388427734375,
0.01065826416015625,
0.059967041015625,
0.0408935546875,
0.04046630859375,
0.040130615234375,
-0.0174407958984375,
0.0211181640625,
-0.0032558441162109375,
-0.0114593505859375,
0.04693603515625,
-0.0305023193359375,
-0.06475830078125,
0.0054473876953125,
0.05230712890625,
0.03631591796875,
0.0015420913696289062,
0.0278472900390625,
0.023681640625,
0.05560302734375,
-0.003986358642578125,
0.00024235248565673828,
-0.00963592529296875,
0.016754150390625,
-0.019439697265625,
0.00519561767578125,
-0.006816864013671875,
-0.0518798828125,
0.00815582275390625,
-0.05352783203125,
-0.004131317138671875,
-0.00403594970703125,
0.114501953125,
-0.01041412353515625,
0.0010595321655273438,
-0.0033721923828125,
0.006500244140625,
0.0626220703125,
-0.0662841796875,
0.01605224609375,
0.03131103515625,
-0.009307861328125,
-0.023040771484375,
-0.049774169921875,
-0.041748046875,
-0.0007410049438476562,
-0.0298919677734375,
0.023223876953125,
-0.0272369384765625,
-0.0110626220703125,
0.0277099609375,
0.03448486328125,
-0.031524658203125,
-0.0135040283203125,
-0.0205078125,
-0.00811767578125,
0.0596923828125,
0.00644683837890625,
0.053253173828125,
-0.0212554931640625,
-0.044921875,
-0.01090240478515625,
-0.01410675048828125,
0.0333251953125,
0.0180511474609375,
0.01389312744140625,
-0.062225341796875,
0.0283966064453125,
-0.0025634765625,
0.035491943359375,
0.03070068359375,
-0.026824951171875,
0.06976318359375,
-0.0160980224609375,
-0.033935546875,
-0.033782958984375,
0.07781982421875,
0.0469970703125,
0.025360107421875,
0.00641632080078125,
-0.01403045654296875,
-0.0271759033203125,
-0.0290679931640625,
-0.0701904296875,
-0.014678955078125,
0.0118560791015625,
-0.049468994140625,
-0.0200653076171875,
0.0253448486328125,
-0.052520751953125,
-0.00006008148193359375,
-0.007740020751953125,
0.017364501953125,
-0.04803466796875,
-0.033966064453125,
0.00843048095703125,
-0.025421142578125,
0.032012939453125,
0.02362060546875,
-0.0249786376953125,
0.01372528076171875,
0.00733184814453125,
0.0653076171875,
0.0182647705078125,
-0.005084991455078125,
-0.00995635986328125,
-0.00397491455078125,
-0.0369873046875,
0.0220947265625,
0.001094818115234375,
-0.00499725341796875,
-0.020782470703125,
0.0223388671875,
-0.021759033203125,
-0.0203704833984375,
0.03619384765625,
0.0196533203125,
0.001468658447265625,
-0.027130126953125,
-0.005794525146484375,
-0.0186004638671875,
0.0241546630859375,
-0.038421630859375,
0.0863037109375,
0.03326416015625,
-0.0845947265625,
0.031158447265625,
-0.03631591796875,
0.0007414817810058594,
-0.017791748046875,
0.013336181640625,
-0.06298828125,
-0.00363922119140625,
0.01006317138671875,
0.0545654296875,
-0.01297760009765625,
-0.0214691162109375,
-0.03009033203125,
0.004093170166015625,
0.03509521484375,
0.02099609375,
0.07659912109375,
0.0271453857421875,
-0.02593994140625,
-0.006572723388671875,
-0.05645751953125,
0.0264434814453125,
0.03387451171875,
-0.018218994140625,
-0.006282806396484375,
-0.0572509765625,
0.00464630126953125,
0.05072021484375,
0.0219268798828125,
-0.046875,
0.02569580078125,
-0.0182647705078125,
0.0235748291015625,
0.04205322265625,
-0.00891876220703125,
0.0159454345703125,
-0.055450439453125,
0.04229736328125,
0.0013475418090820312,
0.0242462158203125,
0.004001617431640625,
-0.035980224609375,
-0.05010986328125,
-0.055389404296875,
0.018890380859375,
0.032745361328125,
-0.0369873046875,
0.060455322265625,
0.01096343994140625,
-0.0518798828125,
-0.041595458984375,
0.018768310546875,
0.042236328125,
0.0200653076171875,
0.006038665771484375,
-0.0303497314453125,
-0.0518798828125,
-0.0675048828125,
-0.018707275390625,
-0.00455474853515625,
-0.0001544952392578125,
0.043731689453125,
0.043853759765625,
-0.00572967529296875,
0.046905517578125,
-0.03338623046875,
-0.026153564453125,
-0.0238189697265625,
-0.0037212371826171875,
0.034454345703125,
0.06463623046875,
0.08551025390625,
-0.047119140625,
-0.06298828125,
0.002765655517578125,
-0.0760498046875,
-0.003253936767578125,
-0.007236480712890625,
-0.021270751953125,
0.026885986328125,
0.01561737060546875,
-0.06488037109375,
0.056640625,
0.0271453857421875,
-0.043975830078125,
0.035247802734375,
-0.027984619140625,
0.02862548828125,
-0.07080078125,
0.0169677734375,
0.0169677734375,
-0.0087127685546875,
-0.050537109375,
0.00652313232421875,
-0.010284423828125,
0.0186920166015625,
-0.038177490234375,
0.05810546875,
-0.047210693359375,
0.003070831298828125,
0.01007843017578125,
0.0008158683776855469,
-0.0015783309936523438,
0.032867431640625,
-0.0022792816162109375,
0.041778564453125,
0.051025390625,
-0.006259918212890625,
0.02606201171875,
0.0287628173828125,
-0.00846099853515625,
0.03887939453125,
-0.045135498046875,
0.005641937255859375,
0.0027923583984375,
0.04022216796875,
-0.0826416015625,
-0.029449462890625,
0.050537109375,
-0.0657958984375,
0.046112060546875,
-0.01727294921875,
-0.0307769775390625,
-0.047576904296875,
-0.0648193359375,
0.0178375244140625,
0.05010986328125,
-0.0419921875,
0.025665283203125,
0.025146484375,
0.007266998291015625,
-0.053955078125,
-0.0567626953125,
0.0008792877197265625,
-0.0280609130859375,
-0.062408447265625,
0.02813720703125,
0.0144500732421875,
-0.012725830078125,
-0.0009417533874511719,
-0.0041351318359375,
-0.0119781494140625,
-0.005733489990234375,
0.042877197265625,
0.03155517578125,
-0.0276947021484375,
-0.02215576171875,
-0.03558349609375,
-0.0068511962890625,
-0.0005331039428710938,
-0.011077880859375,
0.038177490234375,
-0.039306640625,
0.017059326171875,
-0.09307861328125,
0.00146484375,
0.03851318359375,
-0.0013628005981445312,
0.07501220703125,
0.06475830078125,
-0.028656005859375,
0.000324249267578125,
-0.0260467529296875,
-0.00989532470703125,
-0.0372314453125,
-0.023681640625,
-0.045623779296875,
-0.044769287109375,
0.064453125,
0.01012420654296875,
-0.0023403167724609375,
0.0614013671875,
0.020904541015625,
-0.013031005859375,
0.0694580078125,
0.0297698974609375,
-0.004398345947265625,
0.05450439453125,
-0.056640625,
0.0035152435302734375,
-0.050537109375,
-0.048065185546875,
-0.021240234375,
-0.0386962890625,
-0.03985595703125,
-0.0277099609375,
0.0177764892578125,
0.043304443359375,
-0.0250091552734375,
0.0445556640625,
-0.05255126953125,
-0.0025882720947265625,
0.0262298583984375,
0.0303802490234375,
-0.02197265625,
-0.00469970703125,
-0.01462554931640625,
-0.01309967041015625,
-0.049560546875,
-0.01788330078125,
0.060272216796875,
0.04095458984375,
0.04296875,
0.00542449951171875,
0.046234130859375,
0.005706787109375,
0.0195770263671875,
-0.02716064453125,
0.044097900390625,
0.00717926025390625,
-0.0445556640625,
-0.0237884521484375,
-0.017364501953125,
-0.0755615234375,
0.016693115234375,
-0.03424072265625,
-0.062225341796875,
-0.00011914968490600586,
0.01091766357421875,
-0.021148681640625,
0.051513671875,
-0.040985107421875,
0.04351806640625,
0.0031261444091796875,
-0.036041259765625,
0.00077056884765625,
-0.06591796875,
0.0172119140625,
0.0215606689453125,
-0.0013017654418945312,
-0.01021575927734375,
0.0005779266357421875,
0.0625,
-0.057586669921875,
0.040618896484375,
-0.02947998046875,
0.01038360595703125,
0.045074462890625,
-0.003902435302734375,
0.0225067138671875,
-0.0016689300537109375,
-0.0141448974609375,
0.0007634162902832031,
0.00399017333984375,
-0.05029296875,
-0.0164337158203125,
0.040863037109375,
-0.052947998046875,
-0.025787353515625,
-0.05279541015625,
-0.025726318359375,
0.01256561279296875,
0.0005946159362792969,
0.03662109375,
0.04376220703125,
0.002346038818359375,
0.01401519775390625,
0.038421630859375,
-0.031463623046875,
0.037384033203125,
-0.014739990234375,
-0.0004112720489501953,
-0.02862548828125,
0.05450439453125,
-0.0037670135498046875,
0.004352569580078125,
0.005207061767578125,
0.008026123046875,
-0.0195465087890625,
-0.023956298828125,
-0.0208282470703125,
0.04534912109375,
-0.027557373046875,
-0.0312347412109375,
-0.04132080078125,
-0.02728271484375,
-0.038421630859375,
-0.0293121337890625,
-0.03070068359375,
-0.03729248046875,
-0.02099609375,
0.00341033935546875,
0.056884765625,
0.05975341796875,
-0.041229248046875,
0.0243682861328125,
-0.0372314453125,
0.017425537109375,
0.00675201416015625,
0.0284423828125,
-0.01494598388671875,
-0.052215576171875,
0.00318145751953125,
-0.01105499267578125,
-0.006488800048828125,
-0.058563232421875,
0.0592041015625,
0.0013990402221679688,
0.0301513671875,
0.039794921875,
-0.0110015869140625,
0.058563232421875,
-0.0011949539184570312,
0.0362548828125,
0.0513916015625,
-0.0570068359375,
0.0352783203125,
-0.031097412109375,
0.0027675628662109375,
0.018890380859375,
0.01336669921875,
-0.0248870849609375,
-0.030548095703125,
-0.056243896484375,
-0.045379638671875,
0.06396484375,
0.0182037353515625,
-0.0021457672119140625,
0.0009126663208007812,
0.04937744140625,
-0.01219940185546875,
0.0005221366882324219,
-0.038330078125,
-0.06842041015625,
-0.0206451416015625,
-0.0099639892578125,
-0.00007724761962890625,
-0.005008697509765625,
-0.00665283203125,
-0.0513916015625,
0.043731689453125,
0.00043511390686035156,
0.037811279296875,
0.0226898193359375,
-0.0027408599853515625,
0.0013837814331054688,
-0.0256805419921875,
0.055328369140625,
0.045318603515625,
-0.0206451416015625,
-0.027801513671875,
0.0203704833984375,
-0.04412841796875,
0.004329681396484375,
0.0051727294921875,
0.0005846023559570312,
0.0122833251953125,
0.017181396484375,
0.036956787109375,
0.0077056884765625,
-0.0117950439453125,
0.045623779296875,
-0.01294708251953125,
-0.04736328125,
-0.026275634765625,
-0.005115509033203125,
0.0122222900390625,
0.03399658203125,
0.0212860107421875,
0.00921630859375,
-0.024444580078125,
-0.0292816162109375,
0.035430908203125,
0.056793212890625,
-0.04156494140625,
-0.02691650390625,
0.0516357421875,
-0.00797271728515625,
-0.006031036376953125,
0.02569580078125,
-0.003276824951171875,
-0.050506591796875,
0.07904052734375,
0.0227813720703125,
0.04632568359375,
-0.031707763671875,
0.0101318359375,
0.06744384765625,
0.00766754150390625,
0.002208709716796875,
0.0290069580078125,
0.0269012451171875,
-0.043365478515625,
0.005615234375,
-0.046356201171875,
0.020660400390625,
0.03228759765625,
-0.0418701171875,
0.00739288330078125,
-0.056060791015625,
-0.0309906005859375,
0.013702392578125,
0.03173828125,
-0.053375244140625,
0.0283203125,
-0.00002968311309814453,
0.08624267578125,
-0.060028076171875,
0.07489013671875,
0.06915283203125,
-0.0435791015625,
-0.07354736328125,
-0.006439208984375,
0.01328277587890625,
-0.07305908203125,
0.060882568359375,
0.002593994140625,
0.00023031234741210938,
-0.0177001953125,
-0.044952392578125,
-0.04766845703125,
0.102783203125,
0.0100555419921875,
-0.0024871826171875,
0.0218353271484375,
-0.0245513916015625,
0.031280517578125,
-0.024993896484375,
0.03662109375,
0.0262298583984375,
0.0396728515625,
0.01139068603515625,
-0.06591796875,
0.0278472900390625,
-0.034759521484375,
-0.007335662841796875,
0.0184326171875,
-0.09747314453125,
0.0823974609375,
-0.021209716796875,
-0.00014829635620117188,
0.0144500732421875,
0.048553466796875,
0.02850341796875,
-0.0040130615234375,
0.0306243896484375,
0.0589599609375,
0.02960205078125,
-0.023040771484375,
0.07501220703125,
-0.0189056396484375,
0.040863037109375,
0.012420654296875,
0.044219970703125,
0.0279541015625,
0.0226898193359375,
-0.0299224853515625,
0.016326904296875,
0.060699462890625,
-0.00464630126953125,
0.0135650634765625,
0.03375244140625,
-0.0265045166015625,
-0.0233154296875,
-0.01116943359375,
-0.043853759765625,
0.0243988037109375,
0.0155487060546875,
-0.02166748046875,
-0.005096435546875,
-0.0160064697265625,
0.0200958251953125,
0.005123138427734375,
-0.021392822265625,
0.033355712890625,
0.005718231201171875,
-0.0281219482421875,
0.04248046875,
0.00431060791015625,
0.07818603515625,
-0.032440185546875,
0.0038356781005859375,
-0.0289459228515625,
0.0290679931640625,
-0.0176544189453125,
-0.07501220703125,
0.0152130126953125,
-0.0102691650390625,
0.00220489501953125,
-0.0185699462890625,
0.06011962890625,
-0.013031005859375,
-0.02691650390625,
0.02587890625,
0.024261474609375,
0.03216552734375,
0.0166778564453125,
-0.09698486328125,
0.0143890380859375,
0.01113128662109375,
-0.054351806640625,
0.032012939453125,
0.03216552734375,
0.01776123046875,
0.05987548828125,
0.031494140625,
0.023773193359375,
0.01456451416015625,
-0.023681640625,
0.059539794921875,
-0.045135498046875,
-0.0262908935546875,
-0.055999755859375,
0.033843994140625,
-0.01593017578125,
-0.048797607421875,
0.058807373046875,
0.038848876953125,
0.04010009765625,
-0.0023097991943359375,
0.0491943359375,
-0.038330078125,
0.032379150390625,
-0.022979736328125,
0.06243896484375,
-0.06109619140625,
-0.018035888671875,
-0.0220947265625,
-0.032073974609375,
-0.033233642578125,
0.0677490234375,
0.00279998779296875,
0.01200103759765625,
0.0148468017578125,
0.055450439453125,
0.01435089111328125,
-0.0200347900390625,
-0.00865936279296875,
0.0083160400390625,
-0.0068511962890625,
0.05963134765625,
0.053375244140625,
-0.053955078125,
0.01251983642578125,
-0.03973388671875,
-0.0176544189453125,
-0.0304718017578125,
-0.055908203125,
-0.0894775390625,
-0.05242919921875,
-0.029693603515625,
-0.0538330078125,
-0.0137481689453125,
0.0870361328125,
0.062408447265625,
-0.04766845703125,
-0.01453399658203125,
0.0230255126953125,
0.01334381103515625,
-0.01416778564453125,
-0.018463134765625,
0.0391845703125,
0.0057220458984375,
-0.062103271484375,
-0.0274810791015625,
0.01433563232421875,
0.0343017578125,
0.0345458984375,
-0.0287322998046875,
-0.022705078125,
0.0010595321655273438,
0.0266876220703125,
0.05487060546875,
-0.0631103515625,
-0.0251007080078125,
-0.006885528564453125,
-0.032623291015625,
0.027313232421875,
0.0233612060546875,
-0.03350830078125,
-0.006793975830078125,
0.0570068359375,
0.01523590087890625,
0.04644775390625,
0.0086822509765625,
0.013031005859375,
-0.034881591796875,
0.037353515625,
-0.0058746337890625,
0.023468017578125,
0.0090484619140625,
-0.0167694091796875,
0.057769775390625,
0.0302581787109375,
-0.0253448486328125,
-0.07354736328125,
-0.018951416015625,
-0.102783203125,
-0.0184173583984375,
0.049560546875,
-0.0195465087890625,
-0.0287628173828125,
0.0247802734375,
-0.0203399658203125,
0.03338623046875,
-0.018951416015625,
0.023590087890625,
0.0226593017578125,
-0.027130126953125,
-0.0178985595703125,
-0.04986572265625,
0.057098388671875,
0.0230255126953125,
-0.04095458984375,
-0.030120849609375,
0.0023860931396484375,
0.0292816162109375,
0.01788330078125,
0.06085205078125,
-0.0218048095703125,
0.01125335693359375,
0.0005288124084472656,
0.0218048095703125,
-0.005420684814453125,
0.0054931640625,
-0.022125244140625,
-0.004261016845703125,
-0.0164947509765625,
-0.04852294921875
]
] |
BAAI/bge-reranker-large | 2023-10-12T03:39:26.000Z | [
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"text-classification",
"zh",
"en",
"arxiv:2310.07554",
"arxiv:2309.07597",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-classification | BAAI | null | null | BAAI/bge-reranker-large | 33 | 40,171 | transformers | 2023-09-12T07:39:18 | ---
license: mit
language:
- zh
- en
---
<h1 align="center">FlagEmbedding</h1>
<h4 align="center">
<p>
<a href=#model-list>Model List</a> |
<a href=#frequently-asked-questions>FAQ</a> |
<a href=#usage>Usage</a> |
<a href="#evaluation">Evaluation</a> |
<a href="#train">Train</a> |
<a href="#contact">Contact</a> |
<a href="#citation">Citation</a> |
<a href="#license">License</a>
<p>
</h4>
More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding).
[English](README.md) | [中文](https://github.com/FlagOpen/FlagEmbedding/blob/master/README_zh.md)
FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
And it also can be used in vector databases for LLMs.
************* 🌟**Updates**🌟 *************
- 10/12/2023: Release [LLM-Embedder](./FlagEmbedding/llm_embedder/README.md), a unified embedding model to support diverse retrieval augmentation needs for LLMs. [Paper](https://arxiv.org/pdf/2310.07554.pdf) :fire:
- 09/15/2023: The [technical report](https://arxiv.org/pdf/2309.07597.pdf) of BGE has been released
- 09/15/2023: The [masive training data](https://data.baai.ac.cn/details/BAAI-MTP) of BGE has been released
- 09/12/2023: New models:
- **New reranker model**: release cross-encoder models `BAAI/bge-reranker-base` and `BAAI/bge-reranker-large`, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.
- **update embedding model**: release `bge-*-v1.5` embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.
<details>
<summary>More</summary>
<!-- ### More -->
- 09/07/2023: Update [fine-tune code](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md): Add script to mine hard negatives and support adding instruction during fine-tuning.
- 08/09/2023: BGE Models are integrated into **Langchain**, you can use it like [this](#using-langchain); C-MTEB **leaderboard** is [available](https://huggingface.co/spaces/mteb/leaderboard).
- 08/05/2023: Release base-scale and small-scale models, **best performance among the models of the same size 🤗**
- 08/02/2023: Release `bge-large-*`(short for BAAI General Embedding) Models, **rank 1st on MTEB and C-MTEB benchmark!** :tada: :tada:
- 08/01/2023: We release the [Chinese Massive Text Embedding Benchmark](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB) (**C-MTEB**), consisting of 31 test dataset.
</details>
## Model List
`bge` is short for `BAAI general embedding`.
| Model | Language | | Description | query instruction for retrieval [1] |
|:-------------------------------|:--------:| :--------:| :--------:|:--------:|
| [BAAI/llm-embedder](https://huggingface.co/BAAI/llm-embedder) | English | [Inference](./FlagEmbedding/llm_embedder/README.md) [Fine-tune](./FlagEmbedding/llm_embedder/README.md) | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See [README](./FlagEmbedding/llm_embedder/README.md) |
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | Chinese and English | [Inference](#usage-for-reranker) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker) | a cross-encoder model which is more accurate but less efficient [2] | |
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-large-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | version 1.5 with more reasonable similarity distribution | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-large-en](https://huggingface.co/BAAI/bge-large-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [MTEB](https://huggingface.co/spaces/mteb/leaderboard) leaderboard | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-base-en](https://huggingface.co/BAAI/bge-base-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-en` | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-small-en](https://huggingface.co/BAAI/bge-small-en) | English | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) |a small-scale model but with competitive performance | `Represent this sentence for searching relevant passages: ` |
| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | :trophy: rank **1st** in [C-MTEB](https://github.com/FlagOpen/FlagEmbedding/tree/master/C_MTEB) benchmark | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a base-scale model but with similar ability to `bge-large-zh` | `为这个句子生成表示以用于检索相关文章：` |
| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | Chinese | [Inference](#usage-for-embedding-model) [Fine-tune](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) | a small-scale model but with competitive performance | `为这个句子生成表示以用于检索相关文章：` |
[1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, **no instruction** needs to be added to passages.
[2\]: Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. To balance the accuracy and time cost, cross-encoder is widely used to re-rank top-k documents retrieved by other simple models.
For examples, use bge embedding model to retrieve top 100 relevant documents, and then use bge reranker to re-rank the top 100 document to get the final top-3 results.
All models have been uploaded to Huggingface Hub, and you can see them at https://huggingface.co/BAAI.
If you cannot open the Huggingface Hub, you also can download the models at https://model.baai.ac.cn/models .
## Frequently asked questions
<details>
<summary>1. How to fine-tune bge embedding model?</summary>
<!-- ### How to fine-tune bge embedding model? -->
Following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune) to prepare data and fine-tune your model.
Some suggestions:
- Mine hard negatives following this [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune#hard-negatives), which can improve the retrieval performance.
- If you pre-train bge on your data, the pre-trained model cannot be directly used to calculate similarity, and it must be fine-tuned with contrastive learning before computing similarity.
- If the accuracy of the fine-tuned model is still not high, it is recommended to use/fine-tune the cross-encoder model (bge-reranker) to re-rank top-k results. Hard negatives also are needed to fine-tune reranker.
</details>
<details>
<summary>2. The similarity score between two dissimilar sentences is higher than 0.5</summary>
<!-- ### The similarity score between two dissimilar sentences is higher than 0.5 -->
**Suggest to use bge v1.5, which alleviates the issue of the similarity distribution.**
Since we finetune the models by contrastive learning with a temperature of 0.01,
the similarity distribution of the current BGE model is about in the interval \[0.6, 1\].
So a similarity score greater than 0.5 does not indicate that the two sentences are similar.
For downstream tasks, such as passage retrieval or semantic similarity,
**what matters is the relative order of the scores, not the absolute value.**
If you need to filter similar sentences based on a similarity threshold,
please select an appropriate similarity threshold based on the similarity distribution on your data (such as 0.8, 0.85, or even 0.9).
</details>
<details>
<summary>3. When does the query instruction need to be used</summary>
<!-- ### When does the query instruction need to be used -->
For the `bge-*-v1.5`, we improve its retrieval ability when not using instruction.
No instruction only has a slight degradation in retrieval performance compared with using instruction.
So you can generate embedding without instruction in all cases for convenience.
For a retrieval task that uses short queries to find long related documents,
it is recommended to add instructions for these short queries.
**The best method to decide whether to add instructions for queries is choosing the setting that achieves better performance on your task.**
In all cases, the documents/passages do not need to add the instruction.
</details>
## Usage
### Usage for Embedding Model
Here are some examples for using `bge` models with
[FlagEmbedding](#using-flagembedding), [Sentence-Transformers](#using-sentence-transformers), [Langchain](#using-langchain), or [Huggingface Transformers](#using-huggingface-transformers).
#### Using FlagEmbedding
```
pip install -U FlagEmbedding
```
If it doesn't work for you, you can see [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md) for more methods to install FlagEmbedding.
```python
from FlagEmbedding import FlagModel
sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-4"]
model = FlagModel('BAAI/bge-large-zh-v1.5',
query_instruction_for_retrieval="为这个句子生成表示以用于检索相关文章：",
use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
embeddings_1 = model.encode(sentences_1)
embeddings_2 = model.encode(sentences_2)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
# for s2p(short query to long passage) retrieval task, suggest to use encode_queries() which will automatically add the instruction to each query
# corpus in retrieval task can still use encode() or encode_corpus(), since they don't need instruction
queries = ['query_1', 'query_2']
passages = ["样例文档-1", "样例文档-2"]
q_embeddings = model.encode_queries(queries)
p_embeddings = model.encode(passages)
scores = q_embeddings @ p_embeddings.T
```
For the value of the argument `query_instruction_for_retrieval`, see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list).
By default, FlagModel will use all available GPUs when encoding. Please set `os.environ["CUDA_VISIBLE_DEVICES"]` to select specific GPUs.
You also can set `os.environ["CUDA_VISIBLE_DEVICES"]=""` to make all GPUs unavailable.
#### Using Sentence-Transformers
You can also use the `bge` models with [sentence-transformers](https://www.SBERT.net):
```
pip install -U sentence-transformers
```
```python
from sentence_transformers import SentenceTransformer
sentences_1 = ["样例数据-1", "样例数据-2"]
sentences_2 = ["样例数据-3", "样例数据-4"]
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
embeddings_1 = model.encode(sentences_1, normalize_embeddings=True)
embeddings_2 = model.encode(sentences_2, normalize_embeddings=True)
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
```
For s2p(short query to long passage) retrieval task,
each short query should start with an instruction (instructions see [Model List](https://github.com/FlagOpen/FlagEmbedding/tree/master#model-list)).
But the instruction is not needed for passages.
```python
from sentence_transformers import SentenceTransformer
queries = ['query_1', 'query_2']
passages = ["样例文档-1", "样例文档-2"]
instruction = "为这个句子生成表示以用于检索相关文章："
model = SentenceTransformer('BAAI/bge-large-zh-v1.5')
q_embeddings = model.encode([instruction+q for q in queries], normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)
scores = q_embeddings @ p_embeddings.T
```
#### Using Langchain
You can use `bge` in langchain like this:
```python
from langchain.embeddings import HuggingFaceBgeEmbeddings
model_name = "BAAI/bge-large-en-v1.5"
model_kwargs = {'device': 'cuda'}
encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
model = HuggingFaceBgeEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs,
query_instruction="为这个句子生成表示以用于检索相关文章："
)
model.query_instruction = "为这个句子生成表示以用于检索相关文章："
```
#### Using HuggingFace Transformers
With the transformers package, you can use the model like this: First, you pass your input through the transformer model, then you select the last hidden state of the first token (i.e., [CLS]) as the sentence embedding.
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Sentences we want sentence embeddings for
sentences = ["样例数据-1", "样例数据-2"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-large-zh-v1.5')
model = AutoModel.from_pretrained('BAAI/bge-large-zh-v1.5')
model.eval()
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# for s2p(short query to long passage) retrieval task, add an instruction to query (not add instruction for passages)
# encoded_input = tokenizer([instruction + q for q in queries], padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, cls pooling.
sentence_embeddings = model_output[0][:, 0]
# normalize embeddings
sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1)
print("Sentence embeddings:", sentence_embeddings)
```
### Usage for Reranker
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding.
You can get a relevance score by inputting query and passage to the reranker.
The reranker is optimized based cross-entropy loss, so the relevance score is not bounded to a specific range.
#### Using FlagEmbedding
```
pip install -U FlagEmbedding
```
Get relevance scores (higher scores indicate more relevance):
```python
from FlagEmbedding import FlagReranker
reranker = FlagReranker('BAAI/bge-reranker-large', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'])
print(score)
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
print(scores)
```
#### Using Huggingface transformers
```python
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large')
model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-large')
model.eval()
pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
with torch.no_grad():
inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
print(scores)
```
## Evaluation
`baai-general-embedding` models achieve **state-of-the-art performance on both MTEB and C-MTEB leaderboard!**
For more details and evaluation tools see our [scripts](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md).
- **MTEB**:
| Model Name | Dimension | Sequence Length | Average (56) | Retrieval (15) |Clustering (11) | Pair Classification (3) | Reranking (4) | STS (10) | Summarization (1) | Classification (12) |
|:----:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
| [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5) | 1024 | 512 | **64.23** | **54.29** | 46.08 | 87.12 | 60.03 | 83.11 | 31.61 | 75.97 |
| [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) | 768 | 512 | 63.55 | 53.25 | 45.77 | 86.55 | 58.86 | 82.4 | 31.07 | 75.53 |
| [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) | 384 | 512 | 62.17 |51.68 | 43.82 | 84.92 | 58.36 | 81.59 | 30.12 | 74.14 |
| [bge-large-en](https://huggingface.co/BAAI/bge-large-en) | 1024 | 512 | 63.98 | 53.9 | 46.98 | 85.8 | 59.48 | 81.56 | 32.06 | 76.21 |
| [bge-base-en](https://huggingface.co/BAAI/bge-base-en) | 768 | 512 | 63.36 | 53.0 | 46.32 | 85.86 | 58.7 | 81.84 | 29.27 | 75.27 |
| [gte-large](https://huggingface.co/thenlper/gte-large) | 1024 | 512 | 63.13 | 52.22 | 46.84 | 85.00 | 59.13 | 83.35 | 31.66 | 73.33 |
| [gte-base](https://huggingface.co/thenlper/gte-base) | 768 | 512 | 62.39 | 51.14 | 46.2 | 84.57 | 58.61 | 82.3 | 31.17 | 73.01 |
| [e5-large-v2](https://huggingface.co/intfloat/e5-large-v2) | 1024| 512 | 62.25 | 50.56 | 44.49 | 86.03 | 56.61 | 82.05 | 30.19 | 75.24 |
| [bge-small-en](https://huggingface.co/BAAI/bge-small-en) | 384 | 512 | 62.11 | 51.82 | 44.31 | 83.78 | 57.97 | 80.72 | 30.53 | 74.37 |
| [instructor-xl](https://huggingface.co/hkunlp/instructor-xl) | 768 | 512 | 61.79 | 49.26 | 44.74 | 86.62 | 57.29 | 83.06 | 32.32 | 61.79 |
| [e5-base-v2](https://huggingface.co/intfloat/e5-base-v2) | 768 | 512 | 61.5 | 50.29 | 43.80 | 85.73 | 55.91 | 81.05 | 30.28 | 73.84 |
| [gte-small](https://huggingface.co/thenlper/gte-small) | 384 | 512 | 61.36 | 49.46 | 44.89 | 83.54 | 57.7 | 82.07 | 30.42 | 72.31 |
| [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 1536 | 8192 | 60.99 | 49.25 | 45.9 | 84.89 | 56.32 | 80.97 | 30.8 | 70.93 |
| [e5-small-v2](https://huggingface.co/intfloat/e5-base-v2) | 384 | 512 | 59.93 | 49.04 | 39.92 | 84.67 | 54.32 | 80.39 | 31.16 | 72.94 |
| [sentence-t5-xxl](https://huggingface.co/sentence-transformers/sentence-t5-xxl) | 768 | 512 | 59.51 | 42.24 | 43.72 | 85.06 | 56.42 | 82.63 | 30.08 | 73.42 |
| [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) | 768 | 514 | 57.78 | 43.81 | 43.69 | 83.04 | 59.36 | 80.28 | 27.49 | 65.07 |
| [sgpt-bloom-7b1-msmarco](https://huggingface.co/bigscience/sgpt-bloom-7b1-msmarco) | 4096 | 2048 | 57.59 | 48.22 | 38.93 | 81.9 | 55.65 | 77.74 | 33.6 | 66.19 |
- **C-MTEB**:
We create the benchmark C-MTEB for Chinese text embedding which consists of 31 datasets from 6 tasks.
Please refer to [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/README.md) for a detailed introduction.
| Model | Embedding dimension | Avg | Retrieval | STS | PairClassification | Classification | Reranking | Clustering |
|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| [**BAAI/bge-large-zh-v1.5**](https://huggingface.co/BAAI/bge-large-zh-v1.5) | 1024 | **64.53** | 70.46 | 56.25 | 81.6 | 69.13 | 65.84 | 48.99 |
| [BAAI/bge-base-zh-v1.5](https://huggingface.co/BAAI/bge-base-zh-v1.5) | 768 | 63.13 | 69.49 | 53.72 | 79.75 | 68.07 | 65.39 | 47.53 |
| [BAAI/bge-small-zh-v1.5](https://huggingface.co/BAAI/bge-small-zh-v1.5) | 512 | 57.82 | 61.77 | 49.11 | 70.41 | 63.96 | 60.92 | 44.18 |
| [BAAI/bge-large-zh](https://huggingface.co/BAAI/bge-large-zh) | 1024 | 64.20 | 71.53 | 54.98 | 78.94 | 68.32 | 65.11 | 48.39 |
| [bge-large-zh-noinstruct](https://huggingface.co/BAAI/bge-large-zh-noinstruct) | 1024 | 63.53 | 70.55 | 53 | 76.77 | 68.58 | 64.91 | 50.01 |
| [BAAI/bge-base-zh](https://huggingface.co/BAAI/bge-base-zh) | 768 | 62.96 | 69.53 | 54.12 | 77.5 | 67.07 | 64.91 | 47.63 |
| [multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) | 1024 | 58.79 | 63.66 | 48.44 | 69.89 | 67.34 | 56.00 | 48.23 |
| [BAAI/bge-small-zh](https://huggingface.co/BAAI/bge-small-zh) | 512 | 58.27 | 63.07 | 49.45 | 70.35 | 63.64 | 61.48 | 45.09 |
| [m3e-base](https://huggingface.co/moka-ai/m3e-base) | 768 | 57.10 | 56.91 | 50.47 | 63.99 | 67.52 | 59.34 | 47.68 |
| [m3e-large](https://huggingface.co/moka-ai/m3e-large) | 1024 | 57.05 | 54.75 | 50.42 | 64.3 | 68.2 | 59.66 | 48.88 |
| [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) | 768 | 55.48 | 61.63 | 46.49 | 67.07 | 65.35 | 54.35 | 40.68 |
| [multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) | 384 | 55.38 | 59.95 | 45.27 | 66.45 | 65.85 | 53.86 | 45.26 |
| [text-embedding-ada-002(OpenAI)](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings) | 1536 | 53.02 | 52.0 | 43.35 | 69.56 | 64.31 | 54.28 | 45.68 |
| [luotuo](https://huggingface.co/silk-road/luotuo-bert-medium) | 1024 | 49.37 | 44.4 | 42.78 | 66.62 | 61 | 49.25 | 44.39 |
| [text2vec-base](https://huggingface.co/shibing624/text2vec-base-chinese) | 768 | 47.63 | 38.79 | 43.41 | 67.41 | 62.19 | 49.45 | 37.66 |
| [text2vec-large](https://huggingface.co/GanymedeNil/text2vec-large-chinese) | 1024 | 47.36 | 41.94 | 44.97 | 70.86 | 60.66 | 49.16 | 30.02 |
- **Reranking**:
See [C_MTEB](https://github.com/FlagOpen/FlagEmbedding/blob/master/C_MTEB/) for evaluation script.
| Model | T2Reranking | T2RerankingZh2En\* | T2RerankingEn2Zh\* | MMarcoReranking | CMedQAv1 | CMedQAv2 | Avg |
|:-------------------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| text2vec-base-multilingual | 64.66 | 62.94 | 62.51 | 14.37 | 48.46 | 48.6 | 50.26 |
| multilingual-e5-small | 65.62 | 60.94 | 56.41 | 29.91 | 67.26 | 66.54 | 57.78 |
| multilingual-e5-large | 64.55 | 61.61 | 54.28 | 28.6 | 67.42 | 67.92 | 57.4 |
| multilingual-e5-base | 64.21 | 62.13 | 54.68 | 29.5 | 66.23 | 66.98 | 57.29 |
| m3e-base | 66.03 | 62.74 | 56.07 | 17.51 | 77.05 | 76.76 | 59.36 |
| m3e-large | 66.13 | 62.72 | 56.1 | 16.46 | 77.76 | 78.27 | 59.57 |
| bge-base-zh-v1.5 | 66.49 | 63.25 | 57.02 | 29.74 | 80.47 | 84.88 | 63.64 |
| bge-large-zh-v1.5 | 65.74 | 63.39 | 57.03 | 28.74 | 83.45 | 85.44 | 63.97 |
| [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) | 67.28 | 63.95 | 60.45 | 35.46 | 81.26 | 84.1 | 65.42 |
| [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) | 67.6 | 64.03 | 61.44 | 37.16 | 82.15 | 84.18 | 66.09 |
\* : T2RerankingZh2En and T2RerankingEn2Zh are cross-language retrieval tasks
## Train
### BAAI Embedding
We pre-train the models using [retromae](https://github.com/staoxiao/RetroMAE) and train them on large-scale pairs data using contrastive learning.
**You can fine-tune the embedding model on your data following our [examples](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/finetune).**
We also provide a [pre-train example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/pretrain).
Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned.
More training details for bge see [baai_general_embedding](https://github.com/FlagOpen/FlagEmbedding/blob/master/FlagEmbedding/baai_general_embedding/README.md).
### BGE Reranker
Cross-encoder will perform full-attention over the input pair,
which is more accurate than embedding model (i.e., bi-encoder) but more time-consuming than embedding model.
Therefore, it can be used to re-rank the top-k documents returned by embedding model.
We train the cross-encoder on a multilingual pair data,
The data format is the same as embedding model, so you can fine-tune it easily following our [example](https://github.com/FlagOpen/FlagEmbedding/tree/master/examples/reranker).
More details please refer to [./FlagEmbedding/reranker/README.md](https://github.com/FlagOpen/FlagEmbedding/tree/master/FlagEmbedding/reranker)
## Contact
If you have any question or suggestion related to this project, feel free to open an issue or pull request.
You also can email Shitao Xiao(stxiao@baai.ac.cn) and Zheng Liu(liuzheng@baai.ac.cn).
## Citation
If you find this repository useful, please consider giving a star :star: and citation
```
@misc{bge_embedding,
title={C-Pack: Packaged Resources To Advance General Chinese Embedding},
author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
year={2023},
eprint={2309.07597},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## License
FlagEmbedding is licensed under the [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). The released models can be used for commercial purposes free of charge.
| 27,170 | [
[
-0.036651611328125,
-0.0679931640625,
0.029296875,
0.01187896728515625,
-0.02716064453125,
-0.02056884765625,
-0.0237579345703125,
-0.0189666748046875,
0.0300445556640625,
0.0283966064453125,
-0.0260467529296875,
-0.06549072265625,
-0.036102294921875,
-0.004611968994140625,
-0.006378173828125,
0.04150390625,
-0.0037555694580078125,
0.010711669921875,
0.0039215087890625,
-0.0186767578125,
-0.0283966064453125,
-0.0190277099609375,
-0.049163818359375,
-0.0192108154296875,
0.025726318359375,
0.0170745849609375,
0.042205810546875,
0.056365966796875,
0.0222930908203125,
0.020233154296875,
-0.0175933837890625,
0.01165771484375,
-0.0357666015625,
-0.005138397216796875,
-0.01552581787109375,
-0.024871826171875,
-0.03143310546875,
0.01317596435546875,
0.050994873046875,
0.0335693359375,
-0.00774383544921875,
0.0077972412109375,
0.000499725341796875,
0.053192138671875,
-0.034515380859375,
0.020751953125,
-0.042724609375,
0.0027217864990234375,
-0.0180511474609375,
0.01129913330078125,
-0.038604736328125,
-0.0287017822265625,
0.011962890625,
-0.045867919921875,
0.006160736083984375,
0.0216217041015625,
0.097412109375,
0.0154266357421875,
-0.033966064453125,
-0.0123748779296875,
-0.009063720703125,
0.0740966796875,
-0.07525634765625,
0.051177978515625,
0.037933349609375,
0.01904296875,
-0.005809783935546875,
-0.0609130859375,
-0.0269622802734375,
-0.01239776611328125,
-0.01514434814453125,
0.031524658203125,
0.0018978118896484375,
0.0014820098876953125,
0.0236053466796875,
0.044586181640625,
-0.041351318359375,
0.007049560546875,
-0.00511932373046875,
-0.0118560791015625,
0.056884765625,
-0.01230621337890625,
0.034210205078125,
-0.0416259765625,
-0.0223541259765625,
-0.027435302734375,
-0.059661865234375,
0.0034198760986328125,
0.0273590087890625,
0.01023101806640625,
-0.02935791015625,
0.0423583984375,
-0.017120361328125,
0.045501708984375,
0.003780364990234375,
0.00383758544921875,
0.03924560546875,
-0.0278472900390625,
-0.01548004150390625,
-0.01094818115234375,
0.069580078125,
0.029449462890625,
-0.004314422607421875,
0.003849029541015625,
-0.0241241455078125,
-0.00708770751953125,
-0.00695037841796875,
-0.06689453125,
-0.018157958984375,
0.01482391357421875,
-0.05712890625,
-0.01355743408203125,
0.0177459716796875,
-0.05816650390625,
0.00775909423828125,
0.00010699033737182617,
0.043670654296875,
-0.055694580078125,
-0.005523681640625,
0.02337646484375,
-0.0157470703125,
0.029998779296875,
-0.00024139881134033203,
-0.046844482421875,
-0.018524169921875,
0.039764404296875,
0.0640869140625,
0.01251220703125,
-0.0056915283203125,
-0.0279541015625,
0.002826690673828125,
-0.010650634765625,
0.0244903564453125,
-0.03887939453125,
-0.0133209228515625,
0.015777587890625,
0.0289764404296875,
-0.00769805908203125,
-0.0216827392578125,
0.06597900390625,
-0.040130615234375,
0.02691650390625,
-0.0283050537109375,
-0.061553955078125,
-0.037506103515625,
0.0069122314453125,
-0.060089111328125,
0.08282470703125,
-0.00733184814453125,
-0.06341552734375,
0.006221771240234375,
-0.048248291015625,
-0.0161895751953125,
-0.0191192626953125,
-0.0024871826171875,
-0.044769287109375,
-0.0087890625,
0.0284423828125,
0.043670654296875,
-0.017120361328125,
0.002613067626953125,
-0.025970458984375,
-0.042755126953125,
-0.0005273818969726562,
-0.017303466796875,
0.0819091796875,
0.0191650390625,
-0.025115966796875,
-0.0164794921875,
-0.032806396484375,
0.00897979736328125,
0.0227203369140625,
-0.02337646484375,
-0.025787353515625,
0.0165557861328125,
0.0176849365234375,
0.0038738250732421875,
0.03961181640625,
-0.052764892578125,
0.01369476318359375,
-0.043792724609375,
0.044464111328125,
0.04180908203125,
0.012939453125,
0.0179290771484375,
-0.035491943359375,
0.021575927734375,
-0.00174713134765625,
-0.0028533935546875,
-0.016632080078125,
-0.039703369140625,
-0.046966552734375,
-0.02264404296875,
0.055450439453125,
0.04937744140625,
-0.0653076171875,
0.049774169921875,
-0.034210205078125,
-0.04632568359375,
-0.07049560546875,
0.0100860595703125,
0.039947509765625,
0.00014972686767578125,
0.05377197265625,
-0.01033782958984375,
-0.035858154296875,
-0.0699462890625,
-0.00463104248046875,
0.005870819091796875,
-0.006809234619140625,
0.0401611328125,
0.0460205078125,
-0.023895263671875,
0.0305023193359375,
-0.05487060546875,
-0.026153564453125,
-0.0172119140625,
-0.00550079345703125,
0.0253753662109375,
0.036712646484375,
0.04779052734375,
-0.07537841796875,
-0.043701171875,
-0.0006194114685058594,
-0.058319091796875,
0.005710601806640625,
0.002735137939453125,
-0.0224151611328125,
0.01305389404296875,
0.045654296875,
-0.0307769775390625,
0.017791748046875,
0.035675048828125,
-0.019317626953125,
0.0210418701171875,
-0.0015573501586914062,
0.0109710693359375,
-0.09912109375,
0.0016279220581054688,
0.022613525390625,
-0.0085906982421875,
-0.020477294921875,
0.0389404296875,
0.0126953125,
0.0154266357421875,
-0.02587890625,
0.0439453125,
-0.0394287109375,
0.0187530517578125,
0.009674072265625,
0.0460205078125,
-0.0067138671875,
0.038330078125,
-0.0035190582275390625,
0.0537109375,
0.027801513671875,
-0.0299072265625,
0.00928497314453125,
0.03955078125,
-0.033355712890625,
0.006092071533203125,
-0.04937744140625,
-0.0056915283203125,
-0.0055389404296875,
0.0125579833984375,
-0.062103271484375,
-0.005462646484375,
0.0198211669921875,
-0.04296875,
0.039581298828125,
-0.0224609375,
-0.037261962890625,
-0.0276336669921875,
-0.06829833984375,
0.0110015869140625,
0.04376220703125,
-0.048553466796875,
0.0164794921875,
0.022125244140625,
0.00695037841796875,
-0.0579833984375,
-0.061309814453125,
-0.01165771484375,
-0.00017440319061279297,
-0.039520263671875,
0.0408935546875,
-0.002140045166015625,
0.0191650390625,
0.0141754150390625,
-0.005374908447265625,
0.01128387451171875,
0.00867462158203125,
-0.00019729137420654297,
0.0184173583984375,
-0.035797119140625,
0.0035552978515625,
0.02056884765625,
0.00980377197265625,
-0.0148773193359375,
-0.01212310791015625,
0.033111572265625,
-0.0129241943359375,
-0.02679443359375,
-0.017791748046875,
0.0255584716796875,
0.01922607421875,
-0.0303955078125,
0.0445556640625,
0.07452392578125,
-0.0281829833984375,
-0.0062713623046875,
-0.0496826171875,
-0.009246826171875,
-0.0362548828125,
0.034149169921875,
-0.0243377685546875,
-0.07379150390625,
0.02972412109375,
-0.0015201568603515625,
0.0162506103515625,
0.050872802734375,
0.0252532958984375,
-0.01064300537109375,
0.0809326171875,
0.0281524658203125,
-0.0202789306640625,
0.049835205078125,
-0.049774169921875,
0.0133209228515625,
-0.0882568359375,
-0.00335693359375,
-0.0297088623046875,
-0.0297088623046875,
-0.09991455078125,
-0.03802490234375,
0.004638671875,
0.0210113525390625,
-0.02862548828125,
0.0323486328125,
-0.042999267578125,
0.01145172119140625,
0.03643798828125,
0.0222930908203125,
-0.001373291015625,
0.00936126708984375,
-0.032623291015625,
-0.0203704833984375,
-0.04583740234375,
-0.038238525390625,
0.07513427734375,
0.036407470703125,
0.04608154296875,
0.027374267578125,
0.061981201171875,
0.01419830322265625,
0.0073089599609375,
-0.058197021484375,
0.042999267578125,
-0.03936767578125,
-0.04296875,
-0.0269927978515625,
-0.036712646484375,
-0.083984375,
0.02984619140625,
-0.0205841064453125,
-0.058319091796875,
0.00806427001953125,
-0.0148773193359375,
-0.002285003662109375,
0.03515625,
-0.050872802734375,
0.07720947265625,
-0.00812530517578125,
-0.023193359375,
-0.005878448486328125,
-0.03155517578125,
0.0245208740234375,
0.01496124267578125,
0.006221771240234375,
0.005558013916015625,
-0.0195465087890625,
0.05718994140625,
-0.01415252685546875,
0.04803466796875,
-0.01220703125,
0.01122283935546875,
0.03240966796875,
-0.01386260986328125,
0.04168701171875,
0.006069183349609375,
-0.0135498046875,
0.0226898193359375,
0.00672149658203125,
-0.036407470703125,
-0.037384033203125,
0.06634521484375,
-0.050750732421875,
-0.05328369140625,
-0.0282440185546875,
-0.0188751220703125,
0.01348114013671875,
0.032989501953125,
0.0265960693359375,
0.0165252685546875,
-0.00777435302734375,
0.0487060546875,
0.06982421875,
-0.0411376953125,
0.028900146484375,
0.0261077880859375,
-0.0206298828125,
-0.044647216796875,
0.0845947265625,
0.0197906494140625,
-0.003955841064453125,
0.05078125,
0.0010061264038085938,
-0.021087646484375,
-0.040008544921875,
-0.03436279296875,
0.047943115234375,
-0.04473876953125,
-0.01264190673828125,
-0.048309326171875,
-0.0322265625,
-0.0325927734375,
0.001644134521484375,
-0.02044677734375,
-0.0213623046875,
-0.013427734375,
-0.021209716796875,
0.0177764892578125,
0.035797119140625,
0.0091705322265625,
0.006679534912109375,
-0.0535888671875,
0.015899658203125,
-0.00734710693359375,
0.033172607421875,
0.005401611328125,
-0.04071044921875,
-0.046844482421875,
0.013153076171875,
-0.0369873046875,
-0.081787109375,
0.0262451171875,
0.005680084228515625,
0.06317138671875,
0.02484130859375,
-0.0008363723754882812,
0.0309600830078125,
-0.03955078125,
0.08062744140625,
-0.008148193359375,
-0.05926513671875,
0.0384521484375,
-0.02117919921875,
0.012420654296875,
0.042205810546875,
0.049285888671875,
-0.03497314453125,
-0.0206451416015625,
-0.037078857421875,
-0.07275390625,
0.036651611328125,
0.01372528076171875,
0.0032291412353515625,
-0.022369384765625,
0.024810791015625,
-0.01372528076171875,
-0.0001571178436279297,
-0.060302734375,
-0.056243896484375,
-0.0251922607421875,
-0.02655029296875,
-0.007312774658203125,
-0.020904541015625,
0.01558685302734375,
-0.0218963623046875,
0.075439453125,
0.0003418922424316406,
0.041412353515625,
0.0270233154296875,
-0.024658203125,
0.0180511474609375,
0.019073486328125,
0.0224456787109375,
0.01412200927734375,
-0.0291595458984375,
-0.01092529296875,
0.0237579345703125,
-0.041595458984375,
-0.0048065185546875,
0.0233612060546875,
-0.035308837890625,
0.01462554931640625,
0.023040771484375,
0.05328369140625,
0.033843994140625,
-0.03338623046875,
0.042633056640625,
0.00862884521484375,
-0.014190673828125,
-0.022552490234375,
-0.005401611328125,
0.023040771484375,
0.0189666748046875,
0.00879669189453125,
-0.034393310546875,
0.01995849609375,
-0.039947509765625,
0.0255584716796875,
0.033843994140625,
-0.028656005859375,
-0.005062103271484375,
0.052764892578125,
0.002620697021484375,
-0.0016117095947265625,
0.03607177734375,
-0.037841796875,
-0.055450439453125,
0.031982421875,
0.0282440185546875,
0.06329345703125,
-0.0110015869140625,
0.016876220703125,
0.06500244140625,
0.04010009765625,
-0.024078369140625,
0.0269012451171875,
0.005828857421875,
-0.04400634765625,
-0.033447265625,
-0.0408935546875,
-0.00439453125,
0.0200958251953125,
-0.0435791015625,
0.0264434814453125,
-0.031402587890625,
-0.011138916015625,
0.0023632049560546875,
0.033111572265625,
-0.05609130859375,
0.009552001953125,
0.00341033935546875,
0.0848388671875,
-0.04400634765625,
0.06292724609375,
0.07476806640625,
-0.07232666015625,
-0.058197021484375,
0.005970001220703125,
-0.0098419189453125,
-0.0458984375,
0.0283050537109375,
0.0198822021484375,
0.0133514404296875,
0.00469207763671875,
-0.03594970703125,
-0.06890869140625,
0.11822509765625,
0.00287628173828125,
-0.0399169921875,
-0.004669189453125,
-0.021240234375,
0.034454345703125,
-0.02850341796875,
0.033599853515625,
0.0310516357421875,
0.0460205078125,
-0.0139617919921875,
-0.04852294921875,
0.040863037109375,
-0.0238494873046875,
0.0176849365234375,
0.0036945343017578125,
-0.07330322265625,
0.0623779296875,
0.0034313201904296875,
-0.02496337890625,
0.0146484375,
0.054473876953125,
0.0173187255859375,
0.031585693359375,
0.0182037353515625,
0.07000732421875,
0.049652099609375,
-0.01678466796875,
0.08709716796875,
-0.019439697265625,
0.047332763671875,
0.06549072265625,
0.01275634765625,
0.0843505859375,
0.00669097900390625,
-0.0177459716796875,
0.05059814453125,
0.0596923828125,
-0.024078369140625,
0.035064697265625,
0.0014209747314453125,
0.004581451416015625,
-0.024078369140625,
0.0040130615234375,
-0.04034423828125,
0.0217132568359375,
0.0245513916015625,
-0.038970947265625,
0.0033626556396484375,
-0.0220489501953125,
0.009002685546875,
0.00799560546875,
-0.0016984939575195312,
0.043426513671875,
0.0235595703125,
-0.035064697265625,
0.050079345703125,
0.0177459716796875,
0.07611083984375,
-0.03045654296875,
-0.0114898681640625,
-0.02130126953125,
-0.0085906982421875,
-0.01708984375,
-0.05889892578125,
-0.006103515625,
-0.01934814453125,
-0.0155487060546875,
0.00634002685546875,
0.0406494140625,
-0.046966552734375,
-0.0306549072265625,
0.0426025390625,
0.038818359375,
0.01824951171875,
0.01349639892578125,
-0.0826416015625,
0.002353668212890625,
0.0288238525390625,
-0.040130615234375,
0.0231170654296875,
0.035552978515625,
-0.004657745361328125,
0.04443359375,
0.04400634765625,
0.00482940673828125,
-0.0014810562133789062,
0.0030269622802734375,
0.03875732421875,
-0.07037353515625,
-0.0229949951171875,
-0.047607421875,
0.0271759033203125,
-0.0246124267578125,
0.0016651153564453125,
0.060791015625,
0.053009033203125,
0.08074951171875,
-0.003963470458984375,
0.061309814453125,
-0.00861358642578125,
0.03070068359375,
-0.045318603515625,
0.067138671875,
-0.0772705078125,
0.019439697265625,
-0.0266265869140625,
-0.070556640625,
-0.0118255615234375,
0.052703857421875,
-0.025299072265625,
0.0174102783203125,
0.051177978515625,
0.0736083984375,
-0.019287109375,
-0.01438140869140625,
0.023193359375,
0.0328369140625,
0.01189422607421875,
0.0596923828125,
0.0259857177734375,
-0.07366943359375,
0.048248291015625,
-0.017852783203125,
0.00962066650390625,
-0.039154052734375,
-0.04791259765625,
-0.06939697265625,
-0.05511474609375,
-0.031707763671875,
-0.02301025390625,
-0.0034236907958984375,
0.06927490234375,
0.0257568359375,
-0.056365966796875,
-0.0052032470703125,
0.0207977294921875,
0.0364990234375,
-0.02008056640625,
-0.0207061767578125,
0.049652099609375,
-0.005710601806640625,
-0.07037353515625,
0.02471923828125,
-0.006290435791015625,
-0.005138397216796875,
-0.00399017333984375,
-0.0184326171875,
-0.06640625,
0.00894927978515625,
0.044952392578125,
0.0191497802734375,
-0.068603515625,
-0.031585693359375,
0.00634765625,
-0.01959228515625,
-0.01158905029296875,
0.01270294189453125,
-0.0309906005859375,
0.0269927978515625,
0.046600341796875,
0.05792236328125,
0.0496826171875,
-0.0035190582275390625,
0.01529693603515625,
-0.04608154296875,
-0.006412506103515625,
-0.003170013427734375,
0.053375244140625,
0.0273895263671875,
-0.0226287841796875,
0.06781005859375,
0.016082763671875,
-0.030487060546875,
-0.056640625,
0.0024509429931640625,
-0.07928466796875,
-0.02471923828125,
0.08404541015625,
-0.031982421875,
-0.0188140869140625,
0.0205535888671875,
-0.0143890380859375,
0.041259765625,
-0.036956787109375,
0.035369873046875,
0.05999755859375,
0.03271484375,
-0.01172637939453125,
-0.0684814453125,
0.0235137939453125,
0.046722412109375,
-0.0206756591796875,
-0.0255126953125,
0.025390625,
0.036346435546875,
0.0179595947265625,
0.008758544921875,
-0.0185699462890625,
0.024017333984375,
-0.00565338134765625,
-0.0006694793701171875,
-0.01041412353515625,
0.018524169921875,
-0.01372528076171875,
0.0019474029541015625,
-0.0125579833984375,
-0.0232086181640625
]
] |
MingZhong/unieval-dialog | 2022-10-14T01:09:17.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"arxiv:2210.07197",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | MingZhong | null | null | MingZhong/unieval-dialog | 1 | 40,031 | transformers | 2022-10-11T01:08:51 | Pre-trained evaluator in EMNLP 2022 paper
*[Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://arxiv.org/abs/2210.07197)*
## Introduction
**Multi-dimensional evaluation** is the dominant paradigm for human evaluation in Natural Language Generation (NLG), i.e., evaluating the generated text from multiple explainable dimensions, such as coherence and fluency.
However, automatic evaluation in NLG is still dominated by similarity-based metrics (e.g., ROUGE, BLEU), but they are not sufficient to portray the difference between the advanced generation models.
Therefore, we propose **UniEval** to bridge this gap so that a more comprehensive and fine-grained evaluation of NLG systems can be achieved.
## Pre-trained Evaluator
**unieval-dialog** is the pre-trained evaluator for the dialogue response generation task. It can evaluate the model output from five dimensions:
- *naturalness*
- *coherence*
- *engagingness*
- *groundedness*
- *understandability*
## Usage
Please refer to [our GitHub repository](https://github.com/maszhongming/UniEval). | 1,084 | [
[
-0.048797607421875,
-0.0550537109375,
0.033355712890625,
0.0206451416015625,
-0.0159454345703125,
0.0111846923828125,
-0.01837158203125,
-0.01369476318359375,
0.004543304443359375,
0.044036865234375,
-0.046356201171875,
-0.036865234375,
-0.0253448486328125,
0.019500732421875,
-0.01519012451171875,
0.0850830078125,
0.00981903076171875,
-0.004276275634765625,
-0.034576416015625,
0.0022029876708984375,
-0.0304107666015625,
-0.0307769775390625,
-0.049224853515625,
-0.045562744140625,
0.01422119140625,
0.0202789306640625,
0.023101806640625,
-0.0110321044921875,
0.0223541259765625,
0.0307464599609375,
0.00762939453125,
0.01073455810546875,
-0.01529693603515625,
0.00897216796875,
0.00592041015625,
-0.00012445449829101562,
-0.053375244140625,
0.009979248046875,
0.044921875,
0.042724609375,
-0.0142059326171875,
0.0174560546875,
0.0197296142578125,
0.0482177734375,
-0.039154052734375,
0.001857757568359375,
-0.04376220703125,
0.01898193359375,
0.0136871337890625,
-0.02496337890625,
-0.03131103515625,
-0.0257415771484375,
0.0306243896484375,
-0.0452880859375,
0.0174713134765625,
-0.002346038818359375,
0.056243896484375,
0.0335693359375,
-0.033447265625,
-0.0140228271484375,
-0.0428466796875,
0.0499267578125,
-0.053375244140625,
0.0286102294921875,
0.007480621337890625,
0.01319122314453125,
-0.005229949951171875,
-0.07916259765625,
-0.0404052734375,
-0.0101470947265625,
-0.0005412101745605469,
0.04632568359375,
-0.01934814453125,
0.0257110595703125,
0.013214111328125,
0.0230865478515625,
-0.0489501953125,
0.01654052734375,
-0.0201416015625,
-0.02581787109375,
0.0550537109375,
0.009674072265625,
0.007343292236328125,
-0.02142333984375,
-0.040008544921875,
-0.006256103515625,
-0.02703857421875,
0.0085906982421875,
0.03558349609375,
0.0038433074951171875,
-0.00969696044921875,
0.01467132568359375,
-0.01142120361328125,
0.0545654296875,
-0.0003120899200439453,
0.00730133056640625,
0.03436279296875,
-0.041412353515625,
-0.0237579345703125,
0.00299072265625,
0.08819580078125,
0.0287017822265625,
0.0030307769775390625,
0.0113983154296875,
-0.01352691650390625,
-0.019439697265625,
0.044891357421875,
-0.0687255859375,
-0.0220489501953125,
0.0139312744140625,
-0.044647216796875,
-0.04473876953125,
-0.0003120899200439453,
-0.10247802734375,
-0.0029773712158203125,
-0.023590087890625,
0.02685546875,
-0.01192474365234375,
-0.0258941650390625,
0.00444793701171875,
0.002044677734375,
0.00112152099609375,
0.032958984375,
-0.050872802734375,
-0.0009412765502929688,
0.02911376953125,
0.0361328125,
0.01161956787109375,
-0.034423828125,
-0.0310821533203125,
-0.0219879150390625,
0.0006046295166015625,
0.07275390625,
-0.043182373046875,
-0.018707275390625,
0.00400543212890625,
-0.0208282470703125,
-0.00789642333984375,
-0.03466796875,
0.06085205078125,
-0.01340484619140625,
0.04010009765625,
0.00960540771484375,
-0.0207672119140625,
-0.005184173583984375,
0.0128936767578125,
-0.04107666015625,
0.07318115234375,
0.011749267578125,
-0.05029296875,
0.043243408203125,
-0.0894775390625,
0.007366180419921875,
0.005481719970703125,
-0.01371002197265625,
-0.043670654296875,
0.01922607421875,
0.027587890625,
0.0244293212890625,
-0.034881591796875,
0.0266876220703125,
-0.018096923828125,
-0.00652313232421875,
0.00439453125,
-0.058197021484375,
0.060577392578125,
0.027557373046875,
-0.00527191162109375,
0.02099609375,
-0.0853271484375,
0.037384033203125,
-0.0014247894287109375,
-0.03466796875,
-0.0032024383544921875,
-0.030517578125,
0.016448974609375,
0.0204010009765625,
0.022613525390625,
-0.05303955078125,
-0.0009417533874511719,
-0.037200927734375,
0.02166748046875,
0.04046630859375,
0.00036025047302246094,
0.0254974365234375,
0.0014362335205078125,
0.05401611328125,
-0.01461029052734375,
0.006500244140625,
-0.0256500244140625,
-0.033447265625,
-0.047637939453125,
0.0005955696105957031,
0.0440673828125,
0.0297393798828125,
-0.057830810546875,
0.066162109375,
0.0054168701171875,
-0.03887939453125,
-0.03924560546875,
0.007152557373046875,
0.049102783203125,
0.0201873779296875,
0.0211029052734375,
-0.029083251953125,
-0.0672607421875,
-0.05535888671875,
-0.03057861328125,
-0.022125244140625,
-0.01515960693359375,
-0.00008863210678100586,
0.0345458984375,
-0.02044677734375,
0.06524658203125,
-0.0238494873046875,
-0.0102691650390625,
-0.0305633544921875,
0.048980712890625,
-0.0158843994140625,
0.0394287109375,
0.039642333984375,
-0.0400390625,
-0.032806396484375,
-0.01093292236328125,
-0.060546875,
-0.033660888671875,
-0.01265716552734375,
-0.00205230712890625,
0.01708984375,
0.048309326171875,
-0.044708251953125,
0.04486083984375,
0.061248779296875,
-0.028472900390625,
0.04638671875,
-0.0275726318359375,
0.01032257080078125,
-0.10009765625,
0.00890350341796875,
-0.0145263671875,
-0.00617218017578125,
-0.051300048828125,
-0.00826263427734375,
-0.022186279296875,
-0.03521728515625,
-0.0298614501953125,
0.041534423828125,
-0.026519775390625,
-0.0046844482421875,
-0.018524169921875,
0.031951904296875,
0.0196380615234375,
0.035736083984375,
-0.001567840576171875,
0.0419921875,
0.016876220703125,
-0.0352783203125,
0.0318603515625,
0.034149169921875,
-0.0244903564453125,
0.049041748046875,
-0.058685302734375,
0.034027099609375,
-0.001224517822265625,
0.0298614501953125,
-0.0675048828125,
-0.0136566162109375,
-0.0049591064453125,
-0.04669189453125,
0.0257415771484375,
0.00757598876953125,
-0.028839111328125,
-0.038787841796875,
-0.01384735107421875,
0.024383544921875,
0.0302734375,
-0.053680419921875,
0.044708251953125,
0.019805908203125,
-0.005283355712890625,
-0.0421142578125,
-0.0282440185546875,
0.0017366409301757812,
-0.0182342529296875,
-0.04937744140625,
0.004688262939453125,
-0.015777587890625,
-0.004451751708984375,
-0.0159912109375,
0.006801605224609375,
-0.0055389404296875,
0.0046844482421875,
0.0202789306640625,
0.0023651123046875,
-0.0054931640625,
0.00827789306640625,
0.0182342529296875,
-0.0304718017578125,
0.0196380615234375,
-0.01387786865234375,
0.054351806640625,
-0.032562255859375,
-0.0249786376953125,
-0.03326416015625,
0.018096923828125,
0.01959228515625,
-0.0279083251953125,
0.0285186767578125,
0.07415771484375,
-0.01459503173828125,
-0.006313323974609375,
-0.02996826171875,
-0.00833892822265625,
-0.03607177734375,
0.040924072265625,
-0.024749755859375,
-0.0675048828125,
0.0240631103515625,
-0.03466796875,
0.0164794921875,
0.052001953125,
0.04052734375,
-0.0032825469970703125,
0.07635498046875,
0.046844482421875,
0.032562255859375,
0.01715087890625,
-0.0098114013671875,
0.034088134765625,
-0.07708740234375,
-0.02587890625,
-0.049224853515625,
-0.00850677490234375,
-0.04705810546875,
-0.008575439453125,
0.022735595703125,
0.0287322998046875,
-0.0094757080078125,
0.0218505859375,
-0.04437255859375,
0.0258331298828125,
0.022735595703125,
-0.02685546875,
0.0129547119140625,
0.01523590087890625,
-0.0309906005859375,
-0.01528167724609375,
-0.0582275390625,
-0.055816650390625,
0.08721923828125,
0.034210205078125,
0.038055419921875,
-0.007640838623046875,
0.08160400390625,
0.00801849365234375,
0.019500732421875,
-0.041351318359375,
0.040008544921875,
-0.007602691650390625,
-0.02996826171875,
-0.039031982421875,
-0.0268402099609375,
-0.0953369140625,
0.030670166015625,
-0.0235748291015625,
-0.06884765625,
-0.006427764892578125,
0.01348114013671875,
-0.046844482421875,
0.023773193359375,
-0.0478515625,
0.0753173828125,
-0.0165863037109375,
0.00951385498046875,
-0.007312774658203125,
-0.0401611328125,
0.025360107421875,
-0.0305633544921875,
-0.00405120849609375,
0.00226593017578125,
0.020172119140625,
0.06329345703125,
-0.0244293212890625,
0.050323486328125,
-0.0276947021484375,
-0.0036716461181640625,
0.030303955078125,
-0.01123046875,
0.00815582275390625,
0.01403045654296875,
0.0081939697265625,
0.01611328125,
0.005321502685546875,
-0.0071868896484375,
-0.05389404296875,
0.034515380859375,
-0.0509033203125,
-0.0309295654296875,
-0.0223541259765625,
-0.032684326171875,
-0.0172882080078125,
0.0134124755859375,
0.044647216796875,
0.03607177734375,
-0.050933837890625,
0.02984619140625,
0.030487060546875,
-0.04498291015625,
0.04534912109375,
0.0218505859375,
-0.040985107421875,
-0.045013427734375,
0.061248779296875,
-0.0170745849609375,
0.0150146484375,
0.01203155517578125,
0.0190887451171875,
-0.0286407470703125,
-0.024383544921875,
-0.046356201171875,
-0.013641357421875,
-0.039276123046875,
-0.01678466796875,
-0.058258056640625,
-0.0416259765625,
-0.017486572265625,
-0.0007715225219726562,
-0.038543701171875,
-0.03436279296875,
-0.01412200927734375,
0.000016987323760986328,
0.00450897216796875,
0.07421875,
-0.0192413330078125,
0.031524658203125,
-0.08001708984375,
0.009674072265625,
0.0282135009765625,
0.016204833984375,
-0.0153350830078125,
-0.048583984375,
-0.0205535888671875,
0.007965087890625,
-0.052703857421875,
-0.03961181640625,
0.032684326171875,
0.022369384765625,
0.04901123046875,
0.03228759765625,
-0.0021800994873046875,
0.03680419921875,
-0.0321044921875,
0.06964111328125,
0.0440673828125,
-0.07244873046875,
0.05157470703125,
-0.004970550537109375,
0.03729248046875,
0.05450439453125,
0.011138916015625,
-0.0181121826171875,
-0.025543212890625,
-0.07611083984375,
-0.06103515625,
0.039031982421875,
0.020751953125,
0.01450347900390625,
0.00909423828125,
0.0103302001953125,
0.00994110107421875,
0.029998779296875,
-0.043670654296875,
-0.00921630859375,
-0.027984619140625,
-0.012481689453125,
-0.0056610107421875,
-0.029083251953125,
-0.01406097412109375,
-0.01222991943359375,
0.0291290283203125,
-0.016998291015625,
0.0435791015625,
0.002841949462890625,
0.0006961822509765625,
-0.0141143798828125,
0.0452880859375,
0.049224853515625,
0.053863525390625,
-0.0202789306640625,
-0.007549285888671875,
0.023590087890625,
-0.032135009765625,
0.0108795166015625,
0.01384735107421875,
-0.0094757080078125,
0.00975799560546875,
0.03790283203125,
0.0703125,
0.00018799304962158203,
-0.03363037109375,
0.048736572265625,
-0.03131103515625,
-0.048126220703125,
-0.04022216796875,
-0.00726318359375,
-0.02227783203125,
0.017059326171875,
0.00457763671875,
0.023956298828125,
0.01105499267578125,
-0.029296875,
0.023956298828125,
0.0169525146484375,
-0.040008544921875,
-0.038848876953125,
0.04718017578125,
0.049591064453125,
-0.0302734375,
0.052703857421875,
-0.030303955078125,
-0.048004150390625,
0.033782958984375,
0.04022216796875,
0.094970703125,
-0.02630615234375,
0.0298309326171875,
0.04278564453125,
0.015625,
0.0273895263671875,
0.029449462890625,
0.0007300376892089844,
-0.0650634765625,
-0.033477783203125,
-0.0640869140625,
-0.0084228515625,
0.034423828125,
-0.061767578125,
-0.0049896240234375,
-0.03173828125,
-0.0162200927734375,
0.004974365234375,
0.0051422119140625,
-0.06573486328125,
0.0184326171875,
0.004917144775390625,
0.0509033203125,
-0.06256103515625,
0.048309326171875,
0.059112548828125,
-0.031158447265625,
-0.0521240234375,
0.022491455078125,
0.0024890899658203125,
-0.035858154296875,
0.0594482421875,
0.020965576171875,
-0.006988525390625,
0.0002884864807128906,
-0.0267791748046875,
-0.0430908203125,
0.0792236328125,
0.0202484130859375,
-0.0355224609375,
0.0046234130859375,
0.00740814208984375,
0.060638427734375,
-0.049346923828125,
0.048614501953125,
0.049591064453125,
0.044158935546875,
-0.0138702392578125,
-0.09271240234375,
-0.0204010009765625,
-0.034088134765625,
0.006282806396484375,
0.007671356201171875,
-0.05364990234375,
0.046356201171875,
-0.0168914794921875,
-0.00933837890625,
0.020477294921875,
0.04693603515625,
0.0184326171875,
0.03363037109375,
0.04107666015625,
0.06591796875,
0.04974365234375,
-0.0241851806640625,
0.06951904296875,
-0.0280609130859375,
0.030670166015625,
0.09912109375,
-0.004718780517578125,
0.051055908203125,
0.0215911865234375,
-0.0159149169921875,
0.0401611328125,
0.040985107421875,
0.00762176513671875,
0.02667236328125,
0.01096343994140625,
-0.01116180419921875,
-0.0162506103515625,
-0.01239013671875,
-0.0258941650390625,
0.0716552734375,
0.01369476318359375,
-0.022491455078125,
-0.03277587890625,
-0.00217437744140625,
-0.0157623291015625,
0.012939453125,
-0.006977081298828125,
0.06976318359375,
0.00246429443359375,
-0.052734375,
0.044342041015625,
-0.007110595703125,
0.0294036865234375,
-0.038238525390625,
-0.0217132568359375,
0.0008449554443359375,
0.0104522705078125,
-0.01995849609375,
-0.059814453125,
0.0193023681640625,
-0.00038313865661621094,
0.01317596435546875,
-0.0269622802734375,
0.053375244140625,
-0.036468505859375,
-0.0255279541015625,
0.034576416015625,
0.0426025390625,
0.025604248046875,
0.003833770751953125,
-0.0819091796875,
-0.01491546630859375,
0.019989013671875,
-0.032928466796875,
0.0252685546875,
0.045379638671875,
0.0178070068359375,
0.0280609130859375,
0.051116943359375,
-0.00461578369140625,
0.00394439697265625,
0.04095458984375,
0.053375244140625,
-0.0304718017578125,
-0.022247314453125,
-0.0457763671875,
0.05908203125,
-0.0107421875,
-0.05450439453125,
0.055328369140625,
0.043914794921875,
0.07806396484375,
-0.00693511962890625,
0.0673828125,
-0.0012884140014648438,
0.032012939453125,
-0.048370361328125,
0.048553466796875,
-0.0469970703125,
0.0066070556640625,
-0.036865234375,
-0.095947265625,
-0.00749969482421875,
0.049774169921875,
-0.00209808349609375,
0.0304718017578125,
0.0672607421875,
0.040740966796875,
0.016448974609375,
0.00760650634765625,
0.052337646484375,
0.00042319297790527344,
0.0216217041015625,
0.0289154052734375,
0.080810546875,
-0.03851318359375,
0.034088134765625,
-0.00720977783203125,
-0.0043487548828125,
0.00014650821685791016,
-0.061065673828125,
-0.09161376953125,
-0.050628662109375,
-0.011322021484375,
-0.030029296875,
-0.0248870849609375,
0.08074951171875,
0.0386962890625,
-0.046600341796875,
-0.0085296630859375,
-0.0213775634765625,
-0.019317626953125,
0.01474761962890625,
-0.0150604248046875,
0.0171966552734375,
-0.0312347412109375,
-0.063720703125,
0.028533935546875,
0.0271148681640625,
0.003482818603515625,
-0.043701171875,
-0.023101806640625,
-0.00478363037109375,
0.004058837890625,
0.050933837890625,
0.00693511962890625,
-0.058624267578125,
-0.0240325927734375,
-0.0362548828125,
0.0179901123046875,
0.003963470458984375,
0.0738525390625,
-0.049530029296875,
0.05596923828125,
0.0428466796875,
0.041229248046875,
0.0243682861328125,
0.00567626953125,
0.057830810546875,
-0.0689697265625,
0.0197906494140625,
0.01629638671875,
0.0203704833984375,
0.0140838623046875,
-0.02099609375,
0.038787841796875,
-0.0014667510986328125,
-0.06243896484375,
-0.058929443359375,
0.0257720947265625,
-0.051361083984375,
-0.002033233642578125,
0.06781005859375,
-0.023529052734375,
0.006587982177734375,
-0.01136016845703125,
-0.0164794921875,
0.0263671875,
-0.0335693359375,
0.04669189453125,
0.044708251953125,
-0.00998687744140625,
-0.0265655517578125,
-0.04443359375,
0.058929443359375,
0.0443115234375,
-0.088623046875,
-0.00579833984375,
0.0216827392578125,
-0.00493621826171875,
0.037872314453125,
0.04254150390625,
-0.0082244873046875,
0.017669677734375,
0.01541900634765625,
0.036224365234375,
-0.0101470947265625,
-0.0460205078125,
-0.037109375,
-0.0028553009033203125,
0.0035533905029296875,
0.0007677078247070312
]
] |
timm/inception_v3.tv_in1k | 2023-04-25T21:29:59.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1512.00567",
"license:apache-2.0",
"has_space",
"region:us"
] | image-classification | timm | null | null | timm/inception_v3.tv_in1k | 1 | 39,898 | timm | 2023-04-25T21:29:39 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for inception_v3.tv_in1k
A Inception-v3 image classification model. Trained on ImageNet-1k, torchvision weights.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 23.8
- GMACs: 5.7
- Activations (M): 9.0
- Image size: 299 x 299
- **Papers:**
- Rethinking the Inception Architecture for Computer Vision: https://arxiv.org/abs/1512.00567
- **Original:** https://github.com/pytorch/vision
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('inception_v3.tv_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'inception_v3.tv_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 147, 147])
# torch.Size([1, 192, 71, 71])
# torch.Size([1, 288, 35, 35])
# torch.Size([1, 768, 17, 17])
# torch.Size([1, 2048, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'inception_v3.tv_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{DBLP:journals/corr/SzegedyVISW15,
author = {Christian Szegedy and
Vincent Vanhoucke and
Sergey Ioffe and
Jonathon Shlens and
Zbigniew Wojna},
title = {Rethinking the Inception Architecture for Computer Vision},
journal = {CoRR},
volume = {abs/1512.00567},
year = {2015},
url = {http://arxiv.org/abs/1512.00567},
archivePrefix = {arXiv},
eprint = {1512.00567},
timestamp = {Mon, 13 Aug 2018 16:49:07 +0200},
biburl = {https://dblp.org/rec/journals/corr/SzegedyVISW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
| 4,059 | [
[
-0.0411376953125,
-0.042236328125,
0.00855255126953125,
0.00861358642578125,
-0.0300140380859375,
-0.01983642578125,
-0.010650634765625,
-0.037841796875,
0.007183074951171875,
0.021881103515625,
-0.0286712646484375,
-0.0579833984375,
-0.04931640625,
-0.01043701171875,
-0.0222930908203125,
0.068359375,
-0.0015230178833007812,
-0.004543304443359375,
-0.019378662109375,
-0.02850341796875,
-0.0052642822265625,
-0.0117034912109375,
-0.06585693359375,
-0.03143310546875,
0.0184783935546875,
0.01177978515625,
0.042327880859375,
0.04931640625,
0.045654296875,
0.031829833984375,
-0.0135498046875,
-0.0006613731384277344,
-0.0164642333984375,
-0.026611328125,
0.02899169921875,
-0.040985107421875,
-0.0298919677734375,
0.0143890380859375,
0.056060791015625,
0.0401611328125,
0.0007534027099609375,
0.030364990234375,
0.0233154296875,
0.035736083984375,
-0.0177001953125,
0.0036945343017578125,
-0.03192138671875,
0.0237274169921875,
-0.005626678466796875,
0.0066680908203125,
-0.01433563232421875,
-0.027069091796875,
0.0229034423828125,
-0.037445068359375,
0.044921875,
0.003398895263671875,
0.0968017578125,
0.01482391357421875,
0.0187225341796875,
-0.000293731689453125,
-0.0295867919921875,
0.056732177734375,
-0.054351806640625,
0.023193359375,
0.009063720703125,
0.00655364990234375,
-0.002532958984375,
-0.0765380859375,
-0.04681396484375,
-0.00957489013671875,
-0.001293182373046875,
-0.0078887939453125,
-0.01262664794921875,
-0.0006785392761230469,
0.01373291015625,
0.039459228515625,
-0.0316162109375,
0.00847625732421875,
-0.049224853515625,
-0.014495849609375,
0.039154052734375,
-0.00707244873046875,
0.0187225341796875,
-0.01904296875,
-0.042816162109375,
-0.035430908203125,
-0.0297393798828125,
0.0193328857421875,
0.0213623046875,
0.010284423828125,
-0.049896240234375,
0.03265380859375,
0.0113983154296875,
0.04498291015625,
0.00942230224609375,
-0.023590087890625,
0.046142578125,
0.00310516357421875,
-0.032989501953125,
0.003063201904296875,
0.072265625,
0.032073974609375,
0.01220703125,
0.0037441253662109375,
0.006069183349609375,
-0.0283050537109375,
0.0021991729736328125,
-0.0784912109375,
-0.0159912109375,
0.03485107421875,
-0.03875732421875,
-0.0296173095703125,
0.0183258056640625,
-0.04412841796875,
-0.01093292236328125,
0.00009250640869140625,
0.051513671875,
-0.05120849609375,
-0.0283355712890625,
0.00649261474609375,
-0.013427734375,
0.0443115234375,
0.0159759521484375,
-0.03564453125,
-0.0024013519287109375,
0.0252532958984375,
0.09033203125,
0.00437164306640625,
-0.0372314453125,
0.006122589111328125,
-0.016998291015625,
-0.0280303955078125,
0.0382080078125,
0.004932403564453125,
-0.0166778564453125,
-0.022216796875,
0.01270294189453125,
0.00263214111328125,
-0.048187255859375,
0.01953125,
-0.0118255615234375,
0.0181884765625,
0.00815582275390625,
-0.015655517578125,
-0.041839599609375,
0.026397705078125,
-0.026885986328125,
0.089599609375,
0.0265350341796875,
-0.056121826171875,
0.041717529296875,
-0.03363037109375,
-0.00991058349609375,
-0.014678955078125,
-0.01971435546875,
-0.084716796875,
-0.003299713134765625,
0.0229949951171875,
0.042572021484375,
-0.021820068359375,
0.00641632080078125,
-0.044921875,
-0.017822265625,
0.01480865478515625,
-0.0031585693359375,
0.082763671875,
0.0160369873046875,
-0.035400390625,
0.010589599609375,
-0.052337646484375,
0.00922393798828125,
0.03411865234375,
-0.0187225341796875,
0.002079010009765625,
-0.036865234375,
-0.0008654594421386719,
0.01224517822265625,
0.01195526123046875,
-0.045654296875,
0.01422119140625,
-0.02899169921875,
0.03424072265625,
0.045654296875,
-0.0033931732177734375,
0.0194091796875,
-0.0253143310546875,
0.01103973388671875,
0.036773681640625,
0.02484130859375,
-0.00127410888671875,
-0.048492431640625,
-0.06402587890625,
-0.033538818359375,
0.01480865478515625,
0.0261688232421875,
-0.02471923828125,
0.0382080078125,
-0.022552490234375,
-0.053863525390625,
-0.043792724609375,
0.004364013671875,
0.0272674560546875,
0.04144287109375,
0.0249786376953125,
-0.043548583984375,
-0.04638671875,
-0.07415771484375,
0.00695037841796875,
0.00046944618225097656,
-0.0014123916625976562,
0.019500732421875,
0.04681396484375,
0.0000896453857421875,
0.06671142578125,
-0.03448486328125,
-0.02325439453125,
-0.017547607421875,
0.009918212890625,
0.035491943359375,
0.069580078125,
0.055206298828125,
-0.045379638671875,
-0.02508544921875,
-0.0134429931640625,
-0.08367919921875,
0.0279083251953125,
-0.0008368492126464844,
-0.00997161865234375,
0.0189208984375,
0.0179290771484375,
-0.04437255859375,
0.0546875,
0.00046181678771972656,
-0.015777587890625,
0.028778076171875,
-0.016998291015625,
0.0158843994140625,
-0.08831787109375,
0.0070648193359375,
0.0183868408203125,
0.0013875961303710938,
-0.02276611328125,
0.0029277801513671875,
-0.01100921630859375,
-0.011993408203125,
-0.04931640625,
0.037841796875,
-0.04541015625,
-0.0254669189453125,
-0.0011377334594726562,
-0.01500701904296875,
0.004802703857421875,
0.055816650390625,
-0.004894256591796875,
0.03338623046875,
0.07171630859375,
-0.04754638671875,
0.027496337890625,
0.035980224609375,
-0.0347900390625,
0.041473388671875,
-0.051727294921875,
0.018798828125,
-0.0159149169921875,
0.0092620849609375,
-0.072998046875,
-0.01129913330078125,
0.0284271240234375,
-0.0518798828125,
0.035491943359375,
-0.037811279296875,
-0.0243682861328125,
-0.036468505859375,
-0.043212890625,
0.03399658203125,
0.053375244140625,
-0.0455322265625,
0.0416259765625,
0.011810302734375,
0.0219268798828125,
-0.04791259765625,
-0.07049560546875,
-0.00550079345703125,
-0.03216552734375,
-0.05438232421875,
0.0421142578125,
0.01006317138671875,
0.004375457763671875,
0.0185394287109375,
-0.0024871826171875,
0.0034694671630859375,
-0.0110626220703125,
0.0389404296875,
0.026397705078125,
-0.0312347412109375,
-0.02056884765625,
-0.0249481201171875,
0.006938934326171875,
-0.00490570068359375,
-0.0323486328125,
0.04949951171875,
-0.0176849365234375,
-0.011932373046875,
-0.06402587890625,
-0.00783538818359375,
0.03656005859375,
-0.0023517608642578125,
0.06671142578125,
0.083251953125,
-0.044647216796875,
0.00021445751190185547,
-0.0360107421875,
-0.01165771484375,
-0.035064697265625,
0.0362548828125,
-0.036041259765625,
-0.0291748046875,
0.0654296875,
0.0103302001953125,
0.01140594482421875,
0.05877685546875,
0.031768798828125,
-0.00846099853515625,
0.0477294921875,
0.046844482421875,
0.01361846923828125,
0.051544189453125,
-0.08953857421875,
-0.007564544677734375,
-0.07550048828125,
-0.043243408203125,
-0.024658203125,
-0.039276123046875,
-0.035797119140625,
-0.0242462158203125,
0.0411376953125,
0.02984619140625,
-0.029083251953125,
0.031768798828125,
-0.062164306640625,
0.00539398193359375,
0.0526123046875,
0.04315185546875,
-0.015838623046875,
0.0273590087890625,
-0.0211181640625,
0.011810302734375,
-0.056060791015625,
-0.0198211669921875,
0.08966064453125,
0.026885986328125,
0.0445556640625,
-0.01412200927734375,
0.053802490234375,
-0.00946044921875,
0.018798828125,
-0.040283203125,
0.044036865234375,
0.00299072265625,
-0.036346435546875,
-0.01235198974609375,
-0.017303466796875,
-0.08209228515625,
0.005046844482421875,
-0.0191497802734375,
-0.061676025390625,
0.02850341796875,
0.0106048583984375,
-0.036346435546875,
0.05877685546875,
-0.055511474609375,
0.06646728515625,
-0.004901885986328125,
-0.0364990234375,
-0.0025577545166015625,
-0.042327880859375,
0.021514892578125,
0.0214691162109375,
-0.0142822265625,
-0.0032596588134765625,
0.0185089111328125,
0.0784912109375,
-0.03778076171875,
0.068359375,
-0.03143310546875,
0.0174560546875,
0.0511474609375,
-0.00971221923828125,
0.009033203125,
0.0031490325927734375,
-0.003276824951171875,
0.038665771484375,
-0.0008358955383300781,
-0.0302581787109375,
-0.035064697265625,
0.045135498046875,
-0.084228515625,
-0.036773681640625,
-0.03179931640625,
-0.0299224853515625,
0.0191192626953125,
0.01213836669921875,
0.0472412109375,
0.059478759765625,
0.0063629150390625,
0.0280303955078125,
0.03643798828125,
-0.03497314453125,
0.038360595703125,
-0.00959014892578125,
-0.016510009765625,
-0.045166015625,
0.051605224609375,
0.016632080078125,
0.0079498291015625,
0.00689697265625,
0.0083465576171875,
-0.0274658203125,
-0.0606689453125,
-0.032318115234375,
0.0185394287109375,
-0.0517578125,
-0.035003662109375,
-0.043060302734375,
-0.043853759765625,
-0.045013427734375,
-0.00994110107421875,
-0.0303192138671875,
-0.0233154296875,
-0.031524658203125,
0.01265716552734375,
0.0479736328125,
0.040252685546875,
-0.0156707763671875,
0.041717529296875,
-0.03326416015625,
0.01061248779296875,
0.005664825439453125,
0.040924072265625,
-0.0002465248107910156,
-0.06512451171875,
-0.02520751953125,
-0.00966644287109375,
-0.0439453125,
-0.04296875,
0.0251617431640625,
0.0214691162109375,
0.0352783203125,
0.03759765625,
-0.0261383056640625,
0.065185546875,
-0.006114959716796875,
0.05010986328125,
0.01739501953125,
-0.042877197265625,
0.0491943359375,
0.00351715087890625,
0.012298583984375,
0.0102691650390625,
0.0207672119140625,
-0.01058197021484375,
-0.00835418701171875,
-0.07830810546875,
-0.06280517578125,
0.070556640625,
0.013519287109375,
-0.0039520263671875,
0.0262451171875,
0.0587158203125,
0.0045013427734375,
0.005290985107421875,
-0.05755615234375,
-0.024658203125,
-0.0289459228515625,
-0.0275421142578125,
-0.0006809234619140625,
-0.00411224365234375,
-0.006862640380859375,
-0.0489501953125,
0.045013427734375,
0.01084136962890625,
0.06280517578125,
0.044525146484375,
-0.01456451416015625,
-0.006328582763671875,
-0.033172607421875,
0.0291290283203125,
0.03228759765625,
-0.036163330078125,
0.0053253173828125,
0.013519287109375,
-0.0465087890625,
0.003978729248046875,
0.007781982421875,
-0.00975799560546875,
-0.01064300537109375,
0.040374755859375,
0.0731201171875,
0.001132965087890625,
0.00609588623046875,
0.022552490234375,
0.01337432861328125,
-0.0255889892578125,
-0.03277587890625,
0.01369476318359375,
-0.01303863525390625,
0.031982421875,
0.03729248046875,
0.025146484375,
-0.00841522216796875,
-0.0253143310546875,
0.023284912109375,
0.043670654296875,
-0.01336669921875,
-0.0301513671875,
0.055908203125,
-0.0163116455078125,
-0.0193939208984375,
0.06573486328125,
-0.001987457275390625,
-0.026275634765625,
0.07415771484375,
0.032501220703125,
0.073974609375,
-0.00007414817810058594,
-0.00140380859375,
0.06732177734375,
0.02471923828125,
0.00412750244140625,
0.0035457611083984375,
0.005588531494140625,
-0.06573486328125,
0.00432586669921875,
-0.05755615234375,
0.003387451171875,
0.03369140625,
-0.0340576171875,
0.03155517578125,
-0.06634521484375,
-0.02435302734375,
0.01129913330078125,
0.01513671875,
-0.0714111328125,
0.0190277099609375,
0.007709503173828125,
0.0606689453125,
-0.046173095703125,
0.0494384765625,
0.05419921875,
-0.059234619140625,
-0.0628662109375,
-0.0142822265625,
-0.00372314453125,
-0.0809326171875,
0.033782958984375,
0.0352783203125,
-0.00243377685546875,
0.0254364013671875,
-0.065185546875,
-0.0570068359375,
0.10748291015625,
0.039886474609375,
0.00212860107421875,
0.006694793701171875,
0.003986358642578125,
0.01084136962890625,
-0.037811279296875,
0.0268707275390625,
0.0186004638671875,
0.019775390625,
0.0246734619140625,
-0.0357666015625,
0.004314422607421875,
-0.010528564453125,
0.013275146484375,
0.005519866943359375,
-0.049591064453125,
0.06671142578125,
-0.044464111328125,
-0.0191497802734375,
0.004978179931640625,
0.06195068359375,
0.01739501953125,
0.011810302734375,
0.04541015625,
0.07568359375,
0.0241546630859375,
-0.019744873046875,
0.06414794921875,
-0.008270263671875,
0.044921875,
0.038421630859375,
0.0258941650390625,
0.03802490234375,
0.033294677734375,
-0.0303192138671875,
0.03973388671875,
0.08270263671875,
-0.0303955078125,
0.02105712890625,
0.01091766357421875,
0.00702667236328125,
0.001068115234375,
0.013397216796875,
-0.03143310546875,
0.042938232421875,
0.01397705078125,
-0.031982421875,
-0.0177764892578125,
0.01039886474609375,
-0.001934051513671875,
-0.033111572265625,
-0.01433563232421875,
0.0390625,
0.0011138916015625,
-0.02923583984375,
0.066162109375,
0.003955841064453125,
0.058868408203125,
-0.02813720703125,
0.0024127960205078125,
-0.021514892578125,
0.017791748046875,
-0.02740478515625,
-0.06103515625,
0.0241851806640625,
-0.0191192626953125,
0.004314422607421875,
0.01380157470703125,
0.03106689453125,
-0.02099609375,
-0.046630859375,
0.007373809814453125,
0.0182037353515625,
0.042236328125,
0.00392913818359375,
-0.083984375,
0.015472412109375,
0.0006690025329589844,
-0.0394287109375,
0.0084228515625,
0.024322509765625,
0.0068511962890625,
0.04937744140625,
0.0445556640625,
-0.00405120849609375,
0.0144195556640625,
-0.017425537109375,
0.052215576171875,
-0.04693603515625,
-0.0289459228515625,
-0.06951904296875,
0.049591064453125,
-0.00789642333984375,
-0.04681396484375,
0.03558349609375,
0.056060791015625,
0.073974609375,
-0.003448486328125,
0.0311737060546875,
-0.03497314453125,
-0.00559234619140625,
-0.034515380859375,
0.046234130859375,
-0.051422119140625,
-0.000606536865234375,
-0.014495849609375,
-0.06475830078125,
-0.030364990234375,
0.05078125,
-0.01546478271484375,
0.03277587890625,
0.03887939453125,
0.07147216796875,
-0.0265655517578125,
-0.0289459228515625,
0.00600433349609375,
0.0210113525390625,
0.011444091796875,
0.030059814453125,
0.0296173095703125,
-0.058349609375,
0.03399658203125,
-0.042633056640625,
-0.01392364501953125,
-0.011810302734375,
-0.04840087890625,
-0.0545654296875,
-0.0712890625,
-0.049530029296875,
-0.04803466796875,
-0.0189208984375,
0.0660400390625,
0.073974609375,
-0.050567626953125,
-0.01387786865234375,
-0.00308990478515625,
0.0111083984375,
-0.0280609130859375,
-0.0164337158203125,
0.054718017578125,
-0.0125732421875,
-0.06072998046875,
-0.0186004638671875,
0.00783538818359375,
0.03564453125,
-0.01513671875,
-0.005615234375,
-0.01849365234375,
-0.0240936279296875,
0.017578125,
0.0205078125,
-0.054931640625,
-0.027099609375,
-0.0265655517578125,
0.0030269622802734375,
0.045196533203125,
0.033111572265625,
-0.052276611328125,
0.0183258056640625,
0.02227783203125,
0.02508544921875,
0.06378173828125,
-0.0209197998046875,
0.007110595703125,
-0.055999755859375,
0.047637939453125,
-0.0083770751953125,
0.02923583984375,
0.038360595703125,
-0.0301971435546875,
0.035003662109375,
0.037353515625,
-0.019775390625,
-0.0714111328125,
-0.00580596923828125,
-0.079345703125,
-0.005725860595703125,
0.049530029296875,
-0.0178375244140625,
-0.04705810546875,
0.027008056640625,
-0.00016415119171142578,
0.057861328125,
-0.0005846023559570312,
0.050537109375,
0.021484375,
-0.011932373046875,
-0.04693603515625,
-0.03057861328125,
0.03857421875,
0.006500244140625,
-0.040252685546875,
-0.03948974609375,
-0.0035533905029296875,
0.05499267578125,
0.0252532958984375,
0.036651611328125,
-0.026580810546875,
0.0033168792724609375,
0.01000213623046875,
0.0477294921875,
-0.0293426513671875,
-0.0186767578125,
-0.0260162353515625,
0.0110626220703125,
0.0009813308715820312,
-0.05126953125
]
] |
huggingface/CodeBERTa-language-id | 2022-09-09T16:42:28.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"roberta",
"text-classification",
"code",
"dataset:code_search_net",
"arxiv:1909.09436",
"endpoints_compatible",
"region:us"
] | text-classification | huggingface | null | null | huggingface/CodeBERTa-language-id | 26 | 39,876 | transformers | 2022-03-02T23:29:05 | ---
language: code
thumbnail: https://cdn-media.huggingface.co/CodeBERTa/CodeBERTa.png
datasets:
- code_search_net
---
# CodeBERTa-language-id: The World’s fanciest programming language identification algo 🤯
To demonstrate the usefulness of our CodeBERTa pretrained model on downstream tasks beyond language modeling, we fine-tune the [`CodeBERTa-small-v1`](https://huggingface.co/huggingface/CodeBERTa-small-v1) checkpoint on the task of classifying a sample of code into the programming language it's written in (*programming language identification*).
We add a sequence classification head on top of the model.
On the evaluation dataset, we attain an eval accuracy and F1 > 0.999 which is not surprising given that the task of language identification is relatively easy (see an intuition why, below).
## Quick start: using the raw model
```python
CODEBERTA_LANGUAGE_ID = "huggingface/CodeBERTa-language-id"
tokenizer = RobertaTokenizer.from_pretrained(CODEBERTA_LANGUAGE_ID)
model = RobertaForSequenceClassification.from_pretrained(CODEBERTA_LANGUAGE_ID)
input_ids = tokenizer.encode(CODE_TO_IDENTIFY)
logits = model(input_ids)[0]
language_idx = logits.argmax() # index for the resulting label
```
## Quick start: using Pipelines 💪
```python
from transformers import TextClassificationPipeline
pipeline = TextClassificationPipeline(
model=RobertaForSequenceClassification.from_pretrained(CODEBERTA_LANGUAGE_ID),
tokenizer=RobertaTokenizer.from_pretrained(CODEBERTA_LANGUAGE_ID)
)
pipeline(CODE_TO_IDENTIFY)
```
Let's start with something very easy:
```python
pipeline("""
def f(x):
return x**2
""")
# [{'label': 'python', 'score': 0.9999965}]
```
Now let's probe shorter code samples:
```python
pipeline("const foo = 'bar'")
# [{'label': 'javascript', 'score': 0.9977546}]
```
What if I remove the `const` token from the assignment?
```python
pipeline("foo = 'bar'")
# [{'label': 'javascript', 'score': 0.7176245}]
```
For some reason, this is still statistically detected as JS code, even though it's also valid Python code. However, if we slightly tweak it:
```python
pipeline("foo = u'bar'")
# [{'label': 'python', 'score': 0.7638422}]
```
This is now detected as Python (Notice the `u` string modifier).
Okay, enough with the JS and Python domination already! Let's try fancier languages:
```python
pipeline("echo $FOO")
# [{'label': 'php', 'score': 0.9995257}]
```
(Yes, I used the word "fancy" to describe PHP 😅)
```python
pipeline("outcome := rand.Intn(6) + 1")
# [{'label': 'go', 'score': 0.9936151}]
```
Why is the problem of language identification so easy (with the correct toolkit)? Because code's syntax is rigid, and simple tokens such as `:=` (the assignment operator in Go) are perfect predictors of the underlying language:
```python
pipeline(":=")
# [{'label': 'go', 'score': 0.9998052}]
```
By the way, because we trained our own custom tokenizer on the [CodeSearchNet](https://github.blog/2019-09-26-introducing-the-codesearchnet-challenge/) dataset, and it handles streams of bytes in a very generic way, syntactic constructs such `:=` are represented by a single token:
```python
self.tokenizer.encode(" :=", add_special_tokens=False)
# [521]
```
<br>
## Fine-tuning code
<details>
```python
import gzip
import json
import logging
import os
from pathlib import Path
from typing import Dict, List, Tuple
import numpy as np
import torch
from sklearn.metrics import f1_score
from tokenizers.implementations.byte_level_bpe import ByteLevelBPETokenizer
from tokenizers.processors import BertProcessing
from torch.nn.utils.rnn import pad_sequence
from torch.utils.data import DataLoader, Dataset
from torch.utils.data.dataset import Dataset
from torch.utils.tensorboard.writer import SummaryWriter
from tqdm import tqdm, trange
from transformers import RobertaForSequenceClassification
from transformers.data.metrics import acc_and_f1, simple_accuracy
logging.basicConfig(level=logging.INFO)
CODEBERTA_PRETRAINED = "huggingface/CodeBERTa-small-v1"
LANGUAGES = [
"go",
"java",
"javascript",
"php",
"python",
"ruby",
]
FILES_PER_LANGUAGE = 1
EVALUATE = True
# Set up tokenizer
tokenizer = ByteLevelBPETokenizer("./pretrained/vocab.json", "./pretrained/merges.txt",)
tokenizer._tokenizer.post_processor = BertProcessing(
("</s>", tokenizer.token_to_id("</s>")), ("<s>", tokenizer.token_to_id("<s>")),
)
tokenizer.enable_truncation(max_length=512)
# Set up Tensorboard
tb_writer = SummaryWriter()
class CodeSearchNetDataset(Dataset):
examples: List[Tuple[List[int], int]]
def __init__(self, split: str = "train"):
"""
train | valid | test
"""
self.examples = []
src_files = []
for language in LANGUAGES:
src_files += list(
Path("../CodeSearchNet/resources/data/").glob(f"{language}/final/jsonl/{split}/*.jsonl.gz")
)[:FILES_PER_LANGUAGE]
for src_file in src_files:
label = src_file.parents[3].name
label_idx = LANGUAGES.index(label)
print("🔥", src_file, label)
lines = []
fh = gzip.open(src_file, mode="rt", encoding="utf-8")
for line in fh:
o = json.loads(line)
lines.append(o["code"])
examples = [(x.ids, label_idx) for x in tokenizer.encode_batch(lines)]
self.examples += examples
print("🔥🔥")
def __len__(self):
return len(self.examples)
def __getitem__(self, i):
# We’ll pad at the batch level.
return self.examples[i]
model = RobertaForSequenceClassification.from_pretrained(CODEBERTA_PRETRAINED, num_labels=len(LANGUAGES))
train_dataset = CodeSearchNetDataset(split="train")
eval_dataset = CodeSearchNetDataset(split="test")
def collate(examples):
input_ids = pad_sequence([torch.tensor(x[0]) for x in examples], batch_first=True, padding_value=1)
labels = torch.tensor([x[1] for x in examples])
# ^^ uncessary .unsqueeze(-1)
return input_ids, labels
train_dataloader = DataLoader(train_dataset, batch_size=256, shuffle=True, collate_fn=collate)
batch = next(iter(train_dataloader))
model.to("cuda")
model.train()
for param in model.roberta.parameters():
param.requires_grad = False
## ^^ Only train final layer.
print(f"num params:", model.num_parameters())
print(f"num trainable params:", model.num_parameters(only_trainable=True))
def evaluate():
eval_loss = 0.0
nb_eval_steps = 0
preds = np.empty((0), dtype=np.int64)
out_label_ids = np.empty((0), dtype=np.int64)
model.eval()
eval_dataloader = DataLoader(eval_dataset, batch_size=512, collate_fn=collate)
for step, (input_ids, labels) in enumerate(tqdm(eval_dataloader, desc="Eval")):
with torch.no_grad():
outputs = model(input_ids=input_ids.to("cuda"), labels=labels.to("cuda"))
loss = outputs[0]
logits = outputs[1]
eval_loss += loss.mean().item()
nb_eval_steps += 1
preds = np.append(preds, logits.argmax(dim=1).detach().cpu().numpy(), axis=0)
out_label_ids = np.append(out_label_ids, labels.detach().cpu().numpy(), axis=0)
eval_loss = eval_loss / nb_eval_steps
acc = simple_accuracy(preds, out_label_ids)
f1 = f1_score(y_true=out_label_ids, y_pred=preds, average="macro")
print("=== Eval: loss ===", eval_loss)
print("=== Eval: acc. ===", acc)
print("=== Eval: f1 ===", f1)
# print(acc_and_f1(preds, out_label_ids))
tb_writer.add_scalars("eval", {"loss": eval_loss, "acc": acc, "f1": f1}, global_step)
### Training loop
global_step = 0
train_iterator = trange(0, 4, desc="Epoch")
optimizer = torch.optim.AdamW(model.parameters())
for _ in train_iterator:
epoch_iterator = tqdm(train_dataloader, desc="Iteration")
for step, (input_ids, labels) in enumerate(epoch_iterator):
optimizer.zero_grad()
outputs = model(input_ids=input_ids.to("cuda"), labels=labels.to("cuda"))
loss = outputs[0]
loss.backward()
tb_writer.add_scalar("training_loss", loss.item(), global_step)
optimizer.step()
global_step += 1
if EVALUATE and global_step % 50 == 0:
evaluate()
model.train()
evaluate()
os.makedirs("./models/CodeBERT-language-id", exist_ok=True)
model.save_pretrained("./models/CodeBERT-language-id")
```
</details>
<br>
## CodeSearchNet citation
<details>
```bibtex
@article{husain_codesearchnet_2019,
title = {{CodeSearchNet} {Challenge}: {Evaluating} the {State} of {Semantic} {Code} {Search}},
shorttitle = {{CodeSearchNet} {Challenge}},
url = {http://arxiv.org/abs/1909.09436},
urldate = {2020-03-12},
journal = {arXiv:1909.09436 [cs, stat]},
author = {Husain, Hamel and Wu, Ho-Hsiang and Gazit, Tiferet and Allamanis, Miltiadis and Brockschmidt, Marc},
month = sep,
year = {2019},
note = {arXiv: 1909.09436},
}
```
</details>
| 8,962 | [
[
-0.0178070068359375,
-0.03607177734375,
0.0188140869140625,
0.00940704345703125,
-0.01336669921875,
0.01343536376953125,
-0.033172607421875,
-0.0099334716796875,
0.00815582275390625,
0.01087188720703125,
-0.02398681640625,
-0.055084228515625,
-0.039398193359375,
-0.0115203857421875,
-0.0280914306640625,
0.09564208984375,
-0.01136016845703125,
-0.001811981201171875,
0.004680633544921875,
-0.01244354248046875,
-0.0175018310546875,
-0.040557861328125,
-0.0589599609375,
-0.019073486328125,
0.029296875,
0.012969970703125,
0.0340576171875,
0.0491943359375,
0.03448486328125,
0.032440185546875,
0.0033588409423828125,
0.0027008056640625,
-0.032318115234375,
-0.01873779296875,
0.01053619384765625,
-0.051666259765625,
-0.018280029296875,
-0.0013856887817382812,
0.042144775390625,
0.0382080078125,
0.0104827880859375,
0.02935791015625,
-0.002147674560546875,
0.046905517578125,
-0.035919189453125,
0.0192108154296875,
-0.036865234375,
-0.0035037994384765625,
-0.0186920166015625,
-0.017852783203125,
-0.0263671875,
-0.032073974609375,
0.001056671142578125,
-0.0390625,
0.037689208984375,
-0.0127410888671875,
0.09039306640625,
0.0137481689453125,
-0.01175689697265625,
-0.03106689453125,
-0.037872314453125,
0.060943603515625,
-0.061065673828125,
0.0161285400390625,
0.0130157470703125,
0.0006456375122070312,
-0.0033779144287109375,
-0.08319091796875,
-0.0416259765625,
-0.00640106201171875,
-0.00537109375,
0.007732391357421875,
-0.00418853759765625,
-0.0014190673828125,
0.0270843505859375,
0.0271453857421875,
-0.054656982421875,
-0.0013227462768554688,
-0.0535888671875,
-0.0257415771484375,
0.048828125,
0.0113525390625,
0.0275115966796875,
-0.0128326416015625,
-0.019287109375,
-0.021728515625,
-0.0296173095703125,
0.0310516357421875,
0.0347900390625,
0.02276611328125,
-0.0243682861328125,
0.03411865234375,
-0.01334381103515625,
0.052459716796875,
0.005741119384765625,
-0.01200103759765625,
0.04730224609375,
-0.019500732421875,
-0.0274810791015625,
-0.00024068355560302734,
0.0838623046875,
0.021026611328125,
0.016265869140625,
-0.00865936279296875,
-0.01104736328125,
0.002323150634765625,
-0.002834320068359375,
-0.060211181640625,
-0.04364013671875,
0.031219482421875,
-0.0278778076171875,
-0.0308074951171875,
0.007198333740234375,
-0.04571533203125,
-0.00826263427734375,
-0.0024204254150390625,
0.054840087890625,
-0.04583740234375,
-0.007091522216796875,
0.0066070556640625,
-0.0201263427734375,
0.0211334228515625,
-0.003570556640625,
-0.0682373046875,
-0.0017213821411132812,
0.03692626953125,
0.0703125,
0.0068359375,
-0.03692626953125,
-0.0345458984375,
-0.0230255126953125,
-0.0251922607421875,
0.0251007080078125,
-0.0177154541015625,
-0.0117340087890625,
-0.0198822021484375,
0.01169586181640625,
-0.0290374755859375,
-0.0341796875,
0.0263671875,
-0.04010009765625,
0.0239410400390625,
-0.0035533905029296875,
-0.031982421875,
-0.0165557861328125,
-0.0012464523315429688,
-0.03448486328125,
0.0919189453125,
0.028076171875,
-0.0643310546875,
0.01552581787109375,
-0.0341796875,
-0.024932861328125,
-0.001445770263671875,
-0.0101470947265625,
-0.045684814453125,
-0.0017595291137695312,
0.014892578125,
0.035919189453125,
-0.01212310791015625,
0.0252685546875,
-0.004734039306640625,
-0.043731689453125,
0.026092529296875,
-0.027374267578125,
0.08367919921875,
0.0248870849609375,
-0.038116455078125,
0.016845703125,
-0.062744140625,
0.0261077880859375,
0.010406494140625,
-0.04327392578125,
0.0032138824462890625,
-0.0156097412109375,
0.01116180419921875,
0.01418304443359375,
0.0199737548828125,
-0.022491455078125,
0.0204315185546875,
-0.03240966796875,
0.047943115234375,
0.055419921875,
-0.011932373046875,
0.02130126953125,
-0.0212249755859375,
0.034881591796875,
0.002437591552734375,
0.00008147954940795898,
-0.007472991943359375,
-0.0408935546875,
-0.0703125,
-0.02801513671875,
0.0352783203125,
0.03887939453125,
-0.059783935546875,
0.04071044921875,
-0.0295562744140625,
-0.057861328125,
-0.043731689453125,
0.005268096923828125,
0.032318115234375,
0.0438232421875,
0.0280303955078125,
-0.0209808349609375,
-0.05718994140625,
-0.047210693359375,
-0.007114410400390625,
-0.0136871337890625,
-0.00899505615234375,
0.0064849853515625,
0.049285888671875,
-0.0235137939453125,
0.0560302734375,
-0.039520263671875,
-0.009552001953125,
-0.0218963623046875,
0.007465362548828125,
0.053131103515625,
0.06610107421875,
0.042877197265625,
-0.03173828125,
-0.04205322265625,
-0.0023555755615234375,
-0.060333251953125,
-0.0005469322204589844,
-0.02276611328125,
-0.0217437744140625,
0.02069091796875,
0.035400390625,
-0.0322265625,
0.0284271240234375,
0.030548095703125,
-0.0240325927734375,
0.041107177734375,
-0.0231170654296875,
0.00939178466796875,
-0.07916259765625,
0.020050048828125,
-0.0023250579833984375,
0.0036067962646484375,
-0.04638671875,
0.01019287109375,
0.009552001953125,
-0.00461578369140625,
-0.0423583984375,
0.032806396484375,
-0.0233612060546875,
0.0163726806640625,
0.01071929931640625,
0.00528717041015625,
0.00091552734375,
0.05755615234375,
-0.003017425537109375,
0.054595947265625,
0.06622314453125,
-0.05010986328125,
0.038482666015625,
0.0015506744384765625,
-0.027557373046875,
0.01010894775390625,
-0.050628662109375,
0.018646240234375,
-0.004425048828125,
0.0023193359375,
-0.08795166015625,
-0.01071929931640625,
0.0277252197265625,
-0.06060791015625,
0.0286865234375,
-0.0325927734375,
-0.018890380859375,
-0.038909912109375,
-0.035400390625,
0.0283203125,
0.043731689453125,
-0.047882080078125,
0.033843994140625,
0.007541656494140625,
0.0185699462890625,
-0.055267333984375,
-0.0557861328125,
-0.01322174072265625,
-0.023345947265625,
-0.04296875,
0.023895263671875,
-0.011505126953125,
0.0048980712890625,
-0.00620269775390625,
-0.01471710205078125,
-0.0150299072265625,
0.005733489990234375,
0.01458740234375,
0.03662109375,
-0.020111083984375,
0.0008606910705566406,
-0.016021728515625,
-0.00943756103515625,
0.01189422607421875,
-0.036346435546875,
0.06011962890625,
-0.0306396484375,
-0.0031375885009765625,
-0.038848876953125,
-0.00444793701171875,
0.037078857421875,
-0.0161590576171875,
0.06201171875,
0.07806396484375,
-0.02362060546875,
-0.00905609130859375,
-0.0167236328125,
0.0092315673828125,
-0.0416259765625,
0.041595458984375,
-0.03338623046875,
-0.03753662109375,
0.053741455078125,
0.0215606689453125,
-0.0035724639892578125,
0.0479736328125,
0.043365478515625,
-0.004993438720703125,
0.06304931640625,
0.0225982666015625,
-0.01555633544921875,
0.0364990234375,
-0.07879638671875,
0.0209197998046875,
-0.056365966796875,
-0.0244598388671875,
-0.047607421875,
-0.021759033203125,
-0.05621337890625,
-0.03436279296875,
0.0178680419921875,
0.025787353515625,
-0.0303192138671875,
0.03411865234375,
-0.05926513671875,
0.027374267578125,
0.056854248046875,
0.017730712890625,
-0.01373291015625,
-0.00496673583984375,
-0.01537322998046875,
-0.001277923583984375,
-0.0555419921875,
-0.034332275390625,
0.10491943359375,
0.0151519775390625,
0.059906005859375,
-0.01377105712890625,
0.06768798828125,
0.00037860870361328125,
0.01064300537109375,
-0.053955078125,
0.040863037109375,
-0.0011682510375976562,
-0.035858154296875,
-0.01074981689453125,
-0.037109375,
-0.07080078125,
0.00835418701171875,
0.001338958740234375,
-0.07122802734375,
0.002330780029296875,
0.005947113037109375,
-0.0242919921875,
0.0294647216796875,
-0.06878662109375,
0.08184814453125,
-0.0210418701171875,
-0.039093017578125,
0.01465606689453125,
-0.0428466796875,
0.0195465087890625,
0.0015411376953125,
0.0063934326171875,
0.0071868896484375,
0.0100250244140625,
0.092529296875,
-0.04473876953125,
0.04302978515625,
-0.0179595947265625,
0.0054779052734375,
0.0341796875,
-0.01160430908203125,
0.0305328369140625,
0.0059967041015625,
-0.008636474609375,
0.0216064453125,
0.00789642333984375,
-0.033538818359375,
-0.0352783203125,
0.06024169921875,
-0.07159423828125,
-0.0242156982421875,
-0.0364990234375,
-0.032928466796875,
0.008056640625,
0.024627685546875,
0.050628662109375,
0.054046630859375,
0.020477294921875,
0.014892578125,
0.036590576171875,
-0.02899169921875,
0.053192138671875,
0.0086212158203125,
-0.01078033447265625,
-0.035858154296875,
0.09423828125,
0.00897216796875,
0.0101776123046875,
0.0252532958984375,
0.00798797607421875,
-0.025238037109375,
-0.041778564453125,
-0.0382080078125,
0.017059326171875,
-0.06365966796875,
-0.0203857421875,
-0.04656982421875,
-0.0284576416015625,
-0.038818359375,
-0.024749755859375,
-0.03167724609375,
-0.0287322998046875,
-0.030731201171875,
0.0046539306640625,
0.02978515625,
0.0286102294921875,
-0.00920867919921875,
0.0243377685546875,
-0.047210693359375,
0.021759033203125,
0.01105499267578125,
0.028350830078125,
0.00014543533325195312,
-0.0501708984375,
-0.03564453125,
0.0035839080810546875,
-0.016754150390625,
-0.051361083984375,
0.04351806640625,
0.006191253662109375,
0.036834716796875,
0.0249786376953125,
0.002410888671875,
0.055084228515625,
-0.0131378173828125,
0.06634521484375,
0.00821685791015625,
-0.08294677734375,
0.0382080078125,
-0.006855010986328125,
0.018646240234375,
0.0304107666015625,
0.032379150390625,
-0.04351806640625,
-0.0316162109375,
-0.047760009765625,
-0.0831298828125,
0.0740966796875,
0.02001953125,
-0.0022487640380859375,
0.00429534912109375,
0.0155029296875,
-0.004650115966796875,
0.00748443603515625,
-0.0631103515625,
-0.045440673828125,
-0.0222320556640625,
-0.032318115234375,
-0.01220703125,
0.01296234130859375,
-0.0014057159423828125,
-0.041107177734375,
0.06048583984375,
-0.0045623779296875,
0.04681396484375,
0.0204925537109375,
-0.0213165283203125,
0.0085296630859375,
-0.0013637542724609375,
0.037506103515625,
0.0458984375,
-0.0280303955078125,
0.01352691650390625,
0.00759124755859375,
-0.046234130859375,
0.01158905029296875,
0.0033359527587890625,
-0.01036834716796875,
0.0101470947265625,
0.037384033203125,
0.0595703125,
-0.0034885406494140625,
-0.038330078125,
0.029052734375,
-0.01308441162109375,
-0.01296234130859375,
-0.0221710205078125,
0.0183258056640625,
0.0078887939453125,
0.01245880126953125,
0.03460693359375,
0.0202789306640625,
-0.0124664306640625,
-0.0308074951171875,
0.00827789306640625,
0.0242156982421875,
-0.017242431640625,
-0.0238189697265625,
0.07373046875,
-0.0004603862762451172,
-0.0285797119140625,
0.05584716796875,
-0.014434814453125,
-0.0535888671875,
0.072265625,
0.032470703125,
0.07171630859375,
0.01259613037109375,
0.01021575927734375,
0.0537109375,
0.0269775390625,
0.0027942657470703125,
0.0184326171875,
-0.006744384765625,
-0.046875,
-0.007602691650390625,
-0.043304443359375,
-0.004734039306640625,
0.0192413330078125,
-0.04541015625,
0.0239410400390625,
-0.0404052734375,
-0.00823211669921875,
0.010589599609375,
0.0181427001953125,
-0.0728759765625,
0.0193634033203125,
0.012237548828125,
0.052734375,
-0.06231689453125,
0.07183837890625,
0.040740966796875,
-0.0462646484375,
-0.08013916015625,
-0.01090240478515625,
-0.018218994140625,
-0.06024169921875,
0.054107666015625,
0.0269775390625,
0.0071563720703125,
0.018524169921875,
-0.047088623046875,
-0.0714111328125,
0.07843017578125,
0.0225677490234375,
-0.018585205078125,
-0.0008726119995117188,
0.0007224082946777344,
0.046539306640625,
-0.00809478759765625,
0.044708251953125,
0.0482177734375,
0.028076171875,
-0.0169219970703125,
-0.05767822265625,
0.0099029541015625,
-0.02978515625,
-0.00232696533203125,
0.005741119384765625,
-0.04827880859375,
0.0859375,
-0.033203125,
-0.0128936767578125,
0.0013799667358398438,
0.043304443359375,
0.0211181640625,
0.0233154296875,
0.0144805908203125,
0.04449462890625,
0.063232421875,
-0.024932861328125,
0.06939697265625,
-0.0286102294921875,
0.056488037109375,
0.059783935546875,
0.0180511474609375,
0.044342041015625,
0.03173828125,
-0.032257080078125,
0.03875732421875,
0.0526123046875,
-0.0127105712890625,
0.03900146484375,
0.0283050537109375,
-0.01165008544921875,
0.01190185546875,
0.0268096923828125,
-0.042083740234375,
0.03173828125,
0.0179901123046875,
-0.03448486328125,
-0.0024852752685546875,
0.0009870529174804688,
0.01338958740234375,
-0.0173492431640625,
-0.00974273681640625,
0.02972412109375,
-0.018310546875,
-0.053436279296875,
0.0924072265625,
0.0091094970703125,
0.072509765625,
-0.043609619140625,
0.01540374755859375,
-0.0191192626953125,
0.0261077880859375,
-0.0313720703125,
-0.04833984375,
0.005107879638671875,
-0.00502777099609375,
-0.006072998046875,
-0.004718780517578125,
0.0212554931640625,
-0.03985595703125,
-0.035552978515625,
0.014129638671875,
0.01332855224609375,
0.02825927734375,
0.01108551025390625,
-0.0526123046875,
0.0218048095703125,
0.0218963623046875,
-0.032012939453125,
0.01824951171875,
0.022247314453125,
0.01499176025390625,
0.04730224609375,
0.047943115234375,
0.0033721923828125,
0.034454345703125,
-0.0116424560546875,
0.06561279296875,
-0.053375244140625,
-0.019439697265625,
-0.060821533203125,
0.041107177734375,
0.006763458251953125,
-0.04736328125,
0.05517578125,
0.06756591796875,
0.09088134765625,
-0.025146484375,
0.06201171875,
-0.03564453125,
0.00406646728515625,
-0.043487548828125,
0.06060791015625,
-0.03338623046875,
0.01708984375,
-0.019744873046875,
-0.0482177734375,
-0.011444091796875,
0.05755615234375,
-0.0177001953125,
0.00878143310546875,
0.058929443359375,
0.0789794921875,
0.00274658203125,
-0.0308074951171875,
0.0036945343017578125,
0.005161285400390625,
0.03582763671875,
0.07354736328125,
0.037506103515625,
-0.07476806640625,
0.05621337890625,
-0.053253173828125,
-0.003757476806640625,
-0.0079193115234375,
-0.04473876953125,
-0.06707763671875,
-0.05755615234375,
-0.040557861328125,
-0.052459716796875,
-0.0110931396484375,
0.07171630859375,
0.048675537109375,
-0.06561279296875,
-0.0220794677734375,
-0.011993408203125,
0.0208740234375,
-0.0243682861328125,
-0.025115966796875,
0.05194091796875,
-0.034698486328125,
-0.0772705078125,
0.01473236083984375,
-0.00959014892578125,
-0.0064697265625,
0.005893707275390625,
-0.01611328125,
-0.022705078125,
-0.0177001953125,
0.021209716796875,
0.030853271484375,
-0.0390625,
-0.01520538330078125,
-0.00441741943359375,
-0.02508544921875,
0.015838623046875,
0.041473388671875,
-0.0703125,
0.043365478515625,
0.046966552734375,
0.038299560546875,
0.044342041015625,
-0.01763916015625,
0.0174102783203125,
-0.057830810546875,
0.0216522216796875,
0.00576019287109375,
0.0304107666015625,
0.0144195556640625,
-0.0219268798828125,
0.04754638671875,
0.03729248046875,
-0.042449951171875,
-0.07147216796875,
-0.0248870849609375,
-0.0777587890625,
-0.00567626953125,
0.07373046875,
-0.0239105224609375,
-0.0296783447265625,
0.0019702911376953125,
-0.0231781005859375,
0.043487548828125,
-0.0191650390625,
0.0523681640625,
0.032989501953125,
-0.00472259521484375,
0.0042724609375,
-0.03106689453125,
0.035400390625,
0.0164642333984375,
-0.042083740234375,
-0.0132293701171875,
0.00893402099609375,
0.043182373046875,
0.0207366943359375,
0.059783935546875,
0.0031375885009765625,
0.0215606689453125,
0.0133056640625,
0.01441192626953125,
-0.0164337158203125,
-0.006206512451171875,
-0.0295562744140625,
0.008056640625,
-0.01110076904296875,
-0.043975830078125
]
] |
MIT/ast-finetuned-audioset-10-10-0.4593 | 2023-09-06T14:49:15.000Z | [
"transformers",
"pytorch",
"safetensors",
"audio-spectrogram-transformer",
"audio-classification",
"arxiv:2104.01778",
"license:bsd-3-clause",
"endpoints_compatible",
"has_space",
"region:us"
] | audio-classification | MIT | null | null | MIT/ast-finetuned-audioset-10-10-0.4593 | 70 | 39,848 | transformers | 2022-11-14T18:41:48 | ---
license: bsd-3-clause
tags:
- audio-classification
---
# Audio Spectrogram Transformer (fine-tuned on AudioSet)
Audio Spectrogram Transformer (AST) model fine-tuned on AudioSet. It was introduced in the paper [AST: Audio Spectrogram Transformer](https://arxiv.org/abs/2104.01778) by Gong et al. and first released in [this repository](https://github.com/YuanGongND/ast).
Disclaimer: The team releasing Audio Spectrogram Transformer did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
The Audio Spectrogram Transformer is equivalent to [ViT](https://huggingface.co/docs/transformers/model_doc/vit), but applied on audio. Audio is first turned into an image (as a spectrogram), after which a Vision Transformer is applied. The model gets state-of-the-art results on several audio classification benchmarks.
## Usage
You can use the raw model for classifying audio into one of the AudioSet classes. See the [documentation](https://huggingface.co/docs/transformers/main/en/model_doc/audio-spectrogram-transformer#transformers.ASTForAudioClassification.forward.example) for more info. | 1,165 | [
[
-0.057098388671875,
-0.0167694091796875,
0.00748443603515625,
0.009185791015625,
-0.0235443115234375,
0.00455474853515625,
-0.0167388916015625,
-0.050384521484375,
0.03131103515625,
0.03900146484375,
-0.06103515625,
-0.035186767578125,
-0.046539306640625,
-0.009368896484375,
-0.042144775390625,
0.08978271484375,
0.00879669189453125,
0.001636505126953125,
0.01471710205078125,
-0.01409149169921875,
-0.0242462158203125,
-0.01141357421875,
-0.039581298828125,
-0.037384033203125,
-0.0030517578125,
0.0207672119140625,
0.042449951171875,
0.031494140625,
0.058929443359375,
0.0213470458984375,
-0.035736083984375,
-0.02349853515625,
-0.004322052001953125,
-0.0228271484375,
0.009857177734375,
-0.0251312255859375,
-0.06488037109375,
0.0157012939453125,
0.038787841796875,
0.03460693359375,
-0.0216827392578125,
0.039886474609375,
-0.0027866363525390625,
0.0211639404296875,
-0.0284881591796875,
0.0103607177734375,
-0.018951416015625,
0.00815582275390625,
-0.00704193115234375,
-0.0252685546875,
-0.020294189453125,
-0.01197052001953125,
0.019012451171875,
-0.03692626953125,
0.020416259765625,
0.004970550537109375,
0.07958984375,
0.039337158203125,
-0.03924560546875,
-0.00926971435546875,
-0.07635498046875,
0.0216827392578125,
-0.03302001953125,
0.05224609375,
0.008026123046875,
0.0662841796875,
0.03131103515625,
-0.06201171875,
-0.039154052734375,
-0.0133514404296875,
0.00905609130859375,
0.029022216796875,
-0.0263671875,
0.02471923828125,
0.0281524658203125,
0.0640869140625,
-0.0269927978515625,
-0.00811004638671875,
-0.045196533203125,
-0.023834228515625,
0.045166015625,
-0.01282501220703125,
0.0265960693359375,
-0.02984619140625,
-0.046783447265625,
-0.02581787109375,
-0.020843505859375,
-0.005481719970703125,
0.020965576171875,
0.020111083984375,
-0.0374755859375,
0.03460693359375,
0.015960693359375,
0.033416748046875,
0.0300445556640625,
0.0031833648681640625,
0.04058837890625,
-0.0242767333984375,
-0.01091766357421875,
0.02142333984375,
0.06005859375,
0.0374755859375,
0.01910400390625,
0.0016508102416992188,
-0.038726806640625,
0.03460693359375,
0.031951904296875,
-0.06060791015625,
-0.02606201171875,
-0.0004363059997558594,
-0.036773681640625,
-0.0289154052734375,
-0.002414703369140625,
-0.042572021484375,
0.007038116455078125,
-0.01474761962890625,
0.0386962890625,
-0.037872314453125,
-0.035980224609375,
-0.005828857421875,
-0.0267486572265625,
0.0296783447265625,
0.0004744529724121094,
-0.06671142578125,
0.0494384765625,
0.03045654296875,
0.049468994140625,
-0.0063934326171875,
0.001476287841796875,
-0.006008148193359375,
0.0007715225219726562,
-0.00798797607421875,
0.076416015625,
-0.029571533203125,
-0.043182373046875,
-0.0089874267578125,
0.00592041015625,
0.0050811767578125,
-0.056365966796875,
0.06719970703125,
-0.0275421142578125,
0.006168365478515625,
-0.0024890899658203125,
-0.036895751953125,
-0.00550079345703125,
0.00585174560546875,
-0.0435791015625,
0.07598876953125,
0.0088653564453125,
-0.040252685546875,
0.038604736328125,
-0.07232666015625,
0.00119781494140625,
0.007556915283203125,
0.0006194114685058594,
-0.037933349609375,
-0.00400543212890625,
-0.005214691162109375,
0.0088653564453125,
-0.00780487060546875,
-0.0007467269897460938,
-0.0118408203125,
-0.04168701171875,
0.003936767578125,
-0.01197052001953125,
0.06817626953125,
0.019927978515625,
-0.0154571533203125,
0.0219573974609375,
-0.0662841796875,
-0.0163116455078125,
-0.0108642578125,
-0.0234527587890625,
-0.011566162109375,
-0.01873779296875,
0.058868408203125,
0.01520538330078125,
-0.00185394287109375,
-0.06494140625,
0.00399017333984375,
-0.026275634765625,
0.0413818359375,
0.0380859375,
-0.019622802734375,
0.033172607421875,
-0.0286407470703125,
0.038726806640625,
-0.0087738037109375,
0.0218353271484375,
-0.005664825439453125,
-0.034820556640625,
-0.040374755859375,
-0.0200042724609375,
0.02288818359375,
0.050689697265625,
-0.01354217529296875,
0.042938232421875,
-0.017303466796875,
-0.0517578125,
-0.0616455078125,
-0.024139404296875,
0.03692626953125,
0.029266357421875,
0.038543701171875,
-0.02703857421875,
-0.0540771484375,
-0.06585693359375,
-0.0217742919921875,
-0.00589752197265625,
-0.0247802734375,
0.0268096923828125,
0.0120697021484375,
-0.032623291015625,
0.05523681640625,
-0.032257080078125,
-0.033538818359375,
0.0012865066528320312,
0.00449371337890625,
0.014373779296875,
0.0501708984375,
0.057098388671875,
-0.058807373046875,
-0.035186767578125,
-0.01320648193359375,
-0.03143310546875,
-0.022216796875,
0.033599853515625,
-0.0016498565673828125,
-0.0041961669921875,
0.04437255859375,
-0.042205810546875,
0.02813720703125,
0.055908203125,
-0.04150390625,
0.048492431640625,
0.023193359375,
0.01200103759765625,
-0.0904541015625,
0.0023097991943359375,
0.0121307373046875,
-0.040985107421875,
-0.054412841796875,
0.01149749755859375,
0.00524139404296875,
-0.0167236328125,
-0.0284423828125,
0.034912109375,
-0.021148681640625,
-0.0167388916015625,
-0.0235443115234375,
-0.0047454833984375,
-0.0145721435546875,
0.027099609375,
0.0036792755126953125,
0.03350830078125,
0.043182373046875,
-0.0301361083984375,
0.047882080078125,
0.06390380859375,
-0.009185791015625,
0.06243896484375,
-0.051300048828125,
0.0208282470703125,
0.00839996337890625,
0.0255584716796875,
-0.060150146484375,
0.00019884109497070312,
0.0161285400390625,
-0.0445556640625,
0.037384033203125,
-0.0178680419921875,
-0.0274200439453125,
-0.044677734375,
-0.00432586669921875,
0.04595947265625,
0.054534912109375,
-0.053863525390625,
0.056793212890625,
0.0305023193359375,
0.023040771484375,
-0.0023708343505859375,
-0.059326171875,
-0.0287628173828125,
-0.02447509765625,
-0.0430908203125,
0.043670654296875,
-0.0265350341796875,
-0.01355743408203125,
0.004032135009765625,
-0.034149169921875,
-0.01071929931640625,
-0.02410888671875,
0.0308990478515625,
0.02471923828125,
-0.034881591796875,
-0.0003573894500732422,
-0.0099029541015625,
-0.0389404296875,
0.01326751708984375,
-0.0021495819091796875,
0.032440185546875,
-0.0199127197265625,
-0.00885009765625,
-0.04949951171875,
0.01503753662109375,
0.03533935546875,
-0.00981903076171875,
0.007038116455078125,
0.054290771484375,
-0.0204010009765625,
-0.008880615234375,
-0.045806884765625,
-0.0316162109375,
-0.04193115234375,
0.00646209716796875,
-0.03509521484375,
-0.04327392578125,
0.059783935546875,
-0.001956939697265625,
-0.01499176025390625,
0.049560546875,
0.0249481201171875,
-0.017364501953125,
0.0660400390625,
0.0692138671875,
0.0136260986328125,
0.05426025390625,
-0.010772705078125,
-0.006195068359375,
-0.0750732421875,
-0.01373291015625,
-0.0265045166015625,
-0.0302886962890625,
-0.060455322265625,
-0.00363922119140625,
0.0305023193359375,
-0.022186279296875,
-0.0264892578125,
0.047271728515625,
-0.0712890625,
0.026336669921875,
0.050933837890625,
0.01506805419921875,
0.028228759765625,
-0.01296234130859375,
0.0170745849609375,
0.003574371337890625,
-0.0137786865234375,
-0.0207672119140625,
0.0731201171875,
0.03753662109375,
0.04766845703125,
0.002002716064453125,
0.039947509765625,
-0.0012569427490234375,
0.01354217529296875,
-0.0758056640625,
0.02734375,
-0.0256500244140625,
-0.061065673828125,
-0.0028057098388671875,
-0.006565093994140625,
-0.041290283203125,
-0.00928497314453125,
-0.023345947265625,
-0.054656982421875,
0.0260162353515625,
0.0248565673828125,
-0.033935546875,
0.020721435546875,
-0.04718017578125,
0.05859375,
0.01300048828125,
0.0357666015625,
0.00902557373046875,
-0.044708251953125,
0.023040771484375,
0.00933074951171875,
-0.0022735595703125,
-0.0186920166015625,
0.028564453125,
0.07598876953125,
-0.036956787109375,
0.038360595703125,
-0.03363037109375,
-0.003643035888671875,
0.0300140380859375,
0.0023193359375,
0.00882720947265625,
-0.01239013671875,
0.00957489013671875,
0.0260009765625,
0.035308837890625,
-0.0091705322265625,
-0.037567138671875,
0.01454925537109375,
-0.06573486328125,
-0.0160675048828125,
-0.00235748291015625,
-0.04302978515625,
-0.0217437744140625,
0.0152130126953125,
0.053253173828125,
0.043121337890625,
-0.0184326171875,
-0.00656890869140625,
0.047637939453125,
-0.0087738037109375,
0.0174102783203125,
0.0406494140625,
-0.0219268798828125,
-0.01024627685546875,
0.052825927734375,
0.005229949951171875,
0.034271240234375,
0.0145263671875,
0.022491455078125,
-0.0077667236328125,
-0.01483917236328125,
-0.01491546630859375,
0.01517486572265625,
-0.040191650390625,
-0.017852783203125,
-0.03741455078125,
-0.038726806640625,
-0.044342041015625,
-0.003875732421875,
-0.0618896484375,
-0.01409912109375,
0.006389617919921875,
-0.0087738037109375,
0.05767822265625,
0.036865234375,
-0.0192108154296875,
0.04833984375,
-0.051116943359375,
0.051483154296875,
0.0265045166015625,
0.0550537109375,
-0.040863037109375,
-0.06005859375,
0.005191802978515625,
-0.003910064697265625,
-0.01422882080078125,
-0.06903076171875,
0.0215911865234375,
0.01507568359375,
0.0350341796875,
0.035919189453125,
-0.009674072265625,
0.04266357421875,
-0.0455322265625,
0.027618408203125,
0.00225830078125,
-0.0816650390625,
0.043060302734375,
-0.04296875,
0.0272674560546875,
0.03546142578125,
-0.0008182525634765625,
-0.050140380859375,
-0.023712158203125,
-0.06329345703125,
-0.0616455078125,
0.06524658203125,
0.011138916015625,
0.0174407958984375,
0.03302001953125,
0.0188140869140625,
-0.00035881996154785156,
0.0210723876953125,
-0.0450439453125,
-0.043731689453125,
-0.057342529296875,
-0.00957489013671875,
-0.0217437744140625,
-0.0269012451171875,
-0.0189971923828125,
-0.04296875,
0.037353515625,
-0.01163482666015625,
0.0606689453125,
0.00873565673828125,
0.00542449951171875,
-0.0217437744140625,
0.00406646728515625,
0.022186279296875,
-0.005702972412109375,
-0.0535888671875,
0.00406646728515625,
0.001293182373046875,
-0.05999755859375,
-0.01528167724609375,
0.01593017578125,
0.0106201171875,
0.00415802001953125,
0.01404571533203125,
0.0838623046875,
0.03204345703125,
-0.0316162109375,
0.06317138671875,
0.00016415119171142578,
-0.03448486328125,
-0.0565185546875,
0.005645751953125,
0.01349639892578125,
0.0244598388671875,
0.01433563232421875,
0.0170135498046875,
0.037750244140625,
-0.04022216796875,
0.02838134765625,
0.02313232421875,
-0.05108642578125,
-0.0316162109375,
0.071044921875,
0.0034694671630859375,
-0.03985595703125,
0.061187744140625,
0.002872467041015625,
-0.0297698974609375,
0.048004150390625,
0.0562744140625,
0.081298828125,
-0.050994873046875,
0.0021228790283203125,
0.02508544921875,
0.0219268798828125,
0.01373291015625,
0.040802001953125,
-0.03143310546875,
-0.0721435546875,
-0.015533447265625,
-0.054931640625,
-0.034515380859375,
-0.00426483154296875,
-0.09576416015625,
0.03729248046875,
-0.037200927734375,
-0.01324462890625,
0.0306243896484375,
-0.012603759765625,
-0.05535888671875,
0.02801513671875,
0.03564453125,
0.10174560546875,
-0.09039306640625,
0.056396484375,
0.052581787109375,
-0.02740478515625,
-0.0838623046875,
-0.002193450927734375,
0.00693511962890625,
-0.06793212890625,
0.02435302734375,
0.00838470458984375,
-0.0005440711975097656,
0.0170440673828125,
-0.054412841796875,
-0.060638427734375,
0.0740966796875,
0.0237274169921875,
-0.035186767578125,
-0.004817962646484375,
-0.014373779296875,
0.0472412109375,
-0.01262664794921875,
0.037628173828125,
0.058441162109375,
0.048614501953125,
0.03656005859375,
-0.10809326171875,
0.003955841064453125,
-0.054046630859375,
-0.00821685791015625,
0.0088653564453125,
-0.053375244140625,
0.051177978515625,
0.00765228271484375,
-0.00472259521484375,
-0.01253509521484375,
0.04290771484375,
0.01934814453125,
0.01800537109375,
0.0638427734375,
0.034271240234375,
0.029266357421875,
-0.023406982421875,
0.07135009765625,
-0.019317626953125,
0.024993896484375,
0.07525634765625,
0.01215362548828125,
0.0526123046875,
0.025390625,
-0.0154876708984375,
0.042266845703125,
0.050811767578125,
-0.03851318359375,
0.033538818359375,
-0.01055908203125,
-0.0017871856689453125,
-0.0185699462890625,
-0.0019969940185546875,
-0.033843994140625,
0.06683349609375,
0.0274658203125,
-0.0292816162109375,
-0.0008192062377929688,
0.02093505859375,
-0.0201416015625,
-0.0106048583984375,
-0.03265380859375,
0.06964111328125,
0.00844573974609375,
-0.009857177734375,
0.047698974609375,
-0.02606201171875,
0.06884765625,
-0.023345947265625,
0.0089111328125,
-0.001819610595703125,
-0.001636505126953125,
-0.0292205810546875,
-0.05194091796875,
0.05755615234375,
-0.01375579833984375,
-0.022003173828125,
-0.0205841064453125,
0.039215087890625,
-0.0298919677734375,
-0.0260162353515625,
0.040771484375,
0.004787445068359375,
0.0279083251953125,
-0.0036792755126953125,
-0.04461669921875,
0.00807952880859375,
-0.0166473388671875,
-0.027679443359375,
-0.007030487060546875,
0.005420684814453125,
0.01540374755859375,
0.03839111328125,
0.0238037109375,
0.0059051513671875,
0.0120086669921875,
0.0176544189453125,
0.058013916015625,
-0.049224853515625,
-0.059661865234375,
-0.021942138671875,
0.04058837890625,
0.00482940673828125,
-0.017364501953125,
0.049774169921875,
0.040985107421875,
0.054656982421875,
-0.0037097930908203125,
0.042205810546875,
0.009552001953125,
0.0516357421875,
-0.020416259765625,
0.052947998046875,
-0.04998779296875,
-0.0080108642578125,
-0.05438232421875,
-0.0711669921875,
-0.02392578125,
0.04656982421875,
-0.00705718994140625,
0.01134490966796875,
0.0467529296875,
0.053253173828125,
-0.0227813720703125,
0.023406982421875,
0.016937255859375,
0.037139892578125,
0.0017099380493164062,
0.01499176025390625,
0.034088134765625,
-0.05706787109375,
0.0462646484375,
-0.0246429443359375,
-0.02117919921875,
-0.0119171142578125,
-0.034271240234375,
-0.05877685546875,
-0.052978515625,
-0.034271240234375,
-0.03271484375,
0.0026683807373046875,
0.055572509765625,
0.07061767578125,
-0.0654296875,
-0.01187896728515625,
-0.0050506591796875,
-0.021453857421875,
-0.0246429443359375,
-0.0191497802734375,
0.0190582275390625,
0.02105712890625,
-0.07098388671875,
0.031646728515625,
0.00018668174743652344,
0.01473236083984375,
-0.0130462646484375,
0.00621795654296875,
0.022552490234375,
0.0085296630859375,
0.0186920166015625,
0.035888671875,
-0.041473388671875,
-0.042877197265625,
-0.0131072998046875,
-0.003223419189453125,
0.0308990478515625,
0.0301055908203125,
-0.050262451171875,
0.031005859375,
0.0242462158203125,
0.0033817291259765625,
0.054595947265625,
-0.0111083984375,
0.0321044921875,
-0.0509033203125,
0.0189971923828125,
0.01004791259765625,
0.0196380615234375,
0.01436614990234375,
-0.0177001953125,
0.0240325927734375,
0.0140228271484375,
-0.04437255859375,
-0.07672119140625,
0.0160980224609375,
-0.1171875,
0.01282501220703125,
0.0953369140625,
0.033416748046875,
-0.02581787109375,
0.012786865234375,
-0.020965576171875,
0.05328369140625,
-0.0310821533203125,
0.0430908203125,
0.0145721435546875,
-0.0015096664428710938,
-0.0251617431640625,
-0.0360107421875,
0.058013916015625,
-0.001026153564453125,
-0.033782958984375,
-0.02178955078125,
0.0124969482421875,
0.047088623046875,
0.04437255859375,
0.04681396484375,
-0.0198822021484375,
0.022247314453125,
0.0216827392578125,
0.053192138671875,
-0.00007599592208862305,
-0.0169525146484375,
-0.0301513671875,
0.009552001953125,
-0.0090484619140625,
-0.0360107421875
]
] |
roneneldan/TinyStories-33M | 2023-08-08T22:32:26.000Z | [
"transformers",
"pytorch",
"gpt_neo",
"text-generation",
"dataset:roneneldan/TinyStories",
"arxiv:2305.07759",
"endpoints_compatible",
"has_space",
"region:us"
] | text-generation | roneneldan | null | null | roneneldan/TinyStories-33M | 63 | 39,694 | transformers | 2023-05-12T19:16:05 | ---
datasets:
- roneneldan/TinyStories
---
Model trained on the TinyStories Dataset, see https://arxiv.org/abs/2305.07759
Based on GPT-Neo architecture.
License: mit
---
hyperparams used to train this model:
lr = 5e-4,
lr_schedule = constant,
wd=0.1,
adam_beta1=0.9, adam_beta2 = 0.95,
context_length=512,
batch_size=80,
gradient_accumulation_steps=16
------ EXAMPLE USAGE ---
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
model = AutoModelForCausalLM.from_pretrained('roneneldan/TinyStories-33M')
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neo-125M")
prompt = "Once upon a time there was"
input_ids = tokenizer.encode(prompt, return_tensors="pt")
# Generate completion
output = model.generate(input_ids, max_length = 1000, num_beams=1)
# Decode the completion
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
# Print the generated text
print(output_text) | 936 | [
[
-0.030517578125,
-0.03399658203125,
0.03497314453125,
0.007274627685546875,
-0.0224609375,
-0.0269012451171875,
-0.003978729248046875,
-0.00789642333984375,
0.0003180503845214844,
0.0203094482421875,
-0.061553955078125,
-0.0350341796875,
-0.046295166015625,
0.018341064453125,
-0.020538330078125,
0.0919189453125,
0.0105743408203125,
0.0087127685546875,
0.0196380615234375,
0.0008473396301269531,
-0.010498046875,
-0.0227203369140625,
-0.06658935546875,
-0.0224761962890625,
0.0145721435546875,
0.0007839202880859375,
0.049072265625,
0.06866455078125,
0.02703857421875,
0.0276031494140625,
-0.0104522705078125,
0.01629638671875,
-0.0285797119140625,
-0.0202178955078125,
0.0028209686279296875,
-0.0154571533203125,
-0.038238525390625,
-0.00484466552734375,
0.06396484375,
0.0291900634765625,
-0.0082550048828125,
0.0288848876953125,
0.032135009765625,
0.0040130615234375,
-0.026580810546875,
0.0276031494140625,
-0.047576904296875,
0.0243682861328125,
0.002979278564453125,
-0.0031337738037109375,
-0.01107025146484375,
-0.0020751953125,
0.00994873046875,
-0.068115234375,
0.055633544921875,
0.003620147705078125,
0.090576171875,
0.0379638671875,
-0.02581787109375,
-0.01474761962890625,
-0.048492431640625,
0.0645751953125,
-0.054656982421875,
0.0178070068359375,
0.028839111328125,
0.01409912109375,
0.0074310302734375,
-0.08349609375,
-0.038177490234375,
0.003093719482421875,
-0.0292205810546875,
-0.00492095947265625,
-0.010467529296875,
0.01056671142578125,
0.0482177734375,
0.02294921875,
-0.05438232421875,
-0.00371551513671875,
-0.01763916015625,
-0.0196380615234375,
0.0248565673828125,
0.055084228515625,
-0.0238800048828125,
-0.055023193359375,
-0.050323486328125,
-0.0233001708984375,
-0.0255279541015625,
-0.01198577880859375,
0.01216888427734375,
0.0207977294921875,
-0.0148468017578125,
0.033660888671875,
-0.0141448974609375,
0.054931640625,
0.0210418701171875,
0.0015382766723632812,
0.0252685546875,
-0.06011962890625,
-0.0305328369140625,
-0.0225677490234375,
0.08642578125,
-0.00028967857360839844,
-0.00742340087890625,
-0.0026416778564453125,
-0.034515380859375,
-0.01552581787109375,
0.01346588134765625,
-0.081298828125,
-0.025482177734375,
0.0007023811340332031,
-0.03472900390625,
-0.022369384765625,
0.004207611083984375,
-0.04473876953125,
-0.003139495849609375,
-0.0261077880859375,
0.048980712890625,
-0.0224761962890625,
0.0017948150634765625,
0.006626129150390625,
-0.0013637542724609375,
0.006168365478515625,
-0.0008568763732910156,
-0.06060791015625,
0.024200439453125,
0.0372314453125,
0.07177734375,
0.0142059326171875,
-0.042999267578125,
-0.0307159423828125,
0.0156402587890625,
-0.005641937255859375,
0.0305633544921875,
0.0035572052001953125,
-0.033416748046875,
-0.00824737548828125,
0.017181396484375,
-0.018798828125,
-0.0265960693359375,
0.038055419921875,
-0.021728515625,
0.0242767333984375,
-0.0088348388671875,
-0.043548583984375,
0.00817108154296875,
0.0272674560546875,
-0.0260772705078125,
0.0789794921875,
0.0240020751953125,
-0.061248779296875,
0.045501708984375,
-0.040802001953125,
-0.00017404556274414062,
0.006793975830078125,
-0.01593017578125,
-0.053375244140625,
0.006649017333984375,
0.02313232421875,
0.03173828125,
-0.0224609375,
0.0285186767578125,
-0.0228729248046875,
-0.025726318359375,
-0.006771087646484375,
-0.0421142578125,
0.055023193359375,
0.0157012939453125,
-0.034149169921875,
0.004161834716796875,
-0.059478759765625,
-0.005138397216796875,
0.0198822021484375,
-0.0244598388671875,
-0.01009368896484375,
-0.0243072509765625,
0.017364501953125,
0.025177001953125,
0.042449951171875,
-0.04412841796875,
0.0297088623046875,
-0.0271453857421875,
0.034942626953125,
0.054412841796875,
0.0129547119140625,
0.0214996337890625,
-0.015838623046875,
0.0281219482421875,
0.0145263671875,
0.040283203125,
0.00017118453979492188,
-0.025299072265625,
-0.0633544921875,
-0.033172607421875,
0.026763916015625,
0.0211181640625,
-0.05181884765625,
0.0457763671875,
-0.02880859375,
-0.03765869140625,
-0.0281219482421875,
0.010955810546875,
0.0283050537109375,
0.048492431640625,
0.034271240234375,
-0.004100799560546875,
-0.03948974609375,
-0.06829833984375,
0.020233154296875,
-0.0029239654541015625,
-0.01345062255859375,
0.019927978515625,
0.06005859375,
-0.042022705078125,
0.07568359375,
-0.054931640625,
-0.0276336669921875,
0.0075531005859375,
0.03192138671875,
0.0462646484375,
0.04730224609375,
0.0421142578125,
-0.0271453857421875,
-0.022369384765625,
-0.033294677734375,
-0.051849365234375,
0.0103759765625,
-0.00762939453125,
-0.01331329345703125,
-0.00921630859375,
0.0240936279296875,
-0.0780029296875,
0.026885986328125,
0.0202178955078125,
-0.04144287109375,
0.0509033203125,
-0.032806396484375,
-0.00598907470703125,
-0.10797119140625,
0.0096893310546875,
0.0055694580078125,
-0.019500732421875,
-0.01507568359375,
-0.01111602783203125,
0.005229949951171875,
-0.02191162109375,
-0.034637451171875,
0.057220458984375,
-0.0279998779296875,
-0.0130462646484375,
-0.0224609375,
-0.0175628662109375,
0.0095977783203125,
0.0418701171875,
0.0132904052734375,
0.052978515625,
0.047271728515625,
-0.062347412109375,
0.0193939208984375,
0.036224365234375,
-0.0097503662109375,
0.009613037109375,
-0.06585693359375,
0.00743865966796875,
0.0083770751953125,
0.0130462646484375,
-0.06549072265625,
-0.004058837890625,
0.023284912109375,
-0.02490234375,
0.02606201171875,
-0.0400390625,
-0.05828857421875,
-0.0478515625,
-0.00989532470703125,
0.039398193359375,
0.0240325927734375,
-0.05194091796875,
0.04132080078125,
0.00513458251953125,
0.005207061767578125,
-0.04107666015625,
-0.0411376953125,
-0.0238800048828125,
-0.01349639892578125,
-0.02587890625,
0.01270294189453125,
0.0012722015380859375,
0.0178680419921875,
0.003299713134765625,
0.0193939208984375,
0.00579071044921875,
-0.00946807861328125,
0.0167694091796875,
0.0243988037109375,
-0.01470947265625,
0.0021190643310546875,
0.0106658935546875,
-0.03546142578125,
0.009368896484375,
-0.036865234375,
0.06964111328125,
-0.030975341796875,
-0.01041412353515625,
-0.042083740234375,
0.00273895263671875,
0.033966064453125,
0.007564544677734375,
0.058837890625,
0.06829833984375,
-0.039093017578125,
-0.00782012939453125,
-0.0137939453125,
-0.0455322265625,
-0.03936767578125,
0.03814697265625,
-0.03436279296875,
-0.036651611328125,
0.06048583984375,
0.0207061767578125,
0.00684356689453125,
0.06048583984375,
0.03466796875,
0.00920867919921875,
0.09210205078125,
0.0179443359375,
0.001575469970703125,
0.03082275390625,
-0.0780029296875,
-0.007770538330078125,
-0.06610107421875,
-0.006591796875,
-0.037689208984375,
-0.014404296875,
-0.05078125,
-0.0218658447265625,
0.0300445556640625,
0.004238128662109375,
-0.049407958984375,
0.049102783203125,
-0.043701171875,
0.01910400390625,
0.03839111328125,
0.00557708740234375,
0.0097503662109375,
-0.00008404254913330078,
-0.01552581787109375,
-0.0025959014892578125,
-0.075927734375,
-0.0234832763671875,
0.08453369140625,
0.03497314453125,
0.05072021484375,
-0.02191162109375,
0.06683349609375,
0.007717132568359375,
0.0205535888671875,
-0.05059814453125,
0.03662109375,
-0.00978851318359375,
-0.0560302734375,
-0.017822265625,
-0.05474853515625,
-0.06451416015625,
0.01476287841796875,
-0.00322723388671875,
-0.033111572265625,
0.037078857421875,
0.0237579345703125,
-0.05072021484375,
0.0272369384765625,
-0.036529541015625,
0.0787353515625,
0.0020198822021484375,
-0.026885986328125,
-0.001789093017578125,
-0.031982421875,
0.01385498046875,
-0.0008268356323242188,
-0.0107269287109375,
0.02215576171875,
-0.009063720703125,
0.06988525390625,
-0.045684814453125,
0.0567626953125,
-0.03515625,
0.029632568359375,
0.0196380615234375,
-0.00003403425216674805,
0.04791259765625,
0.0304718017578125,
0.005329132080078125,
0.028961181640625,
-0.003421783447265625,
-0.04168701171875,
-0.0262298583984375,
0.054473876953125,
-0.08135986328125,
-0.0242919921875,
-0.044097900390625,
-0.047576904296875,
-0.0007295608520507812,
0.0200347900390625,
0.05975341796875,
0.047698974609375,
-0.0052490234375,
0.006320953369140625,
0.042816162109375,
0.01275634765625,
0.06060791015625,
0.030975341796875,
-0.007656097412109375,
-0.050323486328125,
0.052642822265625,
0.00817108154296875,
0.0019025802612304688,
-0.0140380859375,
0.0118408203125,
-0.046051025390625,
-0.0306854248046875,
-0.05218505859375,
0.0391845703125,
-0.034942626953125,
-0.03533935546875,
-0.06011962890625,
-0.029327392578125,
-0.034027099609375,
0.007099151611328125,
-0.0513916015625,
-0.0240020751953125,
-0.052032470703125,
-0.005077362060546875,
0.0242767333984375,
0.048828125,
-0.017364501953125,
0.047882080078125,
-0.06304931640625,
0.01497650146484375,
0.034820556640625,
0.0005397796630859375,
0.0021419525146484375,
-0.071044921875,
-0.033233642578125,
0.0008568763732910156,
-0.0219573974609375,
-0.045440673828125,
0.036712646484375,
0.0107269287109375,
0.0255279541015625,
0.045501708984375,
-0.01548004150390625,
0.0408935546875,
-0.02313232421875,
0.054412841796875,
0.0088653564453125,
-0.0533447265625,
0.037689208984375,
-0.0411376953125,
0.0333251953125,
0.039215087890625,
0.0311431884765625,
-0.0054779052734375,
-0.00975799560546875,
-0.0780029296875,
-0.0751953125,
0.05706787109375,
0.014862060546875,
0.00555419921875,
-0.0062408447265625,
0.032806396484375,
0.006549835205078125,
0.0162200927734375,
-0.06744384765625,
-0.0160675048828125,
-0.0300750732421875,
-0.016815185546875,
-0.007080078125,
-0.0147705078125,
-0.01776123046875,
-0.035430908203125,
0.06781005859375,
-0.01531982421875,
0.040924072265625,
0.01239013671875,
-0.00794219970703125,
0.0033206939697265625,
-0.00897216796875,
0.033233642578125,
0.047210693359375,
-0.027801513671875,
-0.012054443359375,
0.01837158203125,
-0.03253173828125,
0.011260986328125,
0.035888671875,
-0.0279998779296875,
0.01065826416015625,
0.006649017333984375,
0.082275390625,
0.0015649795532226562,
0.0087432861328125,
0.0309295654296875,
-0.0207061767578125,
-0.0165252685546875,
-0.033050537109375,
0.004711151123046875,
-0.0158538818359375,
0.00824737548828125,
0.034942626953125,
0.0029964447021484375,
0.0110321044921875,
-0.01212310791015625,
0.017181396484375,
0.0240478515625,
-0.031829833984375,
-0.021514892578125,
0.0579833984375,
-0.0016202926635742188,
-0.00644683837890625,
0.07025146484375,
-0.03485107421875,
-0.029205322265625,
0.046539306640625,
0.04547119140625,
0.07366943359375,
0.0009598731994628906,
0.0072021484375,
0.052459716796875,
0.0256500244140625,
-0.0074615478515625,
0.00853729248046875,
-0.01432037353515625,
-0.048919677734375,
-0.0252532958984375,
-0.07781982421875,
-0.007465362548828125,
0.03033447265625,
-0.052337646484375,
0.0203399658203125,
-0.043975830078125,
-0.042877197265625,
-0.0109405517578125,
0.017822265625,
-0.07928466796875,
0.028594970703125,
-0.0031986236572265625,
0.056243896484375,
-0.08746337890625,
0.0626220703125,
0.0479736328125,
-0.03204345703125,
-0.0714111328125,
-0.0007719993591308594,
-0.0161895751953125,
-0.05120849609375,
0.04168701171875,
-0.0021953582763671875,
0.0086822509765625,
0.02618408203125,
-0.033660888671875,
-0.06378173828125,
0.083984375,
0.01267242431640625,
-0.040191650390625,
-0.027191162109375,
0.0157012939453125,
0.0426025390625,
-0.0308380126953125,
0.035552978515625,
0.031982421875,
0.0234222412109375,
-0.0224761962890625,
-0.048553466796875,
-0.00421905517578125,
-0.0180816650390625,
0.0198974609375,
0.014801025390625,
-0.050323486328125,
0.08251953125,
-0.004314422607421875,
0.01305389404296875,
0.01727294921875,
0.06341552734375,
0.0361328125,
0.011260986328125,
0.041656494140625,
0.07611083984375,
0.031524658203125,
-0.016265869140625,
0.08258056640625,
-0.03607177734375,
0.07269287109375,
0.078857421875,
0.013092041015625,
0.027618408203125,
0.02001953125,
0.00296783447265625,
0.0228729248046875,
0.057403564453125,
-0.0250701904296875,
0.046173095703125,
-0.00799560546875,
-0.0107574462890625,
-0.0214996337890625,
0.00531005859375,
-0.044921875,
0.0182342529296875,
0.0303497314453125,
-0.04229736328125,
-0.01849365234375,
0.0097503662109375,
-0.0043792724609375,
-0.0501708984375,
-0.026153564453125,
0.041107177734375,
0.0046539306640625,
-0.0258941650390625,
0.050933837890625,
-0.0005049705505371094,
0.050506591796875,
-0.05096435546875,
0.019073486328125,
-0.01776123046875,
0.02850341796875,
0.0022258758544921875,
-0.03948974609375,
0.00928497314453125,
-0.00470733642578125,
-0.033355712890625,
-0.007305145263671875,
0.042022705078125,
-0.0216522216796875,
-0.04937744140625,
0.0201568603515625,
0.024200439453125,
0.0017805099487304688,
-0.0046844482421875,
-0.0732421875,
-0.0227203369140625,
-0.017364501953125,
-0.053009033203125,
0.01274871826171875,
0.03594970703125,
0.02276611328125,
0.0361328125,
0.047149658203125,
0.005970001220703125,
0.021759033203125,
0.0026264190673828125,
0.07073974609375,
-0.042083740234375,
-0.05120849609375,
-0.052032470703125,
0.03271484375,
-0.00551605224609375,
-0.06365966796875,
0.052642822265625,
0.06585693359375,
0.06585693359375,
-0.01537322998046875,
0.0270843505859375,
0.0012521743774414062,
0.0233612060546875,
-0.03533935546875,
0.0513916015625,
-0.039520263671875,
0.005374908447265625,
-0.004734039306640625,
-0.09442138671875,
0.0207366943359375,
0.03900146484375,
-0.0228271484375,
0.023529052734375,
0.05413818359375,
0.07025146484375,
-0.041839599609375,
-0.00676727294921875,
0.007106781005859375,
0.035369873046875,
0.0045928955078125,
0.032623291015625,
0.048736572265625,
-0.06658935546875,
0.037841796875,
-0.042083740234375,
-0.004428863525390625,
-0.0007486343383789062,
-0.0379638671875,
-0.044677734375,
-0.0301513671875,
-0.0298309326171875,
-0.046783447265625,
-0.0088653564453125,
0.07366943359375,
0.06475830078125,
-0.0634765625,
-0.013336181640625,
-0.018951416015625,
-0.029937744140625,
0.0009589195251464844,
-0.02191162109375,
0.047088623046875,
-0.0267181396484375,
-0.0584716796875,
0.0235443115234375,
-0.01073455810546875,
0.0179901123046875,
-0.0241546630859375,
-0.0214385986328125,
-0.00829315185546875,
-0.0045928955078125,
0.0165863037109375,
0.011016845703125,
-0.0218353271484375,
-0.01525115966796875,
-0.007640838623046875,
-0.03131103515625,
0.006549835205078125,
0.04486083984375,
-0.05548095703125,
0.0150146484375,
0.0305328369140625,
0.023834228515625,
0.0697021484375,
-0.005764007568359375,
0.0196380615234375,
-0.0623779296875,
0.0280303955078125,
0.0212249755859375,
0.050567626953125,
0.020050048828125,
-0.0246734619140625,
0.0307769775390625,
0.043060302734375,
-0.0535888671875,
-0.0548095703125,
-0.004852294921875,
-0.054962158203125,
-0.0032634735107421875,
0.08203125,
-0.01332855224609375,
-0.0282135009765625,
0.00478363037109375,
0.0009202957153320312,
0.04150390625,
-0.0214080810546875,
0.058074951171875,
0.0311737060546875,
0.00006335973739624023,
-0.0007710456848144531,
-0.020355224609375,
0.043060302734375,
0.040191650390625,
-0.0428466796875,
-0.005615234375,
0.0278778076171875,
0.0278167724609375,
0.021759033203125,
0.043060302734375,
-0.0140533447265625,
0.021148681640625,
0.01346588134765625,
0.0037517547607421875,
-0.0226898193359375,
-0.0379638671875,
-0.033355712890625,
0.01493072509765625,
-0.0105743408203125,
-0.02764892578125
]
] |
intfloat/multilingual-e5-base | 2023-09-08T08:05:30.000Z | [
"sentence-transformers",
"pytorch",
"onnx",
"safetensors",
"xlm-roberta",
"mteb",
"Sentence Transformers",
"sentence-similarity",
"multilingual",
"af",
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gu",
"ha",
"he",
"hi",
"hr",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"ne",
"nl",
"no",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"th",
"tl",
"tr",
"ug",
"uk",
"ur",
"uz",
"vi",
"xh",
"yi",
"zh",
"arxiv:2212.03533",
"arxiv:2108.08787",
"arxiv:2104.08663",
"arxiv:2210.07316",
"license:mit",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | sentence-similarity | intfloat | null | null | intfloat/multilingual-e5-base | 113 | 39,565 | sentence-transformers | 2023-05-19T10:26:40 | ---
tags:
- mteb
- Sentence Transformers
- sentence-similarity
- sentence-transformers
model-index:
- name: multilingual-e5-base
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 78.97014925373135
- type: ap
value: 43.69351129103008
- type: f1
value: 73.38075030070492
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (de)
config: de
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 71.7237687366167
- type: ap
value: 82.22089859962671
- type: f1
value: 69.95532758884401
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en-ext)
config: en-ext
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 79.65517241379312
- type: ap
value: 28.507918657094738
- type: f1
value: 66.84516013726119
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (ja)
config: ja
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 73.32976445396146
- type: ap
value: 20.720481637566014
- type: f1
value: 59.78002763416003
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 90.63775
- type: ap
value: 87.22277903861716
- type: f1
value: 90.60378636386807
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 44.546
- type: f1
value: 44.05666638370923
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (de)
config: de
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 41.828
- type: f1
value: 41.2710255644252
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (es)
config: es
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 40.534
- type: f1
value: 39.820743174270326
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (fr)
config: fr
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 39.684
- type: f1
value: 39.11052682815307
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (ja)
config: ja
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 37.436
- type: f1
value: 37.07082931930871
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (zh)
config: zh
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 37.226000000000006
- type: f1
value: 36.65372077739185
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 22.831000000000003
- type: map_at_10
value: 36.42
- type: map_at_100
value: 37.699
- type: map_at_1000
value: 37.724000000000004
- type: map_at_3
value: 32.207
- type: map_at_5
value: 34.312
- type: mrr_at_1
value: 23.257
- type: mrr_at_10
value: 36.574
- type: mrr_at_100
value: 37.854
- type: mrr_at_1000
value: 37.878
- type: mrr_at_3
value: 32.385000000000005
- type: mrr_at_5
value: 34.48
- type: ndcg_at_1
value: 22.831000000000003
- type: ndcg_at_10
value: 44.230000000000004
- type: ndcg_at_100
value: 49.974000000000004
- type: ndcg_at_1000
value: 50.522999999999996
- type: ndcg_at_3
value: 35.363
- type: ndcg_at_5
value: 39.164
- type: precision_at_1
value: 22.831000000000003
- type: precision_at_10
value: 6.935
- type: precision_at_100
value: 0.9520000000000001
- type: precision_at_1000
value: 0.099
- type: precision_at_3
value: 14.841
- type: precision_at_5
value: 10.754
- type: recall_at_1
value: 22.831000000000003
- type: recall_at_10
value: 69.346
- type: recall_at_100
value: 95.235
- type: recall_at_1000
value: 99.36
- type: recall_at_3
value: 44.523
- type: recall_at_5
value: 53.769999999999996
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 40.27789869854063
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 35.41979463347428
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 58.22752045109304
- type: mrr
value: 71.51112430198303
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 84.71147646622866
- type: cos_sim_spearman
value: 85.059167046486
- type: euclidean_pearson
value: 75.88421613600647
- type: euclidean_spearman
value: 75.12821787150585
- type: manhattan_pearson
value: 75.22005646957604
- type: manhattan_spearman
value: 74.42880434453272
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (de-en)
config: de-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 99.23799582463465
- type: f1
value: 99.12665274878218
- type: precision
value: 99.07098121085595
- type: recall
value: 99.23799582463465
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (fr-en)
config: fr-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 97.88685890380806
- type: f1
value: 97.59336708489249
- type: precision
value: 97.44662117543473
- type: recall
value: 97.88685890380806
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (ru-en)
config: ru-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 97.47142362313821
- type: f1
value: 97.1989377670015
- type: precision
value: 97.06384944001847
- type: recall
value: 97.47142362313821
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (zh-en)
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy
value: 98.4728804634018
- type: f1
value: 98.2973494821836
- type: precision
value: 98.2095839915745
- type: recall
value: 98.4728804634018
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 82.74025974025975
- type: f1
value: 82.67420447730439
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 35.0380848063507
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 29.45956405670166
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 32.122
- type: map_at_10
value: 42.03
- type: map_at_100
value: 43.364000000000004
- type: map_at_1000
value: 43.474000000000004
- type: map_at_3
value: 38.804
- type: map_at_5
value: 40.585
- type: mrr_at_1
value: 39.914
- type: mrr_at_10
value: 48.227
- type: mrr_at_100
value: 49.018
- type: mrr_at_1000
value: 49.064
- type: mrr_at_3
value: 45.994
- type: mrr_at_5
value: 47.396
- type: ndcg_at_1
value: 39.914
- type: ndcg_at_10
value: 47.825
- type: ndcg_at_100
value: 52.852
- type: ndcg_at_1000
value: 54.891
- type: ndcg_at_3
value: 43.517
- type: ndcg_at_5
value: 45.493
- type: precision_at_1
value: 39.914
- type: precision_at_10
value: 8.956
- type: precision_at_100
value: 1.388
- type: precision_at_1000
value: 0.182
- type: precision_at_3
value: 20.791999999999998
- type: precision_at_5
value: 14.821000000000002
- type: recall_at_1
value: 32.122
- type: recall_at_10
value: 58.294999999999995
- type: recall_at_100
value: 79.726
- type: recall_at_1000
value: 93.099
- type: recall_at_3
value: 45.017
- type: recall_at_5
value: 51.002
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 29.677999999999997
- type: map_at_10
value: 38.684000000000005
- type: map_at_100
value: 39.812999999999995
- type: map_at_1000
value: 39.945
- type: map_at_3
value: 35.831
- type: map_at_5
value: 37.446
- type: mrr_at_1
value: 37.771
- type: mrr_at_10
value: 44.936
- type: mrr_at_100
value: 45.583
- type: mrr_at_1000
value: 45.634
- type: mrr_at_3
value: 42.771
- type: mrr_at_5
value: 43.994
- type: ndcg_at_1
value: 37.771
- type: ndcg_at_10
value: 44.059
- type: ndcg_at_100
value: 48.192
- type: ndcg_at_1000
value: 50.375
- type: ndcg_at_3
value: 40.172000000000004
- type: ndcg_at_5
value: 41.899
- type: precision_at_1
value: 37.771
- type: precision_at_10
value: 8.286999999999999
- type: precision_at_100
value: 1.322
- type: precision_at_1000
value: 0.178
- type: precision_at_3
value: 19.406000000000002
- type: precision_at_5
value: 13.745
- type: recall_at_1
value: 29.677999999999997
- type: recall_at_10
value: 53.071
- type: recall_at_100
value: 70.812
- type: recall_at_1000
value: 84.841
- type: recall_at_3
value: 41.016000000000005
- type: recall_at_5
value: 46.22
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 42.675000000000004
- type: map_at_10
value: 53.93599999999999
- type: map_at_100
value: 54.806999999999995
- type: map_at_1000
value: 54.867
- type: map_at_3
value: 50.934000000000005
- type: map_at_5
value: 52.583
- type: mrr_at_1
value: 48.339
- type: mrr_at_10
value: 57.265
- type: mrr_at_100
value: 57.873
- type: mrr_at_1000
value: 57.906
- type: mrr_at_3
value: 55.193000000000005
- type: mrr_at_5
value: 56.303000000000004
- type: ndcg_at_1
value: 48.339
- type: ndcg_at_10
value: 59.19799999999999
- type: ndcg_at_100
value: 62.743
- type: ndcg_at_1000
value: 63.99399999999999
- type: ndcg_at_3
value: 54.367
- type: ndcg_at_5
value: 56.548
- type: precision_at_1
value: 48.339
- type: precision_at_10
value: 9.216000000000001
- type: precision_at_100
value: 1.1809999999999998
- type: precision_at_1000
value: 0.134
- type: precision_at_3
value: 23.72
- type: precision_at_5
value: 16.025
- type: recall_at_1
value: 42.675000000000004
- type: recall_at_10
value: 71.437
- type: recall_at_100
value: 86.803
- type: recall_at_1000
value: 95.581
- type: recall_at_3
value: 58.434
- type: recall_at_5
value: 63.754
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.518
- type: map_at_10
value: 30.648999999999997
- type: map_at_100
value: 31.508999999999997
- type: map_at_1000
value: 31.604
- type: map_at_3
value: 28.247
- type: map_at_5
value: 29.65
- type: mrr_at_1
value: 25.650000000000002
- type: mrr_at_10
value: 32.771
- type: mrr_at_100
value: 33.554
- type: mrr_at_1000
value: 33.629999999999995
- type: mrr_at_3
value: 30.433
- type: mrr_at_5
value: 31.812
- type: ndcg_at_1
value: 25.650000000000002
- type: ndcg_at_10
value: 34.929
- type: ndcg_at_100
value: 39.382
- type: ndcg_at_1000
value: 41.913
- type: ndcg_at_3
value: 30.292
- type: ndcg_at_5
value: 32.629999999999995
- type: precision_at_1
value: 25.650000000000002
- type: precision_at_10
value: 5.311
- type: precision_at_100
value: 0.792
- type: precision_at_1000
value: 0.105
- type: precision_at_3
value: 12.58
- type: precision_at_5
value: 8.994
- type: recall_at_1
value: 23.518
- type: recall_at_10
value: 46.19
- type: recall_at_100
value: 67.123
- type: recall_at_1000
value: 86.442
- type: recall_at_3
value: 33.678000000000004
- type: recall_at_5
value: 39.244
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 15.891
- type: map_at_10
value: 22.464000000000002
- type: map_at_100
value: 23.483
- type: map_at_1000
value: 23.613
- type: map_at_3
value: 20.080000000000002
- type: map_at_5
value: 21.526
- type: mrr_at_1
value: 20.025000000000002
- type: mrr_at_10
value: 26.712999999999997
- type: mrr_at_100
value: 27.650000000000002
- type: mrr_at_1000
value: 27.737000000000002
- type: mrr_at_3
value: 24.274
- type: mrr_at_5
value: 25.711000000000002
- type: ndcg_at_1
value: 20.025000000000002
- type: ndcg_at_10
value: 27.028999999999996
- type: ndcg_at_100
value: 32.064
- type: ndcg_at_1000
value: 35.188
- type: ndcg_at_3
value: 22.512999999999998
- type: ndcg_at_5
value: 24.89
- type: precision_at_1
value: 20.025000000000002
- type: precision_at_10
value: 4.776
- type: precision_at_100
value: 0.8500000000000001
- type: precision_at_1000
value: 0.125
- type: precision_at_3
value: 10.531
- type: precision_at_5
value: 7.811
- type: recall_at_1
value: 15.891
- type: recall_at_10
value: 37.261
- type: recall_at_100
value: 59.12
- type: recall_at_1000
value: 81.356
- type: recall_at_3
value: 24.741
- type: recall_at_5
value: 30.753999999999998
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 27.544
- type: map_at_10
value: 36.283
- type: map_at_100
value: 37.467
- type: map_at_1000
value: 37.574000000000005
- type: map_at_3
value: 33.528999999999996
- type: map_at_5
value: 35.028999999999996
- type: mrr_at_1
value: 34.166999999999994
- type: mrr_at_10
value: 41.866
- type: mrr_at_100
value: 42.666
- type: mrr_at_1000
value: 42.716
- type: mrr_at_3
value: 39.541
- type: mrr_at_5
value: 40.768
- type: ndcg_at_1
value: 34.166999999999994
- type: ndcg_at_10
value: 41.577
- type: ndcg_at_100
value: 46.687
- type: ndcg_at_1000
value: 48.967
- type: ndcg_at_3
value: 37.177
- type: ndcg_at_5
value: 39.097
- type: precision_at_1
value: 34.166999999999994
- type: precision_at_10
value: 7.420999999999999
- type: precision_at_100
value: 1.165
- type: precision_at_1000
value: 0.154
- type: precision_at_3
value: 17.291999999999998
- type: precision_at_5
value: 12.166
- type: recall_at_1
value: 27.544
- type: recall_at_10
value: 51.99399999999999
- type: recall_at_100
value: 73.738
- type: recall_at_1000
value: 89.33
- type: recall_at_3
value: 39.179
- type: recall_at_5
value: 44.385999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 26.661
- type: map_at_10
value: 35.475
- type: map_at_100
value: 36.626999999999995
- type: map_at_1000
value: 36.741
- type: map_at_3
value: 32.818000000000005
- type: map_at_5
value: 34.397
- type: mrr_at_1
value: 32.647999999999996
- type: mrr_at_10
value: 40.784
- type: mrr_at_100
value: 41.602
- type: mrr_at_1000
value: 41.661
- type: mrr_at_3
value: 38.68
- type: mrr_at_5
value: 39.838
- type: ndcg_at_1
value: 32.647999999999996
- type: ndcg_at_10
value: 40.697
- type: ndcg_at_100
value: 45.799
- type: ndcg_at_1000
value: 48.235
- type: ndcg_at_3
value: 36.516
- type: ndcg_at_5
value: 38.515
- type: precision_at_1
value: 32.647999999999996
- type: precision_at_10
value: 7.202999999999999
- type: precision_at_100
value: 1.1360000000000001
- type: precision_at_1000
value: 0.151
- type: precision_at_3
value: 17.314
- type: precision_at_5
value: 12.145999999999999
- type: recall_at_1
value: 26.661
- type: recall_at_10
value: 50.995000000000005
- type: recall_at_100
value: 73.065
- type: recall_at_1000
value: 89.781
- type: recall_at_3
value: 39.073
- type: recall_at_5
value: 44.395
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.946583333333333
- type: map_at_10
value: 33.79725
- type: map_at_100
value: 34.86408333333333
- type: map_at_1000
value: 34.9795
- type: map_at_3
value: 31.259999999999998
- type: map_at_5
value: 32.71541666666666
- type: mrr_at_1
value: 30.863749999999996
- type: mrr_at_10
value: 37.99183333333333
- type: mrr_at_100
value: 38.790499999999994
- type: mrr_at_1000
value: 38.85575000000001
- type: mrr_at_3
value: 35.82083333333333
- type: mrr_at_5
value: 37.07533333333333
- type: ndcg_at_1
value: 30.863749999999996
- type: ndcg_at_10
value: 38.52141666666667
- type: ndcg_at_100
value: 43.17966666666667
- type: ndcg_at_1000
value: 45.64608333333333
- type: ndcg_at_3
value: 34.333000000000006
- type: ndcg_at_5
value: 36.34975
- type: precision_at_1
value: 30.863749999999996
- type: precision_at_10
value: 6.598999999999999
- type: precision_at_100
value: 1.0502500000000001
- type: precision_at_1000
value: 0.14400000000000002
- type: precision_at_3
value: 15.557583333333334
- type: precision_at_5
value: 11.020000000000001
- type: recall_at_1
value: 25.946583333333333
- type: recall_at_10
value: 48.36991666666666
- type: recall_at_100
value: 69.02408333333334
- type: recall_at_1000
value: 86.43858333333331
- type: recall_at_3
value: 36.4965
- type: recall_at_5
value: 41.76258333333334
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 22.431
- type: map_at_10
value: 28.889
- type: map_at_100
value: 29.642000000000003
- type: map_at_1000
value: 29.742
- type: map_at_3
value: 26.998
- type: map_at_5
value: 28.172000000000004
- type: mrr_at_1
value: 25.307000000000002
- type: mrr_at_10
value: 31.763
- type: mrr_at_100
value: 32.443
- type: mrr_at_1000
value: 32.531
- type: mrr_at_3
value: 29.959000000000003
- type: mrr_at_5
value: 31.063000000000002
- type: ndcg_at_1
value: 25.307000000000002
- type: ndcg_at_10
value: 32.586999999999996
- type: ndcg_at_100
value: 36.5
- type: ndcg_at_1000
value: 39.133
- type: ndcg_at_3
value: 29.25
- type: ndcg_at_5
value: 31.023
- type: precision_at_1
value: 25.307000000000002
- type: precision_at_10
value: 4.954
- type: precision_at_100
value: 0.747
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 12.577
- type: precision_at_5
value: 8.741999999999999
- type: recall_at_1
value: 22.431
- type: recall_at_10
value: 41.134
- type: recall_at_100
value: 59.28600000000001
- type: recall_at_1000
value: 78.857
- type: recall_at_3
value: 31.926
- type: recall_at_5
value: 36.335
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 17.586
- type: map_at_10
value: 23.304
- type: map_at_100
value: 24.159
- type: map_at_1000
value: 24.281
- type: map_at_3
value: 21.316
- type: map_at_5
value: 22.383
- type: mrr_at_1
value: 21.645
- type: mrr_at_10
value: 27.365000000000002
- type: mrr_at_100
value: 28.108
- type: mrr_at_1000
value: 28.192
- type: mrr_at_3
value: 25.482
- type: mrr_at_5
value: 26.479999999999997
- type: ndcg_at_1
value: 21.645
- type: ndcg_at_10
value: 27.306
- type: ndcg_at_100
value: 31.496000000000002
- type: ndcg_at_1000
value: 34.53
- type: ndcg_at_3
value: 23.73
- type: ndcg_at_5
value: 25.294
- type: precision_at_1
value: 21.645
- type: precision_at_10
value: 4.797
- type: precision_at_100
value: 0.8059999999999999
- type: precision_at_1000
value: 0.121
- type: precision_at_3
value: 10.850999999999999
- type: precision_at_5
value: 7.736
- type: recall_at_1
value: 17.586
- type: recall_at_10
value: 35.481
- type: recall_at_100
value: 54.534000000000006
- type: recall_at_1000
value: 76.456
- type: recall_at_3
value: 25.335
- type: recall_at_5
value: 29.473
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.095
- type: map_at_10
value: 32.374
- type: map_at_100
value: 33.537
- type: map_at_1000
value: 33.634
- type: map_at_3
value: 30.089
- type: map_at_5
value: 31.433
- type: mrr_at_1
value: 29.198
- type: mrr_at_10
value: 36.01
- type: mrr_at_100
value: 37.022
- type: mrr_at_1000
value: 37.083
- type: mrr_at_3
value: 33.94
- type: mrr_at_5
value: 35.148
- type: ndcg_at_1
value: 29.198
- type: ndcg_at_10
value: 36.729
- type: ndcg_at_100
value: 42.114000000000004
- type: ndcg_at_1000
value: 44.592
- type: ndcg_at_3
value: 32.644
- type: ndcg_at_5
value: 34.652
- type: precision_at_1
value: 29.198
- type: precision_at_10
value: 5.970000000000001
- type: precision_at_100
value: 0.967
- type: precision_at_1000
value: 0.129
- type: precision_at_3
value: 14.396999999999998
- type: precision_at_5
value: 10.093
- type: recall_at_1
value: 25.095
- type: recall_at_10
value: 46.392
- type: recall_at_100
value: 69.706
- type: recall_at_1000
value: 87.738
- type: recall_at_3
value: 35.303000000000004
- type: recall_at_5
value: 40.441
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 26.857999999999997
- type: map_at_10
value: 34.066
- type: map_at_100
value: 35.671
- type: map_at_1000
value: 35.881
- type: map_at_3
value: 31.304
- type: map_at_5
value: 32.885
- type: mrr_at_1
value: 32.411
- type: mrr_at_10
value: 38.987
- type: mrr_at_100
value: 39.894
- type: mrr_at_1000
value: 39.959
- type: mrr_at_3
value: 36.626999999999995
- type: mrr_at_5
value: 38.011
- type: ndcg_at_1
value: 32.411
- type: ndcg_at_10
value: 39.208
- type: ndcg_at_100
value: 44.626
- type: ndcg_at_1000
value: 47.43
- type: ndcg_at_3
value: 35.091
- type: ndcg_at_5
value: 37.119
- type: precision_at_1
value: 32.411
- type: precision_at_10
value: 7.51
- type: precision_at_100
value: 1.486
- type: precision_at_1000
value: 0.234
- type: precision_at_3
value: 16.14
- type: precision_at_5
value: 11.976
- type: recall_at_1
value: 26.857999999999997
- type: recall_at_10
value: 47.407
- type: recall_at_100
value: 72.236
- type: recall_at_1000
value: 90.77
- type: recall_at_3
value: 35.125
- type: recall_at_5
value: 40.522999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 21.3
- type: map_at_10
value: 27.412999999999997
- type: map_at_100
value: 28.29
- type: map_at_1000
value: 28.398
- type: map_at_3
value: 25.169999999999998
- type: map_at_5
value: 26.496
- type: mrr_at_1
value: 23.29
- type: mrr_at_10
value: 29.215000000000003
- type: mrr_at_100
value: 30.073
- type: mrr_at_1000
value: 30.156
- type: mrr_at_3
value: 26.956000000000003
- type: mrr_at_5
value: 28.38
- type: ndcg_at_1
value: 23.29
- type: ndcg_at_10
value: 31.113000000000003
- type: ndcg_at_100
value: 35.701
- type: ndcg_at_1000
value: 38.505
- type: ndcg_at_3
value: 26.727
- type: ndcg_at_5
value: 29.037000000000003
- type: precision_at_1
value: 23.29
- type: precision_at_10
value: 4.787
- type: precision_at_100
value: 0.763
- type: precision_at_1000
value: 0.11100000000000002
- type: precision_at_3
value: 11.091
- type: precision_at_5
value: 7.985
- type: recall_at_1
value: 21.3
- type: recall_at_10
value: 40.782000000000004
- type: recall_at_100
value: 62.13999999999999
- type: recall_at_1000
value: 83.012
- type: recall_at_3
value: 29.131
- type: recall_at_5
value: 34.624
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 9.631
- type: map_at_10
value: 16.634999999999998
- type: map_at_100
value: 18.23
- type: map_at_1000
value: 18.419
- type: map_at_3
value: 13.66
- type: map_at_5
value: 15.173
- type: mrr_at_1
value: 21.368000000000002
- type: mrr_at_10
value: 31.56
- type: mrr_at_100
value: 32.58
- type: mrr_at_1000
value: 32.633
- type: mrr_at_3
value: 28.241
- type: mrr_at_5
value: 30.225
- type: ndcg_at_1
value: 21.368000000000002
- type: ndcg_at_10
value: 23.855999999999998
- type: ndcg_at_100
value: 30.686999999999998
- type: ndcg_at_1000
value: 34.327000000000005
- type: ndcg_at_3
value: 18.781
- type: ndcg_at_5
value: 20.73
- type: precision_at_1
value: 21.368000000000002
- type: precision_at_10
value: 7.564
- type: precision_at_100
value: 1.496
- type: precision_at_1000
value: 0.217
- type: precision_at_3
value: 13.876
- type: precision_at_5
value: 11.062
- type: recall_at_1
value: 9.631
- type: recall_at_10
value: 29.517
- type: recall_at_100
value: 53.452
- type: recall_at_1000
value: 74.115
- type: recall_at_3
value: 17.605999999999998
- type: recall_at_5
value: 22.505
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.885
- type: map_at_10
value: 18.798000000000002
- type: map_at_100
value: 26.316
- type: map_at_1000
value: 27.869
- type: map_at_3
value: 13.719000000000001
- type: map_at_5
value: 15.716
- type: mrr_at_1
value: 66
- type: mrr_at_10
value: 74.263
- type: mrr_at_100
value: 74.519
- type: mrr_at_1000
value: 74.531
- type: mrr_at_3
value: 72.458
- type: mrr_at_5
value: 73.321
- type: ndcg_at_1
value: 53.87499999999999
- type: ndcg_at_10
value: 40.355999999999995
- type: ndcg_at_100
value: 44.366
- type: ndcg_at_1000
value: 51.771
- type: ndcg_at_3
value: 45.195
- type: ndcg_at_5
value: 42.187000000000005
- type: precision_at_1
value: 66
- type: precision_at_10
value: 31.75
- type: precision_at_100
value: 10.11
- type: precision_at_1000
value: 1.9800000000000002
- type: precision_at_3
value: 48.167
- type: precision_at_5
value: 40.050000000000004
- type: recall_at_1
value: 8.885
- type: recall_at_10
value: 24.471999999999998
- type: recall_at_100
value: 49.669000000000004
- type: recall_at_1000
value: 73.383
- type: recall_at_3
value: 14.872
- type: recall_at_5
value: 18.262999999999998
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 45.18
- type: f1
value: 40.26878691789978
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 62.751999999999995
- type: map_at_10
value: 74.131
- type: map_at_100
value: 74.407
- type: map_at_1000
value: 74.423
- type: map_at_3
value: 72.329
- type: map_at_5
value: 73.555
- type: mrr_at_1
value: 67.282
- type: mrr_at_10
value: 78.292
- type: mrr_at_100
value: 78.455
- type: mrr_at_1000
value: 78.458
- type: mrr_at_3
value: 76.755
- type: mrr_at_5
value: 77.839
- type: ndcg_at_1
value: 67.282
- type: ndcg_at_10
value: 79.443
- type: ndcg_at_100
value: 80.529
- type: ndcg_at_1000
value: 80.812
- type: ndcg_at_3
value: 76.281
- type: ndcg_at_5
value: 78.235
- type: precision_at_1
value: 67.282
- type: precision_at_10
value: 10.078
- type: precision_at_100
value: 1.082
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 30.178
- type: precision_at_5
value: 19.232
- type: recall_at_1
value: 62.751999999999995
- type: recall_at_10
value: 91.521
- type: recall_at_100
value: 95.997
- type: recall_at_1000
value: 97.775
- type: recall_at_3
value: 83.131
- type: recall_at_5
value: 87.93299999999999
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 18.861
- type: map_at_10
value: 30.252000000000002
- type: map_at_100
value: 32.082
- type: map_at_1000
value: 32.261
- type: map_at_3
value: 25.909
- type: map_at_5
value: 28.296
- type: mrr_at_1
value: 37.346000000000004
- type: mrr_at_10
value: 45.802
- type: mrr_at_100
value: 46.611999999999995
- type: mrr_at_1000
value: 46.659
- type: mrr_at_3
value: 43.056
- type: mrr_at_5
value: 44.637
- type: ndcg_at_1
value: 37.346000000000004
- type: ndcg_at_10
value: 38.169
- type: ndcg_at_100
value: 44.864
- type: ndcg_at_1000
value: 47.974
- type: ndcg_at_3
value: 33.619
- type: ndcg_at_5
value: 35.317
- type: precision_at_1
value: 37.346000000000004
- type: precision_at_10
value: 10.693999999999999
- type: precision_at_100
value: 1.775
- type: precision_at_1000
value: 0.231
- type: precision_at_3
value: 22.325
- type: precision_at_5
value: 16.852
- type: recall_at_1
value: 18.861
- type: recall_at_10
value: 45.672000000000004
- type: recall_at_100
value: 70.60499999999999
- type: recall_at_1000
value: 89.216
- type: recall_at_3
value: 30.361
- type: recall_at_5
value: 36.998999999999995
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 37.852999999999994
- type: map_at_10
value: 59.961
- type: map_at_100
value: 60.78
- type: map_at_1000
value: 60.843
- type: map_at_3
value: 56.39999999999999
- type: map_at_5
value: 58.646
- type: mrr_at_1
value: 75.70599999999999
- type: mrr_at_10
value: 82.321
- type: mrr_at_100
value: 82.516
- type: mrr_at_1000
value: 82.525
- type: mrr_at_3
value: 81.317
- type: mrr_at_5
value: 81.922
- type: ndcg_at_1
value: 75.70599999999999
- type: ndcg_at_10
value: 68.557
- type: ndcg_at_100
value: 71.485
- type: ndcg_at_1000
value: 72.71600000000001
- type: ndcg_at_3
value: 63.524
- type: ndcg_at_5
value: 66.338
- type: precision_at_1
value: 75.70599999999999
- type: precision_at_10
value: 14.463000000000001
- type: precision_at_100
value: 1.677
- type: precision_at_1000
value: 0.184
- type: precision_at_3
value: 40.806
- type: precision_at_5
value: 26.709
- type: recall_at_1
value: 37.852999999999994
- type: recall_at_10
value: 72.316
- type: recall_at_100
value: 83.842
- type: recall_at_1000
value: 91.999
- type: recall_at_3
value: 61.209
- type: recall_at_5
value: 66.77199999999999
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 85.46039999999999
- type: ap
value: 79.9812521351881
- type: f1
value: 85.31722909702084
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 22.704
- type: map_at_10
value: 35.329
- type: map_at_100
value: 36.494
- type: map_at_1000
value: 36.541000000000004
- type: map_at_3
value: 31.476
- type: map_at_5
value: 33.731
- type: mrr_at_1
value: 23.294999999999998
- type: mrr_at_10
value: 35.859
- type: mrr_at_100
value: 36.968
- type: mrr_at_1000
value: 37.008
- type: mrr_at_3
value: 32.085
- type: mrr_at_5
value: 34.299
- type: ndcg_at_1
value: 23.324
- type: ndcg_at_10
value: 42.274
- type: ndcg_at_100
value: 47.839999999999996
- type: ndcg_at_1000
value: 48.971
- type: ndcg_at_3
value: 34.454
- type: ndcg_at_5
value: 38.464
- type: precision_at_1
value: 23.324
- type: precision_at_10
value: 6.648
- type: precision_at_100
value: 0.9440000000000001
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 14.674999999999999
- type: precision_at_5
value: 10.850999999999999
- type: recall_at_1
value: 22.704
- type: recall_at_10
value: 63.660000000000004
- type: recall_at_100
value: 89.29899999999999
- type: recall_at_1000
value: 97.88900000000001
- type: recall_at_3
value: 42.441
- type: recall_at_5
value: 52.04
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 93.1326949384405
- type: f1
value: 92.89743579612082
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (de)
config: de
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 89.62524654832347
- type: f1
value: 88.65106082263151
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (es)
config: es
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 90.59039359573046
- type: f1
value: 90.31532892105662
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (fr)
config: fr
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 86.21046038208581
- type: f1
value: 86.41459529813113
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (hi)
config: hi
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 87.3180351380423
- type: f1
value: 86.71383078226444
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (th)
config: th
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 86.24231464737792
- type: f1
value: 86.31845567592403
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 75.27131782945736
- type: f1
value: 57.52079940417103
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (de)
config: de
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 71.2341504649197
- type: f1
value: 51.349951558039244
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (es)
config: es
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 71.27418278852569
- type: f1
value: 50.1714985749095
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (fr)
config: fr
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 67.68243031631694
- type: f1
value: 50.1066160836192
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (hi)
config: hi
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 69.2362854069559
- type: f1
value: 48.821279948766424
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (th)
config: th
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 71.71428571428571
- type: f1
value: 53.94611389496195
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (af)
config: af
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 59.97646267652992
- type: f1
value: 57.26797883561521
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (am)
config: am
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 53.65501008742435
- type: f1
value: 50.416258382177034
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ar)
config: ar
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 57.45796906523201
- type: f1
value: 53.306690547422185
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (az)
config: az
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.59246805648957
- type: f1
value: 59.818381969051494
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (bn)
config: bn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.126429051782104
- type: f1
value: 58.25993593933026
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (cy)
config: cy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 50.057162071284466
- type: f1
value: 46.96095728790911
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (da)
config: da
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.64425016812375
- type: f1
value: 62.858291698755764
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (de)
config: de
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.08944182918628
- type: f1
value: 62.44639030604241
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (el)
config: el
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.68056489576328
- type: f1
value: 61.775326758789504
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 72.11163416274377
- type: f1
value: 69.70789096927015
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (es)
config: es
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.40282447881641
- type: f1
value: 66.38492065671895
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fa)
config: fa
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.24613315400134
- type: f1
value: 64.3348019501336
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fi)
config: fi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.78345662407531
- type: f1
value: 62.21279452354622
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (fr)
config: fr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.9455279085407
- type: f1
value: 65.48193124964094
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (he)
config: he
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.05110961667788
- type: f1
value: 58.097856564684534
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hi)
config: hi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.95292535305985
- type: f1
value: 62.09182174767901
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hu)
config: hu
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.97310020174848
- type: f1
value: 61.14252567730396
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (hy)
config: hy
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.08069939475453
- type: f1
value: 57.044041742492034
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (id)
config: id
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.63752521856085
- type: f1
value: 63.889340907205316
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (is)
config: is
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 56.385339609952936
- type: f1
value: 53.449033750088304
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (it)
config: it
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.93073301950234
- type: f1
value: 65.9884357824104
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ja)
config: ja
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.94418291862812
- type: f1
value: 66.48740222583132
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (jv)
config: jv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 54.26025554808339
- type: f1
value: 50.19562815100793
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ka)
config: ka
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 48.98789509078682
- type: f1
value: 46.65788438676836
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (km)
config: km
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 44.68728984532616
- type: f1
value: 41.642419349541996
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (kn)
config: kn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 59.19300605245461
- type: f1
value: 55.8626492442437
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ko)
config: ko
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.33826496301278
- type: f1
value: 63.89499791648792
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (lv)
config: lv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.33960995292536
- type: f1
value: 57.15242464180892
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ml)
config: ml
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 63.09347679892402
- type: f1
value: 59.64733214063841
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (mn)
config: mn
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.75924680564896
- type: f1
value: 55.96585692366827
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ms)
config: ms
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.48486886348352
- type: f1
value: 59.45143559032946
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (my)
config: my
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.56422326832549
- type: f1
value: 54.96368702901926
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (nb)
config: nb
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.18022864828512
- type: f1
value: 63.05369805040634
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (nl)
config: nl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.30329522528581
- type: f1
value: 64.06084612020727
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (pl)
config: pl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.36919973100201
- type: f1
value: 65.12154124788887
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (pt)
config: pt
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.98117014122394
- type: f1
value: 66.41847559806962
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ro)
config: ro
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.53799596503026
- type: f1
value: 62.17067330740817
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ru)
config: ru
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.01815736381977
- type: f1
value: 66.24988369607843
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sl)
config: sl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 62.34700739744452
- type: f1
value: 59.957933424941636
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sq)
config: sq
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.23402824478815
- type: f1
value: 57.98836976018471
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sv)
config: sv
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 68.54068594485541
- type: f1
value: 65.43849680666855
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (sw)
config: sw
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 55.998655010087425
- type: f1
value: 52.83737515406804
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ta)
config: ta
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 58.71217215870882
- type: f1
value: 55.051794977833026
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (te)
config: te
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 59.724277067921996
- type: f1
value: 56.33485571838306
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (th)
config: th
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 65.59515803631473
- type: f1
value: 64.96772366193588
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (tl)
config: tl
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 60.860793544048406
- type: f1
value: 58.148845819115394
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (tr)
config: tr
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 67.40753194351043
- type: f1
value: 63.18903778054698
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (ur)
config: ur
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 61.52320107599194
- type: f1
value: 58.356144563398516
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (vi)
config: vi
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 66.17014122394083
- type: f1
value: 63.919964062638925
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-CN)
config: zh-CN
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 69.15601882985878
- type: f1
value: 67.01451905761371
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (zh-TW)
config: zh-TW
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 64.65030262273034
- type: f1
value: 64.14420425129063
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (af)
config: af
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 65.08742434431743
- type: f1
value: 63.044060042311756
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (am)
config: am
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 58.52387357094821
- type: f1
value: 56.82398588814534
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ar)
config: ar
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.239408204438476
- type: f1
value: 61.92570286170469
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (az)
config: az
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.74915938130463
- type: f1
value: 62.130740689396276
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (bn)
config: bn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 65.00336247478144
- type: f1
value: 63.71080635228055
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (cy)
config: cy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 52.837928715534645
- type: f1
value: 50.390741680320836
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (da)
config: da
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.42098184263618
- type: f1
value: 71.41355113538995
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (de)
config: de
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.95359784801613
- type: f1
value: 71.42699340156742
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (el)
config: el
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.18157363819772
- type: f1
value: 69.74836113037671
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 77.08137188971082
- type: f1
value: 76.78000685068261
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (es)
config: es
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.5030262273033
- type: f1
value: 71.71620130425673
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fa)
config: fa
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.24546065904505
- type: f1
value: 69.07638311730359
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fi)
config: fi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.12911903160726
- type: f1
value: 68.32651736539815
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (fr)
config: fr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.89307330195025
- type: f1
value: 71.33986549860187
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (he)
config: he
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 67.44451916610626
- type: f1
value: 66.90192664503866
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hi)
config: hi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.16274377942166
- type: f1
value: 68.01090953775066
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hu)
config: hu
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.75319435104237
- type: f1
value: 70.18035309201403
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (hy)
config: hy
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 63.14391392064559
- type: f1
value: 61.48286540778145
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (id)
config: id
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.70275722932078
- type: f1
value: 70.26164779846495
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (is)
config: is
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 60.93813046402153
- type: f1
value: 58.8852862116525
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (it)
config: it
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.320107599193
- type: f1
value: 72.19836409602924
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ja)
config: ja
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 74.65366509751176
- type: f1
value: 74.55188288799579
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (jv)
config: jv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 59.694014794889036
- type: f1
value: 58.11353311721067
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ka)
config: ka
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 54.37457969065231
- type: f1
value: 52.81306134311697
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (km)
config: km
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 48.3086751849361
- type: f1
value: 45.396449765419376
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (kn)
config: kn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.151983860121064
- type: f1
value: 60.31762544281696
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ko)
config: ko
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.44788164088769
- type: f1
value: 71.68150151736367
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (lv)
config: lv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.81439139206455
- type: f1
value: 62.06735559105593
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ml)
config: ml
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 68.04303967720242
- type: f1
value: 66.68298851670133
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (mn)
config: mn
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 61.43913920645595
- type: f1
value: 60.25605977560783
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ms)
config: ms
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.90316072629456
- type: f1
value: 65.1325924692381
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (my)
config: my
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 61.63752521856086
- type: f1
value: 59.14284778039585
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (nb)
config: nb
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.63080026899797
- type: f1
value: 70.89771864626877
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (nl)
config: nl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.10827168796234
- type: f1
value: 71.71954219691159
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (pl)
config: pl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.59515803631471
- type: f1
value: 70.05040128099003
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (pt)
config: pt
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.83389374579691
- type: f1
value: 70.84877936562735
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ro)
config: ro
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 69.18628110289173
- type: f1
value: 68.97232927921841
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ru)
config: ru
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 72.99260255548083
- type: f1
value: 72.85139492157732
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sl)
config: sl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 65.26227303295225
- type: f1
value: 65.08833655469431
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sq)
config: sq
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 66.48621385339611
- type: f1
value: 64.43483199071298
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sv)
config: sv
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 73.14391392064559
- type: f1
value: 72.2580822579741
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (sw)
config: sw
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 59.88567585743107
- type: f1
value: 58.3073765932569
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ta)
config: ta
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.38399462004034
- type: f1
value: 60.82139544252606
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (te)
config: te
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.58574310692671
- type: f1
value: 60.71443370385374
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (th)
config: th
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.61398789509079
- type: f1
value: 70.99761812049401
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (tl)
config: tl
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 62.73705447209146
- type: f1
value: 61.680849331794796
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (tr)
config: tr
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 71.66778749159381
- type: f1
value: 71.17320646080115
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (ur)
config: ur
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 64.640215198386
- type: f1
value: 63.301805157015444
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (vi)
config: vi
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.00672494956288
- type: f1
value: 70.26005548582106
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-CN)
config: zh-CN
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 75.42030934767989
- type: f1
value: 75.2074842882598
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (zh-TW)
config: zh-TW
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 70.69266980497646
- type: f1
value: 70.94103167391192
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 28.91697191169135
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 28.434000079573313
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 30.96683513343383
- type: mrr
value: 31.967364078714834
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.5280000000000005
- type: map_at_10
value: 11.793
- type: map_at_100
value: 14.496999999999998
- type: map_at_1000
value: 15.783
- type: map_at_3
value: 8.838
- type: map_at_5
value: 10.07
- type: mrr_at_1
value: 43.653
- type: mrr_at_10
value: 51.531000000000006
- type: mrr_at_100
value: 52.205
- type: mrr_at_1000
value: 52.242999999999995
- type: mrr_at_3
value: 49.431999999999995
- type: mrr_at_5
value: 50.470000000000006
- type: ndcg_at_1
value: 42.415000000000006
- type: ndcg_at_10
value: 32.464999999999996
- type: ndcg_at_100
value: 28.927999999999997
- type: ndcg_at_1000
value: 37.629000000000005
- type: ndcg_at_3
value: 37.845
- type: ndcg_at_5
value: 35.147
- type: precision_at_1
value: 43.653
- type: precision_at_10
value: 23.932000000000002
- type: precision_at_100
value: 7.17
- type: precision_at_1000
value: 1.967
- type: precision_at_3
value: 35.397
- type: precision_at_5
value: 29.907
- type: recall_at_1
value: 5.5280000000000005
- type: recall_at_10
value: 15.568000000000001
- type: recall_at_100
value: 28.54
- type: recall_at_1000
value: 59.864
- type: recall_at_3
value: 9.822000000000001
- type: recall_at_5
value: 11.726
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 37.041000000000004
- type: map_at_10
value: 52.664
- type: map_at_100
value: 53.477
- type: map_at_1000
value: 53.505
- type: map_at_3
value: 48.510999999999996
- type: map_at_5
value: 51.036
- type: mrr_at_1
value: 41.338
- type: mrr_at_10
value: 55.071000000000005
- type: mrr_at_100
value: 55.672
- type: mrr_at_1000
value: 55.689
- type: mrr_at_3
value: 51.82
- type: mrr_at_5
value: 53.852
- type: ndcg_at_1
value: 41.338
- type: ndcg_at_10
value: 60.01800000000001
- type: ndcg_at_100
value: 63.409000000000006
- type: ndcg_at_1000
value: 64.017
- type: ndcg_at_3
value: 52.44799999999999
- type: ndcg_at_5
value: 56.571000000000005
- type: precision_at_1
value: 41.338
- type: precision_at_10
value: 9.531
- type: precision_at_100
value: 1.145
- type: precision_at_1000
value: 0.12
- type: precision_at_3
value: 23.416
- type: precision_at_5
value: 16.46
- type: recall_at_1
value: 37.041000000000004
- type: recall_at_10
value: 79.76299999999999
- type: recall_at_100
value: 94.39
- type: recall_at_1000
value: 98.851
- type: recall_at_3
value: 60.465
- type: recall_at_5
value: 69.906
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 69.952
- type: map_at_10
value: 83.758
- type: map_at_100
value: 84.406
- type: map_at_1000
value: 84.425
- type: map_at_3
value: 80.839
- type: map_at_5
value: 82.646
- type: mrr_at_1
value: 80.62
- type: mrr_at_10
value: 86.947
- type: mrr_at_100
value: 87.063
- type: mrr_at_1000
value: 87.064
- type: mrr_at_3
value: 85.96000000000001
- type: mrr_at_5
value: 86.619
- type: ndcg_at_1
value: 80.63
- type: ndcg_at_10
value: 87.64800000000001
- type: ndcg_at_100
value: 88.929
- type: ndcg_at_1000
value: 89.054
- type: ndcg_at_3
value: 84.765
- type: ndcg_at_5
value: 86.291
- type: precision_at_1
value: 80.63
- type: precision_at_10
value: 13.314
- type: precision_at_100
value: 1.525
- type: precision_at_1000
value: 0.157
- type: precision_at_3
value: 37.1
- type: precision_at_5
value: 24.372
- type: recall_at_1
value: 69.952
- type: recall_at_10
value: 94.955
- type: recall_at_100
value: 99.38
- type: recall_at_1000
value: 99.96000000000001
- type: recall_at_3
value: 86.60600000000001
- type: recall_at_5
value: 90.997
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 42.41329517878427
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 55.171278362748666
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.213
- type: map_at_10
value: 9.895
- type: map_at_100
value: 11.776
- type: map_at_1000
value: 12.084
- type: map_at_3
value: 7.2669999999999995
- type: map_at_5
value: 8.620999999999999
- type: mrr_at_1
value: 20.8
- type: mrr_at_10
value: 31.112000000000002
- type: mrr_at_100
value: 32.274
- type: mrr_at_1000
value: 32.35
- type: mrr_at_3
value: 28.133000000000003
- type: mrr_at_5
value: 29.892999999999997
- type: ndcg_at_1
value: 20.8
- type: ndcg_at_10
value: 17.163999999999998
- type: ndcg_at_100
value: 24.738
- type: ndcg_at_1000
value: 30.316
- type: ndcg_at_3
value: 16.665
- type: ndcg_at_5
value: 14.478
- type: precision_at_1
value: 20.8
- type: precision_at_10
value: 8.74
- type: precision_at_100
value: 1.963
- type: precision_at_1000
value: 0.33
- type: precision_at_3
value: 15.467
- type: precision_at_5
value: 12.6
- type: recall_at_1
value: 4.213
- type: recall_at_10
value: 17.698
- type: recall_at_100
value: 39.838
- type: recall_at_1000
value: 66.893
- type: recall_at_3
value: 9.418
- type: recall_at_5
value: 12.773000000000001
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 82.90453315738294
- type: cos_sim_spearman
value: 78.51197850080254
- type: euclidean_pearson
value: 80.09647123597748
- type: euclidean_spearman
value: 78.63548011514061
- type: manhattan_pearson
value: 80.10645285675231
- type: manhattan_spearman
value: 78.57861806068901
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 84.2616156846401
- type: cos_sim_spearman
value: 76.69713867850156
- type: euclidean_pearson
value: 77.97948563800394
- type: euclidean_spearman
value: 74.2371211567807
- type: manhattan_pearson
value: 77.69697879669705
- type: manhattan_spearman
value: 73.86529778022278
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 77.0293269315045
- type: cos_sim_spearman
value: 78.02555120584198
- type: euclidean_pearson
value: 78.25398100379078
- type: euclidean_spearman
value: 78.66963870599464
- type: manhattan_pearson
value: 78.14314682167348
- type: manhattan_spearman
value: 78.57692322969135
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 79.16989925136942
- type: cos_sim_spearman
value: 76.5996225327091
- type: euclidean_pearson
value: 77.8319003279786
- type: euclidean_spearman
value: 76.42824009468998
- type: manhattan_pearson
value: 77.69118862737736
- type: manhattan_spearman
value: 76.25568104762812
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 87.42012286935325
- type: cos_sim_spearman
value: 88.15654297884122
- type: euclidean_pearson
value: 87.34082819427852
- type: euclidean_spearman
value: 88.06333589547084
- type: manhattan_pearson
value: 87.25115596784842
- type: manhattan_spearman
value: 87.9559927695203
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 82.88222044996712
- type: cos_sim_spearman
value: 84.28476589061077
- type: euclidean_pearson
value: 83.17399758058309
- type: euclidean_spearman
value: 83.85497357244542
- type: manhattan_pearson
value: 83.0308397703786
- type: manhattan_spearman
value: 83.71554539935046
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (ko-ko)
config: ko-ko
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 80.20682986257339
- type: cos_sim_spearman
value: 79.94567120362092
- type: euclidean_pearson
value: 79.43122480368902
- type: euclidean_spearman
value: 79.94802077264987
- type: manhattan_pearson
value: 79.32653021527081
- type: manhattan_spearman
value: 79.80961146709178
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (ar-ar)
config: ar-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 74.46578144394383
- type: cos_sim_spearman
value: 74.52496637472179
- type: euclidean_pearson
value: 72.2903807076809
- type: euclidean_spearman
value: 73.55549359771645
- type: manhattan_pearson
value: 72.09324837709393
- type: manhattan_spearman
value: 73.36743103606581
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-ar)
config: en-ar
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 71.37272335116
- type: cos_sim_spearman
value: 71.26702117766037
- type: euclidean_pearson
value: 67.114829954434
- type: euclidean_spearman
value: 66.37938893947761
- type: manhattan_pearson
value: 66.79688574095246
- type: manhattan_spearman
value: 66.17292828079667
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-de)
config: en-de
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 80.61016770129092
- type: cos_sim_spearman
value: 82.08515426632214
- type: euclidean_pearson
value: 80.557340361131
- type: euclidean_spearman
value: 80.37585812266175
- type: manhattan_pearson
value: 80.6782873404285
- type: manhattan_spearman
value: 80.6678073032024
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-en)
config: en-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.00150745350108
- type: cos_sim_spearman
value: 87.83441972211425
- type: euclidean_pearson
value: 87.94826702308792
- type: euclidean_spearman
value: 87.46143974860725
- type: manhattan_pearson
value: 87.97560344306105
- type: manhattan_spearman
value: 87.5267102829796
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (en-tr)
config: en-tr
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 64.76325252267235
- type: cos_sim_spearman
value: 63.32615095463905
- type: euclidean_pearson
value: 64.07920669155716
- type: euclidean_spearman
value: 61.21409893072176
- type: manhattan_pearson
value: 64.26308625680016
- type: manhattan_spearman
value: 61.2438185254079
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (es-en)
config: es-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 75.82644463022595
- type: cos_sim_spearman
value: 76.50381269945073
- type: euclidean_pearson
value: 75.1328548315934
- type: euclidean_spearman
value: 75.63761139408453
- type: manhattan_pearson
value: 75.18610101241407
- type: manhattan_spearman
value: 75.30669266354164
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (es-es)
config: es-es
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 87.49994164686832
- type: cos_sim_spearman
value: 86.73743986245549
- type: euclidean_pearson
value: 86.8272894387145
- type: euclidean_spearman
value: 85.97608491000507
- type: manhattan_pearson
value: 86.74960140396779
- type: manhattan_spearman
value: 85.79285984190273
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (fr-en)
config: fr-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 79.58172210788469
- type: cos_sim_spearman
value: 80.17516468334607
- type: euclidean_pearson
value: 77.56537843470504
- type: euclidean_spearman
value: 77.57264627395521
- type: manhattan_pearson
value: 78.09703521695943
- type: manhattan_spearman
value: 78.15942760916954
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (it-en)
config: it-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 79.7589932931751
- type: cos_sim_spearman
value: 80.15210089028162
- type: euclidean_pearson
value: 77.54135223516057
- type: euclidean_spearman
value: 77.52697996368764
- type: manhattan_pearson
value: 77.65734439572518
- type: manhattan_spearman
value: 77.77702992016121
- task:
type: STS
dataset:
type: mteb/sts17-crosslingual-sts
name: MTEB STS17 (nl-en)
config: nl-en
split: test
revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d
metrics:
- type: cos_sim_pearson
value: 79.16682365511267
- type: cos_sim_spearman
value: 79.25311267628506
- type: euclidean_pearson
value: 77.54882036762244
- type: euclidean_spearman
value: 77.33212935194827
- type: manhattan_pearson
value: 77.98405516064015
- type: manhattan_spearman
value: 77.85075717865719
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (en)
config: en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 59.10473294775917
- type: cos_sim_spearman
value: 61.82780474476838
- type: euclidean_pearson
value: 45.885111672377256
- type: euclidean_spearman
value: 56.88306351932454
- type: manhattan_pearson
value: 46.101218127323186
- type: manhattan_spearman
value: 56.80953694186333
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de)
config: de
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 45.781923079584146
- type: cos_sim_spearman
value: 55.95098449691107
- type: euclidean_pearson
value: 25.4571031323205
- type: euclidean_spearman
value: 49.859978118078935
- type: manhattan_pearson
value: 25.624938455041384
- type: manhattan_spearman
value: 49.99546185049401
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es)
config: es
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 60.00618133997907
- type: cos_sim_spearman
value: 66.57896677718321
- type: euclidean_pearson
value: 42.60118466388821
- type: euclidean_spearman
value: 62.8210759715209
- type: manhattan_pearson
value: 42.63446860604094
- type: manhattan_spearman
value: 62.73803068925271
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (pl)
config: pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 28.460759121626943
- type: cos_sim_spearman
value: 34.13459007469131
- type: euclidean_pearson
value: 6.0917739325525195
- type: euclidean_spearman
value: 27.9947262664867
- type: manhattan_pearson
value: 6.16877864169911
- type: manhattan_spearman
value: 28.00664163971514
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (tr)
config: tr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 57.42546621771696
- type: cos_sim_spearman
value: 63.699663168970474
- type: euclidean_pearson
value: 38.12085278789738
- type: euclidean_spearman
value: 58.12329140741536
- type: manhattan_pearson
value: 37.97364549443335
- type: manhattan_spearman
value: 57.81545502318733
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (ar)
config: ar
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 46.82241380954213
- type: cos_sim_spearman
value: 57.86569456006391
- type: euclidean_pearson
value: 31.80480070178813
- type: euclidean_spearman
value: 52.484000620130104
- type: manhattan_pearson
value: 31.952708554646097
- type: manhattan_spearman
value: 52.8560972356195
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (ru)
config: ru
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 52.00447170498087
- type: cos_sim_spearman
value: 60.664116225735164
- type: euclidean_pearson
value: 33.87382555421702
- type: euclidean_spearman
value: 55.74649067458667
- type: manhattan_pearson
value: 33.99117246759437
- type: manhattan_spearman
value: 55.98749034923899
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh)
config: zh
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 58.06497233105448
- type: cos_sim_spearman
value: 65.62968801135676
- type: euclidean_pearson
value: 47.482076613243905
- type: euclidean_spearman
value: 62.65137791498299
- type: manhattan_pearson
value: 47.57052626104093
- type: manhattan_spearman
value: 62.436916516613294
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (fr)
config: fr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 70.49397298562575
- type: cos_sim_spearman
value: 74.79604041187868
- type: euclidean_pearson
value: 49.661891561317795
- type: euclidean_spearman
value: 70.31535537621006
- type: manhattan_pearson
value: 49.553715741850006
- type: manhattan_spearman
value: 70.24779344636806
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-en)
config: de-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 55.640574515348696
- type: cos_sim_spearman
value: 54.927959317689
- type: euclidean_pearson
value: 29.00139666967476
- type: euclidean_spearman
value: 41.86386566971605
- type: manhattan_pearson
value: 29.47411067730344
- type: manhattan_spearman
value: 42.337438424952786
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es-en)
config: es-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 68.14095292259312
- type: cos_sim_spearman
value: 73.99017581234789
- type: euclidean_pearson
value: 46.46304297872084
- type: euclidean_spearman
value: 60.91834114800041
- type: manhattan_pearson
value: 47.07072666338692
- type: manhattan_spearman
value: 61.70415727977926
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (it)
config: it
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 73.27184653359575
- type: cos_sim_spearman
value: 77.76070252418626
- type: euclidean_pearson
value: 62.30586577544778
- type: euclidean_spearman
value: 75.14246629110978
- type: manhattan_pearson
value: 62.328196884927046
- type: manhattan_spearman
value: 75.1282792981433
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (pl-en)
config: pl-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 71.59448528829957
- type: cos_sim_spearman
value: 70.37277734222123
- type: euclidean_pearson
value: 57.63145565721123
- type: euclidean_spearman
value: 66.10113048304427
- type: manhattan_pearson
value: 57.18897811586808
- type: manhattan_spearman
value: 66.5595511215901
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (zh-en)
config: zh-en
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 66.37520607720838
- type: cos_sim_spearman
value: 69.92282148997948
- type: euclidean_pearson
value: 40.55768770125291
- type: euclidean_spearman
value: 55.189128944669605
- type: manhattan_pearson
value: 41.03566433468883
- type: manhattan_spearman
value: 55.61251893174558
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (es-it)
config: es-it
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 57.791929533771835
- type: cos_sim_spearman
value: 66.45819707662093
- type: euclidean_pearson
value: 39.03686018511092
- type: euclidean_spearman
value: 56.01282695640428
- type: manhattan_pearson
value: 38.91586623619632
- type: manhattan_spearman
value: 56.69394943612747
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-fr)
config: de-fr
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 47.82224468473866
- type: cos_sim_spearman
value: 59.467307194781164
- type: euclidean_pearson
value: 27.428459190256145
- type: euclidean_spearman
value: 60.83463107397519
- type: manhattan_pearson
value: 27.487391578496638
- type: manhattan_spearman
value: 61.281380460246496
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (de-pl)
config: de-pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 16.306666792752644
- type: cos_sim_spearman
value: 39.35486427252405
- type: euclidean_pearson
value: -2.7887154897955435
- type: euclidean_spearman
value: 27.1296051831719
- type: manhattan_pearson
value: -3.202291270581297
- type: manhattan_spearman
value: 26.32895849218158
- task:
type: STS
dataset:
type: mteb/sts22-crosslingual-sts
name: MTEB STS22 (fr-pl)
config: fr-pl
split: test
revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80
metrics:
- type: cos_sim_pearson
value: 59.67006803805076
- type: cos_sim_spearman
value: 73.24670207647144
- type: euclidean_pearson
value: 46.91884681500483
- type: euclidean_spearman
value: 16.903085094570333
- type: manhattan_pearson
value: 46.88391675325812
- type: manhattan_spearman
value: 28.17180849095055
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 83.79555591223837
- type: cos_sim_spearman
value: 85.63658602085185
- type: euclidean_pearson
value: 85.22080894037671
- type: euclidean_spearman
value: 85.54113580167038
- type: manhattan_pearson
value: 85.1639505960118
- type: manhattan_spearman
value: 85.43502665436196
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 80.73900991689766
- type: mrr
value: 94.81624131133934
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 55.678000000000004
- type: map_at_10
value: 65.135
- type: map_at_100
value: 65.824
- type: map_at_1000
value: 65.852
- type: map_at_3
value: 62.736000000000004
- type: map_at_5
value: 64.411
- type: mrr_at_1
value: 58.333
- type: mrr_at_10
value: 66.5
- type: mrr_at_100
value: 67.053
- type: mrr_at_1000
value: 67.08
- type: mrr_at_3
value: 64.944
- type: mrr_at_5
value: 65.89399999999999
- type: ndcg_at_1
value: 58.333
- type: ndcg_at_10
value: 69.34700000000001
- type: ndcg_at_100
value: 72.32
- type: ndcg_at_1000
value: 73.014
- type: ndcg_at_3
value: 65.578
- type: ndcg_at_5
value: 67.738
- type: precision_at_1
value: 58.333
- type: precision_at_10
value: 9.033
- type: precision_at_100
value: 1.0670000000000002
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 25.444
- type: precision_at_5
value: 16.933
- type: recall_at_1
value: 55.678000000000004
- type: recall_at_10
value: 80.72200000000001
- type: recall_at_100
value: 93.93299999999999
- type: recall_at_1000
value: 99.333
- type: recall_at_3
value: 70.783
- type: recall_at_5
value: 75.978
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.74653465346535
- type: cos_sim_ap
value: 93.01476369929063
- type: cos_sim_f1
value: 86.93009118541033
- type: cos_sim_precision
value: 88.09034907597535
- type: cos_sim_recall
value: 85.8
- type: dot_accuracy
value: 99.22970297029703
- type: dot_ap
value: 51.58725659485144
- type: dot_f1
value: 53.51351351351352
- type: dot_precision
value: 58.235294117647065
- type: dot_recall
value: 49.5
- type: euclidean_accuracy
value: 99.74356435643564
- type: euclidean_ap
value: 92.40332894384368
- type: euclidean_f1
value: 86.97838109602817
- type: euclidean_precision
value: 87.46208291203236
- type: euclidean_recall
value: 86.5
- type: manhattan_accuracy
value: 99.73069306930694
- type: manhattan_ap
value: 92.01320815721121
- type: manhattan_f1
value: 86.4135864135864
- type: manhattan_precision
value: 86.32734530938124
- type: manhattan_recall
value: 86.5
- type: max_accuracy
value: 99.74653465346535
- type: max_ap
value: 93.01476369929063
- type: max_f1
value: 86.97838109602817
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 55.2660514302523
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 30.4637783572547
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 49.41377758357637
- type: mrr
value: 50.138451213818854
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 28.887846011166594
- type: cos_sim_spearman
value: 30.10823258355903
- type: dot_pearson
value: 12.888049550236385
- type: dot_spearman
value: 12.827495903098123
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.21
- type: map_at_10
value: 1.667
- type: map_at_100
value: 9.15
- type: map_at_1000
value: 22.927
- type: map_at_3
value: 0.573
- type: map_at_5
value: 0.915
- type: mrr_at_1
value: 80
- type: mrr_at_10
value: 87.167
- type: mrr_at_100
value: 87.167
- type: mrr_at_1000
value: 87.167
- type: mrr_at_3
value: 85.667
- type: mrr_at_5
value: 87.167
- type: ndcg_at_1
value: 76
- type: ndcg_at_10
value: 69.757
- type: ndcg_at_100
value: 52.402
- type: ndcg_at_1000
value: 47.737
- type: ndcg_at_3
value: 71.866
- type: ndcg_at_5
value: 72.225
- type: precision_at_1
value: 80
- type: precision_at_10
value: 75
- type: precision_at_100
value: 53.959999999999994
- type: precision_at_1000
value: 21.568
- type: precision_at_3
value: 76.667
- type: precision_at_5
value: 78
- type: recall_at_1
value: 0.21
- type: recall_at_10
value: 1.9189999999999998
- type: recall_at_100
value: 12.589
- type: recall_at_1000
value: 45.312000000000005
- type: recall_at_3
value: 0.61
- type: recall_at_5
value: 1.019
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (sqi-eng)
config: sqi-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.10000000000001
- type: f1
value: 90.06
- type: precision
value: 89.17333333333333
- type: recall
value: 92.10000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fry-eng)
config: fry-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 56.06936416184971
- type: f1
value: 50.87508028259473
- type: precision
value: 48.97398843930635
- type: recall
value: 56.06936416184971
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kur-eng)
config: kur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 57.3170731707317
- type: f1
value: 52.96080139372822
- type: precision
value: 51.67861124382864
- type: recall
value: 57.3170731707317
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tur-eng)
config: tur-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.3
- type: f1
value: 92.67333333333333
- type: precision
value: 91.90833333333333
- type: recall
value: 94.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (deu-eng)
config: deu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.7
- type: f1
value: 97.07333333333332
- type: precision
value: 96.79500000000002
- type: recall
value: 97.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nld-eng)
config: nld-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.69999999999999
- type: f1
value: 93.2
- type: precision
value: 92.48333333333333
- type: recall
value: 94.69999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ron-eng)
config: ron-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.9
- type: f1
value: 91.26666666666667
- type: precision
value: 90.59444444444445
- type: recall
value: 92.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ang-eng)
config: ang-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 34.32835820895522
- type: f1
value: 29.074180380150533
- type: precision
value: 28.068207322920596
- type: recall
value: 34.32835820895522
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ido-eng)
config: ido-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 78.5
- type: f1
value: 74.3945115995116
- type: precision
value: 72.82967843459222
- type: recall
value: 78.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (jav-eng)
config: jav-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 66.34146341463415
- type: f1
value: 61.2469400518181
- type: precision
value: 59.63977756660683
- type: recall
value: 66.34146341463415
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (isl-eng)
config: isl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 80.9
- type: f1
value: 76.90349206349207
- type: precision
value: 75.32921568627451
- type: recall
value: 80.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (slv-eng)
config: slv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 84.93317132442284
- type: f1
value: 81.92519105034295
- type: precision
value: 80.71283920615635
- type: recall
value: 84.93317132442284
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cym-eng)
config: cym-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 71.1304347826087
- type: f1
value: 65.22394755003451
- type: precision
value: 62.912422360248435
- type: recall
value: 71.1304347826087
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kaz-eng)
config: kaz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 79.82608695652173
- type: f1
value: 75.55693581780538
- type: precision
value: 73.79420289855072
- type: recall
value: 79.82608695652173
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (est-eng)
config: est-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 74
- type: f1
value: 70.51022222222223
- type: precision
value: 69.29673599347512
- type: recall
value: 74
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (heb-eng)
config: heb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 78.7
- type: f1
value: 74.14238095238095
- type: precision
value: 72.27214285714285
- type: recall
value: 78.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gla-eng)
config: gla-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 48.97466827503016
- type: f1
value: 43.080330405420874
- type: precision
value: 41.36505499593557
- type: recall
value: 48.97466827503016
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mar-eng)
config: mar-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.60000000000001
- type: f1
value: 86.62333333333333
- type: precision
value: 85.225
- type: recall
value: 89.60000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lat-eng)
config: lat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 45.2
- type: f1
value: 39.5761253006253
- type: precision
value: 37.991358436312
- type: recall
value: 45.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bel-eng)
config: bel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.5
- type: f1
value: 86.70333333333333
- type: precision
value: 85.53166666666667
- type: recall
value: 89.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pms-eng)
config: pms-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 50.095238095238095
- type: f1
value: 44.60650460650461
- type: precision
value: 42.774116796477045
- type: recall
value: 50.095238095238095
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gle-eng)
config: gle-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 63.4
- type: f1
value: 58.35967261904762
- type: precision
value: 56.54857142857143
- type: recall
value: 63.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pes-eng)
config: pes-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.2
- type: f1
value: 87.075
- type: precision
value: 86.12095238095239
- type: recall
value: 89.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nob-eng)
config: nob-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96.8
- type: f1
value: 95.90333333333334
- type: precision
value: 95.50833333333333
- type: recall
value: 96.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bul-eng)
config: bul-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.9
- type: f1
value: 88.6288888888889
- type: precision
value: 87.61607142857142
- type: recall
value: 90.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cbk-eng)
config: cbk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 65.2
- type: f1
value: 60.54377630539395
- type: precision
value: 58.89434482711381
- type: recall
value: 65.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hun-eng)
config: hun-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87
- type: f1
value: 84.32412698412699
- type: precision
value: 83.25527777777778
- type: recall
value: 87
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (uig-eng)
config: uig-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 68.7
- type: f1
value: 63.07883541295306
- type: precision
value: 61.06117424242426
- type: recall
value: 68.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (rus-eng)
config: rus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.7
- type: f1
value: 91.78333333333335
- type: precision
value: 90.86666666666667
- type: recall
value: 93.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (spa-eng)
config: spa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.7
- type: f1
value: 96.96666666666667
- type: precision
value: 96.61666666666667
- type: recall
value: 97.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hye-eng)
config: hye-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.27493261455525
- type: f1
value: 85.90745732255168
- type: precision
value: 84.91389637616052
- type: recall
value: 88.27493261455525
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tel-eng)
config: tel-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.5982905982906
- type: f1
value: 88.4900284900285
- type: precision
value: 87.57122507122507
- type: recall
value: 90.5982905982906
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (afr-eng)
config: afr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 89.5
- type: f1
value: 86.90769841269842
- type: precision
value: 85.80178571428571
- type: recall
value: 89.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mon-eng)
config: mon-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 82.5
- type: f1
value: 78.36796536796538
- type: precision
value: 76.82196969696969
- type: recall
value: 82.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (arz-eng)
config: arz-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 71.48846960167715
- type: f1
value: 66.78771089148448
- type: precision
value: 64.98302885095339
- type: recall
value: 71.48846960167715
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hrv-eng)
config: hrv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.1
- type: f1
value: 92.50333333333333
- type: precision
value: 91.77499999999999
- type: recall
value: 94.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nov-eng)
config: nov-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 71.20622568093385
- type: f1
value: 66.83278891450098
- type: precision
value: 65.35065777283677
- type: recall
value: 71.20622568093385
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (gsw-eng)
config: gsw-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 48.717948717948715
- type: f1
value: 43.53146853146853
- type: precision
value: 42.04721204721204
- type: recall
value: 48.717948717948715
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nds-eng)
config: nds-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 58.5
- type: f1
value: 53.8564991863928
- type: precision
value: 52.40329436122275
- type: recall
value: 58.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ukr-eng)
config: ukr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 90.8
- type: f1
value: 88.29
- type: precision
value: 87.09166666666667
- type: recall
value: 90.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (uzb-eng)
config: uzb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 67.28971962616822
- type: f1
value: 62.63425307817832
- type: precision
value: 60.98065939771546
- type: recall
value: 67.28971962616822
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lit-eng)
config: lit-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 78.7
- type: f1
value: 75.5264472455649
- type: precision
value: 74.38205086580086
- type: recall
value: 78.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ina-eng)
config: ina-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.7
- type: f1
value: 86.10809523809525
- type: precision
value: 85.07602564102565
- type: recall
value: 88.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lfn-eng)
config: lfn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 56.99999999999999
- type: f1
value: 52.85487521402737
- type: precision
value: 51.53985162713104
- type: recall
value: 56.99999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (zsm-eng)
config: zsm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94
- type: f1
value: 92.45333333333333
- type: precision
value: 91.79166666666667
- type: recall
value: 94
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ita-eng)
config: ita-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.30000000000001
- type: f1
value: 90.61333333333333
- type: precision
value: 89.83333333333331
- type: recall
value: 92.30000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cmn-eng)
config: cmn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.69999999999999
- type: f1
value: 93.34555555555555
- type: precision
value: 92.75416666666668
- type: recall
value: 94.69999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (lvs-eng)
config: lvs-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 80.2
- type: f1
value: 76.6563035113035
- type: precision
value: 75.3014652014652
- type: recall
value: 80.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (glg-eng)
config: glg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 84.7
- type: f1
value: 82.78689263765207
- type: precision
value: 82.06705086580087
- type: recall
value: 84.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ceb-eng)
config: ceb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 50.33333333333333
- type: f1
value: 45.461523661523664
- type: precision
value: 43.93545574795575
- type: recall
value: 50.33333333333333
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bre-eng)
config: bre-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 6.6000000000000005
- type: f1
value: 5.442121400446441
- type: precision
value: 5.146630385487529
- type: recall
value: 6.6000000000000005
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ben-eng)
config: ben-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85
- type: f1
value: 81.04666666666667
- type: precision
value: 79.25
- type: recall
value: 85
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swg-eng)
config: swg-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 47.32142857142857
- type: f1
value: 42.333333333333336
- type: precision
value: 40.69196428571429
- type: recall
value: 47.32142857142857
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (arq-eng)
config: arq-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 30.735455543358945
- type: f1
value: 26.73616790022338
- type: precision
value: 25.397823220451283
- type: recall
value: 30.735455543358945
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kab-eng)
config: kab-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 25.1
- type: f1
value: 21.975989896371022
- type: precision
value: 21.059885632257203
- type: recall
value: 25.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fra-eng)
config: fra-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.3
- type: f1
value: 92.75666666666666
- type: precision
value: 92.06166666666665
- type: recall
value: 94.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (por-eng)
config: por-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.1
- type: f1
value: 92.74
- type: precision
value: 92.09166666666667
- type: recall
value: 94.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tat-eng)
config: tat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 71.3
- type: f1
value: 66.922442002442
- type: precision
value: 65.38249567099568
- type: recall
value: 71.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (oci-eng)
config: oci-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 40.300000000000004
- type: f1
value: 35.78682789299971
- type: precision
value: 34.66425128716588
- type: recall
value: 40.300000000000004
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pol-eng)
config: pol-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 96
- type: f1
value: 94.82333333333334
- type: precision
value: 94.27833333333334
- type: recall
value: 96
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (war-eng)
config: war-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 51.1
- type: f1
value: 47.179074753133584
- type: precision
value: 46.06461044702424
- type: recall
value: 51.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (aze-eng)
config: aze-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 87.7
- type: f1
value: 84.71
- type: precision
value: 83.46166666666667
- type: recall
value: 87.7
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (vie-eng)
config: vie-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.8
- type: f1
value: 94.68333333333334
- type: precision
value: 94.13333333333334
- type: recall
value: 95.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (nno-eng)
config: nno-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.39999999999999
- type: f1
value: 82.5577380952381
- type: precision
value: 81.36833333333334
- type: recall
value: 85.39999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cha-eng)
config: cha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 21.16788321167883
- type: f1
value: 16.948865627297987
- type: precision
value: 15.971932568647897
- type: recall
value: 21.16788321167883
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mhr-eng)
config: mhr-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 6.9
- type: f1
value: 5.515526831658907
- type: precision
value: 5.141966366966367
- type: recall
value: 6.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dan-eng)
config: dan-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.2
- type: f1
value: 91.39666666666668
- type: precision
value: 90.58666666666667
- type: recall
value: 93.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ell-eng)
config: ell-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.2
- type: f1
value: 89.95666666666666
- type: precision
value: 88.92833333333333
- type: recall
value: 92.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (amh-eng)
config: amh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 79.76190476190477
- type: f1
value: 74.93386243386244
- type: precision
value: 73.11011904761904
- type: recall
value: 79.76190476190477
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (pam-eng)
config: pam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 8.799999999999999
- type: f1
value: 6.921439712248537
- type: precision
value: 6.489885109680683
- type: recall
value: 8.799999999999999
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hsb-eng)
config: hsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 45.75569358178054
- type: f1
value: 40.34699501312631
- type: precision
value: 38.57886764719063
- type: recall
value: 45.75569358178054
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (srp-eng)
config: srp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.4
- type: f1
value: 89.08333333333333
- type: precision
value: 88.01666666666668
- type: recall
value: 91.4
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (epo-eng)
config: epo-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.60000000000001
- type: f1
value: 92.06690476190477
- type: precision
value: 91.45095238095239
- type: recall
value: 93.60000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kzj-eng)
config: kzj-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 7.5
- type: f1
value: 6.200363129378736
- type: precision
value: 5.89115314822466
- type: recall
value: 7.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (awa-eng)
config: awa-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 73.59307359307358
- type: f1
value: 68.38933553219267
- type: precision
value: 66.62698412698413
- type: recall
value: 73.59307359307358
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fao-eng)
config: fao-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 69.8473282442748
- type: f1
value: 64.72373682297346
- type: precision
value: 62.82834214131924
- type: recall
value: 69.8473282442748
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mal-eng)
config: mal-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 97.5254730713246
- type: f1
value: 96.72489082969432
- type: precision
value: 96.33672974284326
- type: recall
value: 97.5254730713246
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ile-eng)
config: ile-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 75.6
- type: f1
value: 72.42746031746033
- type: precision
value: 71.14036630036631
- type: recall
value: 75.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (bos-eng)
config: bos-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.24293785310734
- type: f1
value: 88.86064030131826
- type: precision
value: 87.73540489642184
- type: recall
value: 91.24293785310734
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cor-eng)
config: cor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 6.2
- type: f1
value: 4.383083659794954
- type: precision
value: 4.027861324289673
- type: recall
value: 6.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (cat-eng)
config: cat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.8
- type: f1
value: 84.09428571428572
- type: precision
value: 83.00333333333333
- type: recall
value: 86.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (eus-eng)
config: eus-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 60.699999999999996
- type: f1
value: 56.1584972394755
- type: precision
value: 54.713456330903135
- type: recall
value: 60.699999999999996
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (yue-eng)
config: yue-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 84.2
- type: f1
value: 80.66190476190475
- type: precision
value: 79.19690476190476
- type: recall
value: 84.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swe-eng)
config: swe-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 93.2
- type: f1
value: 91.33
- type: precision
value: 90.45
- type: recall
value: 93.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dtp-eng)
config: dtp-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 6.3
- type: f1
value: 5.126828976748276
- type: precision
value: 4.853614328966668
- type: recall
value: 6.3
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kat-eng)
config: kat-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81.76943699731903
- type: f1
value: 77.82873739308057
- type: precision
value: 76.27622452019234
- type: recall
value: 81.76943699731903
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (jpn-eng)
config: jpn-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.30000000000001
- type: f1
value: 90.29666666666665
- type: precision
value: 89.40333333333334
- type: recall
value: 92.30000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (csb-eng)
config: csb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 29.249011857707508
- type: f1
value: 24.561866096392947
- type: precision
value: 23.356583740215456
- type: recall
value: 29.249011857707508
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (xho-eng)
config: xho-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.46478873239437
- type: f1
value: 73.23943661971832
- type: precision
value: 71.66666666666667
- type: recall
value: 77.46478873239437
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (orv-eng)
config: orv-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 20.35928143712575
- type: f1
value: 15.997867865075824
- type: precision
value: 14.882104658301346
- type: recall
value: 20.35928143712575
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ind-eng)
config: ind-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 92.2
- type: f1
value: 90.25999999999999
- type: precision
value: 89.45333333333335
- type: recall
value: 92.2
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tuk-eng)
config: tuk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 23.15270935960591
- type: f1
value: 19.65673625772148
- type: precision
value: 18.793705293464992
- type: recall
value: 23.15270935960591
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (max-eng)
config: max-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 59.154929577464785
- type: f1
value: 52.3868463305083
- type: precision
value: 50.14938113529662
- type: recall
value: 59.154929577464785
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (swh-eng)
config: swh-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 70.51282051282051
- type: f1
value: 66.8089133089133
- type: precision
value: 65.37645687645687
- type: recall
value: 70.51282051282051
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (hin-eng)
config: hin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 94.6
- type: f1
value: 93
- type: precision
value: 92.23333333333333
- type: recall
value: 94.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (dsb-eng)
config: dsb-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 38.62212943632568
- type: f1
value: 34.3278276962583
- type: precision
value: 33.07646935732408
- type: recall
value: 38.62212943632568
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ber-eng)
config: ber-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 28.1
- type: f1
value: 23.579609223054604
- type: precision
value: 22.39622774921555
- type: recall
value: 28.1
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tam-eng)
config: tam-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.27361563517914
- type: f1
value: 85.12486427795874
- type: precision
value: 83.71335504885994
- type: recall
value: 88.27361563517914
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (slk-eng)
config: slk-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.6
- type: f1
value: 86.39928571428571
- type: precision
value: 85.4947557997558
- type: recall
value: 88.6
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tgl-eng)
config: tgl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.5
- type: f1
value: 83.77952380952381
- type: precision
value: 82.67602564102565
- type: recall
value: 86.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ast-eng)
config: ast-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 79.52755905511812
- type: f1
value: 75.3055868016498
- type: precision
value: 73.81889763779527
- type: recall
value: 79.52755905511812
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (mkd-eng)
config: mkd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 77.9
- type: f1
value: 73.76261904761905
- type: precision
value: 72.11670995670995
- type: recall
value: 77.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (khm-eng)
config: khm-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 53.8781163434903
- type: f1
value: 47.25804051288816
- type: precision
value: 45.0603482390186
- type: recall
value: 53.8781163434903
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ces-eng)
config: ces-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 91.10000000000001
- type: f1
value: 88.88
- type: precision
value: 87.96333333333334
- type: recall
value: 91.10000000000001
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tzl-eng)
config: tzl-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 38.46153846153847
- type: f1
value: 34.43978243978244
- type: precision
value: 33.429487179487175
- type: recall
value: 38.46153846153847
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (urd-eng)
config: urd-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.9
- type: f1
value: 86.19888888888887
- type: precision
value: 85.07440476190476
- type: recall
value: 88.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (ara-eng)
config: ara-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 85.9
- type: f1
value: 82.58857142857143
- type: precision
value: 81.15666666666667
- type: recall
value: 85.9
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (kor-eng)
config: kor-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 86.8
- type: f1
value: 83.36999999999999
- type: precision
value: 81.86833333333333
- type: recall
value: 86.8
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (yid-eng)
config: yid-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 68.51415094339622
- type: f1
value: 63.195000099481234
- type: precision
value: 61.394033442972116
- type: recall
value: 68.51415094339622
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (fin-eng)
config: fin-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 88.5
- type: f1
value: 86.14603174603175
- type: precision
value: 85.1162037037037
- type: recall
value: 88.5
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (tha-eng)
config: tha-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 95.62043795620438
- type: f1
value: 94.40389294403892
- type: precision
value: 93.7956204379562
- type: recall
value: 95.62043795620438
- task:
type: BitextMining
dataset:
type: mteb/tatoeba-bitext-mining
name: MTEB Tatoeba (wuu-eng)
config: wuu-eng
split: test
revision: 9080400076fbadbb4c4dcb136ff4eddc40b42553
metrics:
- type: accuracy
value: 81.8
- type: f1
value: 78.6532178932179
- type: precision
value: 77.46348795840176
- type: recall
value: 81.8
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 2.603
- type: map_at_10
value: 8.5
- type: map_at_100
value: 12.985
- type: map_at_1000
value: 14.466999999999999
- type: map_at_3
value: 4.859999999999999
- type: map_at_5
value: 5.817
- type: mrr_at_1
value: 28.571
- type: mrr_at_10
value: 42.331
- type: mrr_at_100
value: 43.592999999999996
- type: mrr_at_1000
value: 43.592999999999996
- type: mrr_at_3
value: 38.435
- type: mrr_at_5
value: 39.966
- type: ndcg_at_1
value: 26.531
- type: ndcg_at_10
value: 21.353
- type: ndcg_at_100
value: 31.087999999999997
- type: ndcg_at_1000
value: 43.163000000000004
- type: ndcg_at_3
value: 22.999
- type: ndcg_at_5
value: 21.451
- type: precision_at_1
value: 28.571
- type: precision_at_10
value: 19.387999999999998
- type: precision_at_100
value: 6.265
- type: precision_at_1000
value: 1.4160000000000001
- type: precision_at_3
value: 24.490000000000002
- type: precision_at_5
value: 21.224
- type: recall_at_1
value: 2.603
- type: recall_at_10
value: 14.474
- type: recall_at_100
value: 40.287
- type: recall_at_1000
value: 76.606
- type: recall_at_3
value: 5.978
- type: recall_at_5
value: 7.819
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 69.7848
- type: ap
value: 13.661023167088224
- type: f1
value: 53.61686134460943
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 61.28183361629882
- type: f1
value: 61.55481034919965
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 35.972128420092396
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 85.59933241938367
- type: cos_sim_ap
value: 72.20760361208136
- type: cos_sim_f1
value: 66.4447731755424
- type: cos_sim_precision
value: 62.35539102267469
- type: cos_sim_recall
value: 71.10817941952506
- type: dot_accuracy
value: 78.98313166835548
- type: dot_ap
value: 44.492521645493795
- type: dot_f1
value: 45.814889336016094
- type: dot_precision
value: 37.02439024390244
- type: dot_recall
value: 60.07915567282321
- type: euclidean_accuracy
value: 85.3907134767837
- type: euclidean_ap
value: 71.53847289080343
- type: euclidean_f1
value: 65.95952206778834
- type: euclidean_precision
value: 61.31006346328196
- type: euclidean_recall
value: 71.37203166226914
- type: manhattan_accuracy
value: 85.40859510043511
- type: manhattan_ap
value: 71.49664104395515
- type: manhattan_f1
value: 65.98569969356485
- type: manhattan_precision
value: 63.928748144482924
- type: manhattan_recall
value: 68.17941952506597
- type: max_accuracy
value: 85.59933241938367
- type: max_ap
value: 72.20760361208136
- type: max_f1
value: 66.4447731755424
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.83261536073273
- type: cos_sim_ap
value: 85.48178133644264
- type: cos_sim_f1
value: 77.87816307403935
- type: cos_sim_precision
value: 75.88953021114926
- type: cos_sim_recall
value: 79.97382198952879
- type: dot_accuracy
value: 79.76287499514883
- type: dot_ap
value: 59.17438838475084
- type: dot_f1
value: 56.34566667855996
- type: dot_precision
value: 52.50349092359864
- type: dot_recall
value: 60.794579611949494
- type: euclidean_accuracy
value: 88.76857996662397
- type: euclidean_ap
value: 85.22764834359887
- type: euclidean_f1
value: 77.65379751543554
- type: euclidean_precision
value: 75.11152683839401
- type: euclidean_recall
value: 80.37419156144134
- type: manhattan_accuracy
value: 88.6987231730508
- type: manhattan_ap
value: 85.18907981724007
- type: manhattan_f1
value: 77.51967028849757
- type: manhattan_precision
value: 75.49992701795358
- type: manhattan_recall
value: 79.65044656606098
- type: max_accuracy
value: 88.83261536073273
- type: max_ap
value: 85.48178133644264
- type: max_f1
value: 77.87816307403935
language:
- multilingual
- af
- am
- ar
- as
- az
- be
- bg
- bn
- br
- bs
- ca
- cs
- cy
- da
- de
- el
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- fy
- ga
- gd
- gl
- gu
- ha
- he
- hi
- hr
- hu
- hy
- id
- is
- it
- ja
- jv
- ka
- kk
- km
- kn
- ko
- ku
- ky
- la
- lo
- lt
- lv
- mg
- mk
- ml
- mn
- mr
- ms
- my
- ne
- nl
- 'no'
- om
- or
- pa
- pl
- ps
- pt
- ro
- ru
- sa
- sd
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- th
- tl
- tr
- ug
- uk
- ur
- uz
- vi
- xh
- yi
- zh
license: mit
---
## Multilingual-E5-base
[Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://arxiv.org/pdf/2212.03533.pdf).
Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022
This model has 12 layers and the embedding size is 768.
## Usage
Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset.
```python
import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel
def average_pool(last_hidden_states: Tensor,
attention_mask: Tensor) -> Tensor:
last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
# Each input text should start with "query: " or "passage: ", even for non-English texts.
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
'query: 南瓜的家常做法',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右,放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"]
tokenizer = AutoTokenizer.from_pretrained('intfloat/multilingual-e5-base')
model = AutoModel.from_pretrained('intfloat/multilingual-e5-base')
# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')
outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])
# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
```
## Supported Languages
This model is initialized from [xlm-roberta-base](https://huggingface.co/xlm-roberta-base)
and continually trained on a mixture of multilingual datasets.
It supports 100 languages from xlm-roberta,
but low-resource languages may see performance degradation.
## Training Details
**Initialization**: [xlm-roberta-base](https://huggingface.co/xlm-roberta-base)
**First stage**: contrastive pre-training with weak supervision
| Dataset | Weak supervision | # of text pairs |
|--------------------------------------------------------------------------------------------------------|---------------------------------------|-----------------|
| Filtered [mC4](https://huggingface.co/datasets/mc4) | (title, page content) | 1B |
| [CC News](https://huggingface.co/datasets/intfloat/multilingual_cc_news) | (title, news content) | 400M |
| [NLLB](https://huggingface.co/datasets/allenai/nllb) | translation pairs | 2.4B |
| [Wikipedia](https://huggingface.co/datasets/intfloat/wikipedia) | (hierarchical section title, passage) | 150M |
| Filtered [Reddit](https://www.reddit.com/) | (comment, response) | 800M |
| [S2ORC](https://github.com/allenai/s2orc) | (title, abstract) and citation pairs | 100M |
| [Stackexchange](https://stackexchange.com/) | (question, answer) | 50M |
| [xP3](https://huggingface.co/datasets/bigscience/xP3) | (input prompt, response) | 80M |
| [Miscellaneous unsupervised SBERT data](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) | - | 10M |
**Second stage**: supervised fine-tuning
| Dataset | Language | # of text pairs |
|----------------------------------------------------------------------------------------|--------------|-----------------|
| [MS MARCO](https://microsoft.github.io/msmarco/) | English | 500k |
| [NQ](https://github.com/facebookresearch/DPR) | English | 70k |
| [Trivia QA](https://github.com/facebookresearch/DPR) | English | 60k |
| [NLI from SimCSE](https://github.com/princeton-nlp/SimCSE) | English | <300k |
| [ELI5](https://huggingface.co/datasets/eli5) | English | 500k |
| [DuReader Retrieval](https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval) | Chinese | 86k |
| [KILT Fever](https://huggingface.co/datasets/kilt_tasks) | English | 70k |
| [KILT HotpotQA](https://huggingface.co/datasets/kilt_tasks) | English | 70k |
| [SQuAD](https://huggingface.co/datasets/squad) | English | 87k |
| [Quora](https://huggingface.co/datasets/quora) | English | 150k |
| [Mr. TyDi](https://huggingface.co/datasets/castorini/mr-tydi) | 11 languages | 50k |
| [MIRACL](https://huggingface.co/datasets/miracl/miracl) | 16 languages | 40k |
For all labeled datasets, we only use its training set for fine-tuning.
For other training details, please refer to our paper at [https://arxiv.org/pdf/2212.03533.pdf](https://arxiv.org/pdf/2212.03533.pdf).
## Benchmark Results on [Mr. TyDi](https://arxiv.org/abs/2108.08787)
| Model | Avg MRR@10 | | ar | bn | en | fi | id | ja | ko | ru | sw | te | th |
|-----------------------|------------|-------|------| --- | --- | --- | --- | --- | --- | --- |------| --- | --- |
| BM25 | 33.3 | | 36.7 | 41.3 | 15.1 | 28.8 | 38.2 | 21.7 | 28.1 | 32.9 | 39.6 | 42.4 | 41.7 |
| mDPR | 16.7 | | 26.0 | 25.8 | 16.2 | 11.3 | 14.6 | 18.1 | 21.9 | 18.5 | 7.3 | 10.6 | 13.5 |
| BM25 + mDPR | 41.7 | | 49.1 | 53.5 | 28.4 | 36.5 | 45.5 | 35.5 | 36.2 | 42.7 | 40.5 | 42.0 | 49.2 |
| | |
| multilingual-e5-small | 64.4 | | 71.5 | 66.3 | 54.5 | 57.7 | 63.2 | 55.4 | 54.3 | 60.8 | 65.4 | 89.1 | 70.1 |
| multilingual-e5-base | 65.9 | | 72.3 | 65.0 | 58.5 | 60.8 | 64.9 | 56.6 | 55.8 | 62.7 | 69.0 | 86.6 | 72.7 |
| multilingual-e5-large | **70.5** | | 77.5 | 73.2 | 60.8 | 66.8 | 68.5 | 62.5 | 61.6 | 65.8 | 72.7 | 90.2 | 76.2 |
## MTEB Benchmark Evaluation
Check out [unilm/e5](https://github.com/microsoft/unilm/tree/master/e5) to reproduce evaluation results
on the [BEIR](https://arxiv.org/abs/2104.08663) and [MTEB benchmark](https://arxiv.org/abs/2210.07316).
## Support for Sentence Transformers
Below is an example for usage with sentence_transformers.
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/multilingual-e5-base')
input_texts = [
'query: how much protein should a female eat',
'query: 南瓜的家常做法',
"passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 i s 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or traini ng for a marathon. Check out the chart below to see how much protein you should be eating each day.",
"passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮 ,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右, 放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油 锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"
]
embeddings = model.encode(input_texts, normalize_embeddings=True)
```
Package requirements
`pip install sentence_transformers~=2.2.2`
Contributors: [michaelfeil](https://huggingface.co/michaelfeil)
## FAQ
**1. Do I need to add the prefix "query: " and "passage: " to input texts?**
Yes, this is how the model is trained, otherwise you will see a performance degradation.
Here are some rules of thumb:
- Use "query: " and "passage: " correspondingly for asymmetric tasks such as passage retrieval in open QA, ad-hoc information retrieval.
- Use "query: " prefix for symmetric tasks such as semantic similarity, bitext mining, paraphrase retrieval.
- Use "query: " prefix if you want to use embeddings as features, such as linear probing classification, clustering.
**2. Why are my reproduced results slightly different from reported in the model card?**
Different versions of `transformers` and `pytorch` could cause negligible but non-zero performance differences.
**3. Why does the cosine similarity scores distribute around 0.7 to 1.0?**
This is a known and expected behavior as we use a low temperature 0.01 for InfoNCE contrastive loss.
For text embedding tasks like text retrieval or semantic similarity,
what matters is the relative order of the scores instead of the absolute values,
so this should not be an issue.
## Citation
If you find our paper or models helpful, please consider cite as follows:
```
@article{wang2022text,
title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
journal={arXiv preprint arXiv:2212.03533},
year={2022}
}
```
## Limitations
Long texts will be truncated to at most 512 tokens.
| 178,527 | [
[
-0.035064697265625,
-0.037994384765625,
0.00774383544921875,
0.02374267578125,
-0.0174560546875,
-0.0080413818359375,
-0.0221099853515625,
-0.032012939453125,
0.026702880859375,
0.0165863037109375,
-0.037994384765625,
-0.055389404296875,
-0.054046630859375,
0.023162841796875,
0.005157470703125,
0.07769775390625,
-0.0106201171875,
0.003337860107421875,
-0.0011281967163085938,
-0.02728271484375,
-0.0204315185546875,
-0.032989501953125,
-0.047149658203125,
-0.0162506103515625,
0.0244140625,
0.0290374755859375,
0.034820556640625,
0.0465087890625,
0.032745361328125,
0.025177001953125,
-0.0118255615234375,
0.024658203125,
-0.02874755859375,
-0.01468658447265625,
0.01146697998046875,
-0.0328369140625,
-0.034088134765625,
-0.00014829635620117188,
0.04339599609375,
0.04290771484375,
0.0011243820190429688,
0.01727294921875,
0.0164337158203125,
0.0633544921875,
-0.026885986328125,
0.0197296142578125,
-0.0163726806640625,
0.0087127685546875,
-0.0189208984375,
-0.0012655258178710938,
-0.011688232421875,
-0.007129669189453125,
0.0028095245361328125,
-0.0400390625,
-0.0010433197021484375,
0.004436492919921875,
0.09405517578125,
0.01332855224609375,
-0.0303497314453125,
-0.0167083740234375,
-0.0084228515625,
0.06597900390625,
-0.05511474609375,
0.036407470703125,
0.049041748046875,
-0.0033721923828125,
0.0008559226989746094,
-0.04931640625,
-0.03729248046875,
0.0012464523315429688,
-0.03472900390625,
0.028564453125,
-0.011444091796875,
-0.01152801513671875,
0.02105712890625,
0.032623291015625,
-0.06256103515625,
0.0053558349609375,
-0.024566650390625,
-0.01104736328125,
0.054840087890625,
0.006923675537109375,
0.02777099609375,
-0.0382080078125,
-0.025177001953125,
-0.01302337646484375,
-0.0303497314453125,
0.0220794677734375,
0.0266876220703125,
0.0193634033203125,
-0.045501708984375,
0.034515380859375,
-0.0204925537109375,
0.044921875,
0.009735107421875,
-0.01210784912109375,
0.052947998046875,
-0.05352783203125,
-0.0161285400390625,
-0.01404571533203125,
0.0863037109375,
0.0270233154296875,
0.0032291412353515625,
0.006618499755859375,
-0.00859832763671875,
-0.003948211669921875,
-0.016845703125,
-0.0626220703125,
-0.0225372314453125,
0.033111572265625,
-0.039520263671875,
-0.0186767578125,
0.002277374267578125,
-0.055877685546875,
0.006404876708984375,
-0.01444244384765625,
0.020782470703125,
-0.048004150390625,
-0.023223876953125,
0.0064849853515625,
0.00266265869140625,
0.01528167724609375,
0.0088348388671875,
-0.05682373046875,
0.016845703125,
0.0125732421875,
0.06939697265625,
-0.01033782958984375,
-0.0228118896484375,
-0.0191192626953125,
0.0007171630859375,
-0.010833740234375,
0.04473876953125,
-0.0168304443359375,
-0.01149749755859375,
-0.0067291259765625,
0.0281982421875,
-0.030670166015625,
-0.02294921875,
0.0465087890625,
-0.0152740478515625,
0.039154052734375,
-0.0219573974609375,
-0.03082275390625,
-0.006259918212890625,
0.028533935546875,
-0.047027587890625,
0.10137939453125,
0.01806640625,
-0.07843017578125,
0.0189208984375,
-0.04400634765625,
-0.0279541015625,
-0.01235198974609375,
-0.015899658203125,
-0.04681396484375,
-0.02679443359375,
0.03717041015625,
0.03924560546875,
-0.011993408203125,
0.00917816162109375,
-0.0030155181884765625,
-0.016998291015625,
-0.0005178451538085938,
-0.01220703125,
0.08551025390625,
0.0223236083984375,
-0.045989990234375,
-0.0015659332275390625,
-0.06591796875,
0.004650115966796875,
0.0195159912109375,
-0.0318603515625,
-0.01033782958984375,
-0.0158233642578125,
0.0036449432373046875,
0.03778076171875,
0.02935791015625,
-0.0360107421875,
0.0148773193359375,
-0.04718017578125,
0.03692626953125,
0.039642333984375,
-0.007251739501953125,
0.0273895263671875,
-0.0318603515625,
0.0312347412109375,
0.0297698974609375,
0.001415252685546875,
-0.0173797607421875,
-0.04266357421875,
-0.0672607421875,
-0.0278472900390625,
0.029144287109375,
0.049957275390625,
-0.058319091796875,
0.045196533203125,
-0.0230255126953125,
-0.0322265625,
-0.05706787109375,
0.019622802734375,
0.040008544921875,
0.032379150390625,
0.047027587890625,
-0.0007853507995605469,
-0.04779052734375,
-0.07110595703125,
-0.00928497314453125,
0.0014934539794921875,
0.0049591064453125,
0.024932861328125,
0.056396484375,
-0.0225372314453125,
0.04510498046875,
-0.037689208984375,
-0.040802001953125,
-0.02789306640625,
-0.0036029815673828125,
0.036651611328125,
0.0465087890625,
0.048828125,
-0.0635986328125,
-0.0599365234375,
0.006542205810546875,
-0.066650390625,
0.006069183349609375,
0.002506256103515625,
-0.0137786865234375,
0.041656494140625,
0.037445068359375,
-0.04248046875,
0.0217742919921875,
0.051666259765625,
-0.0301971435546875,
0.03533935546875,
-0.02337646484375,
0.010284423828125,
-0.10516357421875,
0.01593017578125,
0.00699615478515625,
-0.00824737548828125,
-0.03277587890625,
-0.00015747547149658203,
0.006847381591796875,
0.004779815673828125,
-0.0297088623046875,
0.04693603515625,
-0.056304931640625,
0.016845703125,
0.0102081298828125,
0.0235137939453125,
0.0006055831909179688,
0.048675537109375,
0.00634002685546875,
0.0535888671875,
0.0399169921875,
-0.04412841796875,
0.00554656982421875,
0.030670166015625,
-0.031158447265625,
0.0285797119140625,
-0.046661376953125,
-0.00782012939453125,
0.0001939535140991211,
0.0189056396484375,
-0.07843017578125,
-0.018463134765625,
0.018951416015625,
-0.04364013671875,
0.031341552734375,
-0.00829315185546875,
-0.039459228515625,
-0.045440673828125,
-0.045867919921875,
0.0099334716796875,
0.0191802978515625,
-0.0298309326171875,
0.03375244140625,
0.01910400390625,
-0.00484466552734375,
-0.0616455078125,
-0.07147216796875,
-0.006549835205078125,
-0.0078582763671875,
-0.06103515625,
0.034698486328125,
-0.01146697998046875,
0.00896453857421875,
0.0036029815673828125,
0.00104522705078125,
0.00817108154296875,
-0.004535675048828125,
0.005199432373046875,
0.01483917236328125,
-0.01126861572265625,
-0.007389068603515625,
-0.0007500648498535156,
-0.005077362060546875,
-0.016998291015625,
-0.008056640625,
0.04541015625,
-0.029510498046875,
0.00392913818359375,
-0.040618896484375,
0.0212554931640625,
0.0299224853515625,
-0.01953125,
0.07745361328125,
0.0706787109375,
-0.019500732421875,
0.006580352783203125,
-0.036376953125,
-0.003551483154296875,
-0.034149169921875,
0.038116455078125,
-0.04327392578125,
-0.06146240234375,
0.052001953125,
0.011322021484375,
0.007232666015625,
0.05682373046875,
0.0367431640625,
-0.011566162109375,
0.08074951171875,
0.031158447265625,
-0.0149383544921875,
0.03143310546875,
-0.053253173828125,
-0.001537322998046875,
-0.064453125,
-0.0274505615234375,
-0.035919189453125,
-0.0199737548828125,
-0.070556640625,
-0.03131103515625,
0.016387939453125,
0.004425048828125,
-0.0255126953125,
0.03253173828125,
-0.04327392578125,
0.01064300537109375,
0.03863525390625,
0.0194549560546875,
0.0048370361328125,
0.00601959228515625,
-0.0280914306640625,
-0.015411376953125,
-0.061767578125,
-0.0309295654296875,
0.08062744140625,
0.0292510986328125,
0.03497314453125,
0.0109100341796875,
0.052337646484375,
-0.00011712312698364258,
0.002468109130859375,
-0.035919189453125,
0.0286865234375,
-0.0207061767578125,
-0.040191650390625,
-0.01480865478515625,
-0.0504150390625,
-0.07562255859375,
0.0253448486328125,
-0.0212249755859375,
-0.055206298828125,
0.0126190185546875,
0.0013799667358398438,
-0.019012451171875,
0.020782470703125,
-0.06634521484375,
0.07257080078125,
-0.023193359375,
-0.0364990234375,
0.0124664306640625,
-0.06134033203125,
0.0195159912109375,
0.00818634033203125,
0.026641845703125,
-0.00021266937255859375,
-0.009063720703125,
0.0675048828125,
-0.032318115234375,
0.05316162109375,
-0.010284423828125,
0.00516510009765625,
0.01355743408203125,
-0.0140228271484375,
0.049163818359375,
-0.0010805130004882812,
-0.00856781005859375,
0.0264434814453125,
0.01297760009765625,
-0.04296875,
-0.02325439453125,
0.062255859375,
-0.07818603515625,
-0.032623291015625,
-0.04833984375,
-0.03009033203125,
-0.004673004150390625,
0.027496337890625,
0.040313720703125,
0.01326751708984375,
0.0079498291015625,
0.0271148681640625,
0.047027587890625,
-0.03271484375,
0.039520263671875,
0.03204345703125,
-0.0011968612670898438,
-0.05242919921875,
0.06536865234375,
0.021697998046875,
0.01264190673828125,
0.034820556640625,
0.01114654541015625,
-0.028533935546875,
-0.033538818359375,
-0.041046142578125,
0.03399658203125,
-0.0318603515625,
-0.0235748291015625,
-0.07080078125,
-0.0181732177734375,
-0.05047607421875,
-0.001903533935546875,
-0.0245513916015625,
-0.0290069580078125,
-0.0270233154296875,
-0.01038360595703125,
0.0228424072265625,
0.034698486328125,
-0.002033233642578125,
0.01291656494140625,
-0.0458984375,
0.0173797607421875,
-0.007781982421875,
0.0206298828125,
-0.0119781494140625,
-0.053009033203125,
-0.04046630859375,
0.01233673095703125,
-0.0259857177734375,
-0.053741455078125,
0.050750732421875,
0.0213775634765625,
0.04302978515625,
0.0269927978515625,
-0.0015354156494140625,
0.0511474609375,
-0.024322509765625,
0.0699462890625,
0.0194854736328125,
-0.055206298828125,
0.04901123046875,
-0.0242462158203125,
0.03399658203125,
0.04742431640625,
0.0545654296875,
-0.03692626953125,
-0.024627685546875,
-0.050048828125,
-0.07489013671875,
0.06866455078125,
0.0293731689453125,
-0.0031871795654296875,
0.0019063949584960938,
0.015716552734375,
-0.01275634765625,
0.0115509033203125,
-0.07275390625,
-0.05389404296875,
-0.020660400390625,
-0.03619384765625,
-0.0092926025390625,
-0.0159759521484375,
-0.0023956298828125,
-0.038055419921875,
0.06060791015625,
-0.00676727294921875,
0.033050537109375,
0.02734375,
-0.0156402587890625,
0.004726409912109375,
0.006198883056640625,
0.051605224609375,
0.035064697265625,
-0.02294921875,
0.0099945068359375,
0.02276611328125,
-0.04833984375,
-0.006755828857421875,
0.0165557861328125,
-0.0165557861328125,
0.00270843505859375,
0.0309906005859375,
0.05609130859375,
0.018402099609375,
-0.03363037109375,
0.0382080078125,
-0.006076812744140625,
-0.02777099609375,
-0.0225982666015625,
-0.00933074951171875,
0.0166473388671875,
0.01331329345703125,
0.0258331298828125,
-0.013641357421875,
-0.0019683837890625,
-0.040008544921875,
0.01549530029296875,
0.01468658447265625,
-0.0289306640625,
-0.021026611328125,
0.0465087890625,
0.00708770751953125,
0.007167816162109375,
0.04229736328125,
-0.014190673828125,
-0.048126220703125,
0.0452880859375,
0.03662109375,
0.042144775390625,
-0.023590087890625,
0.01258087158203125,
0.06878662109375,
0.038299560546875,
0.0021724700927734375,
0.0257110595703125,
0.01116180419921875,
-0.048919677734375,
-0.0180511474609375,
-0.05950927734375,
0.0029048919677734375,
0.0185699462890625,
-0.036346435546875,
0.02294921875,
-0.0156097412109375,
-0.0118865966796875,
-0.0012989044189453125,
0.044219970703125,
-0.05499267578125,
0.0186004638671875,
-0.0009431838989257812,
0.073486328125,
-0.0614013671875,
0.065185546875,
0.060394287109375,
-0.063720703125,
-0.0667724609375,
-0.01641845703125,
-0.006420135498046875,
-0.051483154296875,
0.055877685546875,
0.0228271484375,
0.01232147216796875,
-0.0021114349365234375,
-0.0284576416015625,
-0.06964111328125,
0.0947265625,
0.01611328125,
-0.036407470703125,
-0.00156402587890625,
0.018890380859375,
0.04388427734375,
-0.023162841796875,
0.035858154296875,
0.043060302734375,
0.04254150390625,
-0.0126190185546875,
-0.0670166015625,
0.0136871337890625,
-0.0467529296875,
-0.002780914306640625,
0.0010824203491210938,
-0.07769775390625,
0.07501220703125,
-0.0111083984375,
-0.00569915771484375,
-0.00809478759765625,
0.052337646484375,
0.0257720947265625,
0.021026611328125,
0.0240325927734375,
0.06146240234375,
0.053863525390625,
-0.01432037353515625,
0.086181640625,
-0.038055419921875,
0.038116455078125,
0.0699462890625,
0.017425537109375,
0.058197021484375,
0.031707763671875,
-0.02685546875,
0.04901123046875,
0.06671142578125,
-0.0023040771484375,
0.0367431640625,
-0.01126861572265625,
-0.006351470947265625,
-0.005855560302734375,
0.0013599395751953125,
-0.038818359375,
0.02288818359375,
0.020355224609375,
-0.03778076171875,
0.001220703125,
0.00890350341796875,
0.0294647216796875,
-0.00464630126953125,
-0.01247406005859375,
0.0556640625,
0.0124359130859375,
-0.039947509765625,
0.0650634765625,
0.0020732879638671875,
0.06756591796875,
-0.05242919921875,
0.011383056640625,
-0.0288848876953125,
0.017242431640625,
-0.033477783203125,
-0.06317138671875,
0.01020050048828125,
-0.006175994873046875,
-0.017730712890625,
-0.01491546630859375,
0.03564453125,
-0.04705810546875,
-0.039794921875,
0.035980224609375,
0.0360107421875,
0.0157928466796875,
0.00739288330078125,
-0.08258056640625,
0.0023937225341796875,
0.0192718505859375,
-0.0428466796875,
0.0303955078125,
0.038238525390625,
0.005542755126953125,
0.04345703125,
0.04864501953125,
0.01117706298828125,
0.0038204193115234375,
0.00022280216217041016,
0.07122802734375,
-0.054107666015625,
-0.038909912109375,
-0.055755615234375,
0.036407470703125,
-0.0218048095703125,
-0.0323486328125,
0.07818603515625,
0.05755615234375,
0.071044921875,
0.004119873046875,
0.0537109375,
-0.0153656005859375,
0.0340576171875,
-0.036712646484375,
0.056915283203125,
-0.061767578125,
-0.0023956298828125,
-0.03375244140625,
-0.054229736328125,
-0.0229949951171875,
0.05902099609375,
-0.0285797119140625,
0.013916015625,
0.0601806640625,
0.059844970703125,
0.0013780593872070312,
-0.0165252685546875,
0.0142059326171875,
0.032257080078125,
0.01381683349609375,
0.05828857421875,
0.025726318359375,
-0.07171630859375,
0.05389404296875,
-0.0360107421875,
-0.01006317138671875,
-0.01953125,
-0.044647216796875,
-0.06494140625,
-0.05859375,
-0.03216552734375,
-0.035797119140625,
-0.0022029876708984375,
0.0736083984375,
0.04779052734375,
-0.06597900390625,
-0.021270751953125,
-0.0014066696166992188,
0.0045623779296875,
-0.021484375,
-0.0179901123046875,
0.05902099609375,
-0.0263214111328125,
-0.06787109375,
0.01108551025390625,
-0.0001609325408935547,
0.006011962890625,
-0.004283905029296875,
-0.0221710205078125,
-0.049957275390625,
-0.008819580078125,
0.05352783203125,
0.01806640625,
-0.03900146484375,
-0.0015506744384765625,
0.006927490234375,
-0.026702880859375,
0.0124053955078125,
0.0066375732421875,
-0.029937744140625,
0.02764892578125,
0.0367431640625,
0.03155517578125,
0.058929443359375,
-0.0038814544677734375,
0.01544189453125,
-0.050201416015625,
0.022430419921875,
0.001926422119140625,
0.032989501953125,
0.0274810791015625,
-0.0269012451171875,
0.05853271484375,
0.0256500244140625,
-0.035400390625,
-0.05499267578125,
-0.018280029296875,
-0.08367919921875,
-0.015869140625,
0.09063720703125,
-0.023040771484375,
-0.03411865234375,
-0.0058135986328125,
-0.018524169921875,
0.024932861328125,
-0.033203125,
0.042083740234375,
0.057861328125,
-0.01100921630859375,
-0.0208892822265625,
-0.051361083984375,
0.04364013671875,
0.0330810546875,
-0.061309814453125,
-0.0092010498046875,
0.01441192626953125,
0.0288848876953125,
0.0159759521484375,
0.05426025390625,
-0.0142822265625,
0.0012912750244140625,
-0.0027866363525390625,
0.0081939697265625,
-0.006053924560546875,
0.0005803108215332031,
-0.00984954833984375,
0.0005273818969726562,
-0.0254058837890625,
-0.01293182373046875
]
] |
Rostlab/prot_bert_bfd | 2020-12-11T21:30:10.000Z | [
"transformers",
"pytorch",
"tf",
"fill-mask",
"protein language model",
"protein",
"dataset:BFD",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | Rostlab | null | null | Rostlab/prot_bert_bfd | 9 | 39,462 | transformers | 2022-03-02T23:29:04 | ---
language: protein
tags:
- protein language model
datasets:
- BFD
---
# ProtBert-BFD model
Pretrained model on protein sequences using a masked language modeling (MLM) objective. It was introduced in
[this paper](https://doi.org/10.1101/2020.07.12.199554) and first released in
[this repository](https://github.com/agemagician/ProtTrans). This model is trained on uppercase amino acids: it only works with capital letter amino acids.
## Model description
ProtBert-BFD is based on Bert model which pretrained on a large corpus of protein sequences in a self-supervised fashion.
This means it was pretrained on the raw protein sequences only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those protein sequences.
One important difference between our Bert model and the original Bert version is the way of dealing with sequences as separate documents
This means the Next sentence prediction is not used, as each sequence is treated as a complete document.
The masking follows the original Bert training with randomly masks 15% of the amino acids in the input.
At the end, the feature extracted from this model revealed that the LM-embeddings from unlabeled data (only protein sequences) captured important biophysical properties governing protein
shape.
This implied learning some of the grammar of the language of life realized in protein sequences.
## Intended uses & limitations
The model could be used for protein feature extraction or to be fine-tuned on downstream tasks.
We have noticed in some tasks you could gain more accuracy by fine-tuning the model rather than using it as a feature extractor.
### How to use
You can use this model directly with a pipeline for masked language modeling:
```python
>>> from transformers import BertForMaskedLM, BertTokenizer, pipeline
>>> tokenizer = BertTokenizer.from_pretrained('Rostlab/prot_bert_bfd', do_lower_case=False )
>>> model = BertForMaskedLM.from_pretrained("Rostlab/prot_bert_bfd")
>>> unmasker = pipeline('fill-mask', model=model, tokenizer=tokenizer)
>>> unmasker('D L I P T S S K L V V [MASK] D T S L Q V K K A F F A L V T')
[{'score': 0.1165614128112793,
'sequence': '[CLS] D L I P T S S K L V V L D T S L Q V K K A F F A L V T [SEP]',
'token': 5,
'token_str': 'L'},
{'score': 0.08976086974143982,
'sequence': '[CLS] D L I P T S S K L V V V D T S L Q V K K A F F A L V T [SEP]',
'token': 8,
'token_str': 'V'},
{'score': 0.08864385634660721,
'sequence': '[CLS] D L I P T S S K L V V S D T S L Q V K K A F F A L V T [SEP]',
'token': 10,
'token_str': 'S'},
{'score': 0.06227643042802811,
'sequence': '[CLS] D L I P T S S K L V V A D T S L Q V K K A F F A L V T [SEP]',
'token': 6,
'token_str': 'A'},
{'score': 0.06194969266653061,
'sequence': '[CLS] D L I P T S S K L V V T D T S L Q V K K A F F A L V T [SEP]',
'token': 15,
'token_str': 'T'}]
```
Here is how to use this model to get the features of a given protein sequence in PyTorch:
```python
from transformers import BertModel, BertTokenizer
import re
tokenizer = BertTokenizer.from_pretrained('Rostlab/prot_bert_bfd', do_lower_case=False )
model = BertModel.from_pretrained("Rostlab/prot_bert_bfd")
sequence_Example = "A E T C Z A O"
sequence_Example = re.sub(r"[UZOB]", "X", sequence_Example)
encoded_input = tokenizer(sequence_Example, return_tensors='pt')
output = model(**encoded_input)
```
## Training data
The ProtBert-BFD model was pretrained on [BFD](https://bfd.mmseqs.com/), a dataset consisting of 2.1 billion protein sequences.
## Training procedure
### Preprocessing
The protein sequences are uppercased and tokenized using a single space and a vocabulary size of 21.
The inputs of the model are then of the form:
```
[CLS] Protein Sequence A [SEP] Protein Sequence B [SEP]
```
Furthermore, each protein sequence was treated as a separate document.
The preprocessing step was performed twice, once for a combined length (2 sequences) of less than 512 amino acids, and another time using a combined length (2 sequences) of less than 2048 amino acids.
The details of the masking procedure for each sequence followed the original Bert model as following:
- 15% of the amino acids are masked.
- In 80% of the cases, the masked amino acids are replaced by `[MASK]`.
- In 10% of the cases, the masked amino acids are replaced by a random amino acid (different) from the one they replace.
- In the 10% remaining cases, the masked amino acids are left as is.
### Pretraining
The model was trained on a single TPU Pod V3-1024 for one million steps in total.
800k steps using sequence length 512 (batch size 32k), and 200K steps using sequence length 2048 (batch size 6k).
The optimizer used is Lamb with a learning rate of 0.002, a weight decay of 0.01, learning rate warmup for 140k steps and linear decay of the learning rate after.
## Evaluation results
When fine-tuned on downstream tasks, this model achieves the following results:
Test results :
| Task/Dataset | secondary structure (3-states) | secondary structure (8-states) | Localization | Membrane |
|:-----:|:-----:|:-----:|:-----:|:-----:|
| CASP12 | 76 | 65 | | |
| TS115 | 84 | 73 | | |
| CB513 | 83 | 70 | | |
| DeepLoc | | | 78 | 91 |
### BibTeX entry and citation info
```bibtex
@article {Elnaggar2020.07.12.199554,
author = {Elnaggar, Ahmed and Heinzinger, Michael and Dallago, Christian and Rehawi, Ghalia and Wang, Yu and Jones, Llion and Gibbs, Tom and Feher, Tamas and Angerer, Christoph and Steinegger, Martin and BHOWMIK, DEBSINDHU and Rost, Burkhard},
title = {ProtTrans: Towards Cracking the Language of Life{\textquoteright}s Code Through Self-Supervised Deep Learning and High Performance Computing},
elocation-id = {2020.07.12.199554},
year = {2020},
doi = {10.1101/2020.07.12.199554},
publisher = {Cold Spring Harbor Laboratory},
abstract = {Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive language models (Transformer-XL, XLNet) and two auto-encoder models (Bert, Albert) on data from UniRef and BFD containing up to 393 billion amino acids (words) from 2.1 billion protein sequences (22- and 112 times the entire English Wikipedia). The LMs were trained on the Summit supercomputer at Oak Ridge National Laboratory (ORNL), using 936 nodes (total 5616 GPUs) and one TPU Pod (V3-512 or V3-1024). We validated the advantage of up-scaling LMs to larger models supported by bigger data by predicting secondary structure (3-states: Q3=76-84, 8 states: Q8=65-73), sub-cellular localization for 10 cellular compartments (Q10=74) and whether a protein is membrane-bound or water-soluble (Q2=89). Dimensionality reduction revealed that the LM-embeddings from unlabeled data (only protein sequences) captured important biophysical properties governing protein shape. This implied learning some of the grammar of the language of life realized in protein sequences. The successful up-scaling of protein LMs through HPC to larger data sets slightly reduced the gap between models trained on evolutionary information and LMs. Availability ProtTrans: \<a href="https://github.com/agemagician/ProtTrans"\>https://github.com/agemagician/ProtTrans\</a\>Competing Interest StatementThe authors have declared no competing interest.},
URL = {https://www.biorxiv.org/content/early/2020/07/21/2020.07.12.199554},
eprint = {https://www.biorxiv.org/content/early/2020/07/21/2020.07.12.199554.full.pdf},
journal = {bioRxiv}
}
```
> Created by [Ahmed Elnaggar/@Elnaggar_AI](https://twitter.com/Elnaggar_AI) | [LinkedIn](https://www.linkedin.com/in/prof-ahmed-elnaggar/)
| 7,922 | [
[
-0.013275146484375,
-0.04498291015625,
0.0193634033203125,
0.0067138671875,
-0.024932861328125,
0.016510009765625,
0.0042572021484375,
-0.0222320556640625,
0.0280609130859375,
0.02789306640625,
-0.0430908203125,
-0.03106689453125,
-0.059173583984375,
0.0175628662109375,
-0.02642822265625,
0.072265625,
0.0171051025390625,
0.0251312255859375,
0.007720947265625,
-0.00042510032653808594,
0.0028209686279296875,
-0.047943115234375,
-0.03973388671875,
-0.030975341796875,
0.0465087890625,
0.0192413330078125,
0.041107177734375,
0.057220458984375,
0.03570556640625,
0.0224609375,
-0.020233154296875,
0.0027561187744140625,
-0.0307769775390625,
-0.0022296905517578125,
0.005828857421875,
-0.025634765625,
-0.04193115234375,
-0.0017843246459960938,
0.051300048828125,
0.06402587890625,
0.01241302490234375,
0.0257415771484375,
-0.0008249282836914062,
0.06182861328125,
-0.0286407470703125,
0.01922607421875,
-0.032196044921875,
0.00788116455078125,
-0.017486572265625,
0.01141357421875,
-0.0286407470703125,
-0.0196685791015625,
0.010955810546875,
-0.03076171875,
0.01433563232421875,
0.0036773681640625,
0.0736083984375,
0.00823974609375,
-0.01360321044921875,
-0.007537841796875,
-0.03973388671875,
0.0484619140625,
-0.0657958984375,
0.04522705078125,
0.029937744140625,
0.005718231201171875,
-0.033172607421875,
-0.070556640625,
-0.0433349609375,
-0.018402099609375,
-0.005748748779296875,
0.003238677978515625,
0.00417327880859375,
0.00876617431640625,
0.02520751953125,
0.0333251953125,
-0.054351806640625,
-0.0004284381866455078,
-0.052001953125,
-0.0226593017578125,
0.05731201171875,
-0.0123291015625,
0.0179290771484375,
-0.024871826171875,
-0.0175323486328125,
-0.026641845703125,
-0.0413818359375,
0.01467132568359375,
0.0306549072265625,
0.023284912109375,
-0.0005097389221191406,
0.049468994140625,
-0.01282501220703125,
0.041259765625,
0.00313568115234375,
0.0045623779296875,
0.0372314453125,
-0.0077056884765625,
-0.0305633544921875,
-0.0006403923034667969,
0.07061767578125,
-0.0010633468627929688,
0.0259552001953125,
-0.003383636474609375,
-0.009033203125,
-0.0233001708984375,
0.01432037353515625,
-0.056640625,
-0.04046630859375,
0.039093017578125,
-0.0462646484375,
-0.011566162109375,
0.0247955322265625,
-0.054931640625,
-0.00872802734375,
-0.01457977294921875,
0.05712890625,
-0.048065185546875,
-0.0031871795654296875,
0.013214111328125,
-0.01611328125,
0.0162200927734375,
-0.0009813308715820312,
-0.057373046875,
0.0159912109375,
0.028900146484375,
0.06512451171875,
-0.004913330078125,
-0.01184844970703125,
-0.0308837890625,
-0.002410888671875,
-0.007251739501953125,
0.0406494140625,
-0.03057861328125,
-0.0290985107421875,
-0.0108642578125,
0.019866943359375,
-0.005306243896484375,
-0.030487060546875,
0.030914306640625,
-0.040771484375,
0.005687713623046875,
-0.014923095703125,
-0.056671142578125,
-0.029693603515625,
-0.0099334716796875,
-0.056793212890625,
0.0789794921875,
0.016937255859375,
-0.04791259765625,
0.0173492431640625,
-0.0584716796875,
-0.031005859375,
0.021087646484375,
-0.0010900497436523438,
-0.03900146484375,
0.0032863616943359375,
0.01450347900390625,
0.03338623046875,
0.003986358642578125,
0.0228729248046875,
-0.0279693603515625,
-0.0202789306640625,
0.028228759765625,
-0.0018415451049804688,
0.0640869140625,
0.02496337890625,
-0.020965576171875,
0.00957489013671875,
-0.0732421875,
0.0220489501953125,
0.01152801513671875,
-0.037933349609375,
0.00669097900390625,
-0.00384521484375,
0.0025463104248046875,
0.018096923828125,
0.020416259765625,
-0.048095703125,
0.039794921875,
-0.037322998046875,
0.053955078125,
0.0587158203125,
0.0034656524658203125,
0.0222320556640625,
-0.02081298828125,
0.02777099609375,
0.005786895751953125,
0.0098724365234375,
-0.00214385986328125,
-0.04852294921875,
-0.05426025390625,
-0.03680419921875,
0.046844482421875,
0.04608154296875,
-0.034820556640625,
0.053466796875,
-0.01369476318359375,
-0.04669189453125,
-0.051971435546875,
-0.0013170242309570312,
0.03271484375,
0.01331329345703125,
0.04791259765625,
-0.030242919921875,
-0.060394287109375,
-0.0694580078125,
-0.01532745361328125,
-0.01110076904296875,
-0.0163726806640625,
0.01219940185546875,
0.057952880859375,
-0.023040771484375,
0.0584716796875,
-0.038482666015625,
-0.0188140869140625,
-0.0245361328125,
0.0006937980651855469,
0.03863525390625,
0.055023193359375,
0.018157958984375,
-0.047637939453125,
-0.03436279296875,
-0.02301025390625,
-0.04827880859375,
-0.003582000732421875,
0.00513458251953125,
-0.002635955810546875,
0.010345458984375,
0.033599853515625,
-0.04998779296875,
0.039947509765625,
0.0272979736328125,
-0.0230712890625,
0.04388427734375,
-0.0294189453125,
-0.0046234130859375,
-0.0784912109375,
0.02081298828125,
-0.01328277587890625,
-0.01427459716796875,
-0.06298828125,
-0.004665374755859375,
-0.0021762847900390625,
-0.0005283355712890625,
-0.047119140625,
0.04132080078125,
-0.040283203125,
-0.01007080078125,
-0.002410888671875,
-0.0192413330078125,
-0.002758026123046875,
0.0447998046875,
0.0010089874267578125,
0.042633056640625,
0.037750244140625,
-0.0489501953125,
0.01544189453125,
0.03802490234375,
-0.033203125,
-0.016632080078125,
-0.06524658203125,
0.0069427490234375,
-0.0032291412353515625,
0.0242156982421875,
-0.0689697265625,
-0.01349639892578125,
0.0265960693359375,
-0.048126220703125,
0.023651123046875,
-0.0003018379211425781,
-0.038818359375,
-0.04046630859375,
-0.0219879150390625,
0.035064697265625,
0.046173095703125,
-0.022613525390625,
0.034698486328125,
0.0217742919921875,
-0.0038471221923828125,
-0.042999267578125,
-0.049774169921875,
-0.0122528076171875,
-0.0015401840209960938,
-0.036407470703125,
0.041168212890625,
-0.011505126953125,
0.00505828857421875,
-0.01099395751953125,
-0.0179443359375,
0.0034656524658203125,
-0.0097503662109375,
0.025238037109375,
0.005687713623046875,
-0.007045745849609375,
0.00276947021484375,
-0.01371002197265625,
-0.0025730133056640625,
-0.007568359375,
-0.037628173828125,
0.060394287109375,
-0.006801605224609375,
-0.005138397216796875,
-0.035064697265625,
0.03326416015625,
0.04400634765625,
-0.014739990234375,
0.061676025390625,
0.055023193359375,
-0.039764404296875,
0.0019407272338867188,
-0.0271759033203125,
-0.0205230712890625,
-0.035980224609375,
0.038604736328125,
-0.0306549072265625,
-0.0574951171875,
0.0555419921875,
0.0109405517578125,
-0.01308441162109375,
0.04815673828125,
0.033233642578125,
-0.020751953125,
0.06622314453125,
0.050933837890625,
0.0026607513427734375,
0.034637451171875,
-0.049591064453125,
0.032440185546875,
-0.0634765625,
-0.03515625,
-0.03460693359375,
-0.033935546875,
-0.047515869140625,
-0.0279693603515625,
0.0236968994140625,
0.031494140625,
-0.028717041015625,
0.041168212890625,
-0.0272979736328125,
0.0221710205078125,
0.06378173828125,
0.033416748046875,
-0.0081634521484375,
0.0021381378173828125,
-0.0309906005859375,
0.00305938720703125,
-0.06072998046875,
-0.03204345703125,
0.0941162109375,
0.03900146484375,
0.03973388671875,
0.009429931640625,
0.055511474609375,
0.034149169921875,
-0.0006284713745117188,
-0.056182861328125,
0.042633056640625,
-0.0318603515625,
-0.0491943359375,
-0.0276336669921875,
-0.015289306640625,
-0.07293701171875,
0.0018138885498046875,
-0.0224609375,
-0.07196044921875,
0.0255889892578125,
-0.0002371072769165039,
-0.03155517578125,
0.0186004638671875,
-0.046173095703125,
0.07330322265625,
-0.01470947265625,
-0.0172576904296875,
0.003589630126953125,
-0.07550048828125,
0.0164031982421875,
-0.00972747802734375,
0.014617919921875,
0.00131988525390625,
0.0196685791015625,
0.079345703125,
-0.0506591796875,
0.06524658203125,
-0.00811004638671875,
0.004779815673828125,
0.015869140625,
0.0030879974365234375,
0.026641845703125,
0.006198883056640625,
-0.002079010009765625,
0.0228729248046875,
0.01013946533203125,
-0.04644775390625,
-0.01364898681640625,
0.03118896484375,
-0.06494140625,
-0.03338623046875,
-0.03790283203125,
-0.037200927734375,
0.0081787109375,
0.0212249755859375,
0.044097900390625,
0.040771484375,
0.00820159912109375,
0.02691650390625,
0.050689697265625,
-0.0304718017578125,
0.049285888671875,
0.030242919921875,
-0.0189361572265625,
-0.047119140625,
0.056640625,
0.0208892822265625,
0.0163116455078125,
0.03839111328125,
0.01013946533203125,
-0.04315185546875,
-0.0489501953125,
-0.015289306640625,
0.0196685791015625,
-0.04693603515625,
-0.0233001708984375,
-0.06341552734375,
-0.04327392578125,
-0.04840087890625,
0.004558563232421875,
-0.0268096923828125,
-0.040924072265625,
-0.0187530517578125,
-0.0120849609375,
0.0269317626953125,
0.046783447265625,
-0.029571533203125,
0.0269775390625,
-0.0758056640625,
0.0284271240234375,
0.01407623291015625,
0.018035888671875,
-0.0190277099609375,
-0.060211181640625,
-0.0228118896484375,
0.0133209228515625,
-0.02197265625,
-0.0791015625,
0.048431396484375,
0.051300048828125,
0.05548095703125,
0.01312255859375,
-0.0006895065307617188,
0.035064697265625,
-0.038299560546875,
0.0736083984375,
-0.0048675537109375,
-0.070068359375,
0.05517578125,
-0.0158233642578125,
0.028076171875,
0.025634765625,
0.049407958984375,
-0.0214080810546875,
-0.033111572265625,
-0.07293701171875,
-0.08343505859375,
0.04705810546875,
0.0249176025390625,
-0.01079559326171875,
-0.007068634033203125,
0.038909912109375,
0.01422119140625,
0.01236724853515625,
-0.0706787109375,
-0.037384033203125,
-0.0211334228515625,
-0.0243988037109375,
-0.01177978515625,
-0.024261474609375,
0.0018711090087890625,
-0.0411376953125,
0.0667724609375,
-0.0020236968994140625,
0.044677734375,
0.03399658203125,
-0.02716064453125,
0.004367828369140625,
0.007152557373046875,
0.054656982421875,
0.040130615234375,
-0.0467529296875,
0.005329132080078125,
-0.0037288665771484375,
-0.061309814453125,
0.006500244140625,
0.01317596435546875,
-0.01348876953125,
-0.0011081695556640625,
0.0433349609375,
0.0576171875,
-0.000013113021850585938,
-0.042266845703125,
0.022796630859375,
0.0155487060546875,
-0.0230560302734375,
-0.0117645263671875,
-0.0018596649169921875,
-0.0024566650390625,
0.0338134765625,
0.049835205078125,
-0.004337310791015625,
0.005786895751953125,
-0.03564453125,
0.04083251953125,
0.0182342529296875,
-0.025177001953125,
-0.032379150390625,
0.05224609375,
-0.002506256103515625,
-0.03497314453125,
0.05035400390625,
-0.0215606689453125,
-0.05743408203125,
0.049072265625,
0.04461669921875,
0.0714111328125,
-0.022705078125,
0.0188140869140625,
0.04705810546875,
0.015716552734375,
-0.01045989990234375,
0.033355712890625,
0.0162811279296875,
-0.05499267578125,
-0.028106689453125,
-0.086181640625,
-0.0029888153076171875,
0.0389404296875,
-0.040924072265625,
0.01120758056640625,
-0.0379638671875,
-0.01361846923828125,
0.00872039794921875,
0.015838623046875,
-0.04656982421875,
0.024993896484375,
0.01206207275390625,
0.07647705078125,
-0.0733642578125,
0.0865478515625,
0.057830810546875,
-0.0439453125,
-0.05267333984375,
-0.0121917724609375,
-0.0167388916015625,
-0.063232421875,
0.07745361328125,
0.0244598388671875,
0.02178955078125,
0.01702880859375,
-0.045135498046875,
-0.0767822265625,
0.07427978515625,
0.0108184814453125,
-0.052001953125,
-0.0005669593811035156,
0.0102081298828125,
0.046295166015625,
-0.029693603515625,
0.013336181640625,
0.044769287109375,
0.0288848876953125,
0.001346588134765625,
-0.057220458984375,
0.0036334991455078125,
-0.02789306640625,
-0.0040283203125,
0.00716400146484375,
-0.038604736328125,
0.06842041015625,
-0.0194091796875,
-0.007503509521484375,
0.00405120849609375,
0.056304931640625,
0.020294189453125,
-0.003917694091796875,
0.01503753662109375,
0.047607421875,
0.049102783203125,
-0.0093231201171875,
0.056671142578125,
-0.02490234375,
0.033782958984375,
0.0621337890625,
0.0030384063720703125,
0.07122802734375,
0.043243408203125,
-0.037567138671875,
0.04229736328125,
0.0635986328125,
-0.014617919921875,
0.0579833984375,
0.034515380859375,
-0.002033233642578125,
-0.0178375244140625,
0.004802703857421875,
-0.0362548828125,
0.031707763671875,
0.037445068359375,
-0.0322265625,
0.006603240966796875,
-0.0014619827270507812,
-0.007526397705078125,
-0.0107421875,
-0.02313232421875,
0.047821044921875,
0.01508331298828125,
-0.0309906005859375,
0.05096435546875,
-0.002101898193359375,
0.041259765625,
-0.046112060546875,
0.003711700439453125,
-0.02362060546875,
0.018402099609375,
-0.0070953369140625,
-0.050628662109375,
0.018463134765625,
-0.015289306640625,
-0.0254669189453125,
-0.0105438232421875,
0.0465087890625,
-0.034393310546875,
-0.048187255859375,
0.0221710205078125,
0.0311737060546875,
0.02301025390625,
-0.004016876220703125,
-0.060455322265625,
-0.00434112548828125,
0.0006732940673828125,
-0.0296630859375,
0.0224609375,
0.01274871826171875,
0.00664520263671875,
0.06048583984375,
0.0484619140625,
0.0021114349365234375,
0.0109100341796875,
-0.010986328125,
0.061859130859375,
-0.0665283203125,
-0.030059814453125,
-0.06536865234375,
0.043670654296875,
0.003936767578125,
-0.019012451171875,
0.0311431884765625,
0.051025390625,
0.06787109375,
-0.033538818359375,
0.0474853515625,
-0.020660400390625,
0.0299835205078125,
-0.044647216796875,
0.0552978515625,
-0.033905029296875,
0.007266998291015625,
-0.0088348388671875,
-0.07440185546875,
-0.0272064208984375,
0.05584716796875,
-0.005344390869140625,
0.00262451171875,
0.0601806640625,
0.05364990234375,
0.009918212890625,
-0.010894775390625,
0.0103607177734375,
0.03082275390625,
0.029754638671875,
0.04669189453125,
0.03143310546875,
-0.063720703125,
0.0238189697265625,
-0.022003173828125,
-0.00476837158203125,
-0.0297698974609375,
-0.07568359375,
-0.06353759765625,
-0.055023193359375,
-0.030975341796875,
-0.0406494140625,
0.01479339599609375,
0.07989501953125,
0.051300048828125,
-0.083984375,
-0.01444244384765625,
-0.00612640380859375,
-0.01013946533203125,
-0.02313232421875,
-0.0171051025390625,
0.045440673828125,
-0.017913818359375,
-0.03900146484375,
0.035980224609375,
0.003940582275390625,
0.023712158203125,
-0.0043182373046875,
-0.0095062255859375,
-0.05224609375,
0.005615234375,
0.043121337890625,
0.0361328125,
-0.06121826171875,
-0.035736083984375,
0.00836944580078125,
-0.00772857666015625,
0.0109405517578125,
0.0313720703125,
-0.056884765625,
0.01399993896484375,
0.049285888671875,
0.039794921875,
0.04693603515625,
-0.004703521728515625,
0.054840087890625,
-0.0687255859375,
0.0088043212890625,
0.0036106109619140625,
0.0255126953125,
0.02032470703125,
-0.0226287841796875,
0.0394287109375,
0.039886474609375,
-0.046173095703125,
-0.058197021484375,
0.008056640625,
-0.0830078125,
-0.0243377685546875,
0.0826416015625,
-0.0145111083984375,
-0.0285186767578125,
0.00347137451171875,
-0.0123748779296875,
0.04730224609375,
-0.0211181640625,
0.0557861328125,
0.04840087890625,
-0.00609588623046875,
-0.0088653564453125,
-0.037078857421875,
0.05914306640625,
0.032562255859375,
-0.037750244140625,
-0.013580322265625,
0.01088714599609375,
0.024139404296875,
0.01202392578125,
0.03765869140625,
-0.01027679443359375,
0.0051727294921875,
-0.0069732666015625,
0.014984130859375,
-0.01160430908203125,
-0.02685546875,
-0.0309295654296875,
0.01013946533203125,
-0.011627197265625,
-0.02532958984375
]
] |
kresnik/wav2vec2-large-xlsr-korean | 2023-07-03T14:55:40.000Z | [
"transformers",
"pytorch",
"safetensors",
"wav2vec2",
"automatic-speech-recognition",
"speech",
"audio",
"ko",
"dataset:kresnik/zeroth_korean",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | automatic-speech-recognition | kresnik | null | null | kresnik/wav2vec2-large-xlsr-korean | 25 | 39,408 | transformers | 2022-03-02T23:29:05 | ---
language: ko
datasets:
- kresnik/zeroth_korean
tags:
- speech
- audio
- automatic-speech-recognition
license: apache-2.0
model-index:
- name: 'Wav2Vec2 XLSR Korean'
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Zeroth Korean
type: kresnik/zeroth_korean
args: clean
metrics:
- name: Test WER
type: wer
value: 4.74
- name: Test CER
type: cer
value: 1.78
---
## Evaluation on Zeroth-Korean ASR corpus
[Google colab notebook(Korean)](https://colab.research.google.com/github/indra622/tutorials/blob/master/wav2vec2_korean_tutorial.ipynb)
```
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
from datasets import load_dataset
import soundfile as sf
import torch
from jiwer import wer
processor = Wav2Vec2Processor.from_pretrained("kresnik/wav2vec2-large-xlsr-korean")
model = Wav2Vec2ForCTC.from_pretrained("kresnik/wav2vec2-large-xlsr-korean").to('cuda')
ds = load_dataset("kresnik/zeroth_korean", "clean")
test_ds = ds['test']
def map_to_array(batch):
speech, _ = sf.read(batch["file"])
batch["speech"] = speech
return batch
test_ds = test_ds.map(map_to_array)
def map_to_pred(batch):
inputs = processor(batch["speech"], sampling_rate=16000, return_tensors="pt", padding="longest")
input_values = inputs.input_values.to("cuda")
with torch.no_grad():
logits = model(input_values).logits
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)
batch["transcription"] = transcription
return batch
result = test_ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=["speech"])
print("WER:", wer(result["text"], result["transcription"]))
```
### Expected WER: 4.74%
### Expected CER: 1.78% | 1,891 | [
[
-0.017364501953125,
-0.04266357421875,
0.0111083984375,
0.033843994140625,
-0.019439697265625,
0.00970458984375,
-0.041351318359375,
-0.0186004638671875,
-0.0025234222412109375,
0.015167236328125,
-0.02301025390625,
-0.06109619140625,
-0.0477294921875,
-0.009765625,
-0.026519775390625,
0.07391357421875,
0.0098876953125,
0.0135040283203125,
-0.00453948974609375,
-0.01056671142578125,
-0.0291595458984375,
-0.024169921875,
-0.04974365234375,
-0.0229644775390625,
-0.005279541015625,
0.037353515625,
0.015411376953125,
0.0154266357421875,
0.0185699462890625,
0.029510498046875,
-0.01143646240234375,
-0.0276641845703125,
-0.039581298828125,
0.004428863525390625,
0.0158843994140625,
-0.029083251953125,
-0.0221710205078125,
0.006450653076171875,
0.046295166015625,
0.039031982421875,
-0.0059661865234375,
0.036956787109375,
-0.01517486572265625,
0.03173828125,
-0.0308380126953125,
0.0202789306640625,
-0.0430908203125,
-0.017181396484375,
-0.009246826171875,
-0.002777099609375,
-0.038665771484375,
-0.0237884521484375,
0.00948333740234375,
-0.0445556640625,
0.024993896484375,
-0.017730712890625,
0.08233642578125,
0.0254669189453125,
-0.0275726318359375,
-0.04345703125,
-0.045867919921875,
0.060882568359375,
-0.044219970703125,
0.034332275390625,
0.0307464599609375,
0.004337310791015625,
-0.0002505779266357422,
-0.0755615234375,
-0.042877197265625,
-0.0130462646484375,
0.016815185546875,
0.0302734375,
-0.018463134765625,
0.00467681884765625,
0.033477783203125,
0.030792236328125,
-0.04754638671875,
-0.0120697021484375,
-0.06524658203125,
-0.02874755859375,
0.046051025390625,
-0.0174102783203125,
0.0116424560546875,
-0.0168304443359375,
-0.0190582275390625,
-0.043060302734375,
-0.0176849365234375,
0.0187225341796875,
0.0419921875,
0.0177459716796875,
-0.0290679931640625,
0.040435791015625,
-0.005764007568359375,
0.0447998046875,
0.019989013671875,
-0.017578125,
0.061859130859375,
-0.017669677734375,
-0.0208587646484375,
0.037078857421875,
0.07183837890625,
0.01134490966796875,
0.0197906494140625,
-0.001361846923828125,
0.003582000732421875,
0.0362548828125,
0.003314971923828125,
-0.06939697265625,
-0.03997802734375,
0.034332275390625,
-0.0196990966796875,
-0.00168609619140625,
0.0032501220703125,
-0.049560546875,
-0.0007038116455078125,
-0.01021575927734375,
0.06512451171875,
-0.038665771484375,
-0.0214996337890625,
0.01415252685546875,
-0.01268768310546875,
0.0279541015625,
-0.0272979736328125,
-0.052093505859375,
0.024444580078125,
0.0345458984375,
0.04827880859375,
0.0093536376953125,
-0.0157928466796875,
-0.0282135009765625,
-0.0263214111328125,
-0.0224151611328125,
0.045684814453125,
0.00284576416015625,
-0.057464599609375,
-0.01392364501953125,
-0.006038665771484375,
-0.0240478515625,
-0.042205810546875,
0.07861328125,
-0.031982421875,
0.02459716796875,
-0.00926971435546875,
-0.036895751953125,
-0.020721435546875,
-0.0236358642578125,
-0.0245208740234375,
0.08184814453125,
0.02142333984375,
-0.039825439453125,
0.02294921875,
-0.047821044921875,
-0.050567626953125,
-0.01371002197265625,
-0.0209503173828125,
-0.045928955078125,
-0.0007076263427734375,
0.005954742431640625,
0.01885986328125,
-0.0189971923828125,
0.0150604248046875,
0.0022068023681640625,
-0.050018310546875,
0.0279541015625,
-0.02294921875,
0.087890625,
0.0299224853515625,
-0.04095458984375,
0.02716064453125,
-0.07379150390625,
0.025909423828125,
-0.00910186767578125,
-0.02142333984375,
-0.0006937980651855469,
-0.028594970703125,
0.031890869140625,
0.0143890380859375,
0.012847900390625,
-0.062469482421875,
-0.005428314208984375,
-0.047210693359375,
0.022613525390625,
0.031524658203125,
-0.0092010498046875,
0.0194244384765625,
-0.00617218017578125,
0.031585693359375,
-0.01255035400390625,
-0.017242431640625,
0.007305145263671875,
-0.03369140625,
-0.05328369140625,
-0.04766845703125,
0.037567138671875,
0.04351806640625,
-0.0328369140625,
0.0465087890625,
-0.0191650390625,
-0.057708740234375,
-0.0753173828125,
-0.0264739990234375,
0.0399169921875,
0.058441162109375,
0.03631591796875,
-0.01235198974609375,
-0.07098388671875,
-0.055633544921875,
0.004955291748046875,
-0.005096435546875,
-0.0213470458984375,
0.0036106109619140625,
0.0340576171875,
-0.033233642578125,
0.052642822265625,
-0.03631591796875,
-0.02001953125,
-0.0146484375,
0.0178680419921875,
0.05487060546875,
0.0399169921875,
0.00853729248046875,
-0.037200927734375,
-0.0596923828125,
-0.0190582275390625,
-0.0340576171875,
-0.02685546875,
-0.005718231201171875,
-0.00823211669921875,
0.02984619140625,
0.03070068359375,
-0.0465087890625,
0.0275421142578125,
0.0260162353515625,
-0.0498046875,
0.04034423828125,
-0.01500701904296875,
0.0264892578125,
-0.0745849609375,
0.0235137939453125,
-0.024871826171875,
0.00412750244140625,
-0.04974365234375,
-0.01236724853515625,
0.0008668899536132812,
0.0012369155883789062,
-0.0258026123046875,
0.028778076171875,
-0.030609130859375,
-0.014373779296875,
-0.01540374755859375,
0.01531982421875,
-0.00844573974609375,
0.0297393798828125,
-0.0030345916748046875,
0.058258056640625,
0.056854248046875,
-0.042266845703125,
0.0243988037109375,
0.048980712890625,
-0.03759765625,
0.0126800537109375,
-0.0687255859375,
0.02166748046875,
0.01132965087890625,
0.005107879638671875,
-0.08551025390625,
-0.0010995864868164062,
0.0103302001953125,
-0.07513427734375,
0.0280914306640625,
-0.006038665771484375,
-0.019866943359375,
-0.0263519287109375,
-0.0293731689453125,
0.03192138671875,
0.06353759765625,
-0.034210205078125,
0.0242156982421875,
0.0311737060546875,
0.00490570068359375,
-0.046844482421875,
-0.049407958984375,
-0.02587890625,
-0.0087890625,
-0.059967041015625,
0.0249786376953125,
-0.008270263671875,
-0.0120391845703125,
-0.004856109619140625,
-0.0265960693359375,
0.0098419189453125,
-0.014862060546875,
0.0341796875,
0.037841796875,
-0.01824951171875,
-0.022064208984375,
-0.02056884765625,
-0.021636962890625,
0.011260986328125,
-0.0111846923828125,
0.061492919921875,
-0.0246734619140625,
-0.019317626953125,
-0.033599853515625,
-0.007564544677734375,
0.03564453125,
0.001735687255859375,
0.031768798828125,
0.0819091796875,
-0.0179595947265625,
0.0159912109375,
-0.0313720703125,
0.00968170166015625,
-0.036712646484375,
0.05108642578125,
-0.037506103515625,
-0.0364990234375,
0.050506591796875,
0.0174407958984375,
-0.0146484375,
0.060546875,
0.058380126953125,
0.0016527175903320312,
0.0489501953125,
0.0033721923828125,
0.0013475418090820312,
0.0120391845703125,
-0.0654296875,
0.01419830322265625,
-0.081298828125,
-0.0232086181640625,
-0.050567626953125,
-0.0083770751953125,
-0.059234619140625,
-0.03533935546875,
0.024505615234375,
0.005260467529296875,
-0.026336669921875,
0.0287628173828125,
-0.046630859375,
0.0184326171875,
0.049957275390625,
-0.0188140869140625,
-0.006107330322265625,
0.006557464599609375,
-0.01019287109375,
0.00018334388732910156,
-0.03228759765625,
-0.020416259765625,
0.09735107421875,
0.0196380615234375,
0.046417236328125,
-0.01061248779296875,
0.044403076171875,
-0.005687713623046875,
-0.007053375244140625,
-0.0640869140625,
0.0340576171875,
-0.0204315185546875,
-0.03173828125,
-0.0233154296875,
-0.0145263671875,
-0.080322265625,
0.0231475830078125,
-0.002849578857421875,
-0.058868408203125,
0.00705718994140625,
-0.0101165771484375,
-0.032928466796875,
-0.005496978759765625,
-0.0555419921875,
0.06427001953125,
0.00783538818359375,
-0.01248931884765625,
0.00281524658203125,
-0.045867919921875,
0.016204833984375,
0.01129150390625,
-0.005550384521484375,
-0.0014390945434570312,
0.026031494140625,
0.09210205078125,
-0.009552001953125,
0.025604248046875,
-0.02655029296875,
0.01172637939453125,
0.047943115234375,
-0.0158233642578125,
0.01617431640625,
-0.0015850067138671875,
-0.024017333984375,
0.043182373046875,
0.0185394287109375,
-0.0198211669921875,
-0.01174163818359375,
0.0626220703125,
-0.08111572265625,
-0.02044677734375,
-0.045623779296875,
-0.038726806640625,
-0.015533447265625,
0.004047393798828125,
0.058563232421875,
0.0460205078125,
-0.00891876220703125,
0.034881591796875,
0.03997802734375,
-0.0155029296875,
0.0302734375,
0.018402099609375,
-0.02154541015625,
-0.057281494140625,
0.06494140625,
0.008941650390625,
0.01476287841796875,
-0.00595855712890625,
0.00785064697265625,
-0.054443359375,
-0.0312347412109375,
-0.0343017578125,
0.005596160888671875,
-0.04449462890625,
-0.00839996337890625,
-0.046722412109375,
-0.03607177734375,
-0.054351806640625,
-0.0054931640625,
-0.034820556640625,
-0.0301666259765625,
-0.028411865234375,
-0.004852294921875,
0.02838134765625,
0.0231475830078125,
-0.020233154296875,
0.03350830078125,
-0.034332275390625,
0.045257568359375,
-0.00600433349609375,
0.0111236572265625,
-0.0147857666015625,
-0.0777587890625,
-0.0166168212890625,
-0.004688262939453125,
-0.01385498046875,
-0.060516357421875,
0.044403076171875,
0.003063201904296875,
0.038055419921875,
0.01513671875,
-0.0005817413330078125,
0.058837890625,
-0.02435302734375,
0.057220458984375,
0.0074310302734375,
-0.08209228515625,
0.020477294921875,
-0.00937652587890625,
0.034393310546875,
0.04620361328125,
0.014678955078125,
-0.04302978515625,
-0.0135345458984375,
-0.059661865234375,
-0.09130859375,
0.0687255859375,
0.027252197265625,
-0.002620697021484375,
0.00725555419921875,
0.0009641647338867188,
0.0038738250732421875,
0.0031986236572265625,
-0.03948974609375,
-0.043426513671875,
-0.025909423828125,
-0.027191162109375,
-0.0174102783203125,
-0.029205322265625,
-0.0011138916015625,
-0.0278472900390625,
0.0750732421875,
0.020172119140625,
0.04168701171875,
0.037353515625,
-0.006412506103515625,
0.0001920461654663086,
0.025482177734375,
0.057281494140625,
0.0301971435546875,
-0.04095458984375,
0.006755828857421875,
0.0205841064453125,
-0.0653076171875,
0.003437042236328125,
0.0126800537109375,
-0.00849151611328125,
0.00946807861328125,
0.0255584716796875,
0.07769775390625,
-0.0031299591064453125,
-0.03253173828125,
0.032623291015625,
-0.0162506103515625,
-0.0269775390625,
-0.056243896484375,
-0.003948211669921875,
0.0262908935546875,
-0.0009250640869140625,
0.042083740234375,
0.0132598876953125,
0.006603240966796875,
-0.0211334228515625,
0.0191650390625,
0.01424407958984375,
-0.034210205078125,
-0.0218353271484375,
0.05389404296875,
-0.0050201416015625,
-0.025146484375,
0.056243896484375,
-0.0253143310546875,
-0.044830322265625,
0.052734375,
0.053192138671875,
0.0721435546875,
-0.00894927978515625,
-0.015869140625,
0.057281494140625,
0.0092926025390625,
0.0087890625,
0.04925537109375,
-0.004825592041015625,
-0.040771484375,
-0.03155517578125,
-0.05645751953125,
0.0009250640869140625,
0.0247039794921875,
-0.05572509765625,
0.0307159423828125,
-0.005870819091796875,
-0.0075225830078125,
0.0022106170654296875,
0.022369384765625,
-0.042083740234375,
0.016998291015625,
-0.0004162788391113281,
0.057891845703125,
-0.056243896484375,
0.06744384765625,
0.024566650390625,
-0.0299224853515625,
-0.07659912109375,
0.0015153884887695312,
-0.0224761962890625,
-0.049041748046875,
0.05596923828125,
0.0111846923828125,
-0.017578125,
0.0047454833984375,
-0.01561737060546875,
-0.07183837890625,
0.0797119140625,
0.0275115966796875,
-0.0288543701171875,
0.039093017578125,
-0.00455474853515625,
0.051666259765625,
-0.006122589111328125,
0.033966064453125,
0.0472412109375,
0.035430908203125,
0.0172271728515625,
-0.07427978515625,
-0.0054473876953125,
-0.0186767578125,
-0.01534271240234375,
-0.00675201416015625,
-0.029541015625,
0.076904296875,
-0.0270843505859375,
-0.0233612060546875,
0.006168365478515625,
0.0643310546875,
0.04083251953125,
0.044952392578125,
0.033721923828125,
0.045257568359375,
0.05908203125,
-0.005565643310546875,
0.06182861328125,
-0.02032470703125,
0.032745361328125,
0.084716796875,
-0.00894927978515625,
0.06524658203125,
0.033416748046875,
-0.0262451171875,
0.037841796875,
0.034332275390625,
-0.01367950439453125,
0.05224609375,
0.0311431884765625,
-0.0273590087890625,
0.0187530517578125,
0.01421356201171875,
-0.04547119140625,
0.06317138671875,
0.0200958251953125,
-0.00263214111328125,
0.01522064208984375,
-0.00830841064453125,
0.007289886474609375,
0.0077667236328125,
-0.014984130859375,
0.0316162109375,
-0.00791168212890625,
-0.041259765625,
0.06744384765625,
0.006622314453125,
0.0645751953125,
-0.03399658203125,
0.0021305084228515625,
0.0181427001953125,
0.020538330078125,
-0.0267791748046875,
-0.043243408203125,
0.0338134765625,
0.00426483154296875,
-0.01800537109375,
0.005657196044921875,
0.04351806640625,
-0.04608154296875,
-0.039520263671875,
0.0298919677734375,
0.00933837890625,
0.037506103515625,
0.005275726318359375,
-0.0247344970703125,
0.0206451416015625,
0.025543212890625,
-0.0230712890625,
0.0093841552734375,
0.00499725341796875,
0.01006317138671875,
0.0169830322265625,
0.05853271484375,
0.019378662109375,
0.0159912109375,
0.0089874267578125,
0.0302581787109375,
-0.047698974609375,
-0.0289154052734375,
-0.05218505859375,
0.03265380859375,
-0.005649566650390625,
-0.0308074951171875,
0.05242919921875,
0.06854248046875,
0.07562255859375,
-0.0253143310546875,
0.048675537109375,
-0.0267486572265625,
0.03997802734375,
-0.0288543701171875,
0.06744384765625,
-0.00807952880859375,
0.0054473876953125,
-0.00849151611328125,
-0.049041748046875,
-0.006744384765625,
0.06829833984375,
-0.0214385986328125,
0.0005249977111816406,
0.05853271484375,
0.07281494140625,
0.00261688232421875,
-0.0062713623046875,
0.035064697265625,
0.0362548828125,
0.007068634033203125,
0.035491943359375,
0.0361328125,
-0.07415771484375,
0.05389404296875,
-0.027496337890625,
-0.00382232666015625,
0.00524139404296875,
-0.034912109375,
-0.04034423828125,
-0.06207275390625,
-0.031982421875,
-0.0489501953125,
-0.0136260986328125,
0.07940673828125,
0.040618896484375,
-0.0799560546875,
-0.033233642578125,
0.013580322265625,
-0.0031032562255859375,
-0.00807952880859375,
-0.0181427001953125,
0.06732177734375,
-0.0050506591796875,
-0.06329345703125,
0.04620361328125,
-0.0140228271484375,
-0.0216522216796875,
0.01025390625,
-0.0209503173828125,
-0.0263519287109375,
-0.008941650390625,
0.03289794921875,
0.02862548828125,
-0.05279541015625,
-0.015869140625,
0.0007028579711914062,
-0.0234222412109375,
0.01091766357421875,
0.018646240234375,
-0.0595703125,
0.03863525390625,
0.045379638671875,
0.027496337890625,
0.061676025390625,
-0.0142822265625,
0.0125732421875,
-0.0465087890625,
0.019683837890625,
0.00995635986328125,
0.02032470703125,
0.03253173828125,
-0.0232086181640625,
0.0404052734375,
0.01113128662109375,
-0.05828857421875,
-0.0589599609375,
-0.0198211669921875,
-0.10186767578125,
0.00458526611328125,
0.10174560546875,
-0.00911712646484375,
-0.0187835693359375,
-0.0020751953125,
-0.0360107421875,
0.0706787109375,
-0.03363037109375,
0.058746337890625,
0.03607177734375,
-0.023406982421875,
0.038604736328125,
-0.042816162109375,
0.0313720703125,
0.0277099609375,
-0.0325927734375,
-0.006961822509765625,
0.0208892822265625,
0.044769287109375,
0.0233612060546875,
0.072998046875,
-0.021697998046875,
0.0232391357421875,
0.036407470703125,
0.044158935546875,
-0.0104827880859375,
0.0006618499755859375,
-0.05133056640625,
0.01032257080078125,
-0.004039764404296875,
-0.056640625
]
] |
facebook/sam-vit-huge | 2023-07-11T15:07:59.000Z | [
"transformers",
"pytorch",
"tf",
"sam",
"mask-generation",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | null | facebook | null | null | facebook/sam-vit-huge | 49 | 39,352 | transformers | 2023-04-10T13:51:24 | ---
license: apache-2.0
---
# Model Card for Segment Anything Model (SAM) - ViT Huge (ViT-H) version
<p>
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-architecture.png" alt="Model architecture">
<em> Detailed architecture of Segment Anything Model (SAM).</em>
</p>
# Table of Contents
0. [TL;DR](#TL;DR)
1. [Model Details](#model-details)
2. [Usage](#usage)
3. [Citation](#citation)
# TL;DR
[Link to original repository](https://github.com/facebookresearch/segment-anything)
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-beancans.png" alt="Snow" width="600" height="600"> | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-dog-masks.png" alt="Forest" width="600" height="600"> | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/sam-car-seg.png" alt="Mountains" width="600" height="600"> |
|---------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|
The **Segment Anything Model (SAM)** produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a [dataset](https://segment-anything.com/dataset/index.html) of 11 million images and 1.1 billion masks, and has strong zero-shot performance on a variety of segmentation tasks.
The abstract of the paper states:
> We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at [https://segment-anything.com](https://segment-anything.com) to foster research into foundation models for computer vision.
**Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the original [SAM model card](https://github.com/facebookresearch/segment-anything).
# Model Details
The SAM model is made up of 3 modules:
- The `VisionEncoder`: a VIT based image encoder. It computes the image embeddings using attention on patches of the image. Relative Positional Embedding is used.
- The `PromptEncoder`: generates embeddings for points and bounding boxes
- The `MaskDecoder`: a two-ways transformer which performs cross attention between the image embedding and the point embeddings (->) and between the point embeddings and the image embeddings. The outputs are fed
- The `Neck`: predicts the output masks based on the contextualized masks produced by the `MaskDecoder`.
# Usage
## Prompted-Mask-Generation
```python
from PIL import Image
import requests
from transformers import SamModel, SamProcessor
model = SamModel.from_pretrained("facebook/sam-vit-huge")
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")
img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
input_points = [[[450, 600]]] # 2D localization of a window
```
```python
inputs = processor(raw_image, input_points=input_points, return_tensors="pt").to("cuda")
outputs = model(**inputs)
masks = processor.image_processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu())
scores = outputs.iou_scores
```
Among other arguments to generate masks, you can pass 2D locations on the approximate position of your object of interest, a bounding box wrapping the object of interest (the format should be x, y coordinate of the top right and bottom left point of the bounding box), a segmentation mask. At this time of writing, passing a text as input is not supported by the official model according to [the official repository](https://github.com/facebookresearch/segment-anything/issues/4#issuecomment-1497626844).
For more details, refer to this notebook, which shows a walk throught of how to use the model, with a visual example!
## Automatic-Mask-Generation
The model can be used for generating segmentation masks in a "zero-shot" fashion, given an input image. The model is automatically prompt with a grid of `1024` points
which are all fed to the model.
The pipeline is made for automatic mask generation. The following snippet demonstrates how easy you can run it (on any device! Simply feed the appropriate `points_per_batch` argument)
```python
from transformers import pipeline
generator = pipeline("mask-generation", device = 0, points_per_batch = 256)
image_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
outputs = generator(image_url, points_per_batch = 256)
```
Now to display the image:
```python
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
def show_mask(mask, ax, random_color=False):
if random_color:
color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
else:
color = np.array([30 / 255, 144 / 255, 255 / 255, 0.6])
h, w = mask.shape[-2:]
mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
ax.imshow(mask_image)
plt.imshow(np.array(raw_image))
ax = plt.gca()
for mask in outputs["masks"]:
show_mask(mask, ax=ax, random_color=True)
plt.axis("off")
plt.show()
```
This should give you the following 
# Citation
If you use this model, please use the following BibTeX entry.
```
@article{kirillov2023segany,
title={Segment Anything},
author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
journal={arXiv:2304.02643},
year={2023}
}
``` | 6,871 | [
[
-0.039306640625,
-0.0548095703125,
0.0382080078125,
0.005489349365234375,
-0.034759521484375,
-0.01059722900390625,
0.019775390625,
-0.03912353515625,
0.04638671875,
0.033233642578125,
-0.041900634765625,
-0.04608154296875,
-0.041229248046875,
-0.0217132568359375,
-0.024322509765625,
0.04241943359375,
0.01491546630859375,
-0.01419830322265625,
-0.006702423095703125,
-0.0036869049072265625,
-0.025482177734375,
-0.03271484375,
-0.053619384765625,
-0.0008769035339355469,
0.0202789306640625,
0.006114959716796875,
0.052734375,
0.0965576171875,
0.0382080078125,
0.023345947265625,
-0.0132293701171875,
0.0009527206420898438,
-0.0031452178955078125,
-0.009246826171875,
-0.0011005401611328125,
-0.0193023681640625,
-0.01873779296875,
-0.0009503364562988281,
0.0565185546875,
0.031402587890625,
0.0009775161743164062,
0.0183868408203125,
-0.0246124267578125,
0.032440185546875,
-0.040435791015625,
0.0013475418090820312,
-0.039154052734375,
-0.01025390625,
-0.01336669921875,
0.01096343994140625,
-0.01096343994140625,
-0.0253448486328125,
-0.00597381591796875,
-0.039154052734375,
0.01181793212890625,
0.006198883056640625,
0.12158203125,
0.03363037109375,
-0.00963592529296875,
0.004299163818359375,
-0.034942626953125,
0.04345703125,
-0.04498291015625,
0.02239990234375,
0.01047515869140625,
0.0224151611328125,
0.0155792236328125,
-0.06329345703125,
-0.039215087890625,
0.01050567626953125,
-0.0161895751953125,
0.0037994384765625,
-0.027801513671875,
-0.01222991943359375,
0.0261383056640625,
0.0203704833984375,
-0.039520263671875,
-0.0239715576171875,
-0.055023193359375,
-0.01690673828125,
0.061553955078125,
0.0124969482421875,
0.0308837890625,
-0.04473876953125,
-0.048858642578125,
-0.0225677490234375,
-0.033599853515625,
0.0303192138671875,
-0.0016679763793945312,
0.0029964447021484375,
-0.027557373046875,
0.04522705078125,
-0.0185546875,
0.0648193359375,
0.0225067138671875,
-0.03118896484375,
0.028900146484375,
-0.00713348388671875,
-0.0350341796875,
-0.00235748291015625,
0.044921875,
0.0408935546875,
-0.009124755859375,
0.005252838134765625,
-0.006267547607421875,
0.00905609130859375,
0.01212310791015625,
-0.08013916015625,
-0.02703857421875,
0.019287109375,
-0.040740966796875,
-0.0157928466796875,
0.023529052734375,
-0.046234130859375,
-0.00783538818359375,
-0.0207061767578125,
0.043609619140625,
-0.03912353515625,
-0.01297760009765625,
0.00899505615234375,
-0.01806640625,
0.04876708984375,
0.00803375244140625,
-0.03668212890625,
-0.00786590576171875,
0.030609130859375,
0.07379150390625,
-0.00848388671875,
-0.014007568359375,
-0.01800537109375,
0.0165252685546875,
-0.0198516845703125,
0.0765380859375,
-0.05145263671875,
-0.0179901123046875,
-0.0220184326171875,
0.03680419921875,
-0.02642822265625,
-0.038360595703125,
0.034942626953125,
-0.02630615234375,
-0.009765625,
-0.009307861328125,
-0.029022216796875,
-0.04315185546875,
0.01438140869140625,
-0.037322998046875,
0.0672607421875,
0.0178680419921875,
-0.038848876953125,
0.01776123046875,
-0.05670166015625,
-0.032470703125,
-0.0003809928894042969,
-0.005252838134765625,
-0.055755615234375,
0.006481170654296875,
0.0300750732421875,
0.042572021484375,
-0.006404876708984375,
0.0128631591796875,
-0.03656005859375,
-0.01751708984375,
0.0202789306640625,
0.00434112548828125,
0.07720947265625,
0.01502227783203125,
-0.0380859375,
0.0171966552734375,
-0.05694580078125,
-0.0016040802001953125,
0.035491943359375,
0.00980377197265625,
-0.0045623779296875,
-0.024444580078125,
-0.01183319091796875,
0.03277587890625,
0.015533447265625,
-0.051666259765625,
-0.004131317138671875,
-0.00524139404296875,
0.04608154296875,
0.055023193359375,
0.0333251953125,
0.037811279296875,
-0.03643798828125,
0.03912353515625,
0.00962066650390625,
0.040679931640625,
-0.05303955078125,
-0.048828125,
-0.0711669921875,
-0.054840087890625,
0.01439666748046875,
0.0287933349609375,
-0.038543701171875,
0.0377197265625,
0.004123687744140625,
-0.053985595703125,
-0.038238525390625,
-0.0274200439453125,
0.0170135498046875,
0.03912353515625,
0.01445770263671875,
-0.03607177734375,
-0.04437255859375,
-0.07672119140625,
0.0195159912109375,
-0.007099151611328125,
-0.006500244140625,
0.03387451171875,
0.04193115234375,
-0.01453399658203125,
0.06903076171875,
-0.07391357421875,
-0.0201416015625,
0.0017194747924804688,
-0.030914306640625,
0.0000674128532409668,
0.05291748046875,
0.048309326171875,
-0.056640625,
-0.037445068359375,
-0.01194000244140625,
-0.054901123046875,
0.0044097900390625,
0.0027446746826171875,
-0.030517578125,
0.015350341796875,
0.028656005859375,
-0.0523681640625,
0.0509033203125,
0.0187530517578125,
-0.0330810546875,
0.038482666015625,
0.0162353515625,
-0.0009298324584960938,
-0.0806884765625,
0.03033447265625,
0.01143646240234375,
-0.0289154052734375,
-0.0462646484375,
0.0126800537109375,
-0.0014247894287109375,
-0.0287933349609375,
-0.04779052734375,
0.04779052734375,
-0.016448974609375,
-0.007701873779296875,
-0.007843017578125,
-0.0015048980712890625,
0.0204010009765625,
0.0582275390625,
0.01502227783203125,
0.026641845703125,
0.0633544921875,
-0.048004150390625,
0.0193328857421875,
0.032012939453125,
-0.0374755859375,
0.059112548828125,
-0.061065673828125,
0.0005440711975097656,
-0.0199432373046875,
0.0198974609375,
-0.07684326171875,
-0.050201416015625,
0.037139892578125,
-0.0312347412109375,
0.016937255859375,
-0.015838623046875,
-0.01171875,
-0.0287628173828125,
-0.01318359375,
0.0273284912109375,
0.046630859375,
-0.03912353515625,
0.042236328125,
0.052734375,
-0.00519561767578125,
-0.015899658203125,
-0.04327392578125,
-0.0212860107421875,
-0.0252838134765625,
-0.06640625,
0.04193115234375,
0.0006074905395507812,
-0.00470733642578125,
0.019378662109375,
-0.002986907958984375,
-0.003345489501953125,
-0.016357421875,
0.047607421875,
0.047210693359375,
-0.00794219970703125,
-0.0149993896484375,
-0.005344390869140625,
-0.017608642578125,
-0.003162384033203125,
-0.01311492919921875,
0.057281494140625,
-0.01020050048828125,
-0.03277587890625,
-0.044952392578125,
0.00997161865234375,
0.035186767578125,
-0.037139892578125,
0.030120849609375,
0.053680419921875,
-0.032989501953125,
0.000050961971282958984,
-0.052734375,
-0.016876220703125,
-0.035980224609375,
0.02288818359375,
-0.02972412109375,
-0.068359375,
0.057769775390625,
0.007740020751953125,
-0.0002841949462890625,
0.05706787109375,
0.03173828125,
-0.01175689697265625,
0.08221435546875,
0.042938232421875,
0.00969696044921875,
0.043426513671875,
-0.0426025390625,
0.016845703125,
-0.070556640625,
-0.051239013671875,
-0.024322509765625,
-0.034088134765625,
-0.031036376953125,
-0.053802490234375,
0.035980224609375,
0.01107025146484375,
-0.040069580078125,
0.0374755859375,
-0.0677490234375,
0.045562744140625,
0.040802001953125,
0.01433563232421875,
-0.006038665771484375,
0.0171966552734375,
0.0008392333984375,
0.0133514404296875,
-0.04925537109375,
-0.019622802734375,
0.053619384765625,
0.0240325927734375,
0.0345458984375,
-0.0301055908203125,
0.04278564453125,
0.002887725830078125,
0.00742340087890625,
-0.041900634765625,
0.0489501953125,
-0.0032787322998046875,
-0.0694580078125,
-0.007045745849609375,
-0.00861358642578125,
-0.06610107421875,
0.02301025390625,
0.006450653076171875,
-0.06890869140625,
0.048126220703125,
-0.0025196075439453125,
-0.047454833984375,
0.045196533203125,
-0.05694580078125,
0.0701904296875,
-0.007843017578125,
-0.01213836669921875,
0.0254058837890625,
-0.061309814453125,
0.0364990234375,
0.0088043212890625,
-0.0037708282470703125,
-0.02166748046875,
0.00865936279296875,
0.06402587890625,
-0.02496337890625,
0.060699462890625,
-0.027984619140625,
0.0198974609375,
0.05291748046875,
-0.01157379150390625,
0.0304718017578125,
-0.0029430389404296875,
0.00656890869140625,
0.024871826171875,
0.00782012939453125,
-0.038787841796875,
-0.0294647216796875,
0.048126220703125,
-0.051788330078125,
-0.040252685546875,
-0.029449462890625,
-0.0248260498046875,
0.025177001953125,
0.0131683349609375,
0.031280517578125,
0.0258331298828125,
0.01343536376953125,
0.0082550048828125,
0.0311431884765625,
-0.0275421142578125,
0.04461669921875,
0.0211944580078125,
-0.032379150390625,
-0.0469970703125,
0.0892333984375,
0.004169464111328125,
0.0177001953125,
0.006488800048828125,
-0.00226593017578125,
-0.0267486572265625,
-0.00347137451171875,
-0.040069580078125,
0.037750244140625,
-0.044830322265625,
-0.0430908203125,
-0.0433349609375,
-0.044464111328125,
-0.0275421142578125,
-0.0308685302734375,
-0.03515625,
-0.04425048828125,
-0.016876220703125,
-0.0029144287109375,
0.024261474609375,
0.038482666015625,
-0.01800537109375,
0.04071044921875,
-0.035980224609375,
0.01435089111328125,
0.0272674560546875,
0.0243682861328125,
-0.0001494884490966797,
-0.040985107421875,
-0.0072784423828125,
-0.00031375885009765625,
-0.045501708984375,
-0.04595947265625,
0.039031982421875,
-0.006198883056640625,
0.0311737060546875,
0.0501708984375,
-0.0018520355224609375,
0.0780029296875,
-0.017364501953125,
0.06268310546875,
0.020782470703125,
-0.06683349609375,
0.038848876953125,
-0.0099029541015625,
0.0150299072265625,
0.02423095703125,
0.0211181640625,
-0.03643798828125,
-0.0027599334716796875,
-0.070556640625,
-0.06378173828125,
0.0789794921875,
0.0156707763671875,
-0.0091705322265625,
0.00833892822265625,
0.02337646484375,
-0.01290130615234375,
0.019500732421875,
-0.057281494140625,
-0.039764404296875,
-0.0271759033203125,
0.0148773193359375,
0.01354217529296875,
-0.0031490325927734375,
-0.0031719207763671875,
-0.041656494140625,
0.0634765625,
0.01119232177734375,
0.05242919921875,
0.0284423828125,
-0.0033245086669921875,
-0.00931549072265625,
-0.0159149169921875,
0.05072021484375,
0.043853759765625,
-0.0251922607421875,
0.00388336181640625,
-0.00885009765625,
-0.01300048828125,
0.0082550048828125,
0.0178680419921875,
-0.04443359375,
0.010498046875,
0.00698089599609375,
0.0828857421875,
-0.01055908203125,
-0.031280517578125,
0.0335693359375,
0.0213775634765625,
-0.0220184326171875,
-0.02313232421875,
0.0097198486328125,
0.00530242919921875,
0.033050537109375,
0.03485107421875,
0.0164337158203125,
-0.004730224609375,
-0.029693603515625,
0.01806640625,
0.03790283203125,
-0.03472900390625,
-0.0257415771484375,
0.056396484375,
-0.006198883056640625,
-0.0247802734375,
0.027130126953125,
-0.0303497314453125,
-0.056884765625,
0.06622314453125,
0.040924072265625,
0.0689697265625,
-0.034088134765625,
0.0399169921875,
0.058380126953125,
0.024658203125,
0.0185089111328125,
0.002994537353515625,
0.005321502685546875,
-0.03326416015625,
-0.031005859375,
-0.0704345703125,
-0.007503509521484375,
0.027130126953125,
-0.03472900390625,
0.01690673828125,
-0.040802001953125,
-0.00922393798828125,
0.01053619384765625,
-0.01020050048828125,
-0.040069580078125,
0.033447265625,
0.004627227783203125,
0.057403564453125,
-0.064208984375,
0.0423583984375,
0.05340576171875,
-0.040557861328125,
-0.071044921875,
-0.0159149169921875,
-0.009796142578125,
-0.079833984375,
0.024169921875,
0.03387451171875,
0.0181884765625,
-0.0006031990051269531,
-0.0589599609375,
-0.08209228515625,
0.08990478515625,
0.0276336669921875,
-0.0202789306640625,
-0.004917144775390625,
0.0192718505859375,
0.00824737548828125,
-0.049560546875,
0.01161956787109375,
0.0460205078125,
0.046112060546875,
0.04052734375,
-0.03485107421875,
0.0204315185546875,
-0.02325439453125,
0.011199951171875,
0.01727294921875,
-0.07080078125,
0.07073974609375,
-0.00966644287109375,
-0.0265960693359375,
0.00707244873046875,
0.0303192138671875,
0.0293731689453125,
0.035400390625,
0.049407958984375,
0.056976318359375,
0.035797119140625,
-0.02032470703125,
0.07513427734375,
-0.02716064453125,
0.022369384765625,
0.056671142578125,
0.0017881393432617188,
0.0401611328125,
0.023101806640625,
-0.01525115966796875,
0.03472900390625,
0.06787109375,
-0.035369873046875,
0.039794921875,
0.0005674362182617188,
-0.005100250244140625,
-0.031280517578125,
-0.027740478515625,
-0.03387451171875,
0.041290283203125,
0.012298583984375,
-0.042572021484375,
-0.0128631591796875,
0.00457000732421875,
0.00409698486328125,
-0.035125732421875,
-0.02716064453125,
0.048065185546875,
0.001323699951171875,
-0.042877197265625,
0.04913330078125,
0.0168914794921875,
0.028289794921875,
-0.041046142578125,
0.008453369140625,
-0.017425537109375,
0.0057220458984375,
-0.02789306640625,
-0.0462646484375,
0.044830322265625,
-0.00801849365234375,
-0.008392333984375,
0.01297760009765625,
0.0670166015625,
-0.0211181640625,
-0.06231689453125,
-0.0010709762573242188,
0.0100860595703125,
0.0276336669921875,
-0.0206451416015625,
-0.05938720703125,
0.0289154052734375,
0.0223541259765625,
-0.0176849365234375,
0.0207366943359375,
0.01332855224609375,
0.0016984939575195312,
0.03643798828125,
0.061798095703125,
-0.0050048828125,
0.018829345703125,
-0.0265655517578125,
0.08160400390625,
-0.058563232421875,
-0.0390625,
-0.05731201171875,
0.06353759765625,
-0.020782470703125,
-0.00966644287109375,
0.05267333984375,
0.06256103515625,
0.06842041015625,
-0.0055999755859375,
0.041412353515625,
-0.034088134765625,
0.020416259765625,
-0.01445770263671875,
0.041229248046875,
-0.057281494140625,
-0.00522613525390625,
-0.0226593017578125,
-0.08380126953125,
-0.0290374755859375,
0.06890869140625,
-0.0165252685546875,
0.01537322998046875,
0.03912353515625,
0.07354736328125,
-0.015655517578125,
-0.004825592041015625,
0.0196075439453125,
0.00969696044921875,
0.01666259765625,
0.0249786376953125,
0.04827880859375,
-0.040618896484375,
0.043212890625,
-0.06329345703125,
-0.00928497314453125,
-0.004261016845703125,
-0.045379638671875,
-0.060089111328125,
-0.060638427734375,
-0.04345703125,
-0.02508544921875,
-0.014984130859375,
0.04046630859375,
0.08984375,
-0.046295166015625,
-0.005611419677734375,
0.00890350341796875,
0.01532745361328125,
-0.01267242431640625,
-0.0177459716796875,
0.05078125,
0.0035495758056640625,
-0.06817626953125,
0.00884246826171875,
0.03875732421875,
0.007167816162109375,
-0.00678253173828125,
-0.002712249755859375,
-0.01337432861328125,
0.01433563232421875,
0.046875,
0.0287322998046875,
-0.04779052734375,
-0.0188751220703125,
0.001068115234375,
0.00859832763671875,
0.0205230712890625,
0.03662109375,
-0.037017822265625,
0.029632568359375,
0.0223541259765625,
0.0308685302734375,
0.0655517578125,
0.0240631103515625,
-0.00396728515625,
-0.0460205078125,
0.01403045654296875,
-0.005176544189453125,
0.0212554931640625,
0.031646728515625,
-0.0123291015625,
0.046234130859375,
0.0272979736328125,
-0.041168212890625,
-0.064697265625,
0.0098419189453125,
-0.08953857421875,
-0.024871826171875,
0.08404541015625,
-0.018951416015625,
-0.0533447265625,
0.0104827880859375,
-0.0208587646484375,
0.0217132568359375,
-0.03192138671875,
0.043121337890625,
0.0211639404296875,
-0.0154876708984375,
-0.024505615234375,
-0.01751708984375,
0.0284881591796875,
0.01221466064453125,
-0.054901123046875,
-0.028472900390625,
0.027984619140625,
0.031402587890625,
0.03656005859375,
0.03515625,
-0.0189971923828125,
0.01198577880859375,
0.0008020401000976562,
0.01291656494140625,
-0.021820068359375,
-0.021209716796875,
-0.0207061767578125,
0.024871826171875,
-0.034637451171875,
-0.0445556640625
]
] |
jonatasgrosman/wav2vec2-large-xlsr-53-japanese | 2022-12-14T01:58:09.000Z | [
"transformers",
"pytorch",
"jax",
"wav2vec2",
"automatic-speech-recognition",
"audio",
"speech",
"xlsr-fine-tuning-week",
"ja",
"dataset:common_voice",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | automatic-speech-recognition | jonatasgrosman | null | null | jonatasgrosman/wav2vec2-large-xlsr-53-japanese | 15 | 39,258 | transformers | 2022-03-02T23:29:05 | ---
language: ja
datasets:
- common_voice
metrics:
- wer
- cer
tags:
- audio
- automatic-speech-recognition
- speech
- xlsr-fine-tuning-week
license: apache-2.0
model-index:
- name: XLSR Wav2Vec2 Japanese by Jonatas Grosman
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice ja
type: common_voice
args: ja
metrics:
- name: Test WER
type: wer
value: 81.80
- name: Test CER
type: cer
value: 20.16
---
# Fine-tuned XLSR-53 large model for speech recognition in Japanese
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Japanese using the train and validation splits of [Common Voice 6.1](https://huggingface.co/datasets/common_voice), [CSS10](https://github.com/Kyubyong/css10) and [JSUT](https://sites.google.com/site/shinnosuketakamichi/publication/jsut).
When using this model, make sure that your speech input is sampled at 16kHz.
This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
## Usage
The model can be used directly (without a language model) as follows...
Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
```python
from huggingsound import SpeechRecognitionModel
model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-japanese")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
transcriptions = model.transcribe(audio_paths)
```
Writing your own inference script:
```python
import torch
import librosa
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
LANG_ID = "ja"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-japanese"
SAMPLES = 10
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
batch["speech"] = speech_array
batch["sentence"] = batch["sentence"].upper()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
predicted_ids = torch.argmax(logits, dim=-1)
predicted_sentences = processor.batch_decode(predicted_ids)
for i, predicted_sentence in enumerate(predicted_sentences):
print("-" * 100)
print("Reference:", test_dataset[i]["sentence"])
print("Prediction:", predicted_sentence)
```
| Reference | Prediction |
| ------------- | ------------- |
| 祖母は、おおむね機嫌よく、サイコロをころがしている。 | 人母は重にきね起くさいがしている |
| 財布をなくしたので、交番へ行きます。 | 財布をなく手端ので勾番へ行きます |
| 飲み屋のおやじ、旅館の主人、医者をはじめ、交際のある人にきいてまわったら、みんな、私より収入が多いはずなのに、税金は安い。 | ノ宮屋のお親じ旅館の主に医者をはじめ交際のアル人トに聞いて回ったらみんな私より収入が多いはなうに税金は安い |
| 新しい靴をはいて出かけます。 | だらしい靴をはいて出かけます |
| このためプラズマ中のイオンや電子の持つ平均運動エネルギーを温度で表現することがある | このためプラズマ中のイオンや電子の持つ平均運動エネルギーを温度で表弁することがある |
| 松井さんはサッカーより野球のほうが上手です。 | 松井さんはサッカーより野球のほうが上手です |
| 新しいお皿を使います。 | 新しいお皿を使います |
| 結婚以来三年半ぶりの東京も、旧友とのお酒も、夜行列車も、駅で寝て、朝を待つのも久しぶりだ。 | 結婚ル二来三年半降りの東京も吸とのお酒も野越者も駅で寝て朝を待つの久しぶりた |
| これまで、少年野球、ママさんバレーなど、地域スポーツを支え、市民に密着してきたのは、無数のボランティアだった。 | これまで少年野球<unk>三バレーなど地域スポーツを支え市民に満着してきたのは娘数のボランティアだった |
| 靴を脱いで、スリッパをはきます。 | 靴を脱いでスイパーをはきます |
## Evaluation
The model can be evaluated as follows on the Japanese test data of Common Voice.
```python
import torch
import re
import librosa
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
LANG_ID = "ja"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-japanese"
DEVICE = "cuda"
CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
"؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
"{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
"、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
"『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "'", "ʻ", "ˆ"]
test_dataset = load_dataset("common_voice", LANG_ID, split="test")
wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
model.to(DEVICE)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
batch["speech"] = speech_array
batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids)
return batch
result = test_dataset.map(evaluate, batched=True, batch_size=8)
predictions = [x.upper() for x in result["pred_strings"]]
references = [x.upper() for x in result["sentence"]]
print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
```
**Test Result**:
In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-05-10). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.
| Model | WER | CER |
| ------------- | ------------- | ------------- |
| jonatasgrosman/wav2vec2-large-xlsr-53-japanese | **81.80%** | **20.16%** |
| vumichien/wav2vec2-large-xlsr-japanese | 1108.86% | 23.40% |
| qqhann/w2v_hf_jsut_xlsr53 | 1012.18% | 70.77% |
## Citation
If you want to cite this model you can use this:
```bibtex
@misc{grosman2021xlsr53-large-japanese,
title={Fine-tuned {XLSR}-53 large model for speech recognition in {J}apanese},
author={Grosman, Jonatas},
howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-japanese}},
year={2021}
}
``` | 7,360 | [
[
-0.0285186767578125,
-0.050811767578125,
0.01629638671875,
0.01342010498046875,
-0.01494598388671875,
-0.0127410888671875,
-0.0284576416015625,
-0.03338623046875,
0.00801849365234375,
0.026824951171875,
-0.047760009765625,
-0.047454833984375,
-0.038604736328125,
-0.0019168853759765625,
-0.00958251953125,
0.0703125,
0.004405975341796875,
0.0008077621459960938,
0.01195526123046875,
-0.01006317138671875,
-0.03155517578125,
-0.0240020751953125,
-0.047821044921875,
-0.0256500244140625,
0.0205078125,
0.018951416015625,
0.0352783203125,
0.031646728515625,
0.028717041015625,
0.0277099609375,
-0.006679534912109375,
0.006931304931640625,
-0.01375579833984375,
-0.0092620849609375,
0.0177459716796875,
-0.04022216796875,
-0.0285186767578125,
-0.0013370513916015625,
0.04754638671875,
0.0380859375,
-0.010894775390625,
0.023651123046875,
0.003482818603515625,
0.035308837890625,
-0.02191162109375,
0.0232391357421875,
-0.034576416015625,
-0.01154327392578125,
-0.01137542724609375,
-0.006595611572265625,
-0.0171356201171875,
-0.0259857177734375,
0.0029163360595703125,
-0.051727294921875,
0.01153564453125,
-0.003864288330078125,
0.09197998046875,
0.01438140869140625,
0.0010471343994140625,
-0.0294036865234375,
-0.0404052734375,
0.0771484375,
-0.07720947265625,
0.0191802978515625,
0.0374755859375,
0.0066070556640625,
-0.01324462890625,
-0.060272216796875,
-0.053131103515625,
-0.0077056884765625,
-0.004024505615234375,
0.020843505859375,
-0.02947998046875,
-0.00634765625,
0.030914306640625,
0.005474090576171875,
-0.045623779296875,
0.007389068603515625,
-0.0498046875,
-0.026031494140625,
0.0611572265625,
-0.0013265609741210938,
0.037841796875,
-0.02557373046875,
-0.00881195068359375,
-0.035125732421875,
-0.0183868408203125,
0.0252685546875,
0.0321044921875,
0.0343017578125,
-0.045501708984375,
0.039520263671875,
-0.00838470458984375,
0.0455322265625,
-0.00023627281188964844,
-0.031890869140625,
0.063232421875,
-0.0243988037109375,
-0.022979736328125,
0.019378662109375,
0.0892333984375,
0.0263671875,
0.0250701904296875,
0.01308441162109375,
-0.00038743019104003906,
0.016815185546875,
-0.0247344970703125,
-0.0548095703125,
-0.016937255859375,
0.030517578125,
-0.031219482421875,
-0.0092010498046875,
-0.0013427734375,
-0.0609130859375,
0.0023193359375,
-0.01451873779296875,
0.051025390625,
-0.04315185546875,
-0.0229339599609375,
0.014984130859375,
-0.010986328125,
0.00771331787109375,
-0.00583648681640625,
-0.06610107421875,
0.01293182373046875,
0.0311737060546875,
0.060150146484375,
0.0276031494140625,
-0.028961181640625,
-0.0243377685546875,
-0.01084136962890625,
-0.017333984375,
0.041839599609375,
-0.0135498046875,
-0.033172607421875,
-0.021026611328125,
0.00717926025390625,
-0.0284576416015625,
-0.031982421875,
0.049530029296875,
-0.00756072998046875,
0.0285186767578125,
-0.0139617919921875,
-0.03192138671875,
-0.017791748046875,
-0.01084136962890625,
-0.0399169921875,
0.08221435546875,
-0.0001932382583618164,
-0.07049560546875,
0.00634765625,
-0.043701171875,
-0.03662109375,
-0.0181427001953125,
-0.009429931640625,
-0.042724609375,
-0.0161590576171875,
0.0295257568359375,
0.03656005859375,
-0.0288238525390625,
0.011016845703125,
-0.014068603515625,
-0.04205322265625,
0.02960205078125,
-0.0274810791015625,
0.0845947265625,
0.0246429443359375,
-0.03955078125,
0.0027065277099609375,
-0.07318115234375,
0.0221405029296875,
0.01519775390625,
-0.024566650390625,
-0.01287078857421875,
-0.005077362060546875,
0.01641845703125,
0.01178741455078125,
0.0169677734375,
-0.039215087890625,
-0.001850128173828125,
-0.04693603515625,
0.046630859375,
0.044158935546875,
-0.0025997161865234375,
0.00853729248046875,
-0.033050537109375,
0.0301666259765625,
-0.0038700103759765625,
-0.01113128662109375,
-0.0190277099609375,
-0.034515380859375,
-0.060882568359375,
-0.0264129638671875,
0.014678955078125,
0.044525146484375,
-0.033447265625,
0.05389404296875,
-0.020477294921875,
-0.06298828125,
-0.06854248046875,
-0.012969970703125,
0.029205322265625,
0.0416259765625,
0.035919189453125,
-0.00008779764175415039,
-0.07122802734375,
-0.062103271484375,
-0.00853729248046875,
-0.02215576171875,
-0.0010232925415039062,
0.021942138671875,
0.03875732421875,
-0.027069091796875,
0.0555419921875,
-0.038055419921875,
-0.02545166015625,
-0.0212554931640625,
0.01313018798828125,
0.055023193359375,
0.04876708984375,
0.0238037109375,
-0.0496826171875,
-0.037994384765625,
0.005702972412109375,
-0.0462646484375,
-0.00958251953125,
-0.01457977294921875,
-0.0016078948974609375,
0.0155792236328125,
0.028594970703125,
-0.037322998046875,
0.020263671875,
0.038055419921875,
-0.02178955078125,
0.047515869140625,
-0.00983428955078125,
0.016265869140625,
-0.09344482421875,
0.0183868408203125,
0.0023193359375,
-0.0018835067749023438,
-0.038818359375,
-0.0209197998046875,
-0.007343292236328125,
0.0107879638671875,
-0.027069091796875,
0.036041259765625,
-0.03045654296875,
-0.005359649658203125,
0.00042629241943359375,
0.0139923095703125,
-0.0016889572143554688,
0.050689697265625,
0.0023403167724609375,
0.0565185546875,
0.051025390625,
-0.044708251953125,
0.0275115966796875,
0.02532958984375,
-0.050872802734375,
0.0165863037109375,
-0.062225341796875,
0.02099609375,
-0.0003571510314941406,
0.004302978515625,
-0.07623291015625,
-0.013092041015625,
0.0216064453125,
-0.0589599609375,
0.0246429443359375,
0.0029144287109375,
-0.032135009765625,
-0.042327880859375,
-0.0101776123046875,
0.00923919677734375,
0.05194091796875,
-0.02850341796875,
0.039306640625,
0.0267486572265625,
-0.0149993896484375,
-0.057037353515625,
-0.06964111328125,
-0.0235137939453125,
-0.0210113525390625,
-0.053924560546875,
0.0203399658203125,
-0.007434844970703125,
-0.00862884521484375,
-0.004802703857421875,
-0.007472991943359375,
0.0029315948486328125,
-0.00213623046875,
0.021881103515625,
0.030853271484375,
-0.017974853515625,
-0.01165771484375,
-0.005828857421875,
-0.004245758056640625,
0.0031890869140625,
-0.0012912750244140625,
0.06298828125,
-0.01158905029296875,
-0.01044464111328125,
-0.0594482421875,
0.005298614501953125,
0.038818359375,
-0.020721435546875,
0.03448486328125,
0.0655517578125,
-0.0233612060546875,
0.00324249267578125,
-0.0361328125,
0.0008401870727539062,
-0.0364990234375,
0.06658935546875,
-0.028717041015625,
-0.045196533203125,
0.050537109375,
0.0185089111328125,
0.00469970703125,
0.04949951171875,
0.039154052734375,
-0.0174560546875,
0.0797119140625,
0.01983642578125,
-0.017303466796875,
0.0233306884765625,
-0.052642822265625,
0.00396728515625,
-0.071044921875,
-0.032073974609375,
-0.0572509765625,
-0.014373779296875,
-0.046630859375,
-0.0298919677734375,
0.0218505859375,
0.008880615234375,
-0.0294189453125,
0.029998779296875,
-0.04583740234375,
0.0185089111328125,
0.03363037109375,
0.0038700103759765625,
-0.0003542900085449219,
0.00951385498046875,
-0.0166473388671875,
-0.00826263427734375,
-0.0399169921875,
-0.032257080078125,
0.08306884765625,
0.034271240234375,
0.05157470703125,
-0.002960205078125,
0.050140380859375,
0.001956939697265625,
-0.007061004638671875,
-0.0577392578125,
0.03680419921875,
-0.0200653076171875,
-0.04144287109375,
-0.0219268798828125,
-0.028961181640625,
-0.07574462890625,
0.0241851806640625,
-0.0080108642578125,
-0.08416748046875,
0.01177978515625,
-0.01023101806640625,
-0.031707763671875,
0.0162200927734375,
-0.04571533203125,
0.0594482421875,
-0.007663726806640625,
-0.01216888427734375,
-0.0098419189453125,
-0.0426025390625,
0.021759033203125,
0.0031585693359375,
0.031524658203125,
-0.0175933837890625,
0.02020263671875,
0.10028076171875,
-0.0233612060546875,
0.055084228515625,
-0.01128387451171875,
0.00350189208984375,
0.034912109375,
-0.02069091796875,
0.03173828125,
-0.01076507568359375,
-0.0198974609375,
0.01983642578125,
0.021209716796875,
-0.0118408203125,
-0.026885986328125,
0.049774169921875,
-0.08197021484375,
-0.0250701904296875,
-0.035125732421875,
-0.039764404296875,
-0.004657745361328125,
0.0216827392578125,
0.055419921875,
0.04571533203125,
0.0011234283447265625,
0.025482177734375,
0.031707763671875,
-0.026031494140625,
0.040283203125,
0.027801513671875,
-0.01239013671875,
-0.05108642578125,
0.05767822265625,
0.0215911865234375,
0.0171966552734375,
0.0160675048828125,
0.0177764892578125,
-0.03900146484375,
-0.028289794921875,
-0.0194854736328125,
0.0302581787109375,
-0.047332763671875,
-0.00598907470703125,
-0.051971435546875,
-0.017791748046875,
-0.05572509765625,
0.0006356239318847656,
-0.0247650146484375,
-0.0207977294921875,
-0.033172607421875,
-0.00112152099609375,
0.031646728515625,
0.0274658203125,
-0.012237548828125,
0.02362060546875,
-0.052581787109375,
0.0263824462890625,
-0.0059661865234375,
0.0029010772705078125,
0.004657745361328125,
-0.0611572265625,
-0.03173828125,
0.01490020751953125,
-0.0166015625,
-0.0625,
0.04693603515625,
0.0087432861328125,
0.040313720703125,
0.015228271484375,
-0.006015777587890625,
0.06805419921875,
-0.023468017578125,
0.0606689453125,
0.03057861328125,
-0.0787353515625,
0.04925537109375,
-0.024688720703125,
0.0246124267578125,
0.031524658203125,
0.022705078125,
-0.058563232421875,
-0.0186309814453125,
-0.055084228515625,
-0.07098388671875,
0.0821533203125,
0.0164794921875,
0.00557708740234375,
0.01178741455078125,
0.0041656494140625,
-0.007415771484375,
0.0071258544921875,
-0.050811767578125,
-0.047119140625,
-0.0164794921875,
-0.031402587890625,
-0.019989013671875,
-0.0016937255859375,
0.0007634162902832031,
-0.031341552734375,
0.07574462890625,
0.005344390869140625,
0.0306243896484375,
0.03387451171875,
0.004474639892578125,
-0.0043487548828125,
0.0221099853515625,
0.03741455078125,
0.018341064453125,
-0.0289154052734375,
-0.01392364501953125,
0.0208740234375,
-0.052764892578125,
0.01107025146484375,
0.01247406005859375,
-0.0134124755859375,
0.017364501953125,
0.04071044921875,
0.0887451171875,
0.018402099609375,
-0.0380859375,
0.0207977294921875,
-0.0019216537475585938,
-0.019134521484375,
-0.044830322265625,
0.00965118408203125,
0.0216522216796875,
0.01110076904296875,
0.0309600830078125,
0.00839996337890625,
-0.007259368896484375,
-0.0421142578125,
0.01158905029296875,
0.01544952392578125,
-0.01373291015625,
-0.01959228515625,
0.05218505859375,
-0.0029296875,
-0.017303466796875,
0.045257568359375,
0.004791259765625,
-0.04132080078125,
0.069580078125,
0.04608154296875,
0.059234619140625,
-0.0244293212890625,
-0.0005326271057128906,
0.06781005859375,
0.0218505859375,
-0.013458251953125,
0.03887939453125,
0.00336456298828125,
-0.0596923828125,
-0.01654052734375,
-0.0521240234375,
-0.00638580322265625,
0.0316162109375,
-0.06298828125,
0.033447265625,
-0.032440185546875,
-0.0242156982421875,
0.018157958984375,
0.024444580078125,
-0.05120849609375,
0.0279693603515625,
0.015716552734375,
0.0587158203125,
-0.06646728515625,
0.07379150390625,
0.0298919677734375,
-0.04547119140625,
-0.1031494140625,
-0.00860595703125,
-0.015289306640625,
-0.05352783203125,
0.043060302734375,
0.023284912109375,
-0.0018167495727539062,
0.0110931396484375,
-0.0270233154296875,
-0.0782470703125,
0.0836181640625,
0.0176239013671875,
-0.0604248046875,
-0.0016717910766601562,
0.0023937225341796875,
0.037261962890625,
-0.0160369873046875,
0.035430908203125,
0.0594482421875,
0.04888916015625,
-0.002674102783203125,
-0.08087158203125,
0.004825592041015625,
-0.03302001953125,
-0.01409149169921875,
-0.004016876220703125,
-0.05096435546875,
0.0753173828125,
-0.0283203125,
-0.0134124755859375,
0.0149078369140625,
0.05712890625,
0.0435791015625,
0.0294952392578125,
0.033447265625,
0.038360595703125,
0.06903076171875,
-0.0166778564453125,
0.06591796875,
-0.005603790283203125,
0.04327392578125,
0.08087158203125,
-0.00749969482421875,
0.07537841796875,
0.0206146240234375,
-0.042877197265625,
0.046356201171875,
0.040557861328125,
-0.02996826171875,
0.041015625,
0.00406646728515625,
-0.005809783935546875,
-0.000004291534423828125,
0.005863189697265625,
-0.044036865234375,
0.04803466796875,
0.0245361328125,
-0.0260467529296875,
0.01512908935546875,
0.0070037841796875,
0.022430419921875,
-0.003017425537109375,
-0.015655517578125,
0.03997802734375,
0.01404571533203125,
-0.048614501953125,
0.0712890625,
0.0031604766845703125,
0.07586669921875,
-0.057037353515625,
0.01580810546875,
0.0138702392578125,
0.0176544189453125,
-0.0309600830078125,
-0.053985595703125,
0.00913238525390625,
0.006740570068359375,
-0.01236724853515625,
0.017791748046875,
0.03021240234375,
-0.041900634765625,
-0.0465087890625,
0.035003662109375,
-0.0035400390625,
0.03155517578125,
0.0180816650390625,
-0.06719970703125,
0.0234527587890625,
0.03155517578125,
-0.03350830078125,
0.0038700103759765625,
0.01328277587890625,
0.01453399658203125,
0.03582763671875,
0.059600830078125,
0.0237274169921875,
0.006885528564453125,
0.01392364501953125,
0.044464111328125,
-0.049530029296875,
-0.04656982421875,
-0.0582275390625,
0.047698974609375,
0.0008082389831542969,
-0.02716064453125,
0.05328369140625,
0.048675537109375,
0.05938720703125,
-0.0017557144165039062,
0.0751953125,
-0.01666259765625,
0.04815673828125,
-0.0462646484375,
0.0687255859375,
-0.04248046875,
0.01126861572265625,
-0.031402587890625,
-0.054412841796875,
-0.007049560546875,
0.06243896484375,
-0.0235137939453125,
0.0143585205078125,
0.044464111328125,
0.07440185546875,
0.01016998291015625,
-0.0003056526184082031,
0.0187835693359375,
0.036102294921875,
0.020721435546875,
0.05938720703125,
0.03228759765625,
-0.06640625,
0.04473876953125,
-0.046051025390625,
-0.003894805908203125,
-0.00516510009765625,
-0.041229248046875,
-0.0548095703125,
-0.059600830078125,
-0.035980224609375,
-0.042633056640625,
-0.01239776611328125,
0.08172607421875,
0.046417236328125,
-0.061431884765625,
-0.02764892578125,
0.0081329345703125,
-0.0081329345703125,
-0.0236358642578125,
-0.0183868408203125,
0.0592041015625,
-0.0010004043579101562,
-0.0753173828125,
0.033172607421875,
-0.0191192626953125,
0.00748443603515625,
0.0027923583984375,
-0.021759033203125,
-0.015655517578125,
0.004833221435546875,
0.00908660888671875,
0.0276031494140625,
-0.060791015625,
-0.006031036376953125,
-0.00772857666015625,
-0.01494598388671875,
0.0064849853515625,
0.01523590087890625,
-0.042327880859375,
0.0328369140625,
0.04443359375,
0.0100555419921875,
0.042205810546875,
-0.017852783203125,
0.0211029052734375,
-0.03302001953125,
0.027099609375,
0.0086212158203125,
0.044036865234375,
0.0298614501953125,
-0.0245819091796875,
0.0273284912109375,
0.018585205078125,
-0.035552978515625,
-0.07391357421875,
-0.0195770263671875,
-0.09100341796875,
-0.0179443359375,
0.08935546875,
-0.016937255859375,
-0.030853271484375,
0.007678985595703125,
-0.0298004150390625,
0.056365966796875,
-0.0323486328125,
0.038818359375,
0.046875,
0.002422332763671875,
0.0056915283203125,
-0.044677734375,
0.0281829833984375,
0.0340576171875,
-0.04266357421875,
0.0008397102355957031,
0.015289306640625,
0.04620361328125,
0.0236358642578125,
0.060150146484375,
-0.0136566162109375,
0.0272064208984375,
0.01178741455078125,
0.031768798828125,
-0.01377105712890625,
0.00254058837890625,
-0.03424072265625,
-0.009246826171875,
-0.0176239013671875,
-0.035064697265625
]
] |
timm/hrnet_w18.ms_aug_in1k | 2023-04-24T21:25:48.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1908.07919",
"license:mit",
"region:us"
] | image-classification | timm | null | null | timm/hrnet_w18.ms_aug_in1k | 1 | 39,005 | timm | 2023-04-24T21:25:16 | ---
tags:
- image-classification
- timm
library_name: timm
license: mit
datasets:
- imagenet-1k
---
# Model card for hrnet_w18.ms_aug_in1k
A HRNet image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 21.3
- GMACs: 4.3
- Activations (M): 16.3
- Image size: 224 x 224
- **Papers:**
- Deep High-Resolution Representation Learning for Visual Recognition: https://arxiv.org/abs/1908.07919
- **Original:** https://github.com/HRNet/HRNet-Image-Classification
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('hrnet_w18.ms_aug_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'hrnet_w18.ms_aug_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 128, 56, 56])
# torch.Size([1, 256, 28, 28])
# torch.Size([1, 512, 14, 14])
# torch.Size([1, 1024, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'hrnet_w18.ms_aug_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{WangSCJDZLMTWLX19,
title={Deep High-Resolution Representation Learning for Visual Recognition},
author={Jingdong Wang and Ke Sun and Tianheng Cheng and
Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and
Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao},
journal = {TPAMI}
year={2019}
}
```
| 3,771 | [
[
-0.037811279296875,
-0.032470703125,
-0.0005311965942382812,
0.011627197265625,
-0.02593994140625,
-0.0299835205078125,
-0.0195159912109375,
-0.0298614501953125,
0.0171966552734375,
0.033599853515625,
-0.03387451171875,
-0.056732177734375,
-0.0484619140625,
-0.0060272216796875,
-0.0018301010131835938,
0.06439208984375,
-0.0059814453125,
-0.0013256072998046875,
-0.01348114013671875,
-0.040985107421875,
-0.01540374755859375,
-0.0258636474609375,
-0.0546875,
-0.032012939453125,
0.0297393798828125,
0.01131439208984375,
0.030548095703125,
0.0531005859375,
0.050201416015625,
0.038421630859375,
-0.006259918212890625,
0.004222869873046875,
-0.0188140869140625,
-0.0201568603515625,
0.032867431640625,
-0.039825439453125,
-0.037200927734375,
0.026275634765625,
0.052276611328125,
0.02923583984375,
-0.0025615692138671875,
0.035003662109375,
0.0142669677734375,
0.041900634765625,
-0.0173797607421875,
0.011749267578125,
-0.031890869140625,
0.0238037109375,
-0.01528167724609375,
0.002277374267578125,
-0.0179901123046875,
-0.0300750732421875,
0.0167388916015625,
-0.039459228515625,
0.0311431884765625,
0.008270263671875,
0.10150146484375,
0.01328277587890625,
-0.0009784698486328125,
0.0041351318359375,
-0.0182342529296875,
0.06298828125,
-0.06951904296875,
0.020172119140625,
0.02532958984375,
0.010223388671875,
-0.004993438720703125,
-0.067138671875,
-0.044219970703125,
-0.0145111083984375,
-0.007781982421875,
-0.0029125213623046875,
-0.01155853271484375,
0.003345489501953125,
0.0291748046875,
0.0299835205078125,
-0.03643798828125,
0.01155853271484375,
-0.047088623046875,
-0.020111083984375,
0.040130615234375,
0.00047326087951660156,
0.019561767578125,
-0.0231170654296875,
-0.043792724609375,
-0.035186767578125,
-0.0213623046875,
0.0255584716796875,
0.02044677734375,
0.0232696533203125,
-0.0498046875,
0.0299530029296875,
0.01263427734375,
0.037994384765625,
0.0009160041809082031,
-0.026275634765625,
0.05096435546875,
0.01116180419921875,
-0.04473876953125,
-0.008331298828125,
0.08709716796875,
0.0189666748046875,
0.0159149169921875,
0.01473236083984375,
-0.00843048095703125,
-0.02862548828125,
-0.0063629150390625,
-0.0814208984375,
-0.02252197265625,
0.0178375244140625,
-0.054046630859375,
-0.0294189453125,
0.026947021484375,
-0.05047607421875,
-0.01355743408203125,
-0.005893707275390625,
0.04168701171875,
-0.031402587890625,
-0.0243988037109375,
0.003814697265625,
-0.01351165771484375,
0.02734375,
0.01226806640625,
-0.033172607421875,
0.0030002593994140625,
0.01383209228515625,
0.07574462890625,
0.0023708343505859375,
-0.040313720703125,
-0.0207061767578125,
-0.0253448486328125,
-0.0227508544921875,
0.02783203125,
-0.0013399124145507812,
-0.0034027099609375,
-0.01580810546875,
0.0261688232421875,
-0.0069580078125,
-0.05548095703125,
0.0145263671875,
-0.019012451171875,
0.0247802734375,
-0.0081329345703125,
-0.01528167724609375,
-0.037078857421875,
0.02313232421875,
-0.036102294921875,
0.09197998046875,
0.02587890625,
-0.06439208984375,
0.022674560546875,
-0.03778076171875,
-0.00875091552734375,
-0.0160675048828125,
-0.00157928466796875,
-0.07855224609375,
-0.00540924072265625,
0.01271820068359375,
0.054046630859375,
-0.0160064697265625,
-0.0033206939697265625,
-0.045654296875,
-0.0192413330078125,
0.023345947265625,
-0.0093841552734375,
0.07818603515625,
0.00567626953125,
-0.030731201171875,
0.0244598388671875,
-0.047698974609375,
0.00948333740234375,
0.039031982421875,
-0.03277587890625,
-0.002063751220703125,
-0.053131103515625,
0.01387786865234375,
0.0286407470703125,
0.01806640625,
-0.047027587890625,
0.019744873046875,
-0.012176513671875,
0.03167724609375,
0.0540771484375,
-0.013702392578125,
0.0213623046875,
-0.0222015380859375,
0.0217132568359375,
0.024749755859375,
0.0179901123046875,
0.00008565187454223633,
-0.0430908203125,
-0.059051513671875,
-0.02911376953125,
0.0300750732421875,
0.0312347412109375,
-0.035491943359375,
0.041839599609375,
-0.00811767578125,
-0.049560546875,
-0.0369873046875,
0.0129852294921875,
0.035980224609375,
0.045806884765625,
0.0269012451171875,
-0.0325927734375,
-0.046051025390625,
-0.066162109375,
0.01352691650390625,
-0.0046234130859375,
0.00140380859375,
0.020355224609375,
0.04962158203125,
-0.01131439208984375,
0.045501708984375,
-0.026702880859375,
-0.0265655517578125,
-0.01654052734375,
0.01409149169921875,
0.032073974609375,
0.05963134765625,
0.054107666015625,
-0.0467529296875,
-0.032806396484375,
-0.01016998291015625,
-0.08123779296875,
0.02191162109375,
-0.0057830810546875,
-0.0250091552734375,
0.0227203369140625,
0.01074981689453125,
-0.04180908203125,
0.052337646484375,
0.017333984375,
-0.025634765625,
0.037017822265625,
-0.0250244140625,
0.021026611328125,
-0.083740234375,
0.00588226318359375,
0.03277587890625,
-0.00949859619140625,
-0.027557373046875,
0.00012552738189697266,
0.0012407302856445312,
-0.00885009765625,
-0.04150390625,
0.04522705078125,
-0.043121337890625,
-0.01554107666015625,
-0.006134033203125,
-0.0201568603515625,
0.0025539398193359375,
0.066162109375,
-0.00815582275390625,
0.026275634765625,
0.05645751953125,
-0.040802001953125,
0.04327392578125,
0.037811279296875,
-0.0180206298828125,
0.02490234375,
-0.046875,
0.01195526123046875,
0.0009012222290039062,
0.00856781005859375,
-0.06756591796875,
-0.0178985595703125,
0.020111083984375,
-0.04168701171875,
0.0469970703125,
-0.034881591796875,
-0.0281524658203125,
-0.049957275390625,
-0.03924560546875,
0.0278778076171875,
0.059722900390625,
-0.05389404296875,
0.0258331298828125,
0.0159454345703125,
0.0260772705078125,
-0.04290771484375,
-0.07073974609375,
-0.019866943359375,
-0.03167724609375,
-0.045684814453125,
0.0282440185546875,
0.00983428955078125,
0.011962890625,
0.01010894775390625,
-0.004535675048828125,
-0.0032501220703125,
-0.0177154541015625,
0.041290283203125,
0.03338623046875,
-0.030120849609375,
-0.01007843017578125,
-0.034698486328125,
0.004489898681640625,
0.00457763671875,
-0.0170135498046875,
0.04888916015625,
-0.0235137939453125,
-0.020965576171875,
-0.06719970703125,
-0.004947662353515625,
0.037322998046875,
-0.01442718505859375,
0.0604248046875,
0.093994140625,
-0.044830322265625,
0.007534027099609375,
-0.032379150390625,
-0.0176544189453125,
-0.036834716796875,
0.035858154296875,
-0.0229034423828125,
-0.02880859375,
0.06427001953125,
0.006988525390625,
0.00641632080078125,
0.05267333984375,
0.0219268798828125,
-0.0169830322265625,
0.053680419921875,
0.044830322265625,
0.007785797119140625,
0.055694580078125,
-0.07537841796875,
-0.0171051025390625,
-0.07171630859375,
-0.042694091796875,
-0.025177001953125,
-0.044830322265625,
-0.04931640625,
-0.02496337890625,
0.0301666259765625,
0.0218048095703125,
-0.03704833984375,
0.039825439453125,
-0.05902099609375,
-0.006103515625,
0.059112548828125,
0.052032470703125,
-0.0308074951171875,
0.02703857421875,
-0.0204315185546875,
-0.0006361007690429688,
-0.05084228515625,
-0.0181121826171875,
0.07305908203125,
0.0411376953125,
0.048828125,
-0.01517486572265625,
0.055877685546875,
-0.00661468505859375,
0.01611328125,
-0.042327880859375,
0.0477294921875,
-0.007480621337890625,
-0.023529052734375,
-0.0221710205078125,
-0.03564453125,
-0.08135986328125,
0.001377105712890625,
-0.0304107666015625,
-0.057525634765625,
0.01403045654296875,
0.0111236572265625,
-0.01904296875,
0.06573486328125,
-0.0570068359375,
0.07537841796875,
-0.0089111328125,
-0.0293121337890625,
0.00830841064453125,
-0.042999267578125,
0.0142059326171875,
0.023773193359375,
-0.0202178955078125,
-0.01081085205078125,
0.024139404296875,
0.0965576171875,
-0.0389404296875,
0.06561279296875,
-0.0389404296875,
0.022735595703125,
0.03607177734375,
-0.0135040283203125,
0.023712158203125,
-0.01427459716796875,
-0.0078277587890625,
0.0256805419921875,
-0.0014696121215820312,
-0.04248046875,
-0.038482666015625,
0.039459228515625,
-0.06787109375,
-0.032196044921875,
-0.0277099609375,
-0.037445068359375,
0.01111602783203125,
0.0097198486328125,
0.040313720703125,
0.054656982421875,
0.01520538330078125,
0.0194244384765625,
0.04730224609375,
-0.0391845703125,
0.0369873046875,
-0.0190887451171875,
-0.01416015625,
-0.036224365234375,
0.06494140625,
0.0142364501953125,
0.0028400421142578125,
0.007717132568359375,
0.0178985595703125,
-0.02587890625,
-0.043670654296875,
-0.0263824462890625,
0.03118896484375,
-0.050079345703125,
-0.037689208984375,
-0.034332275390625,
-0.0394287109375,
-0.036712646484375,
0.0010099411010742188,
-0.03021240234375,
-0.0149078369140625,
-0.0289459228515625,
0.01552581787109375,
0.05224609375,
0.0538330078125,
-0.00922393798828125,
0.038177490234375,
-0.0478515625,
0.01065826416015625,
0.01751708984375,
0.03448486328125,
-0.003265380859375,
-0.06805419921875,
-0.0286102294921875,
-0.0027008056640625,
-0.033477783203125,
-0.0584716796875,
0.040802001953125,
0.00986480712890625,
0.042877197265625,
0.035369873046875,
-0.014617919921875,
0.0628662109375,
-0.0003426074981689453,
0.042388916015625,
0.0306854248046875,
-0.043853759765625,
0.04742431640625,
-0.0038356781005859375,
0.0165557861328125,
0.00279998779296875,
0.025909423828125,
-0.0162506103515625,
0.002841949462890625,
-0.07049560546875,
-0.045654296875,
0.06500244140625,
0.004909515380859375,
-0.0025882720947265625,
0.031585693359375,
0.04833984375,
-0.0008134841918945312,
0.00604248046875,
-0.054534912109375,
-0.027618408203125,
-0.0208282470703125,
-0.0230255126953125,
0.004024505615234375,
-0.006500244140625,
-0.00022232532501220703,
-0.053436279296875,
0.04974365234375,
0.001857757568359375,
0.066162109375,
0.0229034423828125,
-0.00418853759765625,
-0.00649261474609375,
-0.0275726318359375,
0.03326416015625,
0.02728271484375,
-0.030517578125,
0.0063934326171875,
0.019439697265625,
-0.04486083984375,
-0.0006823539733886719,
0.0083465576171875,
0.0122222900390625,
-0.0016775131225585938,
0.04852294921875,
0.07611083984375,
-0.004497528076171875,
0.0043182373046875,
0.030517578125,
0.002216339111328125,
-0.0303192138671875,
-0.0138702392578125,
0.008758544921875,
-0.006618499755859375,
0.032073974609375,
0.02642822265625,
0.02716064453125,
-0.0133209228515625,
-0.027618408203125,
0.0197906494140625,
0.038330078125,
-0.0270843505859375,
-0.0288238525390625,
0.047027587890625,
-0.0160980224609375,
-0.0138397216796875,
0.07122802734375,
-0.013214111328125,
-0.0439453125,
0.08221435546875,
0.033172607421875,
0.06182861328125,
-0.00638580322265625,
0.0015010833740234375,
0.06829833984375,
0.0129241943359375,
0.004138946533203125,
0.01861572265625,
0.01149749755859375,
-0.05523681640625,
0.00795745849609375,
-0.0499267578125,
0.00637054443359375,
0.035797119140625,
-0.05108642578125,
0.0202178955078125,
-0.0484619140625,
-0.0340576171875,
0.00665283203125,
0.026275634765625,
-0.078857421875,
0.0132293701171875,
0.005474090576171875,
0.063232421875,
-0.057098388671875,
0.060028076171875,
0.064453125,
-0.044464111328125,
-0.0718994140625,
-0.005298614501953125,
-0.004901885986328125,
-0.07476806640625,
0.044647216796875,
0.035980224609375,
0.0171051025390625,
0.00006812810897827148,
-0.060028076171875,
-0.040130615234375,
0.103759765625,
0.0380859375,
-0.0081939697265625,
0.006927490234375,
-0.0023212432861328125,
0.012786865234375,
-0.031707763671875,
0.02471923828125,
0.01045989990234375,
0.03131103515625,
0.0157012939453125,
-0.0538330078125,
0.0197296142578125,
-0.0192718505859375,
0.01337432861328125,
0.007572174072265625,
-0.04791259765625,
0.07440185546875,
-0.03973388671875,
-0.0112152099609375,
-0.002887725830078125,
0.06024169921875,
0.0233612060546875,
0.0100555419921875,
0.04071044921875,
0.060272216796875,
0.045654296875,
-0.02032470703125,
0.060638427734375,
0.01202392578125,
0.0458984375,
0.038787841796875,
0.024017333984375,
0.0474853515625,
0.027740478515625,
-0.027557373046875,
0.033660888671875,
0.08575439453125,
-0.032012939453125,
0.0233154296875,
0.017578125,
0.0081939697265625,
-0.00891876220703125,
0.007656097412109375,
-0.033203125,
0.038787841796875,
0.01024627685546875,
-0.0335693359375,
-0.01413726806640625,
0.0181427001953125,
-0.00864410400390625,
-0.02471923828125,
-0.0172271728515625,
0.039276123046875,
-0.0017366409301757812,
-0.0222625732421875,
0.06817626953125,
0.0018758773803710938,
0.07293701171875,
-0.0253753662109375,
-0.0082550048828125,
-0.0175933837890625,
0.0110321044921875,
-0.0277099609375,
-0.061920166015625,
0.0171356201171875,
-0.0222015380859375,
-0.0021419525146484375,
0.0030155181884765625,
0.044647216796875,
-0.0297088623046875,
-0.0330810546875,
0.020050048828125,
0.0247039794921875,
0.040802001953125,
0.0007863044738769531,
-0.09307861328125,
0.0129241943359375,
0.007076263427734375,
-0.047821044921875,
0.02392578125,
0.035919189453125,
0.01032257080078125,
0.050537109375,
0.044219970703125,
-0.001678466796875,
0.016265869140625,
-0.015106201171875,
0.052764892578125,
-0.047332763671875,
-0.0202484130859375,
-0.061767578125,
0.044097900390625,
-0.00949859619140625,
-0.043701171875,
0.037200927734375,
0.041473388671875,
0.06475830078125,
-0.00531005859375,
0.0330810546875,
-0.0170135498046875,
-0.01104736328125,
-0.03778076171875,
0.05706787109375,
-0.05010986328125,
-0.007518768310546875,
-0.00971221923828125,
-0.053009033203125,
-0.0181427001953125,
0.05462646484375,
-0.0132598876953125,
0.034393310546875,
0.0352783203125,
0.067138671875,
-0.027618408203125,
-0.0288848876953125,
0.0196075439453125,
0.0105743408203125,
0.0029125213623046875,
0.034393310546875,
0.029510498046875,
-0.06317138671875,
0.0257110595703125,
-0.052215576171875,
-0.01432037353515625,
-0.01047515869140625,
-0.04754638671875,
-0.08062744140625,
-0.07769775390625,
-0.046142578125,
-0.054901123046875,
-0.023468017578125,
0.0758056640625,
0.0921630859375,
-0.052642822265625,
-0.01097869873046875,
0.00963592529296875,
0.01141357421875,
-0.018951416015625,
-0.0174102783203125,
0.053863525390625,
-0.01117706298828125,
-0.054656982421875,
-0.023956298828125,
-0.004241943359375,
0.036346435546875,
-0.00751495361328125,
-0.02215576171875,
-0.0165863037109375,
-0.0234375,
0.01947021484375,
0.029022216796875,
-0.05145263671875,
-0.0093536376953125,
-0.0186004638671875,
-0.0177764892578125,
0.038330078125,
0.0302734375,
-0.04144287109375,
0.0103759765625,
0.033599853515625,
0.0303192138671875,
0.06439208984375,
-0.023712158203125,
-0.0007033348083496094,
-0.067138671875,
0.04010009765625,
-0.01396942138671875,
0.041473388671875,
0.032684326171875,
-0.0287322998046875,
0.034912109375,
0.031402587890625,
-0.027618408203125,
-0.06744384765625,
-0.01158905029296875,
-0.08428955078125,
-0.0079193115234375,
0.058563232421875,
-0.0274505615234375,
-0.046142578125,
0.03619384765625,
-0.00011152029037475586,
0.055694580078125,
-0.00926971435546875,
0.03240966796875,
0.016448974609375,
-0.01184844970703125,
-0.04901123046875,
-0.042694091796875,
0.035247802734375,
0.0000050067901611328125,
-0.05120849609375,
-0.0308074951171875,
-0.008270263671875,
0.04541015625,
0.0219268798828125,
0.0335693359375,
-0.01038360595703125,
0.00299072265625,
0.00284576416015625,
0.04840087890625,
-0.036590576171875,
-0.00899505615234375,
-0.0244598388671875,
0.003780364990234375,
-0.00867462158203125,
-0.056671142578125
]
] |
lmsys/vicuna-13b-v1.3 | 2023-08-01T18:26:48.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2302.13971",
"arxiv:2306.05685",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | lmsys | null | null | lmsys/vicuna-13b-v1.3 | 161 | 38,996 | transformers | 2023-06-18T03:38:59 | ---
inference: false
---
**NOTE: New version available**
Please check out a newer version of the weights [here](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md).
<br>
# Vicuna Model Card
## Model Details
Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture.
- **License:** Non-commercial license
- **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971).
### Model Sources
- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/
## Uses
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
## How to Get Started with the Model
- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights.
- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api.
## Training Details
Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
The training data is around 125K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).
## Difference between different versions of Vicuna
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md) | 1,977 | [
[
-0.01258087158203125,
-0.06414794921875,
0.0270843505859375,
0.034271240234375,
-0.039825439453125,
-0.0162506103515625,
-0.01666259765625,
-0.04339599609375,
0.0282440185546875,
0.02685546875,
-0.03997802734375,
-0.03717041015625,
-0.04931640625,
-0.002422332763671875,
-0.0115814208984375,
0.0650634765625,
0.00702667236328125,
0.0156402587890625,
-0.00658416748046875,
-0.02734375,
-0.06640625,
-0.037811279296875,
-0.076416015625,
-0.026336669921875,
0.04693603515625,
0.03509521484375,
0.0472412109375,
0.03912353515625,
0.0253143310546875,
0.0294647216796875,
-0.007274627685546875,
0.0197601318359375,
-0.04473876953125,
0.004199981689453125,
0.02728271484375,
-0.06573486328125,
-0.0509033203125,
-0.018768310546875,
0.041748046875,
0.006175994873046875,
-0.0187835693359375,
0.01418304443359375,
0.0005002021789550781,
0.0352783203125,
-0.02496337890625,
0.02728271484375,
-0.045257568359375,
-0.0195770263671875,
-0.01739501953125,
-0.042266845703125,
-0.0218963623046875,
-0.0244140625,
-0.0100250244140625,
-0.035552978515625,
-0.0037670135498046875,
-0.004619598388671875,
0.08349609375,
0.041168212890625,
-0.02874755859375,
-0.01389312744140625,
-0.04595947265625,
0.045440673828125,
-0.0679931640625,
0.032318115234375,
0.032867431640625,
0.045379638671875,
-0.01702880859375,
-0.043182373046875,
-0.037811279296875,
-0.02899169921875,
0.005046844482421875,
-0.0041351318359375,
-0.019866943359375,
0.00362396240234375,
0.00397491455078125,
0.035247802734375,
-0.0271759033203125,
0.029815673828125,
-0.042449951171875,
0.0009765625,
0.044525146484375,
0.0245819091796875,
0.0127105712890625,
-0.0129241943359375,
-0.0271759033203125,
-0.029541015625,
-0.0209808349609375,
-0.0022106170654296875,
0.02947998046875,
0.0379638671875,
-0.041412353515625,
0.040557861328125,
-0.0212860107421875,
0.04449462890625,
-0.00379180908203125,
-0.015289306640625,
0.037933349609375,
-0.0086517333984375,
-0.032073974609375,
-0.01355743408203125,
0.0863037109375,
0.03668212890625,
0.0011539459228515625,
0.01276397705078125,
0.002838134765625,
-0.0107421875,
0.0124359130859375,
-0.06048583984375,
0.0012731552124023438,
0.0377197265625,
-0.0218048095703125,
-0.03826904296875,
-0.01459503173828125,
-0.02398681640625,
-0.036285400390625,
-0.0177459716796875,
0.032806396484375,
-0.033905029296875,
-0.02777099609375,
0.025543212890625,
0.0007791519165039062,
0.0234222412109375,
0.03863525390625,
-0.04742431640625,
0.033416748046875,
0.035736083984375,
0.07879638671875,
0.0002391338348388672,
-0.029571533203125,
-0.0164794921875,
-0.029815673828125,
-0.010955810546875,
0.06298828125,
0.003124237060546875,
-0.019775390625,
-0.0093231201171875,
0.0163116455078125,
-0.0033550262451171875,
-0.0380859375,
0.05072021484375,
-0.0229644775390625,
0.027587890625,
-0.01218414306640625,
-0.0382080078125,
0.0007748603820800781,
0.01702880859375,
-0.047149658203125,
0.09210205078125,
0.005275726318359375,
-0.060272216796875,
0.00778961181640625,
-0.0384521484375,
-0.0013952255249023438,
0.006008148193359375,
0.0014104843139648438,
-0.038818359375,
-0.00665283203125,
0.0015192031860351562,
0.0421142578125,
-0.030914306640625,
0.0281829833984375,
-0.018524169921875,
-0.0411376953125,
0.0174560546875,
-0.032012939453125,
0.08056640625,
0.0189056396484375,
-0.0236968994140625,
0.03387451171875,
-0.057037353515625,
-0.00817108154296875,
0.02587890625,
-0.0241546630859375,
-0.0291900634765625,
-0.01038360595703125,
-0.0011224746704101562,
-0.0013818740844726562,
0.038360595703125,
-0.02349853515625,
0.02435302734375,
-0.004810333251953125,
0.01526641845703125,
0.052642822265625,
-0.00537872314453125,
0.018951416015625,
-0.032501220703125,
0.0273590087890625,
-0.00357818603515625,
0.049530029296875,
0.0157012939453125,
-0.0372314453125,
-0.0791015625,
-0.032745361328125,
0.003997802734375,
0.04803466796875,
-0.057586669921875,
0.050048828125,
-0.031402587890625,
-0.07806396484375,
-0.066162109375,
0.0184173583984375,
0.02874755859375,
0.0043182373046875,
0.0238037109375,
-0.036712646484375,
-0.05328369140625,
-0.0670166015625,
-0.01282501220703125,
-0.0232696533203125,
-0.004795074462890625,
0.029754638671875,
0.0189056396484375,
-0.036468505859375,
0.0601806640625,
-0.03704833984375,
-0.0257720947265625,
-0.01132965087890625,
-0.00013637542724609375,
0.005245208740234375,
0.0288848876953125,
0.046630859375,
-0.044342041015625,
-0.0267791748046875,
-0.008453369140625,
-0.0531005859375,
-0.0032901763916015625,
-0.004695892333984375,
-0.03143310546875,
0.00484466552734375,
0.034088134765625,
-0.04864501953125,
0.0276947021484375,
0.0517578125,
-0.031158447265625,
0.03521728515625,
-0.017242431640625,
-0.00217437744140625,
-0.101806640625,
-0.00226593017578125,
0.00772857666015625,
-0.035430908203125,
-0.04156494140625,
-0.0016679763793945312,
-0.0013818740844726562,
0.030609130859375,
-0.052764892578125,
0.0740966796875,
-0.030731201171875,
0.01041412353515625,
-0.0361328125,
-0.0070037841796875,
-0.008026123046875,
0.05792236328125,
-0.0015993118286132812,
0.04925537109375,
0.02923583984375,
-0.06280517578125,
0.03515625,
0.01125335693359375,
-0.0213775634765625,
0.02020263671875,
-0.06976318359375,
0.018707275390625,
0.0002970695495605469,
0.024139404296875,
-0.06298828125,
-0.0026569366455078125,
0.04248046875,
-0.042083740234375,
0.01422119140625,
-0.0024051666259765625,
-0.03448486328125,
-0.0142974853515625,
-0.020660400390625,
0.01495361328125,
0.0247650146484375,
-0.032745361328125,
0.0199432373046875,
0.035919189453125,
0.00959014892578125,
-0.04290771484375,
-0.04339599609375,
-0.0010900497436523438,
-0.028961181640625,
-0.007251739501953125,
0.0032062530517578125,
-0.0211029052734375,
-0.01751708984375,
-0.0164947509765625,
0.0075225830078125,
-0.007213592529296875,
0.00807952880859375,
0.0229644775390625,
0.002811431884765625,
0.00321197509765625,
0.0125274658203125,
-0.0118560791015625,
0.0011491775512695312,
-0.01177978515625,
-0.004962921142578125,
0.07635498046875,
-0.037017822265625,
0.0074920654296875,
-0.0628662109375,
-0.0121917724609375,
0.043548583984375,
0.00768280029296875,
0.0947265625,
0.0633544921875,
-0.017791748046875,
0.014007568359375,
-0.051910400390625,
-0.01534271240234375,
-0.036773681640625,
0.03302001953125,
-0.01485443115234375,
-0.061920166015625,
0.044586181640625,
0.0293731689453125,
0.024627685546875,
0.034271240234375,
0.059326171875,
0.00839996337890625,
0.042572021484375,
0.06707763671875,
-0.0128021240234375,
0.07562255859375,
-0.0195770263671875,
-0.0110931396484375,
-0.0579833984375,
-0.0223236083984375,
-0.048248291015625,
-0.009552001953125,
-0.050445556640625,
-0.04766845703125,
0.00034356117248535156,
-0.00223541259765625,
-0.02655029296875,
0.055511474609375,
-0.04010009765625,
0.00537109375,
0.04266357421875,
0.025726318359375,
0.02166748046875,
-0.006221771240234375,
0.018310546875,
0.0101318359375,
-0.049530029296875,
-0.042877197265625,
0.07672119140625,
0.04925537109375,
0.052703857421875,
0.00992584228515625,
0.045501708984375,
0.0196380615234375,
0.0384521484375,
-0.06842041015625,
0.039215087890625,
0.0199127197265625,
-0.0533447265625,
-0.031585693359375,
-0.0611572265625,
-0.0821533203125,
0.0274505615234375,
-0.01346588134765625,
-0.056365966796875,
0.010162353515625,
0.006771087646484375,
-0.01045989990234375,
0.0221710205078125,
-0.054412841796875,
0.0599365234375,
-0.03009033203125,
-0.0176849365234375,
-0.003658294677734375,
-0.037017822265625,
0.04376220703125,
0.0111846923828125,
0.0099334716796875,
-0.01495361328125,
-0.007659912109375,
0.0625,
-0.048828125,
0.0858154296875,
-0.01288604736328125,
-0.027618408203125,
0.018280029296875,
-0.0096435546875,
0.021209716796875,
0.0006356239318847656,
0.0037326812744140625,
0.0297088623046875,
0.00911712646484375,
-0.03973388671875,
-0.04144287109375,
0.04473876953125,
-0.08367919921875,
-0.02783203125,
-0.0205535888671875,
-0.030914306640625,
0.0069732666015625,
0.0126800537109375,
0.0266876220703125,
0.021026611328125,
-0.01291656494140625,
0.0213165283203125,
0.040069580078125,
-0.030303955078125,
-0.0013818740844726562,
0.03533935546875,
-0.0236968994140625,
-0.033935546875,
0.047119140625,
-0.0020503997802734375,
0.01206207275390625,
0.043243408203125,
0.01517486572265625,
-0.00902557373046875,
-0.01247406005859375,
-0.012481689453125,
0.02825927734375,
-0.03558349609375,
-0.0170745849609375,
-0.061370849609375,
-0.015625,
-0.031585693359375,
0.035003662109375,
-0.06182861328125,
-0.0285186767578125,
-0.0232696533203125,
-0.0035953521728515625,
0.05657958984375,
0.0301971435546875,
0.023040771484375,
0.06463623046875,
-0.04296875,
0.01629638671875,
0.015960693359375,
0.02508544921875,
0.003082275390625,
-0.053558349609375,
-0.039276123046875,
0.0128021240234375,
-0.023040771484375,
-0.06109619140625,
0.037567138671875,
-0.006656646728515625,
0.03399658203125,
0.0297088623046875,
-0.00002288818359375,
0.05950927734375,
-0.01629638671875,
0.04248046875,
0.0137176513671875,
-0.037994384765625,
0.03131103515625,
-0.0187835693359375,
0.0267791748046875,
0.04791259765625,
0.03021240234375,
-0.04730224609375,
-0.02239990234375,
-0.05859375,
-0.0548095703125,
0.036041259765625,
0.0240325927734375,
0.0261077880859375,
-0.0016832351684570312,
0.035888671875,
0.00579071044921875,
0.02020263671875,
-0.063720703125,
-0.0377197265625,
-0.005908966064453125,
-0.024383544921875,
-0.0173492431640625,
-0.0208892822265625,
0.002460479736328125,
-0.032318115234375,
0.053131103515625,
-0.00862884521484375,
0.040008544921875,
0.004695892333984375,
-0.0020503997802734375,
-0.00405120849609375,
0.01122283935546875,
0.04931640625,
0.0221710205078125,
-0.036102294921875,
-0.0200347900390625,
0.01422882080078125,
-0.03912353515625,
-0.006458282470703125,
0.00995635986328125,
0.0015430450439453125,
0.007537841796875,
0.025054931640625,
0.10919189453125,
0.0283966064453125,
-0.037109375,
0.0277252197265625,
-0.05859375,
-0.015869140625,
-0.031402587890625,
0.01467132568359375,
0.0113525390625,
0.03125,
0.0099334716796875,
-0.01021575927734375,
-0.00858306884765625,
-0.0517578125,
-0.015869140625,
0.027801513671875,
-0.030609130859375,
-0.0210113525390625,
0.04632568359375,
0.01329803466796875,
-0.035369873046875,
0.02752685546875,
0.0030879974365234375,
-0.025421142578125,
0.0308074951171875,
0.01018524169921875,
0.0645751953125,
-0.0184326171875,
0.00835418701171875,
0.036468505859375,
0.0222320556640625,
-0.01258087158203125,
0.01468658447265625,
-0.0157012939453125,
-0.0584716796875,
-0.00005733966827392578,
-0.050445556640625,
-0.044342041015625,
0.0228271484375,
-0.048553466796875,
0.03436279296875,
-0.0259552001953125,
-0.040283203125,
-0.0293426513671875,
0.042236328125,
-0.06866455078125,
-0.0021820068359375,
-0.010589599609375,
0.064697265625,
-0.054779052734375,
0.07562255859375,
0.04473876953125,
-0.03436279296875,
-0.06707763671875,
-0.026153564453125,
-0.004795074462890625,
-0.06451416015625,
0.01171112060546875,
0.003841400146484375,
-0.0010776519775390625,
-0.00757598876953125,
-0.052581787109375,
-0.057098388671875,
0.10418701171875,
0.0281829833984375,
-0.04412841796875,
-0.0156707763671875,
-0.01081085205078125,
0.048797607421875,
-0.00743865966796875,
0.043182373046875,
0.0301971435546875,
0.0139617919921875,
0.00519561767578125,
-0.09100341796875,
0.00049591064453125,
-0.03662109375,
-0.0011396408081054688,
-0.0141448974609375,
-0.08544921875,
0.0670166015625,
0.0032749176025390625,
-0.0028018951416015625,
0.019866943359375,
0.0643310546875,
0.03857421875,
0.00821685791015625,
0.040863037109375,
0.027008056640625,
0.07354736328125,
0.00804901123046875,
0.0855712890625,
-0.0115814208984375,
0.0151519775390625,
0.0888671875,
0.005191802978515625,
0.06494140625,
0.0312042236328125,
-0.0014886856079101562,
0.041534423828125,
0.0579833984375,
0.0187530517578125,
0.014617919921875,
0.00014829635620117188,
0.005443572998046875,
0.0012922286987304688,
0.0038394927978515625,
-0.032806396484375,
0.03619384765625,
0.0180816650390625,
-0.01287841796875,
0.01030731201171875,
-0.00739288330078125,
0.0264434814453125,
-0.022979736328125,
-0.003490447998046875,
0.056365966796875,
0.0229644775390625,
-0.041656494140625,
0.08001708984375,
0.0102996826171875,
0.08197021484375,
-0.055755615234375,
0.0187835693359375,
-0.03607177734375,
0.0283203125,
-0.0008158683776855469,
-0.01433563232421875,
0.0040130615234375,
0.0107269287109375,
0.018646240234375,
0.0017404556274414062,
0.037139892578125,
-0.027557373046875,
-0.02520751953125,
0.02716064453125,
0.0408935546875,
0.038665771484375,
0.0003478527069091797,
-0.056671142578125,
0.035369873046875,
-0.0068511962890625,
-0.04388427734375,
0.0175323486328125,
0.027557373046875,
-0.01435089111328125,
0.07733154296875,
0.037353515625,
0.009857177734375,
0.0020599365234375,
0.0252838134765625,
0.06585693359375,
-0.03741455078125,
-0.03240966796875,
-0.056182861328125,
0.0242919921875,
-0.00433349609375,
-0.037017822265625,
0.06884765625,
0.0345458984375,
0.05328369140625,
0.01174163818359375,
0.029327392578125,
-0.0024471282958984375,
0.02105712890625,
-0.037139892578125,
0.054473876953125,
-0.061737060546875,
0.0156707763671875,
-0.02728271484375,
-0.0653076171875,
-0.01146697998046875,
0.04541015625,
-0.01316070556640625,
0.0121307373046875,
0.0340576171875,
0.057586669921875,
0.01047515869140625,
-0.0189056396484375,
0.019134521484375,
0.0231781005859375,
0.034820556640625,
0.036346435546875,
0.042633056640625,
-0.05975341796875,
0.039031982421875,
-0.01377105712890625,
-0.0213165283203125,
-0.037109375,
-0.048736572265625,
-0.08349609375,
-0.048858642578125,
-0.0153045654296875,
-0.0220184326171875,
0.0119476318359375,
0.0760498046875,
0.052978515625,
-0.02099609375,
-0.04791259765625,
0.00638580322265625,
-0.0030384063720703125,
-0.0194244384765625,
-0.016387939453125,
0.015533447265625,
-0.004230499267578125,
-0.06732177734375,
0.0145416259765625,
-0.024658203125,
0.0175628662109375,
-0.0231781005859375,
-0.0306854248046875,
-0.0224609375,
0.006740570068359375,
0.031402587890625,
0.039031982421875,
-0.034881591796875,
0.0007472038269042969,
-0.0075531005859375,
-0.03192138671875,
0.0136566162109375,
0.02325439453125,
-0.052978515625,
0.004302978515625,
0.028228759765625,
0.01161956787109375,
0.0506591796875,
-0.00441741943359375,
0.033905029296875,
-0.053863525390625,
0.043548583984375,
-0.00653839111328125,
0.0305328369140625,
0.038848876953125,
-0.025390625,
0.031646728515625,
-0.0036411285400390625,
-0.028564453125,
-0.07220458984375,
-0.01433563232421875,
-0.07464599609375,
-0.014617919921875,
0.0928955078125,
0.0200347900390625,
-0.044708251953125,
0.0117340087890625,
-0.04345703125,
0.05133056640625,
-0.0269317626953125,
0.0565185546875,
0.03369140625,
0.01947021484375,
-0.040283203125,
-0.0560302734375,
0.038360595703125,
0.0200347900390625,
-0.06549072265625,
0.0047149658203125,
0.0203704833984375,
0.03302001953125,
-0.00029349327087402344,
0.09368896484375,
-0.0035648345947265625,
0.00004011392593383789,
-0.01227569580078125,
0.03887939453125,
-0.021575927734375,
-0.0298614501953125,
-0.01763916015625,
-0.027923583984375,
0.01427459716796875,
-0.0247955322265625
]
] |
timm/beit_base_patch16_224.in22k_ft_in22k_in1k | 2023-05-08T23:19:17.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:imagenet-22k",
"arxiv:2106.08254",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/beit_base_patch16_224.in22k_ft_in22k_in1k | 0 | 38,949 | timm | 2022-12-23T02:25:09 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- imagenet-22k
---
# Model card for beit_base_patch16_224.in22k_ft_in22k_in1k
A BEiT image classification model. Trained on ImageNet-22k with self-supervised masked image modelling (MIM) using a DALL-E dVAE as visual tokenizer. Fine-tuned on ImageNet-22k and then ImageNet-1k.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 86.5
- GMACs: 17.6
- Activations (M): 23.9
- Image size: 224 x 224
- **Papers:**
- BEiT: BERT Pre-Training of Image Transformers: https://arxiv.org/abs/2106.08254
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-22k
- **Original:** https://github.com/microsoft/unilm/tree/master/beit
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('beit_base_patch16_224.in22k_ft_in22k_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'beit_base_patch16_224.in22k_ft_in22k_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 197, 768) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{bao2021beit,
title={Beit: Bert pre-training of image transformers},
author={Bao, Hangbo and Dong, Li and Piao, Songhao and Wei, Furu},
journal={arXiv preprint arXiv:2106.08254},
year={2021}
}
```
```bibtex
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 3,734 | [
[
-0.042694091796875,
-0.0261077880859375,
-0.000019609928131103516,
0.01265716552734375,
-0.032501220703125,
-0.0186309814453125,
-0.0171356201171875,
-0.03887939453125,
0.016571044921875,
0.027313232421875,
-0.043212890625,
-0.04876708984375,
-0.056610107421875,
-0.00530242919921875,
-0.0145416259765625,
0.0791015625,
-0.01200103759765625,
0.00103759765625,
-0.00814056396484375,
-0.032440185546875,
-0.01302337646484375,
-0.0255126953125,
-0.048370361328125,
-0.035919189453125,
0.022857666015625,
0.00969696044921875,
0.043975830078125,
0.0426025390625,
0.04632568359375,
0.03460693359375,
-0.0062713623046875,
0.0022144317626953125,
-0.0154266357421875,
-0.0224761962890625,
0.02734375,
-0.041351318359375,
-0.03533935546875,
0.0213470458984375,
0.055816650390625,
0.031707763671875,
0.00909423828125,
0.0287322998046875,
0.0085906982421875,
0.044219970703125,
-0.0177459716796875,
0.01354217529296875,
-0.039215087890625,
0.019561767578125,
-0.01300811767578125,
0.00577545166015625,
-0.026458740234375,
-0.0284881591796875,
0.018768310546875,
-0.0379638671875,
0.03533935546875,
-0.00225830078125,
0.10980224609375,
0.011871337890625,
0.00013887882232666016,
-0.0017385482788085938,
-0.023468017578125,
0.0570068359375,
-0.06280517578125,
0.0303955078125,
0.020294189453125,
0.00896453857421875,
-0.0024166107177734375,
-0.07476806640625,
-0.0447998046875,
-0.01230621337890625,
-0.0218505859375,
0.005199432373046875,
-0.031982421875,
0.00571441650390625,
0.02569580078125,
0.0256805419921875,
-0.0298614501953125,
0.00820159912109375,
-0.0386962890625,
-0.0262603759765625,
0.033721923828125,
-0.00846099853515625,
0.0198516845703125,
-0.0163116455078125,
-0.0428466796875,
-0.03662109375,
-0.033660888671875,
0.0184326171875,
0.0333251953125,
0.006805419921875,
-0.04034423828125,
0.031341552734375,
0.0123138427734375,
0.042938232421875,
0.0247802734375,
-0.017303466796875,
0.049774169921875,
-0.00701904296875,
-0.0281829833984375,
-0.0040740966796875,
0.07977294921875,
0.0233917236328125,
0.0196075439453125,
-0.0014781951904296875,
-0.01233673095703125,
-0.01085662841796875,
-0.0011091232299804688,
-0.08837890625,
-0.028717041015625,
0.006885528564453125,
-0.047332763671875,
-0.025604248046875,
0.0186614990234375,
-0.04974365234375,
-0.00250244140625,
-0.0041351318359375,
0.056365966796875,
-0.040374755859375,
-0.025787353515625,
0.00960540771484375,
-0.00382232666015625,
0.0277557373046875,
0.01372528076171875,
-0.041107177734375,
0.01387786865234375,
0.01554107666015625,
0.0755615234375,
0.0064697265625,
-0.03265380859375,
-0.0140380859375,
-0.025360107421875,
-0.02777099609375,
0.039306640625,
-0.003528594970703125,
-0.01042938232421875,
-0.01145172119140625,
0.0243072509765625,
-0.0126800537109375,
-0.04840087890625,
0.027587890625,
-0.0239715576171875,
0.025634765625,
0.0012826919555664062,
-0.022796630859375,
-0.02886962890625,
0.0176849365234375,
-0.03662109375,
0.0928955078125,
0.0321044921875,
-0.07354736328125,
0.033721923828125,
-0.040802001953125,
-0.0084381103515625,
-0.01099395751953125,
0.002185821533203125,
-0.08331298828125,
-0.004482269287109375,
0.020965576171875,
0.0491943359375,
-0.01025390625,
-0.0017652511596679688,
-0.033966064453125,
-0.024017333984375,
0.0253448486328125,
-0.008880615234375,
0.0733642578125,
0.009063720703125,
-0.033447265625,
0.0229644775390625,
-0.044952392578125,
0.00771331787109375,
0.03533935546875,
-0.0191650390625,
-0.0007529258728027344,
-0.044403076171875,
0.0097503662109375,
0.024200439453125,
0.0174560546875,
-0.053070068359375,
0.017120361328125,
-0.0244293212890625,
0.02850341796875,
0.055267333984375,
-0.0186309814453125,
0.0268707275390625,
-0.0301666259765625,
0.025726318359375,
0.02813720703125,
0.01788330078125,
-0.0029697418212890625,
-0.043212890625,
-0.06793212890625,
-0.04376220703125,
0.0361328125,
0.0276031494140625,
-0.040069580078125,
0.05328369140625,
-0.0219268798828125,
-0.059539794921875,
-0.046844482421875,
0.005519866943359375,
0.037506103515625,
0.04266357421875,
0.03106689453125,
-0.04193115234375,
-0.039215087890625,
-0.070556640625,
0.00189971923828125,
-0.007598876953125,
-0.0011081695556640625,
0.02203369140625,
0.04559326171875,
-0.0179595947265625,
0.05841064453125,
-0.0267486572265625,
-0.02825927734375,
-0.01824951171875,
0.01551055908203125,
0.031707763671875,
0.056182861328125,
0.06317138671875,
-0.040130615234375,
-0.042633056640625,
-0.0168304443359375,
-0.06195068359375,
0.003955841064453125,
-0.00222015380859375,
-0.0202789306640625,
0.0308990478515625,
0.01806640625,
-0.057342529296875,
0.05047607421875,
0.0225830078125,
-0.028594970703125,
0.04095458984375,
-0.0214691162109375,
0.00556182861328125,
-0.08392333984375,
-0.0002357959747314453,
0.02337646484375,
-0.01163482666015625,
-0.036956787109375,
-0.0032024383544921875,
0.0084381103515625,
-0.0004546642303466797,
-0.03411865234375,
0.04278564453125,
-0.0382080078125,
-0.0117340087890625,
-0.003452301025390625,
-0.0229339599609375,
-0.000949859619140625,
0.05609130859375,
-0.00754547119140625,
0.03704833984375,
0.05926513671875,
-0.033203125,
0.0264739990234375,
0.036529541015625,
-0.029510498046875,
0.036895751953125,
-0.05291748046875,
0.01593017578125,
-0.0013723373413085938,
0.025177001953125,
-0.0814208984375,
-0.00998687744140625,
0.031402587890625,
-0.044830322265625,
0.053558349609375,
-0.031951904296875,
-0.048583984375,
-0.0445556640625,
-0.03466796875,
0.03472900390625,
0.056121826171875,
-0.05865478515625,
0.042724609375,
0.0088348388671875,
0.0191802978515625,
-0.040130615234375,
-0.061248779296875,
-0.0180511474609375,
-0.033172607421875,
-0.055694580078125,
0.038787841796875,
-0.0008721351623535156,
0.0178680419921875,
0.01226043701171875,
-0.00775909423828125,
0.0015268325805664062,
-0.01459503173828125,
0.032470703125,
0.037353515625,
-0.0163726806640625,
-0.0035953521728515625,
-0.0194091796875,
-0.012908935546875,
0.00579071044921875,
-0.021148681640625,
0.04840087890625,
-0.0242156982421875,
-0.0178375244140625,
-0.057830810546875,
-0.007415771484375,
0.038055419921875,
-0.0159149169921875,
0.05865478515625,
0.08660888671875,
-0.035675048828125,
0.00658416748046875,
-0.038848876953125,
-0.0233154296875,
-0.038787841796875,
0.035614013671875,
-0.0291595458984375,
-0.03521728515625,
0.0634765625,
0.00312042236328125,
0.0016183853149414062,
0.058258056640625,
0.03375244140625,
-0.00543975830078125,
0.0677490234375,
0.04620361328125,
0.004207611083984375,
0.055023193359375,
-0.06488037109375,
-0.003772735595703125,
-0.06719970703125,
-0.027099609375,
-0.0251922607421875,
-0.042388916015625,
-0.052825927734375,
-0.018890380859375,
0.03216552734375,
0.00955963134765625,
-0.031524658203125,
0.03814697265625,
-0.061187744140625,
0.00218963623046875,
0.059600830078125,
0.04058837890625,
-0.020416259765625,
0.0244293212890625,
-0.0234832763671875,
-0.0055084228515625,
-0.054840087890625,
-0.016082763671875,
0.0823974609375,
0.0379638671875,
0.053619384765625,
-0.01214599609375,
0.056884765625,
-0.01486968994140625,
0.031158447265625,
-0.049041748046875,
0.0484619140625,
-0.006916046142578125,
-0.037628173828125,
-0.010284423828125,
-0.027374267578125,
-0.08447265625,
0.0030517578125,
-0.0242462158203125,
-0.05859375,
0.01045989990234375,
0.01073455810546875,
-0.0178070068359375,
0.056915283203125,
-0.0601806640625,
0.0693359375,
-0.006103515625,
-0.0189971923828125,
0.0032367706298828125,
-0.05462646484375,
0.0129241943359375,
0.003665924072265625,
-0.01617431640625,
-0.0033016204833984375,
0.0201568603515625,
0.08343505859375,
-0.0408935546875,
0.0662841796875,
-0.03192138671875,
0.0217742919921875,
0.03167724609375,
-0.00959014892578125,
0.02734375,
-0.0154266357421875,
0.00208282470703125,
0.033935546875,
0.00934600830078125,
-0.031524658203125,
-0.034271240234375,
0.036712646484375,
-0.0816650390625,
-0.0286102294921875,
-0.035919189453125,
-0.039947509765625,
0.00580596923828125,
0.01081085205078125,
0.0501708984375,
0.045562744140625,
0.0217132568359375,
0.022735595703125,
0.0467529296875,
-0.031585693359375,
0.030517578125,
0.0009927749633789062,
-0.01702880859375,
-0.03704833984375,
0.059051513671875,
0.0240936279296875,
0.01259613037109375,
0.00286102294921875,
0.020477294921875,
-0.02825927734375,
-0.04083251953125,
-0.032257080078125,
0.036529541015625,
-0.056396484375,
-0.03802490234375,
-0.04388427734375,
-0.042633056640625,
-0.0246734619140625,
-0.002368927001953125,
-0.029754638671875,
-0.0174407958984375,
-0.031524658203125,
0.007671356201171875,
0.05291748046875,
0.041595458984375,
-0.0107269287109375,
0.041839599609375,
-0.0482177734375,
0.007083892822265625,
0.0154266357421875,
0.046356201171875,
-0.00485992431640625,
-0.0782470703125,
-0.024566650390625,
-0.003204345703125,
-0.034637451171875,
-0.060546875,
0.035369873046875,
0.0110015869140625,
0.040679931640625,
0.027099609375,
-0.013702392578125,
0.056182861328125,
-0.014068603515625,
0.039764404296875,
0.0301666259765625,
-0.050537109375,
0.03533935546875,
-0.006290435791015625,
0.01513671875,
0.01055145263671875,
0.0268096923828125,
-0.01454925537109375,
-0.004924774169921875,
-0.0823974609375,
-0.05487060546875,
0.06304931640625,
0.01531219482421875,
0.01033782958984375,
0.027374267578125,
0.041839599609375,
0.0027618408203125,
0.00415802001953125,
-0.06280517578125,
-0.03143310546875,
-0.031158447265625,
-0.0269927978515625,
0.0002009868621826172,
-0.00902557373046875,
-0.004611968994140625,
-0.056304931640625,
0.059722900390625,
-0.0024509429931640625,
0.06622314453125,
0.0234222412109375,
-0.005809783935546875,
-0.0145263671875,
-0.02288818359375,
0.0291290283203125,
0.0199737548828125,
-0.028778076171875,
0.0041656494140625,
0.014129638671875,
-0.046051025390625,
0.0004000663757324219,
0.02386474609375,
-0.00376129150390625,
0.00881195068359375,
0.0321044921875,
0.07501220703125,
-0.0015687942504882812,
-0.001750946044921875,
0.03515625,
-0.0018825531005859375,
-0.036102294921875,
-0.0201568603515625,
-0.005176544189453125,
-0.004245758056640625,
0.02655029296875,
0.0243072509765625,
0.0232696533203125,
-0.0162506103515625,
-0.01788330078125,
0.019195556640625,
0.044586181640625,
-0.0284881591796875,
-0.031646728515625,
0.04229736328125,
-0.0256805419921875,
-0.013671875,
0.0628662109375,
-0.00986480712890625,
-0.046539306640625,
0.0692138671875,
0.037994384765625,
0.07110595703125,
-0.0062713623046875,
0.00618743896484375,
0.05718994140625,
0.0182647705078125,
0.005031585693359375,
0.010711669921875,
0.0128631591796875,
-0.06744384765625,
0.0006985664367675781,
-0.047821044921875,
0.00249481201171875,
0.0296173095703125,
-0.037261962890625,
0.0263214111328125,
-0.044769287109375,
-0.031585693359375,
0.0157623291015625,
0.0196533203125,
-0.07098388671875,
0.0184478759765625,
0.0029201507568359375,
0.06036376953125,
-0.05810546875,
0.060516357421875,
0.060333251953125,
-0.044281005859375,
-0.07940673828125,
-0.00823211669921875,
-0.0103912353515625,
-0.06756591796875,
0.04998779296875,
0.03802490234375,
0.0084381103515625,
0.0152130126953125,
-0.0601806640625,
-0.055084228515625,
0.09423828125,
0.034912109375,
-0.0018825531005859375,
0.0154876708984375,
-0.0008435249328613281,
0.0262298583984375,
-0.0269012451171875,
0.0292510986328125,
0.0149688720703125,
0.028778076171875,
0.0247344970703125,
-0.05615234375,
0.011138916015625,
-0.0250396728515625,
0.000640869140625,
0.021209716796875,
-0.056060791015625,
0.07012939453125,
-0.0221099853515625,
-0.011260986328125,
0.01348876953125,
0.049468994140625,
0.0207061767578125,
0.005023956298828125,
0.04974365234375,
0.06854248046875,
0.0306549072265625,
-0.0250244140625,
0.0601806640625,
-0.0160369873046875,
0.0458984375,
0.041778564453125,
0.0273284912109375,
0.037628173828125,
0.0287628173828125,
-0.031036376953125,
0.04071044921875,
0.080078125,
-0.0333251953125,
0.032379150390625,
0.0158233642578125,
-0.0011463165283203125,
-0.0135345458984375,
0.0000016093254089355469,
-0.03497314453125,
0.038360595703125,
0.01366424560546875,
-0.036865234375,
-0.01885986328125,
0.0033550262451171875,
0.004848480224609375,
-0.02593994140625,
-0.0154266357421875,
0.038604736328125,
-0.0006308555603027344,
-0.031341552734375,
0.05718994140625,
0.0057220458984375,
0.06866455078125,
-0.042083740234375,
0.0026607513427734375,
-0.0144500732421875,
0.02508544921875,
-0.021881103515625,
-0.05889892578125,
0.0205841064453125,
-0.0216064453125,
0.00020945072174072266,
-0.001708984375,
0.057342529296875,
-0.02496337890625,
-0.0474853515625,
0.017578125,
0.0222930908203125,
0.029449462890625,
0.0006356239318847656,
-0.08563232421875,
0.0013370513916015625,
-0.004711151123046875,
-0.041656494140625,
0.027984619140625,
0.0325927734375,
0.0035762786865234375,
0.048431396484375,
0.05072021484375,
-0.004547119140625,
0.0196075439453125,
-0.01103973388671875,
0.06756591796875,
-0.02581787109375,
-0.0275421142578125,
-0.062164306640625,
0.03814697265625,
-0.0028133392333984375,
-0.036773681640625,
0.046722412109375,
0.03704833984375,
0.072265625,
-0.00809478759765625,
0.0302581787109375,
-0.0147857666015625,
0.00357818603515625,
-0.02630615234375,
0.056365966796875,
-0.0518798828125,
-0.01114654541015625,
-0.026885986328125,
-0.054840087890625,
-0.02581787109375,
0.0650634765625,
-0.0199737548828125,
0.034881591796875,
0.035919189453125,
0.0721435546875,
-0.022186279296875,
-0.0272216796875,
0.013031005859375,
0.011444091796875,
0.00774383544921875,
0.029266357421875,
0.035430908203125,
-0.057098388671875,
0.0316162109375,
-0.047760009765625,
-0.01166534423828125,
-0.007442474365234375,
-0.052398681640625,
-0.0792236328125,
-0.06488037109375,
-0.0423583984375,
-0.0516357421875,
-0.025421142578125,
0.0723876953125,
0.080078125,
-0.050933837890625,
-0.00634002685546875,
-0.0017786026000976562,
-0.0029621124267578125,
-0.0210723876953125,
-0.015289306640625,
0.05438232421875,
-0.009002685546875,
-0.052825927734375,
-0.03179931640625,
-0.00197601318359375,
0.036102294921875,
-0.01036834716796875,
-0.01763916015625,
-0.0181884765625,
-0.00969696044921875,
0.01885986328125,
0.01554107666015625,
-0.053619384765625,
-0.0203399658203125,
-0.00913238525390625,
-0.006557464599609375,
0.038543701171875,
0.023895263671875,
-0.048187255859375,
0.029571533203125,
0.0276336669921875,
0.031219482421875,
0.06573486328125,
-0.0205230712890625,
-0.0023956298828125,
-0.0628662109375,
0.037506103515625,
-0.005756378173828125,
0.040374755859375,
0.034149169921875,
-0.0234375,
0.03875732421875,
0.036407470703125,
-0.031219482421875,
-0.061492919921875,
0.0002639293670654297,
-0.08135986328125,
-0.001781463623046875,
0.06317138671875,
-0.032440185546875,
-0.02886962890625,
0.03033447265625,
-0.0105133056640625,
0.05474853515625,
-0.004985809326171875,
0.04400634765625,
0.034210205078125,
-0.0003876686096191406,
-0.04205322265625,
-0.0313720703125,
0.0323486328125,
0.02093505859375,
-0.0450439453125,
-0.03619384765625,
0.0021343231201171875,
0.044708251953125,
0.027984619140625,
0.0362548828125,
-0.0172119140625,
0.006072998046875,
-0.00452423095703125,
0.03778076171875,
-0.02252197265625,
-0.006473541259765625,
-0.0214385986328125,
-0.006961822509765625,
-0.00589752197265625,
-0.045654296875
]
] |
timm/cspdarknet53.ra_in1k | 2023-04-12T20:39:34.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1911.11929",
"arxiv:1804.02767",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/cspdarknet53.ra_in1k | 0 | 38,858 | timm | 2023-04-12T20:39:07 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
---
# Model card for cspdarknet53.ra_in1k
A CSP-DarkNet (Cross-Stage-Partial) image classification model. Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* RandAugment `RA` recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as `B` recipe in [ResNet Strikes Back](https://arxiv.org/abs/2110.00476).
* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
* Step (exponential decay w/ staircase) LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 27.6
- GMACs: 6.6
- Activations (M): 16.8
- Image size: 256 x 256
- **Papers:**
- CSPNet: A New Backbone that can Enhance Learning Capability of CNN: https://arxiv.org/abs/1911.11929
- YOLOv3: An Incremental Improvement: https://arxiv.org/abs/1804.02767
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('cspdarknet53.ra_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'cspdarknet53.ra_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 32, 256, 256])
# torch.Size([1, 64, 128, 128])
# torch.Size([1, 128, 64, 64])
# torch.Size([1, 256, 32, 32])
# torch.Size([1, 512, 16, 16])
# torch.Size([1, 1024, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'cspdarknet53.ra_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1024, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{Wang2019CSPNetAN,
title={CSPNet: A New Backbone that can Enhance Learning Capability of CNN},
author={Chien-Yao Wang and Hong-Yuan Mark Liao and I-Hau Yeh and Yueh-Hua Wu and Ping-Yang Chen and Jun-Wei Hsieh},
journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
year={2019},
pages={1571-1580}
}
```
```bibtex
@article{Redmon2018YOLOv3AI,
title={YOLOv3: An Incremental Improvement},
author={Joseph Redmon and Ali Farhadi},
journal={ArXiv},
year={2018},
volume={abs/1804.02767}
}
```
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 5,042 | [
[
-0.033172607421875,
-0.0179595947265625,
-0.0065460205078125,
0.00922393798828125,
-0.02056884765625,
-0.0160064697265625,
-0.021636962890625,
-0.0292816162109375,
0.0138092041015625,
0.02850341796875,
-0.0301666259765625,
-0.045989990234375,
-0.054229736328125,
-0.00640106201171875,
-0.0139312744140625,
0.06768798828125,
0.0004374980926513672,
0.0113525390625,
-0.003200531005859375,
-0.0292816162109375,
-0.006359100341796875,
-0.025115966796875,
-0.06787109375,
-0.035675048828125,
0.036102294921875,
0.022064208984375,
0.039947509765625,
0.044219970703125,
0.04022216796875,
0.034637451171875,
-0.0125274658203125,
0.01032257080078125,
-0.0194091796875,
-0.0226898193359375,
0.023773193359375,
-0.044464111328125,
-0.032928466796875,
0.01494598388671875,
0.05224609375,
0.0384521484375,
0.005306243896484375,
0.0200958251953125,
0.0194091796875,
0.04962158203125,
-0.034332275390625,
0.00524139404296875,
-0.0263824462890625,
0.0286712646484375,
-0.00817108154296875,
-0.0053863525390625,
-0.022552490234375,
-0.0263214111328125,
0.0234527587890625,
-0.040130615234375,
0.038970947265625,
0.00165557861328125,
0.0948486328125,
0.005336761474609375,
-0.00005167722702026367,
0.00386810302734375,
-0.01198577880859375,
0.06512451171875,
-0.0626220703125,
0.01450347900390625,
0.0237274169921875,
0.02410888671875,
-0.01198577880859375,
-0.08343505859375,
-0.04571533203125,
-0.01552581787109375,
-0.00576019287109375,
0.00176239013671875,
-0.01494598388671875,
-0.006137847900390625,
0.0146484375,
0.026458740234375,
-0.031524658203125,
0.01488494873046875,
-0.0484619140625,
-0.01641845703125,
0.033660888671875,
0.005859375,
0.0212860107421875,
-0.021240234375,
-0.0288848876953125,
-0.0350341796875,
-0.0271148681640625,
0.020660400390625,
0.0267486572265625,
0.0198211669921875,
-0.047943115234375,
0.0229339599609375,
0.0010824203491210938,
0.048065185546875,
0.01551055908203125,
-0.0202178955078125,
0.0474853515625,
0.0038852691650390625,
-0.03228759765625,
-0.0060272216796875,
0.08001708984375,
0.0234832763671875,
0.01317596435546875,
0.006046295166015625,
0.0040435791015625,
-0.036590576171875,
-0.003078460693359375,
-0.0838623046875,
-0.037353515625,
0.020751953125,
-0.053955078125,
-0.040924072265625,
0.014801025390625,
-0.0467529296875,
-0.0225372314453125,
-0.004978179931640625,
0.021148681640625,
-0.04803466796875,
-0.0316162109375,
0.0077972412109375,
-0.017333984375,
0.0340576171875,
0.0276947021484375,
-0.04296875,
0.01549530029296875,
0.0269775390625,
0.08270263671875,
0.00107574462890625,
-0.03765869140625,
-0.01503753662109375,
-0.032867431640625,
-0.025299072265625,
0.037445068359375,
-0.0072021484375,
-0.0032196044921875,
-0.0259857177734375,
0.0264434814453125,
-0.00643157958984375,
-0.046356201171875,
0.0193939208984375,
-0.0203857421875,
0.027862548828125,
-0.007228851318359375,
-0.00939178466796875,
-0.041717529296875,
0.028533935546875,
-0.031890869140625,
0.0882568359375,
0.01922607421875,
-0.0712890625,
0.0200042724609375,
-0.0335693359375,
-0.00934600830078125,
-0.023284912109375,
-0.0024013519287109375,
-0.07879638671875,
-0.0107421875,
0.0199127197265625,
0.05487060546875,
-0.032745361328125,
-0.004940032958984375,
-0.049224853515625,
-0.02685546875,
0.0283966064453125,
-0.0093994140625,
0.08392333984375,
0.0154876708984375,
-0.03338623046875,
0.009552001953125,
-0.058441162109375,
0.0174713134765625,
0.038543701171875,
-0.0260009765625,
0.007106781005859375,
-0.037628173828125,
0.01433563232421875,
0.0262603759765625,
0.005672454833984375,
-0.03662109375,
0.0095672607421875,
-0.02410888671875,
0.032012939453125,
0.052703857421875,
-0.0122833251953125,
0.02862548828125,
-0.032989501953125,
0.02520751953125,
0.0218048095703125,
0.0204925537109375,
-0.0029659271240234375,
-0.03497314453125,
-0.06634521484375,
-0.0391845703125,
0.0303497314453125,
0.0305938720703125,
-0.0310516357421875,
0.0361328125,
-0.00995635986328125,
-0.059051513671875,
-0.0197601318359375,
-0.0005846023559570312,
0.03631591796875,
0.0455322265625,
0.02996826171875,
-0.0455322265625,
-0.04364013671875,
-0.06549072265625,
0.00749969482421875,
0.01395416259765625,
0.0030269622802734375,
0.02410888671875,
0.044281005859375,
0.006755828857421875,
0.041534423828125,
-0.031463623046875,
-0.019195556640625,
-0.0239715576171875,
0.0089874267578125,
0.0295257568359375,
0.06353759765625,
0.0631103515625,
-0.0474853515625,
-0.04559326171875,
-0.00780487060546875,
-0.06475830078125,
0.01812744140625,
-0.005706787109375,
-0.007904052734375,
0.018646240234375,
0.01033782958984375,
-0.0308990478515625,
0.046783447265625,
0.01629638671875,
-0.01091766357421875,
0.041900634765625,
-0.01247406005859375,
0.0283966064453125,
-0.08697509765625,
0.01076507568359375,
0.0263519287109375,
-0.0024013519287109375,
-0.0290985107421875,
-0.0013303756713867188,
0.00482177734375,
-0.016937255859375,
-0.0472412109375,
0.0305633544921875,
-0.05023193359375,
-0.020904541015625,
-0.0195159912109375,
-0.009765625,
0.0025787353515625,
0.06500244140625,
-0.006366729736328125,
0.0280303955078125,
0.07568359375,
-0.035064697265625,
0.03509521484375,
0.02166748046875,
-0.0163726806640625,
0.03875732421875,
-0.049713134765625,
0.0173797607421875,
-0.0032444000244140625,
0.0245819091796875,
-0.07269287109375,
-0.01473236083984375,
0.03631591796875,
-0.051300048828125,
0.051910400390625,
-0.040924072265625,
-0.03497314453125,
-0.041717529296875,
-0.03704833984375,
0.02471923828125,
0.0455322265625,
-0.056610107421875,
0.038482666015625,
0.005947113037109375,
0.0298614501953125,
-0.053802490234375,
-0.07000732421875,
-0.00170135498046875,
-0.0218048095703125,
-0.051483154296875,
0.0298919677734375,
0.01282501220703125,
0.0193328857421875,
0.00922393798828125,
-0.006725311279296875,
-0.018157958984375,
-0.00727081298828125,
0.03936767578125,
0.02294921875,
-0.02490234375,
-0.0169830322265625,
-0.0297088623046875,
-0.004673004150390625,
-0.005306243896484375,
-0.0305938720703125,
0.04644775390625,
-0.0220794677734375,
-0.01233673095703125,
-0.06768798828125,
-0.0008029937744140625,
0.0341796875,
-0.0194854736328125,
0.06109619140625,
0.07952880859375,
-0.037078857421875,
-0.0087432861328125,
-0.0278167724609375,
-0.02117919921875,
-0.03863525390625,
0.03857421875,
-0.0211639404296875,
-0.03619384765625,
0.062164306640625,
-0.0035839080810546875,
-0.005390167236328125,
0.041290283203125,
0.0210723876953125,
-0.008026123046875,
0.055633544921875,
0.045257568359375,
0.01445770263671875,
0.049835205078125,
-0.07470703125,
-0.01085662841796875,
-0.0709228515625,
-0.035614013671875,
-0.03619384765625,
-0.044281005859375,
-0.045074462890625,
-0.0291290283203125,
0.0288238525390625,
0.0189666748046875,
-0.032928466796875,
0.042205810546875,
-0.06854248046875,
0.006847381591796875,
0.0482177734375,
0.047088623046875,
-0.0299530029296875,
0.0197601318359375,
-0.0251007080078125,
-0.00518798828125,
-0.0645751953125,
-0.01000213623046875,
0.082763671875,
0.02490234375,
0.040771484375,
-0.0100555419921875,
0.054107666015625,
-0.0182647705078125,
0.0164337158203125,
-0.038818359375,
0.050140380859375,
-0.01023101806640625,
-0.0275421142578125,
-0.00243377685546875,
-0.0273284912109375,
-0.07733154296875,
0.01092529296875,
-0.031707763671875,
-0.05902099609375,
0.0267181396484375,
0.0181884765625,
-0.0164947509765625,
0.059417724609375,
-0.05572509765625,
0.06280517578125,
-0.01384735107421875,
-0.037261962890625,
-0.0054779052734375,
-0.053680419921875,
0.0238800048828125,
0.0169830322265625,
-0.0250091552734375,
-0.004650115966796875,
0.0161895751953125,
0.068115234375,
-0.050140380859375,
0.072265625,
-0.0274505615234375,
0.033721923828125,
0.0302886962890625,
-0.01395416259765625,
0.027862548828125,
-0.0150299072265625,
-0.01549530029296875,
0.0253143310546875,
-0.005451202392578125,
-0.037384033203125,
-0.04473876953125,
0.049224853515625,
-0.0762939453125,
-0.0258636474609375,
-0.040313720703125,
-0.0318603515625,
0.01406097412109375,
0.01512908935546875,
0.03564453125,
0.052703857421875,
0.0228271484375,
0.0269012451171875,
0.047088623046875,
-0.045928955078125,
0.033966064453125,
0.0078125,
-0.00311279296875,
-0.04400634765625,
0.0621337890625,
0.0186004638671875,
0.00783538818359375,
0.0176239013671875,
0.018798828125,
-0.00931549072265625,
-0.052642822265625,
-0.01186370849609375,
0.0180206298828125,
-0.061981201171875,
-0.035247802734375,
-0.0440673828125,
-0.03179931640625,
-0.03643798828125,
-0.0113983154296875,
-0.03955078125,
-0.0330810546875,
-0.036590576171875,
0.0225677490234375,
0.0487060546875,
0.032012939453125,
-0.0173187255859375,
0.03424072265625,
-0.0328369140625,
0.0034656524658203125,
0.007007598876953125,
0.0328369140625,
0.0053558349609375,
-0.06396484375,
-0.0218048095703125,
-0.01000213623046875,
-0.0413818359375,
-0.055450439453125,
0.034759521484375,
0.01300048828125,
0.03961181640625,
0.0205535888671875,
-0.0102996826171875,
0.058258056640625,
-0.004123687744140625,
0.04547119140625,
0.04193115234375,
-0.0438232421875,
0.041168212890625,
-0.006534576416015625,
0.0228424072265625,
0.006237030029296875,
0.0271453857421875,
-0.0215606689453125,
-0.006496429443359375,
-0.06439208984375,
-0.058135986328125,
0.071044921875,
0.00283050537109375,
-0.00525665283203125,
0.022857666015625,
0.048828125,
-0.00998687744140625,
-0.004207611083984375,
-0.05560302734375,
-0.0361328125,
-0.041748046875,
-0.01201629638671875,
0.01369476318359375,
0.0006833076477050781,
-0.002780914306640625,
-0.048065185546875,
0.053955078125,
-0.009063720703125,
0.055877685546875,
0.0300750732421875,
0.0034885406494140625,
-0.004543304443359375,
-0.025146484375,
0.036590576171875,
0.03369140625,
-0.0218353271484375,
0.0055694580078125,
0.0212249755859375,
-0.041717529296875,
-0.0037975311279296875,
0.0191650390625,
0.00594329833984375,
-0.01415252685546875,
0.034942626953125,
0.062164306640625,
0.010009765625,
0.00421142578125,
0.036468505859375,
-0.0038928985595703125,
-0.03460693359375,
-0.0300750732421875,
0.015289306640625,
-0.0032176971435546875,
0.03369140625,
0.032196044921875,
0.040313720703125,
-0.007396697998046875,
-0.01453399658203125,
0.026458740234375,
0.0288848876953125,
-0.025054931640625,
-0.018402099609375,
0.050537109375,
-0.017303466796875,
-0.01273345947265625,
0.060760498046875,
-0.006534576416015625,
-0.040191650390625,
0.082275390625,
0.03387451171875,
0.06964111328125,
0.0023136138916015625,
0.00434112548828125,
0.06658935546875,
0.01514434814453125,
0.007251739501953125,
0.007144927978515625,
0.006622314453125,
-0.055023193359375,
-0.0031299591064453125,
-0.0303802490234375,
0.00118255615234375,
0.0259246826171875,
-0.0411376953125,
0.03564453125,
-0.06475830078125,
-0.01995849609375,
0.0174560546875,
0.0258331298828125,
-0.07135009765625,
0.0198822021484375,
-0.00036334991455078125,
0.072265625,
-0.03826904296875,
0.06451416015625,
0.0552978515625,
-0.0462646484375,
-0.08282470703125,
-0.0017137527465820312,
0.006725311279296875,
-0.0677490234375,
0.051727294921875,
0.0282745361328125,
0.004848480224609375,
0.00127410888671875,
-0.061492919921875,
-0.047760009765625,
0.10980224609375,
0.03741455078125,
-0.00812530517578125,
0.0217132568359375,
-0.0046539306640625,
0.0198822021484375,
-0.0283355712890625,
0.03521728515625,
0.002162933349609375,
0.024658203125,
0.0258636474609375,
-0.048614501953125,
0.020172119140625,
-0.027587890625,
0.01007843017578125,
0.00443267822265625,
-0.06396484375,
0.06707763671875,
-0.039520263671875,
-0.0096435546875,
0.0058135986328125,
0.05517578125,
0.01971435546875,
0.00432586669921875,
0.037872314453125,
0.060943603515625,
0.037445068359375,
-0.0182647705078125,
0.07061767578125,
-0.00925445556640625,
0.0411376953125,
0.056854248046875,
0.0242767333984375,
0.037750244140625,
0.021484375,
-0.0179290771484375,
0.033172607421875,
0.08184814453125,
-0.03497314453125,
0.03277587890625,
0.0245819091796875,
0.0016393661499023438,
-0.01079559326171875,
0.0123291015625,
-0.03619384765625,
0.038665771484375,
0.00385284423828125,
-0.0450439453125,
-0.020111083984375,
0.0031833648681640625,
0.007129669189453125,
-0.01543426513671875,
-0.0116729736328125,
0.0279083251953125,
0.0006608963012695312,
-0.0291290283203125,
0.0701904296875,
0.01568603515625,
0.06451416015625,
-0.03765869140625,
-0.006015777587890625,
-0.0182647705078125,
0.019287109375,
-0.031524658203125,
-0.057861328125,
0.0185394287109375,
-0.0262908935546875,
-0.004428863525390625,
0.0092010498046875,
0.05145263671875,
-0.0174102783203125,
-0.0311431884765625,
0.01474761962890625,
0.007106781005859375,
0.0310821533203125,
0.01399993896484375,
-0.09820556640625,
0.01311492919921875,
0.0011081695556640625,
-0.04083251953125,
0.0296783447265625,
0.0286712646484375,
0.0140533447265625,
0.05340576171875,
0.04827880859375,
-0.004344940185546875,
0.009246826171875,
-0.01450347900390625,
0.06787109375,
-0.033050537109375,
-0.0276947021484375,
-0.047943115234375,
0.048828125,
-0.0199737548828125,
-0.048065185546875,
0.048370361328125,
0.04541015625,
0.062744140625,
0.0008902549743652344,
0.040496826171875,
-0.026702880859375,
0.0015392303466796875,
-0.023223876953125,
0.053314208984375,
-0.050506591796875,
0.00785064697265625,
-0.01751708984375,
-0.04302978515625,
-0.03131103515625,
0.05657958984375,
-0.0224456787109375,
0.0281219482421875,
0.0419921875,
0.08148193359375,
-0.0301055908203125,
-0.0199127197265625,
0.0090484619140625,
0.0032482147216796875,
0.006389617919921875,
0.038726806640625,
0.0296630859375,
-0.064697265625,
0.037994384765625,
-0.055023193359375,
-0.014739990234375,
-0.00514984130859375,
-0.061920166015625,
-0.07403564453125,
-0.065673828125,
-0.04901123046875,
-0.056365966796875,
-0.005611419677734375,
0.06439208984375,
0.09002685546875,
-0.054656982421875,
-0.006633758544921875,
-0.005344390869140625,
0.01157379150390625,
-0.0305023193359375,
-0.018402099609375,
0.0528564453125,
-0.0159454345703125,
-0.054107666015625,
-0.0137481689453125,
0.002918243408203125,
0.0231781005859375,
-0.00476837158203125,
-0.023712158203125,
-0.018310546875,
-0.0237274169921875,
0.0098419189453125,
0.03436279296875,
-0.044158935546875,
-0.015655517578125,
-0.01428985595703125,
-0.00905609130859375,
0.0323486328125,
0.042083740234375,
-0.037750244140625,
0.02349853515625,
0.033355712890625,
0.0285186767578125,
0.0653076171875,
-0.037567138671875,
0.0126800537109375,
-0.0616455078125,
0.045074462890625,
-0.005886077880859375,
0.037445068359375,
0.037872314453125,
-0.0277252197265625,
0.037384033203125,
0.034423828125,
-0.0335693359375,
-0.061798095703125,
-0.005832672119140625,
-0.08123779296875,
-0.019073486328125,
0.058135986328125,
-0.03643798828125,
-0.03802490234375,
0.0242156982421875,
-0.00238800048828125,
0.048126220703125,
-0.003658294677734375,
0.039031982421875,
0.014068603515625,
-0.005611419677734375,
-0.06317138671875,
-0.03485107421875,
0.032440185546875,
0.01375579833984375,
-0.0438232421875,
-0.035125732421875,
0.004871368408203125,
0.054473876953125,
0.017486572265625,
0.03863525390625,
-0.0224456787109375,
0.024017333984375,
0.002719879150390625,
0.03704833984375,
-0.038421630859375,
-0.004302978515625,
-0.02191162109375,
0.0115203857421875,
-0.01068115234375,
-0.045654296875
]
] |
timm/inception_v3.tf_adv_in1k | 2023-05-10T01:04:13.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1512.00567",
"arxiv:1804.00097",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/inception_v3.tf_adv_in1k | 1 | 38,691 | timm | 2023-04-25T21:28:52 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for inception_v3.tf_adv_in1k
A Inception-v3 image classification model. Adversarially trained on ImageNet-1k by paper authors. Ported from Tensorflow by Ross Wightman.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 23.8
- GMACs: 5.7
- Activations (M): 9.0
- Image size: 299 x 299
- **Papers:**
- Rethinking the Inception Architecture for Computer Vision: https://arxiv.org/abs/1512.00567
- Adversarial Attacks and Defences Competition: https://arxiv.org/abs/1804.00097
- **Original:** https://github.com/tensorflow/models
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('inception_v3.tf_adv_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'inception_v3.tf_adv_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 147, 147])
# torch.Size([1, 192, 71, 71])
# torch.Size([1, 288, 35, 35])
# torch.Size([1, 768, 17, 17])
# torch.Size([1, 2048, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'inception_v3.tf_adv_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{DBLP:journals/corr/SzegedyVISW15,
author = {Christian Szegedy and
Vincent Vanhoucke and
Sergey Ioffe and
Jonathon Shlens and
Zbigniew Wojna},
title = {Rethinking the Inception Architecture for Computer Vision},
journal = {CoRR},
volume = {abs/1512.00567},
year = {2015},
url = {http://arxiv.org/abs/1512.00567},
archivePrefix = {arXiv},
eprint = {1512.00567},
timestamp = {Mon, 13 Aug 2018 16:49:07 +0200},
biburl = {https://dblp.org/rec/journals/corr/SzegedyVISW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
```bibtex
@article{Kurakin2018AdversarialAA,
title={Adversarial Attacks and Defences Competition},
author={Alexey Kurakin and Ian J. Goodfellow and Samy Bengio and Yinpeng Dong and Fangzhou Liao and Ming Liang and Tianyu Pang and Jun Zhu and Xiaolin Hu and Cihang Xie and Jianyu Wang and Zhishuai Zhang and Zhou Ren and Alan Loddon Yuille and Sangxia Huang and Yao Zhao and Yuzhe Zhao and Zhonglin Han and Junjiajia Long and Yerkebulan Berdibekov and Takuya Akiba and Seiya Tokui and Motoki Abe},
journal={ArXiv},
year={2018},
volume={abs/1804.00097}
}
```
| 4,779 | [
[
-0.040618896484375,
-0.046051025390625,
0.01091766357421875,
0.0025482177734375,
-0.0213165283203125,
-0.0152130126953125,
-0.006992340087890625,
-0.0411376953125,
0.006023406982421875,
0.02081298828125,
-0.025787353515625,
-0.05535888671875,
-0.053253173828125,
-0.0104522705078125,
-0.0235443115234375,
0.06689453125,
-0.00115203857421875,
-0.00634002685546875,
-0.018951416015625,
-0.0293731689453125,
-0.0014543533325195312,
-0.02276611328125,
-0.07147216796875,
-0.0262603759765625,
0.01416015625,
0.003734588623046875,
0.045440673828125,
0.051971435546875,
0.046478271484375,
0.031890869140625,
-0.022308349609375,
0.000972747802734375,
-0.0179290771484375,
-0.024688720703125,
0.0239105224609375,
-0.04217529296875,
-0.035552978515625,
0.0146026611328125,
0.056732177734375,
0.04241943359375,
0.0034122467041015625,
0.02325439453125,
0.0193634033203125,
0.03973388671875,
-0.0204315185546875,
-0.001529693603515625,
-0.0323486328125,
0.0196380615234375,
-0.014068603515625,
0.00856781005859375,
-0.0170135498046875,
-0.02471923828125,
0.018463134765625,
-0.043304443359375,
0.0439453125,
0.0005240440368652344,
0.09912109375,
0.012847900390625,
0.01239776611328125,
-0.0004925727844238281,
-0.0296173095703125,
0.05780029296875,
-0.0537109375,
0.02142333984375,
0.003871917724609375,
0.0018777847290039062,
-0.01345062255859375,
-0.074462890625,
-0.0433349609375,
-0.006542205810546875,
-0.003509521484375,
-0.0036678314208984375,
-0.022216796875,
-0.002269744873046875,
0.01232147216796875,
0.038604736328125,
-0.03240966796875,
0.01081085205078125,
-0.048797607421875,
-0.01171875,
0.042938232421875,
-0.00504302978515625,
0.0205230712890625,
-0.01287078857421875,
-0.046142578125,
-0.035980224609375,
-0.038360595703125,
0.023345947265625,
0.026641845703125,
0.0130615234375,
-0.044647216796875,
0.0302276611328125,
0.01546478271484375,
0.046478271484375,
0.00998687744140625,
-0.022552490234375,
0.042724609375,
-0.0074920654296875,
-0.03167724609375,
-0.00035643577575683594,
0.08282470703125,
0.0253143310546875,
0.00800323486328125,
-0.0006666183471679688,
0.0018892288208007812,
-0.026763916015625,
0.006793975830078125,
-0.07586669921875,
-0.01177978515625,
0.03167724609375,
-0.03778076171875,
-0.033416748046875,
0.0198822021484375,
-0.050811767578125,
-0.01525115966796875,
0.00818634033203125,
0.0455322265625,
-0.045867919921875,
-0.028045654296875,
0.0016613006591796875,
-0.0136566162109375,
0.03765869140625,
0.0108489990234375,
-0.033203125,
0.0022449493408203125,
0.033416748046875,
0.08941650390625,
-0.0015344619750976562,
-0.03607177734375,
0.00293731689453125,
-0.014373779296875,
-0.03472900390625,
0.037506103515625,
-0.0026645660400390625,
-0.023712158203125,
-0.0241851806640625,
0.00933837890625,
-0.004055023193359375,
-0.04437255859375,
0.02349853515625,
-0.0220489501953125,
0.0192413330078125,
0.00600433349609375,
-0.0144805908203125,
-0.043487548828125,
0.029052734375,
-0.033355712890625,
0.08172607421875,
0.021026611328125,
-0.05517578125,
0.035247802734375,
-0.0400390625,
-0.0181121826171875,
-0.01291656494140625,
-0.0164947509765625,
-0.08245849609375,
-0.01113128662109375,
0.024383544921875,
0.040130615234375,
-0.0257110595703125,
0.004512786865234375,
-0.05126953125,
-0.01468658447265625,
0.0147247314453125,
-0.00004184246063232422,
0.0946044921875,
0.0205230712890625,
-0.036041259765625,
0.00994110107421875,
-0.0548095703125,
0.0037384033203125,
0.04058837890625,
-0.0166778564453125,
-0.0038623809814453125,
-0.0341796875,
-0.0112762451171875,
0.010894775390625,
0.01140594482421875,
-0.044921875,
0.01212310791015625,
-0.0321044921875,
0.04010009765625,
0.0479736328125,
0.003314971923828125,
0.0224151611328125,
-0.026458740234375,
0.016815185546875,
0.034515380859375,
0.0257415771484375,
-0.0018100738525390625,
-0.048370361328125,
-0.061920166015625,
-0.033782958984375,
0.0172119140625,
0.0281829833984375,
-0.0296783447265625,
0.032806396484375,
-0.02215576171875,
-0.05548095703125,
-0.047088623046875,
0.0048980712890625,
0.033416748046875,
0.040924072265625,
0.0267791748046875,
-0.037506103515625,
-0.045562744140625,
-0.07159423828125,
0.0014657974243164062,
-0.01285552978515625,
0.005275726318359375,
0.0223236083984375,
0.0469970703125,
-0.0013628005981445312,
0.061309814453125,
-0.03607177734375,
-0.0272064208984375,
-0.0159759521484375,
0.007720947265625,
0.0308074951171875,
0.06378173828125,
0.061920166015625,
-0.051361083984375,
-0.0252227783203125,
-0.013946533203125,
-0.07867431640625,
0.0299224853515625,
-0.0020503997802734375,
-0.01502227783203125,
0.0241546630859375,
0.0197296142578125,
-0.045379638671875,
0.04522705078125,
0.0025234222412109375,
-0.01702880859375,
0.025543212890625,
-0.0120086669921875,
0.0187530517578125,
-0.093505859375,
0.01288604736328125,
0.0173187255859375,
0.0023784637451171875,
-0.032073974609375,
0.0130615234375,
-0.01203155517578125,
-0.01233673095703125,
-0.049041748046875,
0.0390625,
-0.043304443359375,
-0.014495849609375,
0.003421783447265625,
-0.012969970703125,
0.00609588623046875,
0.055816650390625,
-0.0107421875,
0.041656494140625,
0.06707763671875,
-0.05010986328125,
0.030487060546875,
0.035797119140625,
-0.0277557373046875,
0.043701171875,
-0.05511474609375,
0.0151519775390625,
-0.010284423828125,
0.0103302001953125,
-0.07452392578125,
-0.0036449432373046875,
0.0303497314453125,
-0.052001953125,
0.039276123046875,
-0.03826904296875,
-0.022918701171875,
-0.039031982421875,
-0.045745849609375,
0.030517578125,
0.046356201171875,
-0.04693603515625,
0.03570556640625,
0.0195159912109375,
0.022430419921875,
-0.05157470703125,
-0.07086181640625,
-0.0035228729248046875,
-0.031951904296875,
-0.056640625,
0.040008544921875,
0.0031871795654296875,
-0.0010776519775390625,
0.01678466796875,
0.0021762847900390625,
0.006877899169921875,
-0.0006213188171386719,
0.037567138671875,
0.0294952392578125,
-0.0311431884765625,
-0.0243988037109375,
-0.03228759765625,
0.005889892578125,
0.00018644332885742188,
-0.032958984375,
0.040802001953125,
-0.019683837890625,
-0.0152130126953125,
-0.054168701171875,
-0.004108428955078125,
0.043426513671875,
-0.005847930908203125,
0.06964111328125,
0.07568359375,
-0.041900634765625,
0.005207061767578125,
-0.032562255859375,
-0.00446319580078125,
-0.03497314453125,
0.034881591796875,
-0.0364990234375,
-0.02972412109375,
0.06646728515625,
0.01788330078125,
0.014373779296875,
0.06768798828125,
0.029052734375,
0.0011301040649414062,
0.05126953125,
0.042999267578125,
0.00836181640625,
0.0477294921875,
-0.08721923828125,
-0.00588226318359375,
-0.07501220703125,
-0.043304443359375,
-0.0261993408203125,
-0.035614013671875,
-0.0386962890625,
-0.0170135498046875,
0.038116455078125,
0.02264404296875,
-0.0311431884765625,
0.032501220703125,
-0.059326171875,
0.00014889240264892578,
0.0531005859375,
0.0374755859375,
-0.0177001953125,
0.0214691162109375,
-0.01898193359375,
0.01091766357421875,
-0.0521240234375,
-0.013336181640625,
0.09210205078125,
0.028533935546875,
0.04248046875,
-0.0020542144775390625,
0.053070068359375,
-0.005146026611328125,
0.01502227783203125,
-0.04071044921875,
0.0465087890625,
-0.0015544891357421875,
-0.041473388671875,
-0.01070404052734375,
-0.0223541259765625,
-0.0826416015625,
0.00481414794921875,
-0.0180511474609375,
-0.05615234375,
0.03228759765625,
0.003917694091796875,
-0.04217529296875,
0.06121826171875,
-0.055511474609375,
0.0640869140625,
-0.004810333251953125,
-0.033203125,
0.0019407272338867188,
-0.042083740234375,
0.024932861328125,
0.01776123046875,
-0.01309967041015625,
0.002185821533203125,
0.013153076171875,
0.08477783203125,
-0.038360595703125,
0.0611572265625,
-0.02813720703125,
0.0152435302734375,
0.0489501953125,
-0.00806427001953125,
0.017822265625,
0.0028743743896484375,
-0.007045745849609375,
0.0347900390625,
-0.0046844482421875,
-0.030487060546875,
-0.031646728515625,
0.04791259765625,
-0.08441162109375,
-0.04791259765625,
-0.0350341796875,
-0.0244903564453125,
0.0193023681640625,
0.0185699462890625,
0.0477294921875,
0.054931640625,
-0.0013437271118164062,
0.0318603515625,
0.042999267578125,
-0.0301971435546875,
0.04071044921875,
-0.0014276504516601562,
-0.0031280517578125,
-0.0478515625,
0.051971435546875,
0.0195465087890625,
0.01242828369140625,
0.0125579833984375,
0.0020923614501953125,
-0.0247650146484375,
-0.064208984375,
-0.034881591796875,
0.0179443359375,
-0.050140380859375,
-0.0362548828125,
-0.0482177734375,
-0.0465087890625,
-0.0465087890625,
-0.00968170166015625,
-0.0357666015625,
-0.0253143310546875,
-0.03582763671875,
0.01445770263671875,
0.045562744140625,
0.04547119140625,
-0.013153076171875,
0.034027099609375,
-0.0292205810546875,
0.01029205322265625,
0.006565093994140625,
0.03692626953125,
0.004608154296875,
-0.06353759765625,
-0.0229339599609375,
-0.0037631988525390625,
-0.045745849609375,
-0.048614501953125,
0.0237274169921875,
0.0187530517578125,
0.041107177734375,
0.039794921875,
-0.0160064697265625,
0.06671142578125,
-0.00852203369140625,
0.056854248046875,
0.0170135498046875,
-0.039093017578125,
0.04595947265625,
0.00211334228515625,
0.00731658935546875,
0.00827789306640625,
0.0207366943359375,
-0.00902557373046875,
-0.0134124755859375,
-0.08294677734375,
-0.06591796875,
0.074462890625,
0.01186370849609375,
-0.00946807861328125,
0.02447509765625,
0.05303955078125,
-0.0019989013671875,
-0.0019054412841796875,
-0.056915283203125,
-0.03826904296875,
-0.02691650390625,
-0.0229034423828125,
-0.002803802490234375,
-0.0117340087890625,
-0.0174407958984375,
-0.0362548828125,
0.0545654296875,
0.0168609619140625,
0.0625,
0.04022216796875,
-0.01003265380859375,
-0.003658294677734375,
-0.0233001708984375,
0.03387451171875,
0.030487060546875,
-0.031402587890625,
0.004108428955078125,
0.0153350830078125,
-0.049041748046875,
0.008392333984375,
0.0212860107421875,
-0.0131988525390625,
-0.01509857177734375,
0.042083740234375,
0.07110595703125,
-0.0030956268310546875,
0.00693511962890625,
0.02899169921875,
0.0106964111328125,
-0.02874755859375,
-0.032684326171875,
0.0159149169921875,
-0.0149993896484375,
0.0357666015625,
0.03753662109375,
0.02880859375,
-0.0030117034912109375,
-0.0234222412109375,
0.0184326171875,
0.048828125,
-0.017120361328125,
-0.0291290283203125,
0.06298828125,
-0.01540374755859375,
-0.017730712890625,
0.053680419921875,
-0.00732421875,
-0.031494140625,
0.0731201171875,
0.035400390625,
0.072998046875,
-0.00017726421356201172,
-0.004425048828125,
0.06365966796875,
0.0284271240234375,
0.0022029876708984375,
-0.00348663330078125,
0.01151275634765625,
-0.0550537109375,
0.0115814208984375,
-0.048492431640625,
0.00396728515625,
0.03948974609375,
-0.0345458984375,
0.0267486572265625,
-0.061492919921875,
-0.025787353515625,
0.016754150390625,
0.024322509765625,
-0.06658935546875,
0.0157623291015625,
0.007205963134765625,
0.05816650390625,
-0.046478271484375,
0.0433349609375,
0.06353759765625,
-0.05670166015625,
-0.055877685546875,
-0.0121917724609375,
0.001865386962890625,
-0.07550048828125,
0.0341796875,
0.0225372314453125,
-0.0024871826171875,
0.017547607421875,
-0.0596923828125,
-0.06488037109375,
0.10760498046875,
0.03826904296875,
0.0094451904296875,
0.007266998291015625,
0.0022449493408203125,
0.0162506103515625,
-0.033447265625,
0.0231170654296875,
0.019439697265625,
0.0184326171875,
0.0245208740234375,
-0.032440185546875,
0.01203155517578125,
-0.0206756591796875,
0.01422882080078125,
0.006084442138671875,
-0.059173583984375,
0.06756591796875,
-0.043487548828125,
-0.022552490234375,
0.002132415771484375,
0.06298828125,
0.019012451171875,
0.00948333740234375,
0.043304443359375,
0.07421875,
0.0259857177734375,
-0.020294189453125,
0.0657958984375,
-0.0098419189453125,
0.03564453125,
0.03741455078125,
0.0294647216796875,
0.038177490234375,
0.02740478515625,
-0.034698486328125,
0.037322998046875,
0.08251953125,
-0.030487060546875,
0.0264434814453125,
0.00269317626953125,
0.006916046142578125,
0.003459930419921875,
0.01177978515625,
-0.03753662109375,
0.03546142578125,
0.01480865478515625,
-0.03289794921875,
-0.01322174072265625,
0.0018110275268554688,
0.00722503662109375,
-0.0269927978515625,
-0.015838623046875,
0.0439453125,
0.002483367919921875,
-0.03326416015625,
0.06744384765625,
0.006679534912109375,
0.0562744140625,
-0.02972412109375,
0.007965087890625,
-0.0203857421875,
0.0233306884765625,
-0.0241241455078125,
-0.0634765625,
0.019775390625,
-0.014495849609375,
-0.0014820098876953125,
0.01226043701171875,
0.033538818359375,
-0.022613525390625,
-0.043243408203125,
0.01079559326171875,
0.01348114013671875,
0.03485107421875,
0.01216888427734375,
-0.08526611328125,
0.006591796875,
0.0025310516357421875,
-0.04522705078125,
0.009368896484375,
0.02728271484375,
0.00841522216796875,
0.048553466796875,
0.046234130859375,
-0.0005679130554199219,
0.01224517822265625,
-0.0215911865234375,
0.056915283203125,
-0.04180908203125,
-0.032623291015625,
-0.07611083984375,
0.04339599609375,
-0.009368896484375,
-0.044677734375,
0.040679931640625,
0.0576171875,
0.0709228515625,
0.005435943603515625,
0.040191650390625,
-0.030517578125,
-0.0002892017364501953,
-0.0301361083984375,
0.051666259765625,
-0.0574951171875,
0.004302978515625,
-0.0145416259765625,
-0.055877685546875,
-0.0294952392578125,
0.038421630859375,
-0.015594482421875,
0.02899169921875,
0.034881591796875,
0.0684814453125,
-0.0239105224609375,
-0.029571533203125,
0.0028362274169921875,
0.023468017578125,
0.02197265625,
0.03472900390625,
0.0242462158203125,
-0.06219482421875,
0.043853759765625,
-0.04058837890625,
-0.0128173828125,
-0.015869140625,
-0.047119140625,
-0.06195068359375,
-0.06976318359375,
-0.042572021484375,
-0.05474853515625,
-0.01187896728515625,
0.06353759765625,
0.06951904296875,
-0.05596923828125,
-0.0084075927734375,
-0.0007596015930175781,
0.017181396484375,
-0.02984619140625,
-0.0159454345703125,
0.05712890625,
-0.0140228271484375,
-0.058685302734375,
-0.0113067626953125,
0.0029087066650390625,
0.040771484375,
-0.01448822021484375,
-0.0106353759765625,
-0.022430419921875,
-0.0194854736328125,
0.0156402587890625,
0.026641845703125,
-0.0517578125,
-0.0161285400390625,
-0.022308349609375,
-0.004894256591796875,
0.0369873046875,
0.02874755859375,
-0.046539306640625,
0.024566650390625,
0.0243988037109375,
0.0305023193359375,
0.057403564453125,
-0.016693115234375,
0.01467132568359375,
-0.056732177734375,
0.045928955078125,
-0.0111541748046875,
0.0297698974609375,
0.03924560546875,
-0.03521728515625,
0.041595458984375,
0.03948974609375,
-0.0164794921875,
-0.07672119140625,
-0.005794525146484375,
-0.07110595703125,
-0.010223388671875,
0.057769775390625,
-0.025115966796875,
-0.04339599609375,
0.02740478515625,
0.0097198486328125,
0.057769775390625,
-0.005741119384765625,
0.048614501953125,
0.030670166015625,
-0.006103515625,
-0.0362548828125,
-0.0313720703125,
0.044525146484375,
0.004444122314453125,
-0.040374755859375,
-0.0362548828125,
-0.007534027099609375,
0.0408935546875,
0.0305938720703125,
0.034027099609375,
-0.02880859375,
0.005985260009765625,
0.0106201171875,
0.03717041015625,
-0.0362548828125,
-0.0158843994140625,
-0.02587890625,
0.01155853271484375,
-0.0014085769653320312,
-0.050140380859375
]
] |
tiiuae/falcon-rw-1b | 2023-07-12T21:34:11.000Z | [
"transformers",
"pytorch",
"falcon",
"text-generation",
"custom_code",
"en",
"dataset:tiiuae/falcon-refinedweb",
"arxiv:2306.01116",
"arxiv:2005.14165",
"arxiv:2108.12409",
"arxiv:2205.14135",
"license:apache-2.0",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | tiiuae | null | null | tiiuae/falcon-rw-1b | 64 | 38,669 | transformers | 2023-04-26T09:25:36 | ---
datasets:
- tiiuae/falcon-refinedweb
language:
- en
inference: false
license: apache-2.0
---
# Falcon-RW-1B
**Falcon-RW-1B is a 1B parameters causal decoder-only model built by [TII](https://www.tii.ae) and trained on 350B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb). It is made available under the Apache 2.0 license.**
See the 📓 [paper on arXiv](https://arxiv.org/abs/2306.01116) for more details.
RefinedWeb is a high-quality web dataset built by leveraging stringent filtering and large-scale deduplication. Falcon-RW-1B, trained on RefinedWeb only, matches or outperforms comparable models trained on curated data.
⚠️ Falcon is now available as a core model in the `transformers` library! To use the in-library version, please install the latest version of `transformers` with `pip install git+https://github.com/huggingface/transformers.git`, then simply remove the `trust_remote_code=True` argument from `from_pretrained()`.
⚠️ This model is intended for use as a **research artifact**, to study the influence of training on web data alone. **If you are interested in state-of-the-art models, we recommend using Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b), both trained on >1,000 billion tokens.**
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "tiiuae/falcon-rw-1b"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
)
sequences = pipeline(
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
💥 **Falcon LLMs require PyTorch 2.0 for use with `transformers`!**
# Model Card for Falcon-RW-1B
## Model Details
### Model Description
- **Developed by:** [https://www.tii.ae](https://www.tii.ae);
- **Model type:** Causal decoder-only;
- **Language(s) (NLP):** English;
- **License:** Apache 2.0.
### Model Source
- **Paper:** [https://arxiv.org/abs/2306.01116](https://arxiv.org/abs/2306.01116).
## Uses
### Direct Use
Research on large language models, specifically the influence of adequately filtered and deduplicated web data on the properties of large language models (fairness, safety, limitations, capabilities, etc.).
### Out-of-Scope Use
Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.
Broadly speaking, we would recommend Falcon-[7B](https://huggingface.co/tiiuae/falcon-7b)/[40B](https://huggingface.co/tiiuae/falcon-40b) for any use not directly related to research on web data pipelines.
## Bias, Risks, and Limitations
Falcon-RW-1B is trained on English data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.
### Recommendations
We recommend users of Falcon-RW-1B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.
## How to Get Started with the Model
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model = "tiiuae/falcon-rw-1b"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
device_map="auto",
)
sequences = pipeline(
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
max_length=200,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## Training Details
### Training Data
Falcon-RW-1B was trained on 350B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), a high-quality filtered and deduplicated web dataset. The data was tokenized with the GPT-2 tokenizer.
### Training Procedure
Falcon-RW-1B was trained on 32 A100 40GB GPUs, using only data parallelism with ZeRO.
#### Training Hyperparameters
Hyperparameters were adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)).
| **Hyperparameter** | **Value** | **Comment** |
|--------------------|------------|-------------------------------------------|
| Precision | `bfloat16` | |
| Optimizer | AdamW | |
| Learning rate | 2e-4 | 500M tokens warm-up, cosine decay to 2e-5 |
| Weight decay | 1e-1 | |
| Batch size | 512 | 4B tokens ramp-up |
#### Speeds, Sizes, Times
Training happened in early December 2022 and took about six days.
## Evaluation
See the 📓 [paper on arXiv](https://arxiv.org/abs/2306.01116) for in-depth evaluation.
## Technical Specifications
### Model Architecture and Objective
Falcon-RW-1B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
The architecture is adapted from the GPT-3 paper ([Brown et al., 2020](https://arxiv.org/abs/2005.14165)), but uses ALiBi ([Ofir et al., 2021](https://arxiv.org/abs/2108.12409)) and FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)).
| **Hyperparameter** | **Value** | **Comment** |
|--------------------|-----------|----------------------------------------|
| Layers | 24 | |
| `d_model` | 2048 | |
| `head_dim` | 64 | Reduced to optimise for FlashAttention |
| Vocabulary | 50304 | |
| Sequence length | 2048 | |
### Compute Infrastructure
#### Hardware
Falcon-RW-1B was trained on AWS SageMaker, on 32 A100 40GB GPUs in P4d instances.
#### Software
Falcon-RW-1B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)
## Citation
```
@article{refinedweb,
title={The {R}efined{W}eb dataset for {F}alcon {LLM}: outperforming curated corpora with web data, and web data only},
author={Guilherme Penedo and Quentin Malartic and Daniel Hesslow and Ruxandra Cojocaru and Alessandro Cappelli and Hamza Alobeidli and Baptiste Pannier and Ebtesam Almazrouei and Julien Launay},
journal={arXiv preprint arXiv:2306.01116},
eprint={2306.01116},
eprinttype = {arXiv},
url={https://arxiv.org/abs/2306.01116},
year={2023}
}
```
## Contact
falconllm@tii.ae
| 7,579 | [
[
-0.042724609375,
-0.07073974609375,
-0.000850677490234375,
0.018951416015625,
-0.0113983154296875,
-0.00748443603515625,
-0.00446319580078125,
-0.042816162109375,
0.01384735107421875,
0.015045166015625,
-0.0487060546875,
-0.0295562744140625,
-0.057098388671875,
0.0114898681640625,
-0.032379150390625,
0.082275390625,
0.0004794597625732422,
-0.00823211669921875,
0.0067138671875,
-0.0011749267578125,
-0.0025882720947265625,
-0.033203125,
-0.0709228515625,
-0.0093231201171875,
0.041290283203125,
0.0236968994140625,
0.046539306640625,
0.08001708984375,
0.053955078125,
0.021331787109375,
-0.00525665283203125,
0.01293182373046875,
-0.03790283203125,
-0.01776123046875,
-0.006389617919921875,
-0.0142364501953125,
-0.0179901123046875,
0.004840850830078125,
0.04150390625,
0.044586181640625,
-0.00460052490234375,
0.029266357421875,
-0.0013551712036132812,
0.0399169921875,
-0.03826904296875,
0.0341796875,
-0.0408935546875,
0.013458251953125,
-0.017059326171875,
-0.003368377685546875,
-0.028778076171875,
0.0015974044799804688,
-0.0128936767578125,
-0.07244873046875,
0.0305633544921875,
0.019775390625,
0.10186767578125,
0.0254974365234375,
-0.032379150390625,
-0.00658416748046875,
-0.037017822265625,
0.054962158203125,
-0.053375244140625,
0.037872314453125,
0.02294921875,
0.0168304443359375,
-0.016632080078125,
-0.07794189453125,
-0.0401611328125,
-0.007785797119140625,
-0.0024261474609375,
0.0266571044921875,
-0.024169921875,
0.0009160041809082031,
0.043212890625,
0.001873016357421875,
-0.046905517578125,
0.01361083984375,
-0.031890869140625,
-0.0196685791015625,
0.042327880859375,
0.009368896484375,
0.00872039794921875,
-0.017333984375,
-0.0341796875,
-0.0278778076171875,
-0.025421142578125,
0.0214691162109375,
0.034088134765625,
0.025360107421875,
-0.01873779296875,
0.031585693359375,
-0.0208282470703125,
0.045867919921875,
0.02557373046875,
-0.0037403106689453125,
0.0284881591796875,
-0.0197296142578125,
-0.024261474609375,
-0.01366424560546875,
0.07958984375,
0.013336181640625,
0.01503753662109375,
-0.01264190673828125,
-0.007541656494140625,
-0.007411956787109375,
0.01032257080078125,
-0.07830810546875,
0.0091552734375,
0.0180511474609375,
-0.0364990234375,
-0.01959228515625,
0.03271484375,
-0.056182861328125,
0.0029926300048828125,
-0.0067901611328125,
0.01061248779296875,
-0.024078369140625,
-0.033660888671875,
0.0163421630859375,
-0.02056884765625,
0.019866943359375,
-0.0118408203125,
-0.0706787109375,
0.02197265625,
0.05487060546875,
0.06378173828125,
0.00299072265625,
-0.05767822265625,
-0.05316162109375,
0.00829315185546875,
-0.0214996337890625,
0.0391845703125,
-0.0212860107421875,
-0.0270538330078125,
-0.005645751953125,
0.024139404296875,
-0.01715087890625,
-0.0077972412109375,
0.055694580078125,
-0.035797119140625,
0.00724029541015625,
-0.0321044921875,
-0.03973388671875,
-0.0272369384765625,
0.00408935546875,
-0.044769287109375,
0.06939697265625,
0.002956390380859375,
-0.08831787109375,
0.0262298583984375,
-0.052520751953125,
-0.034698486328125,
-0.011962890625,
-0.00305938720703125,
-0.03973388671875,
-0.01308441162109375,
0.03082275390625,
0.04833984375,
-0.031585693359375,
0.032073974609375,
-0.042266845703125,
-0.044708251953125,
-0.00567626953125,
-0.0227508544921875,
0.061737060546875,
0.041748046875,
-0.04571533203125,
-0.0007138252258300781,
-0.0501708984375,
-0.007965087890625,
0.03094482421875,
-0.004749298095703125,
0.01088714599609375,
-0.00824737548828125,
0.02008056640625,
0.0229949951171875,
0.01067352294921875,
-0.04217529296875,
0.0086212158203125,
-0.03680419921875,
0.042327880859375,
0.036102294921875,
0.0002124309539794922,
0.00963592529296875,
-0.029815673828125,
0.03631591796875,
0.0275726318359375,
0.0267486572265625,
-0.0067901611328125,
-0.0389404296875,
-0.07171630859375,
-0.014678955078125,
0.0113525390625,
0.03521728515625,
-0.043304443359375,
0.03271484375,
-0.021697998046875,
-0.0506591796875,
-0.0219573974609375,
-0.01383209228515625,
0.03582763671875,
0.0562744140625,
0.040313720703125,
0.01056671142578125,
-0.0565185546875,
-0.07080078125,
-0.0077667236328125,
-0.02435302734375,
0.0215301513671875,
0.01361083984375,
0.055633544921875,
-0.03338623046875,
0.06329345703125,
-0.0341796875,
-0.0115814208984375,
-0.00615692138671875,
0.02703857421875,
0.0207977294921875,
0.03985595703125,
0.0430908203125,
-0.040252685546875,
-0.020050048828125,
0.0010595321655273438,
-0.0709228515625,
0.0047454833984375,
-0.00949859619140625,
-0.003955841064453125,
0.03643798828125,
0.042694091796875,
-0.049041748046875,
0.01528167724609375,
0.0280914306640625,
-0.0219573974609375,
0.03228759765625,
-0.00748443603515625,
0.007511138916015625,
-0.08203125,
0.03021240234375,
0.01885986328125,
0.00885772705078125,
-0.030548095703125,
0.016326904296875,
0.0017862319946289062,
-0.00794219970703125,
-0.042755126953125,
0.0557861328125,
-0.0321044921875,
-0.004238128662109375,
-0.0093841552734375,
-0.01479339599609375,
-0.00533294677734375,
0.059173583984375,
0.01009368896484375,
0.0709228515625,
0.045745849609375,
-0.038116455078125,
-0.002239227294921875,
0.026458740234375,
-0.003055572509765625,
0.007579803466796875,
-0.061859130859375,
0.00632476806640625,
-0.0094451904296875,
0.027679443359375,
-0.056915283203125,
-0.0157470703125,
0.02606201171875,
-0.04388427734375,
0.0225982666015625,
-0.012908935546875,
-0.032623291015625,
-0.0494384765625,
-0.01218414306640625,
0.01503753662109375,
0.030487060546875,
-0.043670654296875,
0.024139404296875,
0.01934814453125,
0.00775909423828125,
-0.0738525390625,
-0.0667724609375,
-0.0006122589111328125,
-0.0143280029296875,
-0.053985595703125,
0.0258941650390625,
0.002773284912109375,
0.0057830810546875,
0.0020294189453125,
0.004322052001953125,
0.0023708343505859375,
0.01102447509765625,
0.03057861328125,
0.01200103759765625,
-0.0147552490234375,
-0.00786590576171875,
0.004505157470703125,
-0.020599365234375,
0.010101318359375,
-0.03607177734375,
0.0313720703125,
-0.038787841796875,
-0.0214080810546875,
-0.041534423828125,
0.0224761962890625,
0.044525146484375,
-0.015228271484375,
0.055755615234375,
0.08123779296875,
-0.0296630859375,
0.00885009765625,
-0.03826904296875,
-0.00685882568359375,
-0.036468505859375,
0.04315185546875,
-0.034027099609375,
-0.05609130859375,
0.04730224609375,
0.01317596435546875,
0.004665374755859375,
0.0704345703125,
0.01629638671875,
0.004711151123046875,
0.08709716796875,
0.0284423828125,
-0.0154266357421875,
0.0300750732421875,
-0.05706787109375,
-0.00844573974609375,
-0.05975341796875,
-0.019744873046875,
-0.049163818359375,
-0.0107269287109375,
-0.055633544921875,
-0.008453369140625,
0.00841522216796875,
0.018402099609375,
-0.06695556640625,
0.0272674560546875,
-0.039154052734375,
0.01471710205078125,
0.039215087890625,
0.0028591156005859375,
-0.006694793701171875,
0.004825592041015625,
-0.024322509765625,
0.01255035400390625,
-0.0633544921875,
-0.0257568359375,
0.08660888671875,
0.0355224609375,
0.042694091796875,
-0.014129638671875,
0.0552978515625,
0.005069732666015625,
0.00417327880859375,
-0.043487548828125,
0.03271484375,
-0.0117340087890625,
-0.0389404296875,
-0.01264190673828125,
-0.041351318359375,
-0.0728759765625,
0.00717926025390625,
-0.01152801513671875,
-0.0455322265625,
0.005565643310546875,
-0.00623321533203125,
-0.0104522705078125,
0.02874755859375,
-0.0611572265625,
0.066650390625,
-0.01617431640625,
-0.036865234375,
0.0007772445678710938,
-0.0513916015625,
0.0271453857421875,
-0.0032863616943359375,
0.0159454345703125,
0.01629638671875,
-0.002933502197265625,
0.08026123046875,
-0.0443115234375,
0.04949951171875,
-0.032562255859375,
0.021087646484375,
0.02227783203125,
-0.019073486328125,
0.0709228515625,
0.00809478759765625,
-0.018829345703125,
0.04327392578125,
0.0078887939453125,
-0.034820556640625,
-0.028778076171875,
0.056427001953125,
-0.091552734375,
-0.046844482421875,
-0.051361083984375,
-0.036468505859375,
-0.01561737060546875,
0.0205535888671875,
0.035858154296875,
0.0275421142578125,
0.0014400482177734375,
0.014923095703125,
0.0218963623046875,
-0.01800537109375,
0.0545654296875,
0.035858154296875,
-0.0133819580078125,
-0.0408935546875,
0.06402587890625,
0.01099395751953125,
-0.001560211181640625,
0.022552490234375,
0.016265869140625,
-0.043365478515625,
-0.03948974609375,
-0.03973388671875,
0.02984619140625,
-0.051513671875,
-0.0213775634765625,
-0.077392578125,
-0.037750244140625,
-0.032623291015625,
-0.01122283935546875,
-0.025482177734375,
-0.03033447265625,
-0.04925537109375,
-0.0103302001953125,
0.040740966796875,
0.041778564453125,
-0.005352020263671875,
0.0225830078125,
-0.051544189453125,
0.0124664306640625,
0.0056304931640625,
0.020751953125,
0.01534271240234375,
-0.052764892578125,
-0.02398681640625,
0.0274810791015625,
-0.02264404296875,
-0.032501220703125,
0.029144287109375,
0.01351165771484375,
0.046966552734375,
0.03363037109375,
-0.0083770751953125,
0.07281494140625,
-0.01898193359375,
0.06011962890625,
0.0203094482421875,
-0.06097412109375,
0.029327392578125,
-0.041748046875,
0.0203704833984375,
0.03607177734375,
0.03900146484375,
-0.0352783203125,
-0.030181884765625,
-0.0634765625,
-0.045196533203125,
0.07733154296875,
0.012176513671875,
-0.0094757080078125,
-0.01428985595703125,
0.03179931640625,
-0.002048492431640625,
-0.00688934326171875,
-0.04339599609375,
-0.030181884765625,
-0.047943115234375,
-0.01183319091796875,
-0.00930023193359375,
0.000194549560546875,
0.01314544677734375,
-0.036285400390625,
0.06866455078125,
-0.01177978515625,
0.043121337890625,
0.01267242431640625,
-0.01070404052734375,
-0.00994873046875,
-0.00818634033203125,
0.05078125,
0.0399169921875,
-0.0217742919921875,
-0.005069732666015625,
0.0097808837890625,
-0.052581787109375,
0.0042877197265625,
0.0322265625,
-0.0165252685546875,
-0.01502227783203125,
0.03253173828125,
0.07562255859375,
0.008331298828125,
-0.01824951171875,
0.03619384765625,
-0.00815582275390625,
-0.028533935546875,
-0.010650634765625,
0.007396697998046875,
0.006557464599609375,
0.013397216796875,
0.0308380126953125,
0.004638671875,
0.00597381591796875,
-0.016510009765625,
0.0241851806640625,
0.0248870849609375,
-0.0174713134765625,
-0.0138092041015625,
0.075927734375,
0.01206207275390625,
-0.01317596435546875,
0.046966552734375,
-0.0258941650390625,
-0.030853271484375,
0.07208251953125,
0.058929443359375,
0.07275390625,
0.0178375244140625,
0.0196380615234375,
0.06451416015625,
0.0211639404296875,
-0.015838623046875,
0.01197052001953125,
0.01366424560546875,
-0.035369873046875,
-0.0141448974609375,
-0.058929443359375,
-0.021453857421875,
0.01502227783203125,
-0.049652099609375,
0.033599853515625,
-0.042266845703125,
-0.0128173828125,
0.0068359375,
0.03271484375,
-0.06396484375,
0.0225677490234375,
-0.0079498291015625,
0.07305908203125,
-0.04986572265625,
0.0653076171875,
0.04736328125,
-0.0687255859375,
-0.0780029296875,
0.0002167224884033203,
-0.01091766357421875,
-0.0673828125,
0.06298828125,
0.0263519287109375,
-0.004344940185546875,
0.031219482421875,
-0.026885986328125,
-0.07330322265625,
0.0894775390625,
0.0234832763671875,
-0.049072265625,
0.0006923675537109375,
0.0256805419921875,
0.03680419921875,
-0.0147857666015625,
0.052520751953125,
0.022674560546875,
0.04345703125,
0.017242431640625,
-0.048309326171875,
0.0162353515625,
-0.0335693359375,
0.00583648681640625,
0.0075225830078125,
-0.07470703125,
0.066650390625,
-0.0200042724609375,
-0.0167083740234375,
-0.012481689453125,
0.06195068359375,
0.0216064453125,
0.01226043701171875,
0.0279388427734375,
0.04766845703125,
0.057098388671875,
-0.00597381591796875,
0.07672119140625,
-0.045318603515625,
0.04974365234375,
0.05865478515625,
-0.0008821487426757812,
0.052581787109375,
0.0263519287109375,
-0.0115966796875,
0.02777099609375,
0.05987548828125,
-0.017242431640625,
0.027679443359375,
-0.0033893585205078125,
0.0183868408203125,
-0.009490966796875,
0.00041985511779785156,
-0.0501708984375,
0.0341796875,
0.0062103271484375,
-0.01488494873046875,
-0.01128387451171875,
0.0056915283203125,
0.023193359375,
-0.024627685546875,
-0.0074310302734375,
0.036224365234375,
-0.0033435821533203125,
-0.06353759765625,
0.07659912109375,
0.0202484130859375,
0.0628662109375,
-0.053253173828125,
0.01129150390625,
-0.03350830078125,
0.0086669921875,
-0.0218353271484375,
-0.044647216796875,
0.027587890625,
0.0091552734375,
-0.014739990234375,
-0.006664276123046875,
0.03424072265625,
-0.0092010498046875,
-0.061431884765625,
0.02490234375,
0.018341064453125,
0.008697509765625,
0.00003784894943237305,
-0.06805419921875,
0.01678466796875,
-0.01666259765625,
-0.027984619140625,
0.0164337158203125,
0.012237548828125,
0.0016355514526367188,
0.055633544921875,
0.05633544921875,
-0.0083465576171875,
0.0032367706298828125,
0.0036334991455078125,
0.05145263671875,
-0.061492919921875,
-0.03271484375,
-0.047088623046875,
0.024749755859375,
0.00389862060546875,
-0.03973388671875,
0.0535888671875,
0.060150146484375,
0.06561279296875,
-0.0025386810302734375,
0.05853271484375,
-0.01012420654296875,
0.014862060546875,
-0.033203125,
0.06085205078125,
-0.051483154296875,
0.004425048828125,
-0.026885986328125,
-0.046966552734375,
-0.0107269287109375,
0.041107177734375,
-0.002101898193359375,
0.016571044921875,
0.066650390625,
0.07159423828125,
-0.0118408203125,
0.02374267578125,
0.00592041015625,
0.0207977294921875,
0.030242919921875,
0.052276611328125,
0.04339599609375,
-0.06854248046875,
0.04974365234375,
-0.024444580078125,
-0.011566162109375,
-0.01337432861328125,
-0.062042236328125,
-0.0684814453125,
-0.051849365234375,
-0.02703857421875,
-0.02056884765625,
0.00910186767578125,
0.068359375,
0.0552978515625,
-0.056549072265625,
-0.020355224609375,
-0.03680419921875,
-0.0086517333984375,
-0.037750244140625,
-0.0159759521484375,
0.042816162109375,
-0.037750244140625,
-0.050567626953125,
0.00897216796875,
-0.004390716552734375,
0.0036220550537109375,
-0.0149383544921875,
-0.0232696533203125,
-0.035888671875,
0.0004165172576904297,
0.0311737060546875,
0.0285186767578125,
-0.056732177734375,
-0.029022216796875,
0.01824951171875,
-0.0185699462890625,
-0.0027294158935546875,
0.0267486572265625,
-0.04644775390625,
0.0145721435546875,
0.0242767333984375,
0.055267333984375,
0.0692138671875,
-0.006717681884765625,
0.0101165771484375,
-0.031646728515625,
0.0267181396484375,
-0.0106353759765625,
0.033599853515625,
0.00623321533203125,
-0.033843994140625,
0.045684814453125,
0.03875732421875,
-0.036376953125,
-0.050384521484375,
-0.01094818115234375,
-0.08599853515625,
-0.018402099609375,
0.10467529296875,
-0.013580322265625,
-0.0191650390625,
0.009796142578125,
-0.007244110107421875,
0.049041748046875,
-0.0286407470703125,
0.04376220703125,
0.044677734375,
0.00337982177734375,
0.0019016265869140625,
-0.0299224853515625,
0.02679443359375,
0.01499176025390625,
-0.0682373046875,
-0.006290435791015625,
0.0204620361328125,
0.0289459228515625,
-0.007205963134765625,
0.02734375,
0.004558563232421875,
0.01483917236328125,
0.0207672119140625,
-0.00203704833984375,
-0.0567626953125,
-0.0233612060546875,
-0.0158538818359375,
0.010040283203125,
-0.020233154296875,
-0.0224456787109375
]
] |
codellama/CodeLlama-34b-hf | 2023-10-27T18:08:08.000Z | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"llama-2",
"code",
"arxiv:2308.12950",
"license:llama2",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | codellama | null | null | codellama/CodeLlama-34b-hf | 127 | 38,655 | transformers | 2023-08-24T16:34:39 | ---
language:
- code
pipeline_tag: text-generation
tags:
- llama-2
license: llama2
---
# **Code Llama**
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the base 34B version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
| | Base Model | Python | Instruct |
| --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
| 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) |
| 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) |
## Model Use
To use this model, please make sure to install transformers from `main` until the next version is released:
```bash
pip install git+https://github.com/huggingface/transformers.git@main accelerate
```
Model capabilities:
- [x] Code completion.
- [ ] Infilling.
- [ ] Instructions / chat.
- [ ] Python specialist.
```python
from transformers import AutoTokenizer
import transformers
import torch
model = "codellama/CodeLlama-34b-hf"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
'import socket\n\ndef ping_exponential_backoff(host: str):',
do_sample=True,
top_k=10,
temperature=0.1,
top_p=0.95,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
```
## Model Details
*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).
**Model Developers** Meta
**Variations** Code Llama comes in three model sizes, and three variants:
* Code Llama: base models designed for general code synthesis and understanding
* Code Llama - Python: designed specifically for Python
* Code Llama - Instruct: for instruction following and safer deployment
All variants are available in sizes of 7B, 13B and 34B parameters.
**This repository contains the base version of the 34B parameters model.**
**Input** Models input text only.
**Output** Models generate text only.
**Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture.
**Model Dates** Code Llama and its variants have been trained between January 2023 and July 2023.
**Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
**Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950).
## Intended Use
**Intended Use Cases** Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
**Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
## Hardware and Software
**Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
**Carbon Footprint** In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
## Training Data
All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the [research paper](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/) for details).
## Evaluation Results
See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.
## Ethical Considerations and Limitations
Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.
Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide). | 6,772 | [
[
-0.0265045166015625,
-0.049041748046875,
0.0185394287109375,
0.040283203125,
-0.017791748046875,
0.01026153564453125,
-0.00571441650390625,
-0.04498291015625,
0.0193328857421875,
0.034881591796875,
-0.029327392578125,
-0.0418701171875,
-0.044769287109375,
0.02117919921875,
-0.03631591796875,
0.08734130859375,
-0.003513336181640625,
-0.0281524658203125,
-0.0164337158203125,
0.0025959014892578125,
-0.0168914794921875,
-0.04241943359375,
-0.0173797607421875,
-0.032562255859375,
0.0192718505859375,
0.0250091552734375,
0.050445556640625,
0.045074462890625,
0.0390625,
0.0266265869140625,
-0.0193634033203125,
0.0019474029541015625,
-0.026885986328125,
-0.025054931640625,
0.0194549560546875,
-0.042694091796875,
-0.055419921875,
-0.0020618438720703125,
0.026824951171875,
0.022186279296875,
-0.0208282470703125,
0.033782958984375,
-0.01320648193359375,
0.035003662109375,
-0.0243377685546875,
0.0177001953125,
-0.049896240234375,
-0.00396728515625,
0.0030574798583984375,
-0.00846099853515625,
-0.01519012451171875,
-0.036712646484375,
-0.006473541259765625,
-0.03369140625,
-0.0023860931396484375,
-0.0019350051879882812,
0.08721923828125,
0.037628173828125,
-0.02166748046875,
-0.01690673828125,
-0.0239410400390625,
0.059539794921875,
-0.0726318359375,
0.002716064453125,
0.0243682861328125,
-0.00543212890625,
-0.010498046875,
-0.0657958984375,
-0.0555419921875,
-0.024261474609375,
-0.0106048583984375,
-0.0004425048828125,
-0.03533935546875,
0.0052337646484375,
0.0308074951171875,
0.0352783203125,
-0.036224365234375,
0.00879669189453125,
-0.03546142578125,
-0.0161895751953125,
0.0673828125,
0.01031494140625,
0.0306243896484375,
-0.0238494873046875,
-0.0273590087890625,
-0.005153656005859375,
-0.05908203125,
0.004993438720703125,
0.03399658203125,
-0.00994873046875,
-0.057830810546875,
0.05224609375,
-0.015625,
0.04339599609375,
0.00763702392578125,
-0.036651611328125,
0.0411376953125,
-0.021514892578125,
-0.0253753662109375,
-0.0130462646484375,
0.07196044921875,
0.038818359375,
0.0263214111328125,
0.00400543212890625,
-0.01473236083984375,
0.0184783935546875,
0.005832672119140625,
-0.064697265625,
-0.0125885009765625,
0.026123046875,
-0.0460205078125,
-0.050537109375,
-0.01763916015625,
-0.060546875,
-0.0037994384765625,
0.0007882118225097656,
0.0116729736328125,
-0.01483917236328125,
-0.033721923828125,
0.0159149169921875,
0.0037670135498046875,
0.03570556640625,
0.0046234130859375,
-0.0662841796875,
0.0038585662841796875,
0.03363037109375,
0.05963134765625,
0.003688812255859375,
-0.03887939453125,
0.0004639625549316406,
-0.0098419189453125,
-0.0203399658203125,
0.048004150390625,
-0.031890869140625,
-0.035980224609375,
-0.01285552978515625,
0.009033203125,
-0.00511932373046875,
-0.0352783203125,
0.014251708984375,
-0.0272369384765625,
0.0001690387725830078,
0.009918212890625,
-0.0230255126953125,
-0.0306549072265625,
0.0010156631469726562,
-0.040313720703125,
0.08746337890625,
0.020782470703125,
-0.0565185546875,
-0.0024814605712890625,
-0.0423583984375,
-0.0258941650390625,
-0.01953125,
-0.0019254684448242188,
-0.05218505859375,
-0.005680084228515625,
0.0165252685546875,
0.03900146484375,
-0.02886962890625,
0.0289154052734375,
-0.01128387451171875,
-0.0300140380859375,
0.016021728515625,
-0.01418304443359375,
0.0799560546875,
0.026336669921875,
-0.03790283203125,
0.0164031982421875,
-0.06317138671875,
-0.006923675537109375,
0.03900146484375,
-0.033599853515625,
0.0138702392578125,
-0.0097503662109375,
0.0006022453308105469,
0.0004029273986816406,
0.03759765625,
-0.0251617431640625,
0.03692626953125,
-0.032257080078125,
0.058990478515625,
0.05023193359375,
-0.0009517669677734375,
0.0279083251953125,
-0.042938232421875,
0.053070068359375,
-0.008087158203125,
0.016845703125,
-0.0232391357421875,
-0.057525634765625,
-0.07708740234375,
-0.0209808349609375,
0.0007386207580566406,
0.053070068359375,
-0.036285400390625,
0.04803466796875,
-0.0017576217651367188,
-0.059906005859375,
-0.03741455078125,
0.012542724609375,
0.034454345703125,
0.025604248046875,
0.026458740234375,
-0.0094757080078125,
-0.059234619140625,
-0.059661865234375,
0.00783538818359375,
-0.035003662109375,
0.00946044921875,
0.0186920166015625,
0.06353759765625,
-0.046661376953125,
0.0611572265625,
-0.032958984375,
-0.0007457733154296875,
-0.026123046875,
-0.0167236328125,
0.040985107421875,
0.0445556640625,
0.053955078125,
-0.041229248046875,
-0.0231781005859375,
0.001613616943359375,
-0.06512451171875,
-0.009185791015625,
-0.0175323486328125,
-0.0044097900390625,
0.0267486572265625,
0.0242156982421875,
-0.051605224609375,
0.038818359375,
0.06256103515625,
-0.0191192626953125,
0.045989990234375,
-0.011688232421875,
-0.006992340087890625,
-0.07916259765625,
0.0175323486328125,
-0.013031005859375,
-0.0037841796875,
-0.037841796875,
0.0256500244140625,
0.0053253173828125,
0.0053253173828125,
-0.04095458984375,
0.0279083251953125,
-0.0306243896484375,
-0.0007224082946777344,
-0.00897216796875,
-0.01352691650390625,
-0.0001232624053955078,
0.0545654296875,
-0.003101348876953125,
0.07049560546875,
0.04241943359375,
-0.04510498046875,
0.0295562744140625,
0.022918701171875,
-0.0235137939453125,
0.013916015625,
-0.07391357421875,
0.026031494140625,
0.00878143310546875,
0.02581787109375,
-0.0634765625,
-0.0157470703125,
0.025634765625,
-0.038909912109375,
0.00775909423828125,
-0.00366973876953125,
-0.036102294921875,
-0.0394287109375,
-0.01812744140625,
0.03485107421875,
0.0650634765625,
-0.04449462890625,
0.029815673828125,
0.0308990478515625,
0.01090240478515625,
-0.05401611328125,
-0.053070068359375,
0.0064544677734375,
-0.0338134765625,
-0.053863525390625,
0.03326416015625,
-0.021697998046875,
-0.01080322265625,
-0.01407623291015625,
0.0075531005859375,
0.00078582763671875,
0.0211944580078125,
0.03289794921875,
0.031005859375,
-0.00949859619140625,
-0.01522064208984375,
-0.003265380859375,
-0.01117706298828125,
0.005558013916015625,
0.007099151611328125,
0.05914306640625,
-0.032379150390625,
-0.018585205078125,
-0.0455322265625,
0.01200103759765625,
0.041839599609375,
-0.019317626953125,
0.045318603515625,
0.032989501953125,
-0.027069091796875,
-0.0005130767822265625,
-0.048675537109375,
0.0034503936767578125,
-0.042266845703125,
0.0239715576171875,
-0.0197906494140625,
-0.060791015625,
0.05291748046875,
0.00823974609375,
0.01541900634765625,
0.040924072265625,
0.05877685546875,
0.005489349365234375,
0.056488037109375,
0.06787109375,
-0.0302734375,
0.0294647216796875,
-0.045379638671875,
0.00617218017578125,
-0.059661865234375,
-0.030731201171875,
-0.042877197265625,
-0.0033397674560546875,
-0.050628662109375,
-0.035552978515625,
0.022918701171875,
0.0150299072265625,
-0.03955078125,
0.053497314453125,
-0.06304931640625,
0.0306549072265625,
0.0323486328125,
0.0036163330078125,
0.025360107421875,
0.0026340484619140625,
-0.004367828369140625,
0.0219879150390625,
-0.03680419921875,
-0.05035400390625,
0.09197998046875,
0.0364990234375,
0.0621337890625,
-0.00510406494140625,
0.06634521484375,
0.002216339111328125,
0.0274505615234375,
-0.044708251953125,
0.043701171875,
0.0210723876953125,
-0.03765869140625,
-0.002017974853515625,
-0.019500732421875,
-0.0679931640625,
0.011199951171875,
0.0050506591796875,
-0.06378173828125,
0.00566864013671875,
0.0008106231689453125,
-0.0185699462890625,
0.0278778076171875,
-0.05169677734375,
0.048583984375,
-0.01416015625,
0.00029349327087402344,
-0.00954437255859375,
-0.040740966796875,
0.04217529296875,
-0.0034465789794921875,
0.0128021240234375,
-0.01220703125,
-0.01190948486328125,
0.05157470703125,
-0.0399169921875,
0.07855224609375,
0.007671356201171875,
-0.027130126953125,
0.04620361328125,
-0.003814697265625,
0.037078857421875,
0.0041351318359375,
-0.0172271728515625,
0.049560546875,
0.00008416175842285156,
-0.019866943359375,
-0.006038665771484375,
0.0472412109375,
-0.0810546875,
-0.05560302734375,
-0.032073974609375,
-0.032012939453125,
0.0222015380859375,
0.01220703125,
0.035675048828125,
0.00470733642578125,
0.01136016845703125,
0.00878143310546875,
0.031494140625,
-0.04852294921875,
0.050445556640625,
0.0240631103515625,
-0.02069091796875,
-0.036468505859375,
0.0625,
-0.01090240478515625,
0.018096923828125,
0.0175323486328125,
0.00258636474609375,
-0.01018524169921875,
-0.032379150390625,
-0.03521728515625,
0.03546142578125,
-0.046356201171875,
-0.04180908203125,
-0.05023193359375,
-0.031524658203125,
-0.0269012451171875,
-0.022705078125,
-0.024810791015625,
-0.0195159912109375,
-0.051177978515625,
-0.0111236572265625,
0.05914306640625,
0.055206298828125,
0.0011234283447265625,
0.0360107421875,
-0.0467529296875,
0.0304107666015625,
0.00980377197265625,
0.02862548828125,
0.003570556640625,
-0.039642333984375,
-0.00797271728515625,
-0.0016965866088867188,
-0.039886474609375,
-0.070068359375,
0.04559326171875,
0.01091766357421875,
0.044403076171875,
0.01019287109375,
-0.0005521774291992188,
0.050750732421875,
-0.030914306640625,
0.067138671875,
0.025390625,
-0.08526611328125,
0.04730224609375,
-0.0188446044921875,
0.006725311279296875,
0.005832672119140625,
0.0218048095703125,
-0.03387451171875,
-0.02374267578125,
-0.0533447265625,
-0.059661865234375,
0.047576904296875,
0.01898193359375,
0.021087646484375,
0.0011014938354492188,
0.03143310546875,
-0.00681304931640625,
0.0186767578125,
-0.080322265625,
-0.02935791015625,
-0.0273590087890625,
-0.0189971923828125,
-0.00437164306640625,
-0.0177001953125,
-0.0033702850341796875,
-0.0227203369140625,
0.035247802734375,
-0.01216888427734375,
0.048370361328125,
0.0152130126953125,
-0.01499176025390625,
-0.0191497802734375,
0.0002493858337402344,
0.04888916015625,
0.044342041015625,
-0.0035686492919921875,
-0.01088714599609375,
0.0323486328125,
-0.041229248046875,
0.0176544189453125,
-0.0037326812744140625,
-0.005962371826171875,
-0.0174102783203125,
0.040008544921875,
0.048736572265625,
0.006175994873046875,
-0.0560302734375,
0.03875732421875,
0.0074462890625,
-0.021759033203125,
-0.037689208984375,
0.0188446044921875,
0.0243377685546875,
0.0251617431640625,
0.0216522216796875,
-0.0010690689086914062,
-0.0093536376953125,
-0.026092529296875,
0.005748748779296875,
0.026336669921875,
0.0115509033203125,
-0.0253753662109375,
0.0697021484375,
0.0101776123046875,
-0.02557373046875,
0.03912353515625,
0.0023250579833984375,
-0.044403076171875,
0.09075927734375,
0.05120849609375,
0.057220458984375,
-0.01458740234375,
0.01041412353515625,
0.03741455078125,
0.043304443359375,
0.00344085693359375,
0.030487060546875,
0.0034923553466796875,
-0.041046142578125,
-0.0231781005859375,
-0.060699462890625,
-0.0242767333984375,
0.005706787109375,
-0.032135009765625,
0.025421142578125,
-0.04681396484375,
-0.00606536865234375,
-0.024993896484375,
0.00832366943359375,
-0.051788330078125,
0.0003390312194824219,
0.00611114501953125,
0.0709228515625,
-0.05023193359375,
0.06719970703125,
0.040283203125,
-0.0506591796875,
-0.0692138671875,
-0.0162200927734375,
-0.00678253173828125,
-0.08990478515625,
0.038543701171875,
0.021636962890625,
0.00598907470703125,
0.00966644287109375,
-0.06634521484375,
-0.08245849609375,
0.09814453125,
0.032684326171875,
-0.03753662109375,
-0.0024051666259765625,
0.01326751708984375,
0.04022216796875,
-0.0282440185546875,
0.03997802734375,
0.046600341796875,
0.029388427734375,
-0.007160186767578125,
-0.08856201171875,
0.0234375,
-0.0300750732421875,
0.01251983642578125,
-0.0172119140625,
-0.0816650390625,
0.08111572265625,
-0.04144287109375,
-0.01052093505859375,
0.0298309326171875,
0.05401611328125,
0.040130615234375,
0.01328277587890625,
0.0274658203125,
0.042205810546875,
0.048370361328125,
-0.001781463623046875,
0.0806884765625,
-0.0364990234375,
0.040924072265625,
0.038238525390625,
-0.006763458251953125,
0.0545654296875,
0.028289794921875,
-0.0404052734375,
0.057281494140625,
0.058380126953125,
-0.0164337158203125,
0.0187225341796875,
0.0234375,
-0.005100250244140625,
-0.002223968505859375,
-0.0005326271057128906,
-0.0572509765625,
0.031219482421875,
0.024444580078125,
-0.0283966064453125,
0.00423431396484375,
-0.0164337158203125,
0.0215911865234375,
-0.0150909423828125,
-0.0018100738525390625,
0.046356201171875,
0.01522064208984375,
-0.03802490234375,
0.08734130859375,
0.00945281982421875,
0.07366943359375,
-0.034423828125,
-0.008087158203125,
-0.029571533203125,
0.0042877197265625,
-0.040008544921875,
-0.039703369140625,
0.015167236328125,
0.01824951171875,
0.0001455545425415039,
-0.0071563720703125,
0.03741455078125,
-0.006748199462890625,
-0.038604736328125,
0.0276336669921875,
0.01349639892578125,
0.0225982666015625,
0.01433563232421875,
-0.055755615234375,
0.033050537109375,
0.01396942138671875,
-0.035125732421875,
0.020599365234375,
0.00821685791015625,
0.01125335693359375,
0.06817626953125,
0.055389404296875,
-0.01001739501953125,
0.01462554931640625,
-0.01488494873046875,
0.08306884765625,
-0.052734375,
-0.0272979736328125,
-0.062286376953125,
0.05120849609375,
0.01517486572265625,
-0.036346435546875,
0.045166015625,
0.0274505615234375,
0.062225341796875,
-0.0074920654296875,
0.05865478515625,
-0.0178070068359375,
0.00534820556640625,
-0.0311737060546875,
0.052093505859375,
-0.052093505859375,
0.0283203125,
-0.03863525390625,
-0.06658935546875,
-0.0190277099609375,
0.06756591796875,
-0.004444122314453125,
0.00954437255859375,
0.039703369140625,
0.0743408203125,
0.018951416015625,
-0.00661468505859375,
0.01226806640625,
0.015869140625,
0.03057861328125,
0.06378173828125,
0.06768798828125,
-0.0499267578125,
0.052459716796875,
-0.045440673828125,
-0.0207977294921875,
-0.0226898193359375,
-0.0755615234375,
-0.0738525390625,
-0.0384521484375,
-0.0255126953125,
-0.03179931640625,
-0.0184783935546875,
0.06951904296875,
0.04779052734375,
-0.04571533203125,
-0.03717041015625,
-0.0133209228515625,
0.0291290283203125,
-0.007598876953125,
-0.0164337158203125,
0.0241546630859375,
-0.0123443603515625,
-0.06146240234375,
0.02044677734375,
-0.002033233642578125,
0.01171875,
-0.0226593017578125,
-0.01910400390625,
-0.01364898681640625,
0.0007963180541992188,
0.033233642578125,
0.02752685546875,
-0.061859130859375,
-0.0170135498046875,
0.00835418701171875,
-0.01537322998046875,
0.01081085205078125,
0.0290679931640625,
-0.048126220703125,
0.00027871131896972656,
0.0286407470703125,
0.0306854248046875,
0.0306396484375,
-0.018157958984375,
0.0182952880859375,
-0.029815673828125,
0.031707763671875,
-0.0009579658508300781,
0.036773681640625,
0.00858306884765625,
-0.04364013671875,
0.047637939453125,
0.0240325927734375,
-0.053436279296875,
-0.067138671875,
0.0094146728515625,
-0.0794677734375,
-0.0134124755859375,
0.09515380859375,
-0.012542724609375,
-0.02435302734375,
0.0122833251953125,
-0.0269775390625,
0.0233154296875,
-0.0287628173828125,
0.0537109375,
0.0215301513671875,
-0.00911712646484375,
-0.01438140869140625,
-0.0284271240234375,
0.02093505859375,
0.0223388671875,
-0.07080078125,
-0.01171112060546875,
0.022857666015625,
0.031646728515625,
0.01396942138671875,
0.055755615234375,
-0.005565643310546875,
0.0147857666015625,
0.005413055419921875,
0.031585693359375,
-0.0051727294921875,
-0.01268768310546875,
-0.0254364013671875,
-0.005413055419921875,
-0.006866455078125,
-0.004909515380859375
]
] |
timm/dm_nfnet_f0.dm_in1k | 2023-03-24T00:47:41.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2102.06171",
"arxiv:2101.08692",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/dm_nfnet_f0.dm_in1k | 1 | 38,645 | timm | 2023-03-24T00:46:50 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for dm_nfnet_f0.dm_in1k
A NFNet (Normalization Free Network) image classification model. Trained on ImageNet-1k by paper authors.
Normalization Free Networks are (pre-activation) ResNet-like models without any normalization layers. Instead of Batch Normalization or alternatives, they use Scaled Weight Standardization and specifically placed scalar gains in residual path and at non-linearities based on signal propagation analysis.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 71.5
- GMACs: 7.2
- Activations (M): 10.2
- Image size: train = 192 x 192, test = 256 x 256
- **Papers:**
- High-Performance Large-Scale Image Recognition Without Normalization: https://arxiv.org/abs/2102.06171
- Characterizing signal propagation to close the performance gap in unnormalized ResNets: https://arxiv.org/abs/2101.08692
- **Original:** https://github.com/deepmind/deepmind-research/tree/master/nfnets
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('dm_nfnet_f0.dm_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'dm_nfnet_f0.dm_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 96, 96])
# torch.Size([1, 256, 48, 48])
# torch.Size([1, 512, 24, 24])
# torch.Size([1, 1536, 12, 12])
# torch.Size([1, 3072, 6, 6])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'dm_nfnet_f0.dm_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 3072, 6, 6) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{brock2021high,
author={Andrew Brock and Soham De and Samuel L. Smith and Karen Simonyan},
title={High-Performance Large-Scale Image Recognition Without Normalization},
journal={arXiv preprint arXiv:2102.06171},
year={2021}
}
```
```bibtex
@inproceedings{brock2021characterizing,
author={Andrew Brock and Soham De and Samuel L. Smith},
title={Characterizing signal propagation to close the performance gap in
unnormalized ResNets},
booktitle={9th International Conference on Learning Representations, {ICLR}},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 4,742 | [
[
-0.038360595703125,
-0.037353515625,
-0.0033664703369140625,
0.0097503662109375,
-0.02874755859375,
-0.02490234375,
-0.0195465087890625,
-0.0308685302734375,
0.0202484130859375,
0.033966064453125,
-0.03607177734375,
-0.05157470703125,
-0.058990478515625,
0.00025153160095214844,
-0.0120391845703125,
0.0711669921875,
-0.005214691162109375,
-0.00365447998046875,
-0.0173797607421875,
-0.036285400390625,
-0.00960540771484375,
-0.0203094482421875,
-0.060150146484375,
-0.036712646484375,
0.0304412841796875,
0.01446533203125,
0.04193115234375,
0.05206298828125,
0.048919677734375,
0.034942626953125,
-0.01407623291015625,
0.0062103271484375,
-0.0197296142578125,
-0.018524169921875,
0.03387451171875,
-0.04302978515625,
-0.037994384765625,
0.02362060546875,
0.06597900390625,
0.041290283203125,
0.00714111328125,
0.0274200439453125,
0.00624847412109375,
0.048919677734375,
-0.01525115966796875,
0.01512908935546875,
-0.03369140625,
0.0140380859375,
-0.00453948974609375,
0.00399017333984375,
-0.0184173583984375,
-0.033966064453125,
0.01210784912109375,
-0.044158935546875,
0.0301361083984375,
-0.0074462890625,
0.09490966796875,
0.019683837890625,
-0.0135345458984375,
-0.0035552978515625,
-0.025177001953125,
0.05841064453125,
-0.06707763671875,
0.01953125,
0.0217742919921875,
0.0222015380859375,
-0.0186767578125,
-0.0714111328125,
-0.045745849609375,
-0.0175323486328125,
-0.01146697998046875,
-0.006134033203125,
-0.0185699462890625,
0.011688232421875,
0.028167724609375,
0.0295867919921875,
-0.0257415771484375,
0.01287841796875,
-0.04193115234375,
-0.01003265380859375,
0.04937744140625,
-0.0015344619750976562,
0.015716552734375,
-0.01145172119140625,
-0.03863525390625,
-0.026092529296875,
-0.02484130859375,
0.0240936279296875,
0.0285797119140625,
0.0194854736328125,
-0.045654296875,
0.0218048095703125,
0.000980377197265625,
0.05224609375,
0.0091705322265625,
-0.0300750732421875,
0.04656982421875,
0.00681304931640625,
-0.0379638671875,
-0.008148193359375,
0.08319091796875,
0.025787353515625,
0.0161590576171875,
-0.0013647079467773438,
-0.0160980224609375,
-0.0225677490234375,
-0.0116729736328125,
-0.08941650390625,
-0.027801513671875,
0.0208892822265625,
-0.051727294921875,
-0.03570556640625,
0.0142974853515625,
-0.049285888671875,
-0.01380157470703125,
-0.0070953369140625,
0.04541015625,
-0.03228759765625,
-0.03546142578125,
0.010589599609375,
-0.0133056640625,
0.019866943359375,
0.01380157470703125,
-0.04144287109375,
0.0159149169921875,
0.0179443359375,
0.0806884765625,
0.01015472412109375,
-0.0276641845703125,
-0.0129852294921875,
-0.03131103515625,
-0.02435302734375,
0.029693603515625,
-0.00814056396484375,
-0.00838470458984375,
-0.0296173095703125,
0.026885986328125,
-0.0130157470703125,
-0.06085205078125,
0.0234222412109375,
-0.0272216796875,
0.0125274658203125,
0.0003418922424316406,
-0.02532958984375,
-0.04522705078125,
0.0223541259765625,
-0.041473388671875,
0.08917236328125,
0.0226898193359375,
-0.065673828125,
0.0276641845703125,
-0.05059814453125,
-0.01042938232421875,
-0.0224456787109375,
-0.002964019775390625,
-0.07672119140625,
-0.005229949951171875,
0.01465606689453125,
0.0594482421875,
-0.02081298828125,
0.0040130615234375,
-0.0443115234375,
-0.03082275390625,
0.0273895263671875,
-0.01348114013671875,
0.078369140625,
0.0119171142578125,
-0.035369873046875,
0.0202178955078125,
-0.058135986328125,
0.00665283203125,
0.0390625,
-0.026092529296875,
-0.001232147216796875,
-0.043853759765625,
0.00824737548828125,
0.0276641845703125,
0.005298614501953125,
-0.05438232421875,
0.0241851806640625,
-0.0189056396484375,
0.041015625,
0.048797607421875,
-0.01068878173828125,
0.0238189697265625,
-0.029296875,
0.0183258056640625,
0.02923583984375,
0.0230560302734375,
-0.0013294219970703125,
-0.043914794921875,
-0.05718994140625,
-0.046875,
0.028411865234375,
0.0194549560546875,
-0.03851318359375,
0.036102294921875,
-0.01971435546875,
-0.0570068359375,
-0.036163330078125,
0.0071258544921875,
0.030548095703125,
0.0487060546875,
0.0280609130859375,
-0.02801513671875,
-0.03759765625,
-0.06439208984375,
0.0115966796875,
0.00940704345703125,
0.00007236003875732422,
0.0240478515625,
0.0494384765625,
-0.0142822265625,
0.04962158203125,
-0.03155517578125,
-0.0250396728515625,
-0.0146484375,
0.00591278076171875,
0.04290771484375,
0.058135986328125,
0.058990478515625,
-0.04815673828125,
-0.037689208984375,
-0.0138397216796875,
-0.07232666015625,
0.0178680419921875,
-0.0009055137634277344,
-0.0101318359375,
0.0181884765625,
0.0136871337890625,
-0.041961669921875,
0.04638671875,
0.0205535888671875,
-0.0202789306640625,
0.02972412109375,
-0.0208587646484375,
0.016571044921875,
-0.08111572265625,
0.01023101806640625,
0.0283203125,
-0.0043487548828125,
-0.041839599609375,
-0.00293731689453125,
0.0014429092407226562,
-0.002330780029296875,
-0.0307159423828125,
0.045654296875,
-0.04718017578125,
-0.0126953125,
-0.01213836669921875,
-0.0170135498046875,
0.0030517578125,
0.0570068359375,
-0.0081634521484375,
0.0275726318359375,
0.06585693359375,
-0.042022705078125,
0.036773681640625,
0.024139404296875,
-0.016571044921875,
0.029632568359375,
-0.050933837890625,
0.0154571533203125,
-0.01174163818359375,
0.0200042724609375,
-0.082763671875,
-0.0161285400390625,
0.02703857421875,
-0.046234130859375,
0.046966552734375,
-0.041473388671875,
-0.0350341796875,
-0.0384521484375,
-0.029937744140625,
0.034027099609375,
0.05419921875,
-0.056640625,
0.0233306884765625,
0.0171661376953125,
0.034515380859375,
-0.039581298828125,
-0.06304931640625,
-0.020172119140625,
-0.031524658203125,
-0.056304931640625,
0.0256805419921875,
0.00902557373046875,
0.0123748779296875,
0.00806427001953125,
-0.00777435302734375,
-0.0169219970703125,
-0.0010805130004882812,
0.043853759765625,
0.028167724609375,
-0.0274200439453125,
-0.0028839111328125,
-0.024078369140625,
-0.0029239654541015625,
0.005489349365234375,
-0.024383544921875,
0.0369873046875,
-0.01279449462890625,
-0.01047515869140625,
-0.0709228515625,
-0.004138946533203125,
0.041259765625,
-0.011260986328125,
0.062347412109375,
0.07867431640625,
-0.043426513671875,
-0.00203704833984375,
-0.03314208984375,
-0.024383544921875,
-0.038116455078125,
0.030364990234375,
-0.0234527587890625,
-0.04046630859375,
0.06158447265625,
-0.001117706298828125,
0.0067138671875,
0.049835205078125,
0.0168914794921875,
-0.0038967132568359375,
0.055511474609375,
0.047119140625,
0.00681304931640625,
0.049102783203125,
-0.07452392578125,
-0.00719451904296875,
-0.0638427734375,
-0.03448486328125,
-0.0213165283203125,
-0.056610107421875,
-0.04779052734375,
-0.03167724609375,
0.030792236328125,
0.02398681640625,
-0.03057861328125,
0.0279541015625,
-0.06695556640625,
0.0093841552734375,
0.044708251953125,
0.037261962890625,
-0.0165252685546875,
0.0245361328125,
-0.0181427001953125,
0.003574371337890625,
-0.055877685546875,
-0.0200042724609375,
0.09259033203125,
0.038055419921875,
0.051116943359375,
-0.0157623291015625,
0.055206298828125,
-0.01824951171875,
0.0280303955078125,
-0.04876708984375,
0.0474853515625,
-0.01171112060546875,
-0.0311737060546875,
-0.01751708984375,
-0.04193115234375,
-0.0869140625,
0.00601959228515625,
-0.0279541015625,
-0.05499267578125,
0.014862060546875,
0.01169586181640625,
-0.0194854736328125,
0.06689453125,
-0.052764892578125,
0.06475830078125,
-0.00357818603515625,
-0.0216522216796875,
0.006618499755859375,
-0.046661376953125,
0.0217132568359375,
0.021240234375,
-0.0154876708984375,
-0.0157623291015625,
0.0135498046875,
0.08294677734375,
-0.031890869140625,
0.06549072265625,
-0.043853759765625,
0.030364990234375,
0.037200927734375,
-0.01293182373046875,
0.0200958251953125,
-0.0072174072265625,
-0.01114654541015625,
0.036590576171875,
0.003963470458984375,
-0.035369873046875,
-0.04156494140625,
0.0465087890625,
-0.075927734375,
-0.0200042724609375,
-0.0202178955078125,
-0.039459228515625,
0.01218414306640625,
0.01316070556640625,
0.03521728515625,
0.053863525390625,
0.01812744140625,
0.0244598388671875,
0.04925537109375,
-0.028778076171875,
0.033966064453125,
-0.006580352783203125,
-0.0130767822265625,
-0.0394287109375,
0.06072998046875,
0.0243988037109375,
0.013519287109375,
0.01145172119140625,
0.0139007568359375,
-0.03057861328125,
-0.0487060546875,
-0.025238037109375,
0.031524658203125,
-0.052093505859375,
-0.035858154296875,
-0.043853759765625,
-0.038848876953125,
-0.033447265625,
0.0030670166015625,
-0.03594970703125,
-0.0264739990234375,
-0.029876708984375,
0.01232147216796875,
0.055145263671875,
0.050048828125,
-0.00676727294921875,
0.042388916015625,
-0.03924560546875,
0.00772857666015625,
0.007358551025390625,
0.047607421875,
0.00414276123046875,
-0.0611572265625,
-0.018157958984375,
0.0003151893615722656,
-0.033966064453125,
-0.05584716796875,
0.030914306640625,
0.0135345458984375,
0.044830322265625,
0.0311279296875,
-0.010498046875,
0.05303955078125,
0.005519866943359375,
0.03424072265625,
0.0275115966796875,
-0.04034423828125,
0.03936767578125,
-0.00333404541015625,
0.01131439208984375,
0.00307464599609375,
0.033416748046875,
-0.0225982666015625,
0.005340576171875,
-0.0667724609375,
-0.05047607421875,
0.0616455078125,
0.00873565673828125,
-0.0017070770263671875,
0.0222930908203125,
0.05841064453125,
-0.001827239990234375,
0.006252288818359375,
-0.05194091796875,
-0.03643798828125,
-0.0244903564453125,
-0.0161285400390625,
-0.0065460205078125,
-0.0038585662841796875,
-0.00844573974609375,
-0.052459716796875,
0.04473876953125,
-0.006591796875,
0.0633544921875,
0.033660888671875,
-0.00037789344787597656,
-0.005126953125,
-0.028594970703125,
0.0325927734375,
0.018798828125,
-0.0275726318359375,
0.0030384063720703125,
0.01059722900390625,
-0.043365478515625,
0.01247406005859375,
0.01380157470703125,
0.0017185211181640625,
0.0011577606201171875,
0.03759765625,
0.07318115234375,
-0.0005435943603515625,
0.007167816162109375,
0.03594970703125,
-0.0047149658203125,
-0.04254150390625,
-0.01357269287109375,
0.00714874267578125,
-0.001956939697265625,
0.03033447265625,
0.0217742919921875,
0.0210723876953125,
-0.011505126953125,
-0.0126953125,
0.0187530517578125,
0.0439453125,
-0.0245513916015625,
-0.0311737060546875,
0.0523681640625,
-0.012847900390625,
-0.005352020263671875,
0.06988525390625,
-0.01371002197265625,
-0.027313232421875,
0.08392333984375,
0.0333251953125,
0.0714111328125,
-0.0026493072509765625,
0.005680084228515625,
0.06683349609375,
0.0158233642578125,
0.006938934326171875,
0.01456451416015625,
0.006618499755859375,
-0.05810546875,
0.0028820037841796875,
-0.047821044921875,
0.00894927978515625,
0.033935546875,
-0.038787841796875,
0.0200347900390625,
-0.06640625,
-0.035614013671875,
0.013580322265625,
0.0250091552734375,
-0.071533203125,
0.018280029296875,
0.0018739700317382812,
0.071044921875,
-0.060089111328125,
0.06317138671875,
0.0643310546875,
-0.035858154296875,
-0.0821533203125,
-0.007404327392578125,
-0.0037689208984375,
-0.06494140625,
0.0487060546875,
0.041015625,
0.0119781494140625,
0.003406524658203125,
-0.0513916015625,
-0.055145263671875,
0.1094970703125,
0.0416259765625,
-0.00272369384765625,
0.018707275390625,
0.00347900390625,
0.0203704833984375,
-0.034515380859375,
0.03369140625,
0.012969970703125,
0.0270233154296875,
0.02996826171875,
-0.05499267578125,
0.0222320556640625,
-0.020172119140625,
0.00968170166015625,
0.0177154541015625,
-0.05816650390625,
0.07672119140625,
-0.034576416015625,
-0.01593017578125,
-0.0018091201782226562,
0.04779052734375,
0.0105438232421875,
0.01200103759765625,
0.04473876953125,
0.060882568359375,
0.044403076171875,
-0.0214996337890625,
0.05621337890625,
-0.00606536865234375,
0.04412841796875,
0.044158935546875,
0.02923583984375,
0.03643798828125,
0.03192138671875,
-0.0207366943359375,
0.024810791015625,
0.07647705078125,
-0.024200439453125,
0.024688720703125,
0.0254669189453125,
-0.0010128021240234375,
-0.00606536865234375,
0.01044464111328125,
-0.0352783203125,
0.0413818359375,
0.00601959228515625,
-0.040069580078125,
-0.0215606689453125,
0.002063751220703125,
0.001461029052734375,
-0.022705078125,
-0.020355224609375,
0.03643798828125,
-0.0014905929565429688,
-0.02532958984375,
0.075439453125,
0.008544921875,
0.0740966796875,
-0.03216552734375,
-0.003383636474609375,
-0.0242767333984375,
0.01800537109375,
-0.037139892578125,
-0.05645751953125,
0.02972412109375,
-0.0255889892578125,
-0.00443267822265625,
0.007694244384765625,
0.045806884765625,
-0.0228729248046875,
-0.035003662109375,
0.0219879150390625,
0.01415252685546875,
0.03778076171875,
-0.0011081695556640625,
-0.08233642578125,
0.00948333740234375,
-0.0007586479187011719,
-0.04345703125,
0.03131103515625,
0.033233642578125,
0.006122589111328125,
0.0572509765625,
0.052947998046875,
-0.0081634521484375,
0.0171051025390625,
-0.02008056640625,
0.067138671875,
-0.036163330078125,
-0.019866943359375,
-0.0595703125,
0.044158935546875,
-0.006740570068359375,
-0.04254150390625,
0.040130615234375,
0.041290283203125,
0.06805419921875,
-0.0014553070068359375,
0.027374267578125,
-0.0129547119140625,
-0.004795074462890625,
-0.025543212890625,
0.05914306640625,
-0.055419921875,
-0.003971099853515625,
-0.01383209228515625,
-0.05230712890625,
-0.03228759765625,
0.054779052734375,
-0.0214385986328125,
0.02801513671875,
0.022796630859375,
0.08203125,
-0.0289459228515625,
-0.019439697265625,
0.0218048095703125,
0.01061248779296875,
0.00814056396484375,
0.035003662109375,
0.0305328369140625,
-0.057891845703125,
0.027923583984375,
-0.0509033203125,
-0.024261474609375,
-0.007396697998046875,
-0.05621337890625,
-0.0745849609375,
-0.06304931640625,
-0.04632568359375,
-0.04449462890625,
-0.0213470458984375,
0.07025146484375,
0.08428955078125,
-0.045562744140625,
-0.0163421630859375,
0.0036792755126953125,
0.01488494873046875,
-0.0238494873046875,
-0.0163421630859375,
0.043060302734375,
-0.0110931396484375,
-0.051177978515625,
-0.020355224609375,
0.0014715194702148438,
0.0303497314453125,
-0.0034332275390625,
-0.0171966552734375,
-0.018157958984375,
-0.0154571533203125,
0.01605224609375,
0.020965576171875,
-0.045684814453125,
-0.01050567626953125,
-0.018707275390625,
-0.006229400634765625,
0.0357666015625,
0.0279541015625,
-0.04302978515625,
0.02459716796875,
0.0294189453125,
0.03106689453125,
0.0567626953125,
-0.0328369140625,
-0.004901885986328125,
-0.0579833984375,
0.041473388671875,
-0.00785064697265625,
0.0303497314453125,
0.031829833984375,
-0.03265380859375,
0.03521728515625,
0.03759765625,
-0.036407470703125,
-0.067138671875,
-0.005245208740234375,
-0.07415771484375,
-0.0048980712890625,
0.0633544921875,
-0.037078857421875,
-0.03729248046875,
0.033843994140625,
0.00386810302734375,
0.05157470703125,
-0.006618499755859375,
0.03680419921875,
0.017547607421875,
-0.0156097412109375,
-0.038665771484375,
-0.04119873046875,
0.037017822265625,
0.0019893646240234375,
-0.04144287109375,
-0.03131103515625,
0.00029778480529785156,
0.06353759765625,
0.011749267578125,
0.045867919921875,
-0.0162506103515625,
0.0005617141723632812,
0.0073394775390625,
0.03338623046875,
-0.0390625,
-0.0112152099609375,
-0.0364990234375,
0.00299835205078125,
-0.005573272705078125,
-0.05462646484375
]
] |
timm/nfnet_l0.ra2_in1k | 2023-03-24T01:15:53.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2102.06171",
"arxiv:2101.08692",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/nfnet_l0.ra2_in1k | 1 | 38,619 | timm | 2023-03-24T01:15:14 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for nfnet_l0.ra2_in1k
A NFNet-Lite (Lightweight NFNet) image classification model. Trained in `timm` by Ross Wightman.
Normalization Free Networks are (pre-activation) ResNet-like models without any normalization layers. Instead of Batch Normalization or alternatives, they use Scaled Weight Standardization and specifically placed scalar gains in residual path and at non-linearities based on signal propagation analysis.
Lightweight NFNets are `timm` specific variants that reduce the SE and bottleneck ratio from 0.5 -> 0.25 (reducing widths) and use a smaller group size while maintaining the same depth. SiLU activations used instead of GELU.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 35.1
- GMACs: 4.4
- Activations (M): 10.5
- Image size: train = 224 x 224, test = 288 x 288
- **Papers:**
- High-Performance Large-Scale Image Recognition Without Normalization: https://arxiv.org/abs/2102.06171
- Characterizing signal propagation to close the performance gap in unnormalized ResNets: https://arxiv.org/abs/2101.08692
- **Original:** https://github.com/huggingface/pytorch-image-models
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('nfnet_l0.ra2_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'nfnet_l0.ra2_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 112, 112])
# torch.Size([1, 256, 56, 56])
# torch.Size([1, 512, 28, 28])
# torch.Size([1, 1536, 14, 14])
# torch.Size([1, 2304, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'nfnet_l0.ra2_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2304, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{brock2021high,
author={Andrew Brock and Soham De and Samuel L. Smith and Karen Simonyan},
title={High-Performance Large-Scale Image Recognition Without Normalization},
journal={arXiv preprint arXiv:2102.06171},
year={2021}
}
```
```bibtex
@inproceedings{brock2021characterizing,
author={Andrew Brock and Soham De and Samuel L. Smith},
title={Characterizing signal propagation to close the performance gap in
unnormalized ResNets},
booktitle={9th International Conference on Learning Representations, {ICLR}},
year={2021}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 4,941 | [
[
-0.0369873046875,
-0.035430908203125,
-0.00908660888671875,
0.00876617431640625,
-0.0262451171875,
-0.0261993408203125,
-0.0225372314453125,
-0.03985595703125,
0.02276611328125,
0.034088134765625,
-0.030853271484375,
-0.046051025390625,
-0.057891845703125,
0.0012340545654296875,
-0.01125335693359375,
0.077392578125,
-0.004467010498046875,
-0.006740570068359375,
-0.01355743408203125,
-0.0433349609375,
-0.00859832763671875,
-0.01174163818359375,
-0.063232421875,
-0.039031982421875,
0.03314208984375,
0.0178070068359375,
0.048065185546875,
0.04827880859375,
0.0458984375,
0.0330810546875,
-0.0124359130859375,
0.00846099853515625,
-0.0164337158203125,
-0.01531219482421875,
0.03363037109375,
-0.04534912109375,
-0.032562255859375,
0.0209197998046875,
0.06121826171875,
0.0396728515625,
0.010528564453125,
0.0286102294921875,
0.007564544677734375,
0.04736328125,
-0.0168609619140625,
0.0108489990234375,
-0.0286407470703125,
0.014923095703125,
-0.005908966064453125,
0.003040313720703125,
-0.0226593017578125,
-0.032440185546875,
0.01316070556640625,
-0.043060302734375,
0.032470703125,
-0.0013895034790039062,
0.0992431640625,
0.013427734375,
-0.01541900634765625,
-0.000029742717742919922,
-0.025726318359375,
0.061798095703125,
-0.062286376953125,
0.0192718505859375,
0.02069091796875,
0.0226593017578125,
-0.0127410888671875,
-0.07452392578125,
-0.039154052734375,
-0.01788330078125,
-0.01264190673828125,
-0.006549835205078125,
-0.0222625732421875,
0.0119476318359375,
0.02716064453125,
0.024566650390625,
-0.0300750732421875,
0.01119232177734375,
-0.043304443359375,
-0.01279449462890625,
0.0455322265625,
-0.008636474609375,
0.0215606689453125,
-0.0136566162109375,
-0.03955078125,
-0.025390625,
-0.02557373046875,
0.0243682861328125,
0.0251007080078125,
0.020904541015625,
-0.050872802734375,
0.0252838134765625,
0.0048065185546875,
0.048431396484375,
0.00567626953125,
-0.0285491943359375,
0.048126220703125,
0.006511688232421875,
-0.03521728515625,
-0.01197052001953125,
0.08441162109375,
0.02716064453125,
0.01953125,
-0.006221771240234375,
-0.0188751220703125,
-0.023529052734375,
-0.0167236328125,
-0.0888671875,
-0.025634765625,
0.018585205078125,
-0.053741455078125,
-0.03436279296875,
0.01611328125,
-0.047088623046875,
-0.012176513671875,
-0.00484466552734375,
0.046295166015625,
-0.031951904296875,
-0.03375244140625,
0.007671356201171875,
-0.01557159423828125,
0.0226898193359375,
0.01459503173828125,
-0.04254150390625,
0.0186767578125,
0.0189666748046875,
0.086181640625,
0.0116119384765625,
-0.025054931640625,
-0.02142333984375,
-0.02899169921875,
-0.0239715576171875,
0.033538818359375,
-0.007259368896484375,
-0.005489349365234375,
-0.02972412109375,
0.0281524658203125,
-0.00887298583984375,
-0.060821533203125,
0.0220794677734375,
-0.024566650390625,
0.01409149169921875,
-0.0017414093017578125,
-0.01837158203125,
-0.0423583984375,
0.0196533203125,
-0.04266357421875,
0.09600830078125,
0.02471923828125,
-0.06878662109375,
0.02496337890625,
-0.050201416015625,
-0.01263427734375,
-0.0235137939453125,
-0.0026721954345703125,
-0.0772705078125,
-0.00251007080078125,
0.01343536376953125,
0.0557861328125,
-0.0287322998046875,
0.0020923614501953125,
-0.0416259765625,
-0.032806396484375,
0.0258941650390625,
-0.006084442138671875,
0.07806396484375,
0.0124664306640625,
-0.0380859375,
0.0235443115234375,
-0.050262451171875,
0.009246826171875,
0.0377197265625,
-0.021270751953125,
-0.0012950897216796875,
-0.047271728515625,
0.0186920166015625,
0.0270538330078125,
0.002071380615234375,
-0.05181884765625,
0.0202789306640625,
-0.0221405029296875,
0.03997802734375,
0.044158935546875,
-0.01165771484375,
0.0264129638671875,
-0.035400390625,
0.020050048828125,
0.0216064453125,
0.0236968994140625,
0.0019273757934570312,
-0.0467529296875,
-0.056915283203125,
-0.040313720703125,
0.028656005859375,
0.0210723876953125,
-0.040863037109375,
0.0304718017578125,
-0.017578125,
-0.05279541015625,
-0.03216552734375,
0.01206207275390625,
0.034393310546875,
0.044647216796875,
0.02801513671875,
-0.034454345703125,
-0.039215087890625,
-0.06536865234375,
0.00637054443359375,
0.0103607177734375,
-0.002704620361328125,
0.0262298583984375,
0.048492431640625,
-0.0137481689453125,
0.051300048828125,
-0.0267486572265625,
-0.0258941650390625,
-0.0231170654296875,
0.01023101806640625,
0.035430908203125,
0.05804443359375,
0.06402587890625,
-0.0477294921875,
-0.037811279296875,
-0.01006317138671875,
-0.0723876953125,
0.013336181640625,
-0.0008654594421386719,
-0.0081939697265625,
0.020599365234375,
0.01482391357421875,
-0.041351318359375,
0.04498291015625,
0.0203399658203125,
-0.019378662109375,
0.0294036865234375,
-0.02099609375,
0.012969970703125,
-0.083251953125,
0.01209259033203125,
0.032470703125,
-0.005596160888671875,
-0.043060302734375,
0.0013427734375,
0.0017185211181640625,
-0.004741668701171875,
-0.0308990478515625,
0.04827880859375,
-0.050018310546875,
-0.0205230712890625,
-0.01324462890625,
-0.01543426513671875,
0.00664520263671875,
0.052490234375,
-0.00839996337890625,
0.03277587890625,
0.06280517578125,
-0.034027099609375,
0.030029296875,
0.0198516845703125,
-0.014923095703125,
0.0255279541015625,
-0.05517578125,
0.0169219970703125,
-0.0127410888671875,
0.02117919921875,
-0.078125,
-0.0186920166015625,
0.025390625,
-0.048553466796875,
0.04400634765625,
-0.042877197265625,
-0.036773681640625,
-0.032684326171875,
-0.035491943359375,
0.03668212890625,
0.055389404296875,
-0.05462646484375,
0.029632568359375,
0.0140533447265625,
0.03399658203125,
-0.041717529296875,
-0.0694580078125,
-0.0175323486328125,
-0.029266357421875,
-0.058349609375,
0.02276611328125,
0.01021575927734375,
0.01206207275390625,
0.00905609130859375,
-0.0066070556640625,
-0.01702880859375,
-0.004055023193359375,
0.045654296875,
0.027801513671875,
-0.02978515625,
-0.0052642822265625,
-0.02557373046875,
-0.00656890869140625,
0.0022182464599609375,
-0.024627685546875,
0.0360107421875,
-0.0157928466796875,
-0.00554656982421875,
-0.07318115234375,
-0.0036830902099609375,
0.038848876953125,
-0.015838623046875,
0.06396484375,
0.0858154296875,
-0.043731689453125,
-0.003971099853515625,
-0.038055419921875,
-0.025054931640625,
-0.037689208984375,
0.0275421142578125,
-0.0189971923828125,
-0.0458984375,
0.060638427734375,
-0.0013723373413085938,
0.007671356201171875,
0.04791259765625,
0.01293182373046875,
-0.003414154052734375,
0.0523681640625,
0.04864501953125,
0.00838470458984375,
0.050048828125,
-0.0745849609375,
-0.00537872314453125,
-0.0643310546875,
-0.03729248046875,
-0.0256500244140625,
-0.055633544921875,
-0.0467529296875,
-0.035125732421875,
0.033203125,
0.0217132568359375,
-0.0287628173828125,
0.0276336669921875,
-0.06512451171875,
0.013336181640625,
0.043670654296875,
0.0341796875,
-0.0205841064453125,
0.0280914306640625,
-0.014862060546875,
0.001430511474609375,
-0.054229736328125,
-0.0176544189453125,
0.09259033203125,
0.0352783203125,
0.04736328125,
-0.01018524169921875,
0.055633544921875,
-0.0162200927734375,
0.028167724609375,
-0.048736572265625,
0.045745849609375,
-0.0136260986328125,
-0.02911376953125,
-0.0122833251953125,
-0.041290283203125,
-0.08758544921875,
0.004604339599609375,
-0.031951904296875,
-0.05865478515625,
0.01346588134765625,
0.01116180419921875,
-0.0192718505859375,
0.0673828125,
-0.056549072265625,
0.06256103515625,
-0.0021381378173828125,
-0.0270233154296875,
0.006381988525390625,
-0.052734375,
0.025177001953125,
0.0239105224609375,
-0.01450347900390625,
-0.0146331787109375,
0.01200103759765625,
0.084228515625,
-0.03253173828125,
0.06341552734375,
-0.04248046875,
0.03619384765625,
0.03826904296875,
-0.01200103759765625,
0.02117919921875,
-0.006244659423828125,
-0.011749267578125,
0.030609130859375,
0.00400543212890625,
-0.036590576171875,
-0.043670654296875,
0.04473876953125,
-0.07861328125,
-0.01474761962890625,
-0.02178955078125,
-0.03955078125,
0.0118408203125,
0.0120697021484375,
0.035614013671875,
0.055450439453125,
0.0227813720703125,
0.02734375,
0.04827880859375,
-0.03125,
0.032135009765625,
-0.00780487060546875,
-0.01384735107421875,
-0.03985595703125,
0.060333251953125,
0.021942138671875,
0.01477813720703125,
0.0112762451171875,
0.01690673828125,
-0.027496337890625,
-0.046783447265625,
-0.021240234375,
0.03436279296875,
-0.04901123046875,
-0.037841796875,
-0.044189453125,
-0.03753662109375,
-0.03271484375,
0.00011456012725830078,
-0.034576416015625,
-0.0281524658203125,
-0.027313232421875,
0.013671875,
0.05389404296875,
0.051910400390625,
-0.00925445556640625,
0.04339599609375,
-0.038055419921875,
0.0110015869140625,
0.004993438720703125,
0.0445556640625,
0.003826141357421875,
-0.0596923828125,
-0.017242431640625,
-0.005340576171875,
-0.0290374755859375,
-0.05450439453125,
0.0296478271484375,
0.0162506103515625,
0.036834716796875,
0.032135009765625,
-0.00992584228515625,
0.049591064453125,
0.00978851318359375,
0.03289794921875,
0.031951904296875,
-0.041107177734375,
0.03961181640625,
-0.0007290840148925781,
0.010589599609375,
0.006870269775390625,
0.026641845703125,
-0.0250244140625,
0.00429534912109375,
-0.0657958984375,
-0.052032470703125,
0.0633544921875,
0.00836944580078125,
-0.0018310546875,
0.024444580078125,
0.060760498046875,
-0.003734588623046875,
0.001079559326171875,
-0.05609130859375,
-0.035491943359375,
-0.0223236083984375,
-0.014007568359375,
-0.0028553009033203125,
-0.0085601806640625,
-0.00927734375,
-0.04931640625,
0.04400634765625,
-0.008544921875,
0.062347412109375,
0.029632568359375,
-0.0012521743774414062,
-0.0079193115234375,
-0.0274810791015625,
0.0316162109375,
0.01506805419921875,
-0.0274810791015625,
0.005939483642578125,
0.0109100341796875,
-0.039764404296875,
0.01036834716796875,
0.00988006591796875,
-0.002689361572265625,
0.0037708282470703125,
0.041900634765625,
0.0728759765625,
0.0038738250732421875,
0.003719329833984375,
0.04119873046875,
-0.003963470458984375,
-0.042755126953125,
-0.0118560791015625,
0.00815582275390625,
-0.002773284912109375,
0.0296783447265625,
0.0195770263671875,
0.0279693603515625,
-0.0109710693359375,
-0.01427459716796875,
0.0198516845703125,
0.04473876953125,
-0.022491455078125,
-0.0343017578125,
0.05517578125,
-0.01470184326171875,
-0.006488800048828125,
0.06768798828125,
-0.0132904052734375,
-0.02276611328125,
0.08245849609375,
0.035491943359375,
0.0723876953125,
-0.00313568115234375,
0.008575439453125,
0.06488037109375,
0.019805908203125,
0.00372314453125,
0.015838623046875,
0.006183624267578125,
-0.057403564453125,
0.0020809173583984375,
-0.04290771484375,
0.008819580078125,
0.031524658203125,
-0.0438232421875,
0.0193939208984375,
-0.071533203125,
-0.036529541015625,
0.01117706298828125,
0.02593994140625,
-0.07025146484375,
0.0169677734375,
-0.002849578857421875,
0.0711669921875,
-0.06494140625,
0.06317138671875,
0.0626220703125,
-0.037139892578125,
-0.08642578125,
-0.006366729736328125,
-0.0001246929168701172,
-0.06402587890625,
0.04638671875,
0.042755126953125,
0.007579803466796875,
-0.002071380615234375,
-0.05218505859375,
-0.052459716796875,
0.10845947265625,
0.044921875,
0.0011968612670898438,
0.0167236328125,
0.0013637542724609375,
0.0191802978515625,
-0.0308990478515625,
0.039306640625,
0.0124359130859375,
0.0271148681640625,
0.029541015625,
-0.055084228515625,
0.021240234375,
-0.0238189697265625,
0.0123291015625,
0.0166015625,
-0.060760498046875,
0.07373046875,
-0.0389404296875,
-0.0158843994140625,
0.0013599395751953125,
0.050506591796875,
0.01015472412109375,
0.01447296142578125,
0.0440673828125,
0.056640625,
0.04193115234375,
-0.022003173828125,
0.0557861328125,
-0.007343292236328125,
0.043243408203125,
0.04388427734375,
0.0272064208984375,
0.038604736328125,
0.03204345703125,
-0.01593017578125,
0.025848388671875,
0.0709228515625,
-0.022796630859375,
0.0199737548828125,
0.0188140869140625,
-0.0033817291259765625,
-0.005939483642578125,
0.0034656524658203125,
-0.034698486328125,
0.037750244140625,
0.0046844482421875,
-0.036590576171875,
-0.023223876953125,
0.00368499755859375,
0.0031375885009765625,
-0.021209716796875,
-0.01346588134765625,
0.03485107421875,
0.00048065185546875,
-0.0237579345703125,
0.07086181640625,
0.0177001953125,
0.07501220703125,
-0.035888671875,
0.00028514862060546875,
-0.0257720947265625,
0.0124053955078125,
-0.041473388671875,
-0.05328369140625,
0.029998779296875,
-0.021087646484375,
-0.001659393310546875,
0.00626373291015625,
0.047576904296875,
-0.0202178955078125,
-0.03204345703125,
0.025665283203125,
0.0154266357421875,
0.0360107421875,
0.00606536865234375,
-0.08233642578125,
0.01363372802734375,
0.00001609325408935547,
-0.042510986328125,
0.033233642578125,
0.0309906005859375,
0.0010833740234375,
0.0579833984375,
0.052459716796875,
-0.007350921630859375,
0.01358795166015625,
-0.013214111328125,
0.064453125,
-0.03424072265625,
-0.021484375,
-0.052947998046875,
0.041229248046875,
-0.004367828369140625,
-0.04205322265625,
0.03717041015625,
0.04547119140625,
0.06304931640625,
0.002166748046875,
0.028350830078125,
-0.013702392578125,
-0.004730224609375,
-0.0258636474609375,
0.055572509765625,
-0.056640625,
-0.002170562744140625,
-0.01204681396484375,
-0.052978515625,
-0.037200927734375,
0.0557861328125,
-0.0207977294921875,
0.031707763671875,
0.0252838134765625,
0.08428955078125,
-0.029754638671875,
-0.019775390625,
0.0164794921875,
0.00786590576171875,
0.00832366943359375,
0.037109375,
0.025390625,
-0.058319091796875,
0.028564453125,
-0.04876708984375,
-0.021728515625,
-0.009185791015625,
-0.05255126953125,
-0.07562255859375,
-0.05999755859375,
-0.046051025390625,
-0.04779052734375,
-0.017364501953125,
0.07421875,
0.0823974609375,
-0.047454833984375,
-0.0190887451171875,
0.005016326904296875,
0.012237548828125,
-0.0206298828125,
-0.0167388916015625,
0.04559326171875,
-0.01129913330078125,
-0.046051025390625,
-0.0186920166015625,
0.004596710205078125,
0.0305633544921875,
0.0027942657470703125,
-0.0207977294921875,
-0.0138092041015625,
-0.015777587890625,
0.01454925537109375,
0.0270538330078125,
-0.04949951171875,
-0.01520538330078125,
-0.0203704833984375,
-0.004901885986328125,
0.03594970703125,
0.0311431884765625,
-0.043304443359375,
0.023712158203125,
0.029022216796875,
0.03167724609375,
0.057861328125,
-0.0312347412109375,
-0.007640838623046875,
-0.06158447265625,
0.04644775390625,
-0.00864410400390625,
0.0299224853515625,
0.033294677734375,
-0.0264739990234375,
0.03582763671875,
0.036773681640625,
-0.032623291015625,
-0.06878662109375,
-0.00475311279296875,
-0.07843017578125,
-0.003482818603515625,
0.0643310546875,
-0.032928466796875,
-0.03607177734375,
0.033233642578125,
0.00353240966796875,
0.051177978515625,
-0.006366729736328125,
0.032562255859375,
0.01181793212890625,
-0.016265869140625,
-0.04644775390625,
-0.0440673828125,
0.03662109375,
0.0087127685546875,
-0.041656494140625,
-0.03289794921875,
-0.002429962158203125,
0.06427001953125,
0.00937652587890625,
0.045684814453125,
-0.01496124267578125,
0.006084442138671875,
0.00415802001953125,
0.0338134765625,
-0.040374755859375,
-0.0124053955078125,
-0.0350341796875,
0.007717132568359375,
0.0018262863159179688,
-0.048126220703125
]
] |
hustvl/yolos-small | 2022-06-27T08:37:45.000Z | [
"transformers",
"pytorch",
"yolos",
"object-detection",
"vision",
"dataset:coco",
"arxiv:2106.00666",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | object-detection | hustvl | null | null | hustvl/yolos-small | 38 | 38,616 | transformers | 2022-04-26T09:38:22 | ---
license: apache-2.0
tags:
- object-detection
- vision
datasets:
- coco
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
example_title: Savanna
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
example_title: Football Match
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
example_title: Airport
---
# YOLOS (small-sized) model
YOLOS model fine-tuned on COCO 2017 object detection (118k annotated images). It was introduced in the paper [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://arxiv.org/abs/2106.00666) by Fang et al. and first released in [this repository](https://github.com/hustvl/YOLOS).
Disclaimer: The team releasing YOLOS did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN).
The model is trained using a "bipartite matching loss": one compares the predicted classes + bounding boxes of each of the N = 100 object queries to the ground truth annotations, padded up to the same length N (so if an image only contains 4 objects, 96 annotations will just have a "no object" as class and "no bounding box" as bounding box). The Hungarian matching algorithm is used to create an optimal one-to-one mapping between each of the N queries and each of the N annotations. Next, standard cross-entropy (for the classes) and a linear combination of the L1 and generalized IoU loss (for the bounding boxes) are used to optimize the parameters of the model.
## Intended uses & limitations
You can use the raw model for object detection. See the [model hub](https://huggingface.co/models?search=hustvl/yolos) to look for all available YOLOS models.
### How to use
Here is how to use this model:
```python
from transformers import YolosFeatureExtractor, YolosForObjectDetection
from PIL import Image
import requests
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = YolosFeatureExtractor.from_pretrained('hustvl/yolos-small')
model = YolosForObjectDetection.from_pretrained('hustvl/yolos-small')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
# model predicts bounding boxes and corresponding COCO classes
logits = outputs.logits
bboxes = outputs.pred_boxes
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The YOLOS model was pre-trained on [ImageNet-1k](https://huggingface.co/datasets/imagenet2012) and fine-tuned on [COCO 2017 object detection](https://cocodataset.org/#download), a dataset consisting of 118k/5k annotated images for training/validation respectively.
### Training
The model was pre-trained for 200 epochs on ImageNet-1k and fine-tuned for 150 epochs on COCO.
## Evaluation results
This model achieves an AP (average precision) of **36.1** on COCO 2017 validation. For more details regarding evaluation results, we refer to table 1 of the original paper.
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-2106-00666,
author = {Yuxin Fang and
Bencheng Liao and
Xinggang Wang and
Jiemin Fang and
Jiyang Qi and
Rui Wu and
Jianwei Niu and
Wenyu Liu},
title = {You Only Look at One Sequence: Rethinking Transformer in Vision through
Object Detection},
journal = {CoRR},
volume = {abs/2106.00666},
year = {2021},
url = {https://arxiv.org/abs/2106.00666},
eprinttype = {arXiv},
eprint = {2106.00666},
timestamp = {Fri, 29 Apr 2022 19:49:16 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-00666.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
``` | 4,173 | [
[
-0.054656982421875,
-0.043365478515625,
0.004756927490234375,
-0.01154327392578125,
-0.0211944580078125,
-0.0230255126953125,
0.00014030933380126953,
-0.06005859375,
0.01476287841796875,
0.03466796875,
-0.040863037109375,
-0.0288543701171875,
-0.040557861328125,
0.0279388427734375,
-0.0262603759765625,
0.06390380859375,
0.01543426513671875,
-0.025543212890625,
-0.0188446044921875,
-0.0207366943359375,
-0.02301025390625,
-0.0085296630859375,
-0.025115966796875,
-0.00830841064453125,
0.02642822265625,
0.025390625,
0.049652099609375,
0.053619384765625,
0.03680419921875,
0.0270538330078125,
-0.0300445556640625,
0.0145721435546875,
-0.0273590087890625,
-0.02349853515625,
0.0006699562072753906,
-0.04400634765625,
-0.03338623046875,
0.0020694732666015625,
0.0311279296875,
0.033050537109375,
0.00423431396484375,
0.022735595703125,
-0.0013275146484375,
0.041107177734375,
-0.056121826171875,
0.01361846923828125,
-0.04547119140625,
0.026153564453125,
-0.01702880859375,
0.004604339599609375,
-0.0321044921875,
-0.009246826171875,
0.016632080078125,
-0.0460205078125,
0.04742431640625,
0.01068878173828125,
0.09735107421875,
0.01541900634765625,
-0.0002472400665283203,
0.00846099853515625,
-0.02203369140625,
0.054412841796875,
-0.050018310546875,
0.0404052734375,
0.0192413330078125,
0.033538818359375,
0.005096435546875,
-0.0621337890625,
-0.04742431640625,
-0.013336181640625,
-0.023712158203125,
-0.00675201416015625,
-0.022125244140625,
-0.0172882080078125,
0.03704833984375,
0.0305633544921875,
-0.03704833984375,
-0.00399017333984375,
-0.05438232421875,
-0.029571533203125,
0.05157470703125,
0.002971649169921875,
0.0046234130859375,
-0.009613037109375,
-0.033447265625,
-0.02471923828125,
-0.03363037109375,
0.0286865234375,
0.0301361083984375,
0.00940704345703125,
-0.0174102783203125,
0.03619384765625,
-0.02716064453125,
0.07171630859375,
0.022247314453125,
-0.023162841796875,
0.031494140625,
-0.0138702392578125,
-0.0307159423828125,
0.0018329620361328125,
0.08416748046875,
0.0198516845703125,
0.01934814453125,
-0.01013946533203125,
0.001445770263671875,
0.0012807846069335938,
0.0254974365234375,
-0.06689453125,
-0.01433563232421875,
-0.00933074951171875,
-0.0280914306640625,
-0.04193115234375,
0.031494140625,
-0.064208984375,
0.0003361701965332031,
-0.0022602081298828125,
0.023712158203125,
-0.0160369873046875,
-0.0105438232421875,
0.0194854736328125,
0.00733184814453125,
0.038238525390625,
0.0182037353515625,
-0.04608154296875,
0.0095367431640625,
0.0224761962890625,
0.061859130859375,
-0.00884246826171875,
-0.0269317626953125,
-0.027587890625,
-0.036224365234375,
-0.036407470703125,
0.0667724609375,
-0.0089874267578125,
-0.016571044921875,
-0.0183258056640625,
0.043060302734375,
-0.00016117095947265625,
-0.0302734375,
0.0399169921875,
-0.02862548828125,
0.01306915283203125,
-0.014434814453125,
0.0014696121215820312,
-0.029632568359375,
0.0421142578125,
-0.048492431640625,
0.0760498046875,
0.0207366943359375,
-0.06072998046875,
0.0286102294921875,
-0.0297088623046875,
-0.0256805419921875,
-0.005817413330078125,
0.0016241073608398438,
-0.06842041015625,
0.00567626953125,
0.0321044921875,
0.024749755859375,
-0.0302276611328125,
0.0148773193359375,
-0.0421142578125,
-0.025360107421875,
0.01361846923828125,
-0.023651123046875,
0.0694580078125,
0.0136260986328125,
-0.0192413330078125,
0.00757598876953125,
-0.047515869140625,
0.00012218952178955078,
0.04449462890625,
0.000046312808990478516,
0.01690673828125,
-0.0184478759765625,
-0.0038738250732421875,
0.01557159423828125,
0.004741668701171875,
-0.045196533203125,
0.024261474609375,
-0.0301361083984375,
0.032012939453125,
0.0345458984375,
-0.0185546875,
0.024749755859375,
-0.01099395751953125,
0.0335693359375,
0.015716552734375,
0.040740966796875,
-0.042388916015625,
-0.058380126953125,
-0.05145263671875,
-0.00579071044921875,
-0.0027256011962890625,
0.01617431640625,
-0.0291595458984375,
0.053863525390625,
-0.01262664794921875,
-0.036285400390625,
-0.037628173828125,
-0.003814697265625,
0.0215301513671875,
0.059295654296875,
0.0389404296875,
-0.039642333984375,
-0.046173095703125,
-0.080078125,
0.0144500732421875,
0.00827789306640625,
0.0104522705078125,
0.0081329345703125,
0.048370361328125,
-0.01556396484375,
0.096435546875,
-0.055999755859375,
-0.03509521484375,
-0.01306915283203125,
-0.010650634765625,
0.0138702392578125,
0.0274658203125,
0.0657958984375,
-0.07525634765625,
-0.03924560546875,
0.004199981689453125,
-0.06414794921875,
0.006256103515625,
0.03271484375,
0.0018835067749023438,
0.019073486328125,
0.0256500244140625,
-0.01378631591796875,
0.0780029296875,
0.0157012939453125,
-0.0153961181640625,
0.04412841796875,
-0.00031113624572753906,
0.0084075927734375,
-0.055419921875,
0.01345062255859375,
0.008087158203125,
-0.0240478515625,
-0.04315185546875,
0.00806427001953125,
0.01531219482421875,
-0.0147247314453125,
-0.057647705078125,
0.0328369140625,
-0.03363037109375,
-0.0115814208984375,
-0.0310821533203125,
-0.005340576171875,
0.030609130859375,
0.05706787109375,
0.0177154541015625,
0.03173828125,
0.060638427734375,
-0.045806884765625,
0.025299072265625,
0.02410888671875,
-0.0301971435546875,
0.05120849609375,
-0.06298828125,
0.02093505859375,
-0.017303466796875,
0.015869140625,
-0.06158447265625,
-0.0142974853515625,
0.0438232421875,
-0.02783203125,
0.034271240234375,
-0.030181884765625,
-0.01273345947265625,
-0.08319091796875,
-0.033477783203125,
0.043701171875,
0.020111083984375,
-0.05035400390625,
0.03125,
0.0038280487060546875,
0.037567138671875,
-0.065673828125,
-0.066162109375,
-0.010833740234375,
-0.00634002685546875,
-0.045379638671875,
0.0255889892578125,
-0.01551055908203125,
0.0204925537109375,
0.00957489013671875,
-0.02880859375,
0.005992889404296875,
-0.0013551712036132812,
0.01904296875,
0.043304443359375,
-0.0211334228515625,
-0.0238037109375,
-0.0204925537109375,
-0.0175018310546875,
-0.0146331787109375,
-0.0263214111328125,
0.046142578125,
-0.041229248046875,
-0.029052734375,
-0.054351806640625,
0.0011034011840820312,
0.050018310546875,
-0.034332275390625,
0.049835205078125,
0.0638427734375,
-0.04034423828125,
0.0177001953125,
-0.052337646484375,
-0.00664520263671875,
-0.036529541015625,
0.0289764404296875,
-0.0343017578125,
-0.03839111328125,
0.05169677734375,
0.038665771484375,
-0.0152435302734375,
0.050323486328125,
0.033782958984375,
0.01338958740234375,
0.06060791015625,
0.04400634765625,
-0.01016998291015625,
0.037811279296875,
-0.06744384765625,
0.0254058837890625,
-0.07733154296875,
-0.05169677734375,
-0.036407470703125,
-0.0255126953125,
-0.04010009765625,
-0.041473388671875,
0.0251617431640625,
0.032745361328125,
-0.023193359375,
0.07012939453125,
-0.06951904296875,
0.032012939453125,
0.042633056640625,
0.0357666015625,
0.01287841796875,
-0.00872802734375,
0.01268768310546875,
0.01107025146484375,
-0.0577392578125,
-0.0180206298828125,
0.07598876953125,
0.0235595703125,
0.056121826171875,
-0.026153564453125,
0.034759521484375,
0.006847381591796875,
0.0238494873046875,
-0.07135009765625,
0.0386962890625,
0.0096282958984375,
-0.05511474609375,
-0.0107879638671875,
-0.0169830322265625,
-0.07183837890625,
0.0172882080078125,
-0.02093505859375,
-0.08038330078125,
0.05072021484375,
0.012725830078125,
-0.0146331787109375,
0.041412353515625,
-0.04150390625,
0.08673095703125,
-0.025177001953125,
-0.03936767578125,
0.02813720703125,
-0.06292724609375,
0.0281829833984375,
0.0013141632080078125,
-0.01192474365234375,
-0.008544921875,
0.02777099609375,
0.05810546875,
-0.032073974609375,
0.049591064453125,
-0.0033626556396484375,
0.00989532470703125,
0.062255859375,
-0.0015516281127929688,
0.034027099609375,
0.0046234130859375,
0.0048370361328125,
0.049072265625,
0.003925323486328125,
-0.023681640625,
-0.022369384765625,
0.03363037109375,
-0.0438232421875,
-0.042388916015625,
-0.0297088623046875,
-0.043426513671875,
0.0240631103515625,
0.0282135009765625,
0.063720703125,
0.02606201171875,
-0.00357818603515625,
0.0243377685546875,
0.03631591796875,
-0.025726318359375,
0.036590576171875,
0.017242431640625,
-0.01464080810546875,
-0.01580810546875,
0.05670166015625,
-0.0015459060668945312,
0.0159759521484375,
0.0287628173828125,
0.04180908203125,
-0.026336669921875,
-0.0234222412109375,
-0.0285186767578125,
0.016265869140625,
-0.045806884765625,
-0.050994873046875,
-0.0455322265625,
-0.0203704833984375,
-0.058319091796875,
-0.015228271484375,
-0.048431396484375,
0.0034236907958984375,
-0.0271148681640625,
0.00225830078125,
0.0162506103515625,
0.03466796875,
0.0018157958984375,
0.0289459228515625,
-0.0301055908203125,
0.032379150390625,
0.02728271484375,
0.027740478515625,
-0.0014104843139648438,
-0.05108642578125,
-0.012451171875,
0.010467529296875,
-0.04278564453125,
-0.0640869140625,
0.033935546875,
-0.0009064674377441406,
0.042938232421875,
0.06549072265625,
-0.0017213821411132812,
0.05902099609375,
-0.01392364501953125,
0.04095458984375,
0.04205322265625,
-0.0611572265625,
0.051727294921875,
0.004703521728515625,
0.0118408203125,
0.028411865234375,
0.0180206298828125,
-0.0244903564453125,
-0.0018606185913085938,
-0.053955078125,
-0.039764404296875,
0.08758544921875,
0.00814056396484375,
-0.020477294921875,
0.0042877197265625,
0.015045166015625,
-0.0007991790771484375,
0.01324462890625,
-0.0728759765625,
-0.0250396728515625,
-0.04254150390625,
-0.004955291748046875,
-0.003993988037109375,
-0.002399444580078125,
0.003360748291015625,
-0.035552978515625,
0.0277252197265625,
-0.0245819091796875,
0.050323486328125,
0.0279998779296875,
-0.01329803466796875,
-0.0177764892578125,
-0.014190673828125,
0.038818359375,
0.0284423828125,
-0.0279693603515625,
-0.01187896728515625,
0.0157012939453125,
-0.032928466796875,
-0.00798797607421875,
0.006031036376953125,
-0.0224456787109375,
-0.0152435302734375,
0.0400390625,
0.072021484375,
0.013641357421875,
-0.0299224853515625,
0.04595947265625,
0.0222930908203125,
-0.01218414306640625,
-0.003643035888671875,
0.016510009765625,
-0.02191162109375,
0.022003173828125,
0.03271484375,
0.0290374755859375,
0.0033779144287109375,
-0.048095703125,
0.01454925537109375,
0.03057861328125,
-0.0259552001953125,
-0.0292510986328125,
0.06640625,
-0.0259552001953125,
-0.0386962890625,
0.036651611328125,
-0.0273590087890625,
-0.061553955078125,
0.07940673828125,
0.038848876953125,
0.05438232421875,
-0.016754150390625,
0.0031871795654296875,
0.06304931640625,
0.024749755859375,
-0.028717041015625,
-0.0273590087890625,
-0.0167388916015625,
-0.0643310546875,
0.0033111572265625,
-0.042236328125,
-0.00453948974609375,
0.00821685791015625,
-0.068115234375,
0.044677734375,
-0.0158538818359375,
-0.007415771484375,
-0.001739501953125,
0.003910064697265625,
-0.0894775390625,
0.02044677734375,
0.018096923828125,
0.06451416015625,
-0.059234619140625,
0.055755615234375,
0.034881591796875,
-0.037628173828125,
-0.048675537109375,
-0.020477294921875,
-0.0009255409240722656,
-0.07940673828125,
0.036285400390625,
0.045318603515625,
-0.002498626708984375,
-0.00832366943359375,
-0.058746337890625,
-0.05670166015625,
0.10040283203125,
0.0198822021484375,
-0.045318603515625,
-0.00272369384765625,
-0.0014390945434570312,
0.02587890625,
-0.03326416015625,
0.03564453125,
0.039093017578125,
0.035430908203125,
0.0296630859375,
-0.051483154296875,
-0.013916015625,
-0.0006928443908691406,
-0.001667022705078125,
0.0136260986328125,
-0.04730224609375,
0.056976318359375,
-0.04132080078125,
-0.0072174072265625,
0.01036834716796875,
0.043060302734375,
0.00849151611328125,
0.044281005859375,
0.0496826171875,
0.063232421875,
0.03717041015625,
-0.01806640625,
0.07666015625,
-0.0006151199340820312,
0.056671142578125,
0.068115234375,
0.00696563720703125,
0.0262298583984375,
0.0233917236328125,
-0.028411865234375,
0.02166748046875,
0.044586181640625,
-0.024658203125,
0.042633056640625,
-0.0018396377563476562,
0.0247955322265625,
-0.007251739501953125,
-0.004978179931640625,
-0.039031982421875,
0.045623779296875,
0.01061248779296875,
-0.017242431640625,
-0.0106353759765625,
0.0238800048828125,
-0.01355743408203125,
-0.01412200927734375,
-0.0201568603515625,
0.0270233154296875,
-0.0138092041015625,
-0.043212890625,
0.04510498046875,
-0.005176544189453125,
0.05889892578125,
-0.03839111328125,
0.0170745849609375,
-0.0274658203125,
0.003376007080078125,
-0.0258636474609375,
-0.047760009765625,
0.0244293212890625,
-0.0019588470458984375,
0.0016870498657226562,
0.0116119384765625,
0.061309814453125,
-0.0185546875,
-0.054290771484375,
0.0229949951171875,
0.0092620849609375,
0.00909423828125,
-0.0178375244140625,
-0.052825927734375,
0.0203857421875,
0.003810882568359375,
-0.035675048828125,
0.00563812255859375,
0.0233612060546875,
-0.005657196044921875,
0.050140380859375,
0.037506103515625,
-0.0169677734375,
0.01611328125,
-0.01494598388671875,
0.064697265625,
-0.038238525390625,
-0.0295257568359375,
-0.043609619140625,
0.033447265625,
-0.007358551025390625,
-0.024749755859375,
0.0313720703125,
0.04638671875,
0.08917236328125,
-0.0162200927734375,
0.008087158203125,
-0.03497314453125,
-0.00449371337890625,
-0.004100799560546875,
0.0218048095703125,
-0.058197021484375,
0.0037441253662109375,
-0.027069091796875,
-0.069580078125,
-0.021514892578125,
0.07354736328125,
-0.020263671875,
0.0054473876953125,
0.045196533203125,
0.06890869140625,
-0.0291595458984375,
-0.01107025146484375,
0.03375244140625,
0.004673004150390625,
0.0167083740234375,
0.04736328125,
0.033050537109375,
-0.07720947265625,
0.04925537109375,
-0.056121826171875,
0.000453948974609375,
-0.04095458984375,
-0.059295654296875,
-0.06903076171875,
-0.0438232421875,
-0.0445556640625,
-0.022247314453125,
-0.024169921875,
0.036895751953125,
0.08929443359375,
-0.060089111328125,
0.007244110107421875,
-0.01348876953125,
0.0207672119140625,
-0.03216552734375,
-0.0213165283203125,
0.030303955078125,
0.0055389404296875,
-0.06982421875,
0.0159149169921875,
0.0178680419921875,
0.0135040283203125,
-0.01050567626953125,
-0.0205841064453125,
-0.018096923828125,
-0.0286712646484375,
0.041717529296875,
0.039703369140625,
-0.055877685546875,
-0.026031494140625,
0.013580322265625,
0.0033283233642578125,
0.036407470703125,
0.054168701171875,
-0.07366943359375,
0.051544189453125,
0.032623291015625,
0.0210418701171875,
0.06951904296875,
-0.00444793701171875,
-0.0078125,
-0.035736083984375,
0.052215576171875,
0.00980377197265625,
0.042236328125,
0.020050048828125,
-0.0283355712890625,
0.051727294921875,
0.044342041015625,
-0.0222930908203125,
-0.06756591796875,
0.01244354248046875,
-0.10601806640625,
-0.01088714599609375,
0.038787841796875,
-0.0172882080078125,
-0.037506103515625,
0.01194000244140625,
-0.006969451904296875,
0.03515625,
-0.006732940673828125,
0.04656982421875,
0.016265869140625,
0.00696563720703125,
-0.03424072265625,
-0.02203369140625,
0.0011510848999023438,
-0.004947662353515625,
-0.05279541015625,
-0.033477783203125,
0.01187896728515625,
0.031768798828125,
0.04296875,
0.0208587646484375,
-0.01885986328125,
0.02081298828125,
-0.0035247802734375,
0.019012451171875,
-0.0423583984375,
-0.04254150390625,
-0.01094818115234375,
0.008697509765625,
-0.027099609375,
-0.040283203125
]
] |
sentence-transformers/msmarco-bert-base-dot-v5 | 2023-11-02T09:31:35.000Z | [
"sentence-transformers",
"pytorch",
"tf",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"en",
"arxiv:1908.10084",
"endpoints_compatible",
"has_space",
"region:us"
] | sentence-similarity | sentence-transformers | null | null | sentence-transformers/msmarco-bert-base-dot-v5 | 11 | 38,462 | sentence-transformers | 2022-03-02T23:29:05 | ---
language:
- en
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# msmarco-bert-base-dot-v5
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for **semantic search**. It has been trained on 500K (query, answer) pairs from the [MS MARCO dataset](https://github.com/microsoft/MSMARCO-Passage-Ranking/). For an introduction to semantic search, have a look at: [SBERT.net - Semantic Search](https://www.sbert.net/examples/applications/semantic-search/README.html)
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer, util
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
#Load the model
model = SentenceTransformer('sentence-transformers/msmarco-bert-base-dot-v5')
#Encode query and documents
query_emb = model.encode(query)
doc_emb = model.encode(docs)
#Compute dot score between query and all document embeddings
scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
print("Query:", query)
for doc, score in doc_score_pairs:
print(score, doc)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the correct pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output.last_hidden_state
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
#Encode text
def encode(texts):
# Tokenize sentences
encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input, return_dict=True)
# Perform pooling
embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
return embeddings
# Sentences we want sentence embeddings for
query = "How many people live in London?"
docs = ["Around 9 Million people live in London", "London is known for its financial district"]
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/msmarco-bert-base-dot-v5")
model = AutoModel.from_pretrained("sentence-transformers/msmarco-bert-base-dot-v5")
#Encode query and docs
query_emb = encode(query)
doc_emb = encode(docs)
#Compute dot score between query and all document embeddings
scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
#Combine docs & scores
doc_score_pairs = list(zip(docs, scores))
#Sort by decreasing score
doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
#Output passages & scores
print("Query:", query)
for doc, score in doc_score_pairs:
print(score, doc)
```
## Technical Details
In the following some technical details how this model must be used:
| Setting | Value |
| --- | :---: |
| Dimensions | 768 |
| Max Sequence Length | 512 |
| Produces normalized embeddings | No |
| Pooling-Method | Mean pooling |
| Suitable score functions | dot-product (e.g. `util.dot_score`) |
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=msmarco-bert-base-base-dot-v5)
## Training
See `train_script.py` in this repository for the used training script.
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 7858 with parameters:
```
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.MarginMSELoss.MarginMSELoss`
Parameters of the fit()-Method:
```
{
"callback": null,
"epochs": 30,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"lr": 1e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 10000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: bert-base-uncased
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
``` | 6,156 | [
[
-0.0178070068359375,
-0.05938720703125,
0.031829833984375,
0.017547607421875,
-0.017730712890625,
-0.029266357421875,
-0.0256195068359375,
-0.006908416748046875,
0.01244354248046875,
0.0267333984375,
-0.03997802734375,
-0.0499267578125,
-0.051788330078125,
0.007778167724609375,
-0.027923583984375,
0.065185546875,
-0.0035724639892578125,
0.01178741455078125,
-0.021881103515625,
-0.01157379150390625,
-0.018035888671875,
-0.02386474609375,
-0.0302734375,
-0.01654052734375,
0.0225677490234375,
0.0177764892578125,
0.037078857421875,
0.030975341796875,
0.02581787109375,
0.030975341796875,
-0.00601959228515625,
0.016571044921875,
-0.031890869140625,
0.0029621124267578125,
0.00261688232421875,
-0.031768798828125,
-0.006923675537109375,
0.0182342529296875,
0.04400634765625,
0.03546142578125,
-0.00982666015625,
0.004047393798828125,
0.00324249267578125,
0.0338134765625,
-0.0224456787109375,
0.03045654296875,
-0.045806884765625,
0.004573822021484375,
0.00640869140625,
-0.004611968994140625,
-0.044952392578125,
-0.020751953125,
0.0240020751953125,
-0.032806396484375,
0.0251007080078125,
0.01335906982421875,
0.0965576171875,
0.0185699462890625,
-0.019195556640625,
-0.04052734375,
-0.01500701904296875,
0.0621337890625,
-0.06756591796875,
0.0185089111328125,
0.0267333984375,
0.0008230209350585938,
-0.005283355712890625,
-0.07293701171875,
-0.05279541015625,
-0.016357421875,
-0.025482177734375,
0.0182037353515625,
-0.013031005859375,
-0.004222869873046875,
0.010772705078125,
0.01297760009765625,
-0.055877685546875,
-0.005886077880859375,
-0.04229736328125,
-0.018310546875,
0.049896240234375,
0.007556915283203125,
0.01690673828125,
-0.0401611328125,
-0.03515625,
-0.0302581787109375,
-0.0165252685546875,
0.011749267578125,
0.020263671875,
0.0164947509765625,
-0.0135345458984375,
0.05511474609375,
0.0007433891296386719,
0.04718017578125,
-0.005809783935546875,
0.01299285888671875,
0.044891357421875,
-0.0220489501953125,
-0.0185394287109375,
-0.0010223388671875,
0.08111572265625,
0.0255279541015625,
0.025665283203125,
-0.0016918182373046875,
-0.0167388916015625,
-0.0042572021484375,
0.0205535888671875,
-0.060638427734375,
-0.02362060546875,
0.0219268798828125,
-0.0300445556640625,
-0.02459716796875,
0.0158538818359375,
-0.04278564453125,
-0.006671905517578125,
0.00339508056640625,
0.060150146484375,
-0.059356689453125,
0.0164031982421875,
0.024383544921875,
-0.0228424072265625,
0.0243988037109375,
-0.0102386474609375,
-0.052459716796875,
0.006511688232421875,
0.01959228515625,
0.06695556640625,
0.012420654296875,
-0.03851318359375,
-0.01910400390625,
-0.00968170166015625,
-0.0016603469848632812,
0.051177978515625,
-0.0311737060546875,
-0.0224761962890625,
0.00838470458984375,
0.0176239013671875,
-0.0421142578125,
-0.017974853515625,
0.055450439453125,
-0.0242462158203125,
0.062347412109375,
-0.00347137451171875,
-0.068603515625,
-0.01522064208984375,
0.01233673095703125,
-0.037994384765625,
0.0919189453125,
0.011749267578125,
-0.06787109375,
0.004398345947265625,
-0.058746337890625,
-0.026275634765625,
-0.01666259765625,
-0.00021529197692871094,
-0.05072021484375,
0.00144195556640625,
0.0391845703125,
0.051483154296875,
0.001766204833984375,
0.00931549072265625,
-0.0134429931640625,
-0.03448486328125,
0.03057861328125,
-0.0244903564453125,
0.0838623046875,
0.009979248046875,
-0.0277252197265625,
0.00823211669921875,
-0.044891357421875,
0.0027313232421875,
0.0245819091796875,
-0.024932861328125,
-0.01058197021484375,
0.0032482147216796875,
0.0179901123046875,
0.023345947265625,
0.023773193359375,
-0.045745849609375,
0.0216522216796875,
-0.04180908203125,
0.054656982421875,
0.052734375,
0.0007429122924804688,
0.0293731689453125,
-0.0263671875,
0.016387939453125,
0.01367950439453125,
-0.000025093555450439453,
-0.011474609375,
-0.043304443359375,
-0.0687255859375,
-0.0222320556640625,
0.033111572265625,
0.040313720703125,
-0.050537109375,
0.07318115234375,
-0.037261962890625,
-0.0423583984375,
-0.07000732421875,
-0.0038471221923828125,
0.00958251953125,
0.042205810546875,
0.0452880859375,
-0.00382232666015625,
-0.037689208984375,
-0.068359375,
-0.00878143310546875,
0.00643157958984375,
-0.0016956329345703125,
0.0274200439453125,
0.05548095703125,
-0.0262298583984375,
0.07354736328125,
-0.056640625,
-0.040740966796875,
-0.02838134765625,
0.01294708251953125,
0.02923583984375,
0.0391845703125,
0.035614013671875,
-0.04840087890625,
-0.0362548828125,
-0.04034423828125,
-0.054840087890625,
-0.0012025833129882812,
-0.01491546630859375,
-0.00983428955078125,
0.0192718505859375,
0.04205322265625,
-0.050079345703125,
0.0215911865234375,
0.03436279296875,
-0.044921875,
0.031036376953125,
-0.033721923828125,
-0.0068206787109375,
-0.099853515625,
0.003429412841796875,
0.0024356842041015625,
-0.0110626220703125,
-0.0281219482421875,
-0.0005893707275390625,
0.01031494140625,
-0.0064239501953125,
-0.0303802490234375,
0.029876708984375,
-0.0369873046875,
0.0121002197265625,
0.0135955810546875,
0.03851318359375,
0.007389068603515625,
0.053314208984375,
-0.00981903076171875,
0.054107666015625,
0.042694091796875,
-0.034820556640625,
0.0167388916015625,
0.042694091796875,
-0.042694091796875,
0.01219940185546875,
-0.05877685546875,
0.004947662353515625,
-0.0057220458984375,
0.01849365234375,
-0.093994140625,
0.0021419525146484375,
0.00830841064453125,
-0.0557861328125,
0.0159149169921875,
0.0213623046875,
-0.0537109375,
-0.037994384765625,
-0.036773681640625,
-0.004390716552734375,
0.038543701171875,
-0.03143310546875,
0.038177490234375,
0.01137542724609375,
0.0002722740173339844,
-0.044464111328125,
-0.0723876953125,
-0.00698089599609375,
-0.004608154296875,
-0.061126708984375,
0.033416748046875,
-0.007564544677734375,
0.0162353515625,
0.0167388916015625,
0.013763427734375,
0.005619049072265625,
-0.0010023117065429688,
0.00032138824462890625,
0.0212249755859375,
-0.0036907196044921875,
0.01537322998046875,
0.00623321533203125,
-0.0032939910888671875,
0.00833892822265625,
-0.01568603515625,
0.05694580078125,
-0.015625,
-0.006359100341796875,
-0.02459716796875,
0.01513671875,
0.032867431640625,
-0.0211944580078125,
0.08563232421875,
0.0758056640625,
-0.018707275390625,
-0.01145172119140625,
-0.033416748046875,
-0.019500732421875,
-0.03594970703125,
0.0418701171875,
-0.021484375,
-0.060516357421875,
0.034912109375,
0.024200439453125,
0.0027408599853515625,
0.055084228515625,
0.04376220703125,
-0.0277252197265625,
0.06329345703125,
0.0294647216796875,
-0.009521484375,
0.0379638671875,
-0.05291748046875,
0.01378631591796875,
-0.063232421875,
-0.01209259033203125,
-0.02972412109375,
-0.030059814453125,
-0.054656982421875,
-0.030364990234375,
0.025390625,
-0.005237579345703125,
-0.01374053955078125,
0.041656494140625,
-0.04833984375,
0.01351165771484375,
0.0496826171875,
0.020904541015625,
-0.00719451904296875,
0.0010404586791992188,
-0.045501708984375,
-0.00946807861328125,
-0.053253173828125,
-0.0374755859375,
0.0831298828125,
0.0278167724609375,
0.032989501953125,
-0.00443267822265625,
0.056243896484375,
0.0137481689453125,
-0.0035858154296875,
-0.052276611328125,
0.04425048828125,
-0.01421356201171875,
-0.038360595703125,
-0.0284881591796875,
-0.0289306640625,
-0.0797119140625,
0.034210205078125,
-0.01849365234375,
-0.05157470703125,
0.0028972625732421875,
-0.024871826171875,
-0.0160064697265625,
0.01389312744140625,
-0.06536865234375,
0.07720947265625,
0.0011997222900390625,
-0.0124359130859375,
-0.01093292236328125,
-0.056915283203125,
0.00824737548828125,
0.0222930908203125,
0.0103912353515625,
-0.00213623046875,
-0.0022869110107421875,
0.06634521484375,
-0.0284576416015625,
0.057098388671875,
-0.01006317138671875,
0.007167816162109375,
0.0218963623046875,
-0.0214691162109375,
0.030914306640625,
-0.01068878173828125,
-0.011993408203125,
0.006237030029296875,
-0.00641632080078125,
-0.03717041015625,
-0.034088134765625,
0.0511474609375,
-0.0703125,
-0.0246734619140625,
-0.042205810546875,
-0.04754638671875,
-0.005893707275390625,
0.018096923828125,
0.03662109375,
0.033477783203125,
-0.005336761474609375,
0.03570556640625,
0.0469970703125,
-0.025238037109375,
0.056121826171875,
0.02587890625,
0.0027675628662109375,
-0.041717529296875,
0.050201416015625,
0.015533447265625,
0.0026988983154296875,
0.033477783203125,
0.0134735107421875,
-0.035797119140625,
-0.02264404296875,
-0.01715087890625,
0.03411865234375,
-0.04766845703125,
-0.008697509765625,
-0.060028076171875,
-0.03387451171875,
-0.05535888671875,
-0.006237030029296875,
-0.0104217529296875,
-0.026336669921875,
-0.033721923828125,
-0.0186920166015625,
0.020904541015625,
0.036773681640625,
0.00589752197265625,
0.0196990966796875,
-0.046478271484375,
0.0084991455078125,
0.00815582275390625,
0.01019287109375,
-0.01226043701171875,
-0.059906005859375,
-0.032501220703125,
-0.0012483596801757812,
-0.03173828125,
-0.07110595703125,
0.046722412109375,
0.0152740478515625,
0.045684814453125,
0.017608642578125,
0.0096282958984375,
0.04071044921875,
-0.042755126953125,
0.0699462890625,
-0.005100250244140625,
-0.070556640625,
0.042724609375,
-0.0084991455078125,
0.0300140380859375,
0.03582763671875,
0.02874755859375,
-0.03546142578125,
-0.035400390625,
-0.060150146484375,
-0.0770263671875,
0.05517578125,
0.040130615234375,
0.0213775634765625,
-0.0120849609375,
0.0113525390625,
-0.01806640625,
0.01107025146484375,
-0.0731201171875,
-0.03594970703125,
-0.02056884765625,
-0.04180908203125,
-0.0240020751953125,
-0.0158843994140625,
0.0036907196044921875,
-0.033355712890625,
0.061676025390625,
0.0027561187744140625,
0.05499267578125,
0.0399169921875,
-0.03472900390625,
0.022674560546875,
0.012481689453125,
0.051971435546875,
0.0235443115234375,
-0.02374267578125,
-0.0012369155883789062,
0.0169525146484375,
-0.037689208984375,
-0.00820159912109375,
0.037139892578125,
-0.004558563232421875,
0.022674560546875,
0.041290283203125,
0.06524658203125,
0.0281829833984375,
-0.0379638671875,
0.054779052734375,
-0.00720977783203125,
-0.026092529296875,
-0.0307159423828125,
-0.0030364990234375,
0.0175323486328125,
0.01788330078125,
0.0290374755859375,
-0.00295257568359375,
-0.00010347366333007812,
-0.027862548828125,
0.02349853515625,
0.01934814453125,
-0.031982421875,
-0.00054931640625,
0.052398681640625,
0.0034694671630859375,
-0.01482391357421875,
0.068359375,
-0.015228271484375,
-0.051177978515625,
0.0380859375,
0.035858154296875,
0.06787109375,
0.000583648681640625,
0.0153656005859375,
0.036865234375,
0.03759765625,
0.0079498291015625,
0.01428985595703125,
0.0005130767822265625,
-0.06475830078125,
-0.003448486328125,
-0.0439453125,
0.0026569366455078125,
-0.004924774169921875,
-0.047332763671875,
0.0248565673828125,
-0.00792694091796875,
-0.005035400390625,
-0.007793426513671875,
0.0203704833984375,
-0.057373046875,
0.01145172119140625,
0.005245208740234375,
0.07403564453125,
-0.06524658203125,
0.07574462890625,
0.048736572265625,
-0.062347412109375,
-0.05938720703125,
0.00018036365509033203,
-0.028076171875,
-0.0665283203125,
0.0341796875,
0.032989501953125,
0.0157470703125,
0.0152587890625,
-0.039276123046875,
-0.056640625,
0.10986328125,
0.018463134765625,
-0.0281219482421875,
-0.022003173828125,
0.00469970703125,
0.0447998046875,
-0.0273895263671875,
0.037506103515625,
0.0309600830078125,
0.03118896484375,
-0.00847625732421875,
-0.04888916015625,
0.00554656982421875,
-0.0185394287109375,
0.00800323486328125,
-0.00933837890625,
-0.045196533203125,
0.0687255859375,
-0.01031494140625,
-0.009124755859375,
0.00396728515625,
0.056732177734375,
0.020233154296875,
0.0026226043701171875,
0.031280517578125,
0.0638427734375,
0.05670166015625,
-0.013427734375,
0.080322265625,
-0.0290679931640625,
0.0626220703125,
0.06939697265625,
0.007572174072265625,
0.07940673828125,
0.0306243896484375,
-0.0180511474609375,
0.060699462890625,
0.047943115234375,
-0.02154541015625,
0.050079345703125,
0.01396942138671875,
0.004825592041015625,
-0.0015354156494140625,
0.02392578125,
-0.0253753662109375,
0.036865234375,
0.0192413330078125,
-0.058319091796875,
-0.00917816162109375,
0.0033740997314453125,
0.01263427734375,
0.0019321441650390625,
0.004791259765625,
0.0467529296875,
0.005352020263671875,
-0.036529541015625,
0.0469970703125,
0.01056671142578125,
0.06610107421875,
-0.04180908203125,
0.0176544189453125,
-0.01183319091796875,
0.02056884765625,
-0.0026454925537109375,
-0.0596923828125,
0.01442718505859375,
-0.0164947509765625,
-0.01255035400390625,
-0.022552490234375,
0.035369873046875,
-0.049468994140625,
-0.049346923828125,
0.027984619140625,
0.0313720703125,
0.015533447265625,
0.00324249267578125,
-0.08001708984375,
-0.006946563720703125,
0.01000213623046875,
-0.042572021484375,
0.00786590576171875,
0.032501220703125,
0.02801513671875,
0.04095458984375,
0.037384033203125,
-0.008453369140625,
0.0106658935546875,
0.007205963134765625,
0.058349609375,
-0.05450439453125,
-0.037994384765625,
-0.06402587890625,
0.049285888671875,
-0.0216522216796875,
-0.032928466796875,
0.05352783203125,
0.050201416015625,
0.0633544921875,
-0.018035888671875,
0.041290283203125,
-0.01471710205078125,
0.0254364013671875,
-0.04510498046875,
0.07318115234375,
-0.04205322265625,
0.01096343994140625,
-0.014190673828125,
-0.0655517578125,
-0.00988006591796875,
0.06842041015625,
-0.0308380126953125,
0.005611419677734375,
0.07000732421875,
0.06781005859375,
-0.00005537271499633789,
-0.015167236328125,
0.0158233642578125,
0.035125732421875,
0.019073486328125,
0.044647216796875,
0.0231781005859375,
-0.069091796875,
0.058441162109375,
-0.02972412109375,
0.0058746337890625,
-0.017486572265625,
-0.051239013671875,
-0.0701904296875,
-0.06903076171875,
-0.0232696533203125,
-0.03271484375,
-0.0067901611328125,
0.07171630859375,
0.038726806640625,
-0.055450439453125,
-0.01003265380859375,
-0.00740814208984375,
-0.0031223297119140625,
-0.0139617919921875,
-0.0269622802734375,
0.04608154296875,
-0.049530029296875,
-0.063720703125,
0.018157958984375,
-0.01274871826171875,
-0.004352569580078125,
-0.020904541015625,
0.0023860931396484375,
-0.057098388671875,
0.0154571533203125,
0.041717529296875,
-0.0189056396484375,
-0.056060791015625,
-0.0203704833984375,
0.0087432861328125,
-0.03887939453125,
0.0036640167236328125,
0.023345947265625,
-0.053955078125,
0.03302001953125,
0.0389404296875,
0.03729248046875,
0.053741455078125,
-0.01116943359375,
0.032867431640625,
-0.065185546875,
0.007015228271484375,
0.0137786865234375,
0.053131103515625,
0.02972412109375,
-0.0240020751953125,
0.0467529296875,
0.0226898193359375,
-0.041900634765625,
-0.050506591796875,
-0.018402099609375,
-0.0819091796875,
-0.031829833984375,
0.08154296875,
-0.0243682861328125,
-0.0280609130859375,
0.019744873046875,
-0.0238800048828125,
0.032135009765625,
-0.03277587890625,
0.058258056640625,
0.0703125,
-0.00255584716796875,
-0.01349639892578125,
-0.035430908203125,
0.01751708984375,
0.037322998046875,
-0.03900146484375,
-0.028564453125,
0.01528167724609375,
0.032806396484375,
0.016754150390625,
0.026031494140625,
-0.0025920867919921875,
0.0016460418701171875,
0.004329681396484375,
0.012176513671875,
-0.01311492919921875,
0.0086212158203125,
-0.0308837890625,
0.016845703125,
-0.0325927734375,
-0.03607177734375
]
] |
baichuan-inc/Baichuan2-13B-Chat | 2023-10-19T03:19:30.000Z | [
"transformers",
"pytorch",
"baichuan",
"text-generation",
"custom_code",
"en",
"zh",
"license:other",
"endpoints_compatible",
"has_space",
"region:us"
] | text-generation | baichuan-inc | null | null | baichuan-inc/Baichuan2-13B-Chat | 295 | 38,110 | transformers | 2023-08-29T02:30:01 | ---
language:
- en
- zh
license: other
tasks:
- text-generation
---
<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<div align="center">
<h1>
Baichuan 2
</h1>
</div>
<div align="center">
<a href="https://github.com/baichuan-inc/Baichuan2" target="_blank">🦉GitHub</a> | <a href="https://github.com/baichuan-inc/Baichuan-7B/blob/main/media/wechat.jpeg?raw=true" target="_blank">💬WeChat</a>
</div>
<div align="center">
🚀 <a href="https://www.baichuan-ai.com/" target="_blank">百川大模型在线对话平台</a> 已正式向公众开放 🎉
</div>
# 目录/Table of Contents
- [📖 模型介绍/Introduction](#Introduction)
- [⚙️ 快速开始/Quick Start](#Start)
- [📊 Benchmark评估/Benchmark Evaluation](#Benchmark)
- [📜 声明与协议/Terms and Conditions](#Terms)
# <span id="Introduction">模型介绍/Introduction</span>
Baichuan 2 是[百川智能]推出的新一代开源大语言模型，采用 **2.6 万亿** Tokens 的高质量语料训练，在权威的中文和英文 benchmark
上均取得同尺寸最好的效果。本次发布包含有 7B、13B 的 Base 和 Chat 版本，并提供了 Chat 版本的 4bits
量化，所有版本不仅对学术研究完全开放，开发者也仅需[邮件申请]并获得官方商用许可后，即可以免费商用。具体发布版本和下载见下表：
Baichuan 2 is the new generation of large-scale open-source language models launched by [Baichuan Intelligence inc.](https://www.baichuan-ai.com/).
It is trained on a high-quality corpus with 2.6 trillion tokens and has achieved the best performance in authoritative Chinese and English benchmarks of the same size.
This release includes 7B and 13B versions for both Base and Chat models, along with a 4bits quantized version for the Chat model.
All versions are fully open to academic research, and developers can also use them for free in commercial applications after obtaining an official commercial license through [email request](mailto:opensource@baichuan-inc.com).
The specific release versions and download links are listed in the table below:
| | Base Model | Chat Model | 4bits Quantized Chat Model |
|:---:|:--------------------:|:--------------------:|:--------------------------:|
| 7B | [Baichuan2-7B-Base](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base) | [Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat) | [Baichuan2-7B-Chat-4bits](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base-4bits) |
| 13B | [Baichuan2-13B-Base](https://huggingface.co/baichuan-inc/Baichuan2-13B-Base) | [Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat) | [Baichuan2-13B-Chat-4bits](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat-4bits) |
# <span id="Start">快速开始/Quick Start</span>
在Baichuan2系列模型中，我们为了加快推理速度使用了Pytorch2.0加入的新功能F.scaled_dot_product_attention，因此模型需要在Pytorch2.0环境下运行。
In the Baichuan 2 series models, we have utilized the new feature `F.scaled_dot_product_attention` introduced in PyTorch 2.0 to accelerate inference speed. Therefore, the model needs to be run in a PyTorch 2.0 environment.
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation.utils import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan2-13B-Chat", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-13B-Chat", device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True)
model.generation_config = GenerationConfig.from_pretrained("baichuan-inc/Baichuan2-13B-Chat")
messages = []
messages.append({"role": "user", "content": "解释一下“温故而知新”"})
response = model.chat(tokenizer, messages)
print(response)
"温故而知新"是一句中国古代的成语，出自《论语·为政》篇。这句话的意思是：通过回顾过去，我们可以发现新的知识和理解。换句话说，学习历史和经验可以让我们更好地理解现在和未来。
这句话鼓励我们在学习和生活中不断地回顾和反思过去的经验，从而获得新的启示和成长。通过重温旧的知识和经历，我们可以发现新的观点和理解，从而更好地应对不断变化的世界和挑战。
```
# <span id="Benchmark">Benchmark 结果/Benchmark Evaluation</span>
我们在[通用]、[法律]、[医疗]、[数学]、[代码]和[多语言翻译]六个领域的中英文权威数据集上对模型进行了广泛测试，更多详细测评结果可查看[GitHub]。
We have extensively tested the model on authoritative Chinese-English datasets across six domains: [General](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md#general-domain), [Legal](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md#law-and-medicine), [Medical](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md#law-and-medicine), [Mathematics](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md#mathematics-and-code), [Code](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md#mathematics-and-code), and [Multilingual Translation](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md#multilingual-translation). For more detailed evaluation results, please refer to [GitHub](https://github.com/baichuan-inc/Baichuan2/blob/main/README_EN.md).
### 7B Model Results
| | **C-Eval** | **MMLU** | **CMMLU** | **Gaokao** | **AGIEval** | **BBH** |
|:-----------------------:|:----------:|:--------:|:---------:|:----------:|:-----------:|:-------:|
| | 5-shot | 5-shot | 5-shot | 5-shot | 5-shot | 3-shot |
| **GPT-4** | 68.40 | 83.93 | 70.33 | 66.15 | 63.27 | 75.12 |
| **GPT-3.5 Turbo** | 51.10 | 68.54 | 54.06 | 47.07 | 46.13 | 61.59 |
| **LLaMA-7B** | 27.10 | 35.10 | 26.75 | 27.81 | 28.17 | 32.38 |
| **LLaMA2-7B** | 28.90 | 45.73 | 31.38 | 25.97 | 26.53 | 39.16 |
| **MPT-7B** | 27.15 | 27.93 | 26.00 | 26.54 | 24.83 | 35.20 |
| **Falcon-7B** | 24.23 | 26.03 | 25.66 | 24.24 | 24.10 | 28.77 |
| **ChatGLM2-6B** | 50.20 | 45.90 | 49.00 | 49.44 | 45.28 | 31.65 |
| **[Baichuan-7B]** | 42.80 | 42.30 | 44.02 | 36.34 | 34.44 | 32.48 |
| **[Baichuan2-7B-Base]** | 54.00 | 54.16 | 57.07 | 47.47 | 42.73 | 41.56 |
### 13B Model Results
| | **C-Eval** | **MMLU** | **CMMLU** | **Gaokao** | **AGIEval** | **BBH** |
|:---------------------------:|:----------:|:--------:|:---------:|:----------:|:-----------:|:-------:|
| | 5-shot | 5-shot | 5-shot | 5-shot | 5-shot | 3-shot |
| **GPT-4** | 68.40 | 83.93 | 70.33 | 66.15 | 63.27 | 75.12 |
| **GPT-3.5 Turbo** | 51.10 | 68.54 | 54.06 | 47.07 | 46.13 | 61.59 |
| **LLaMA-13B** | 28.50 | 46.30 | 31.15 | 28.23 | 28.22 | 37.89 |
| **LLaMA2-13B** | 35.80 | 55.09 | 37.99 | 30.83 | 32.29 | 46.98 |
| **Vicuna-13B** | 32.80 | 52.00 | 36.28 | 30.11 | 31.55 | 43.04 |
| **Chinese-Alpaca-Plus-13B** | 38.80 | 43.90 | 33.43 | 34.78 | 35.46 | 28.94 |
| **XVERSE-13B** | 53.70 | 55.21 | 58.44 | 44.69 | 42.54 | 38.06 |
| **[Baichuan-13B-Base]** | 52.40 | 51.60 | 55.30 | 49.69 | 43.20 | 43.01 |
| **[Baichuan2-13B-Base]** | 58.10 | 59.17 | 61.97 | 54.33 | 48.17 | 48.78 |
## 训练过程模型/Training Dynamics
除了训练了 2.6 万亿 Tokens 的 [Baichuan2-7B-Base](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base) 模型，我们还提供了在此之前的另外 11 个中间过程的模型（分别对应训练了约 0.2 ~ 2.4 万亿 Tokens）供社区研究使用
（[训练过程checkpoint下载](https://huggingface.co/baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints)）。下图给出了这些 checkpoints 在 C-Eval、MMLU、CMMLU 三个 benchmark 上的效果变化：
In addition to the [Baichuan2-7B-Base](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base) model trained on 2.6 trillion tokens, we also offer 11 additional intermediate-stage models for community research, corresponding to training on approximately 0.2 to 2.4 trillion tokens each ([Intermediate Checkpoints Download](https://huggingface.co/baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints)). The graph below shows the performance changes of these checkpoints on three benchmarks: C-Eval, MMLU, and CMMLU.
# <span id="Terms">声明与协议/Terms and Conditions</span>
## 声明
我们在此声明，我们的开发团队并未基于 Baichuan 2 模型开发任何应用，无论是在 iOS、Android、网页或任何其他平台。我们强烈呼吁所有使用者，不要利用
Baichuan 2 模型进行任何危害国家社会安全或违法的活动。另外，我们也要求使用者不要将 Baichuan 2
模型用于未经适当安全审查和备案的互联网服务。我们希望所有的使用者都能遵守这个原则，确保科技的发展能在规范和合法的环境下进行。
我们已经尽我们所能，来确保模型训练过程中使用的数据的合规性。然而，尽管我们已经做出了巨大的努力，但由于模型和数据的复杂性，仍有可能存在一些无法预见的问题。因此，如果由于使用
Baichuan 2 开源模型而导致的任何问题，包括但不限于数据安全问题、公共舆论风险，或模型被误导、滥用、传播或不当利用所带来的任何风险和问题，我们将不承担任何责任。
We hereby declare that our team has not developed any applications based on Baichuan 2 models, not on iOS, Android, the web, or any other platform. We strongly call on all users not to use Baichuan 2 models for any activities that harm national / social security or violate the law. Also, we ask users not to use Baichuan 2 models for Internet services that have not undergone appropriate security reviews and filings. We hope that all users can abide by this principle and ensure that the development of technology proceeds in a regulated and legal environment.
We have done our best to ensure the compliance of the data used in the model training process. However, despite our considerable efforts, there may still be some unforeseeable issues due to the complexity of the model and data. Therefore, if any problems arise due to the use of Baichuan 2 open-source models, including but not limited to data security issues, public opinion risks, or any risks and problems brought about by the model being misled, abused, spread or improperly exploited, we will not assume any responsibility.
## 协议
社区使用 Baichuan 2 模型需要遵循 [Apache 2.0](https://github.com/baichuan-inc/Baichuan2/blob/main/LICENSE) 和[《Baichuan 2 模型社区许可协议》](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/resolve/main/Baichuan%202%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf)。Baichuan 2 模型支持商业用途，如果您计划将 Baichuan 2 模型或其衍生品用于商业目的，请您确认您的主体符合以下情况：
1. 您或您的关联方的服务或产品的日均用户活跃量（DAU）低于100万。
2. 您或您的关联方不是软件服务提供商、云服务提供商。
3. 您或您的关联方不存在将授予您的商用许可，未经百川许可二次授权给其他第三方的可能。
在符合以上条件的前提下，您需要通过以下联系邮箱 opensource@baichuan-inc.com ，提交《Baichuan 2 模型社区许可协议》要求的申请材料。审核通过后，百川将特此授予您一个非排他性、全球性、不可转让、不可再许可、可撤销的商用版权许可。
The community usage of Baichuan 2 model requires adherence to [Apache 2.0](https://github.com/baichuan-inc/Baichuan2/blob/main/LICENSE) and [Community License for Baichuan2 Model](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/resolve/main/Baichuan%202%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf). The Baichuan 2 model supports commercial use. If you plan to use the Baichuan 2 model or its derivatives for commercial purposes, please ensure that your entity meets the following conditions:
1. The Daily Active Users (DAU) of your or your affiliate's service or product is less than 1 million.
2. Neither you nor your affiliates are software service providers or cloud service providers.
3. There is no possibility for you or your affiliates to grant the commercial license given to you, to reauthorize it to other third parties without Baichuan's permission.
Upon meeting the above conditions, you need to submit the application materials required by the Baichuan 2 Model Community License Agreement via the following contact email: opensource@baichuan-inc.com. Once approved, Baichuan will hereby grant you a non-exclusive, global, non-transferable, non-sublicensable, revocable commercial copyright license.
[GitHub]:https://github.com/baichuan-inc/Baichuan2
[Baichuan2]:https://github.com/baichuan-inc/Baichuan2
[Baichuan-7B]:https://huggingface.co/baichuan-inc/Baichuan-7B
[Baichuan2-7B-Base]:https://huggingface.co/baichuan-inc/Baichuan2-7B-Base
[Baichuan2-7B-Chat]:https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat
[Baichuan2-7B-Chat-4bits]:https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat-4bits
[Baichuan-13B-Base]:https://huggingface.co/baichuan-inc/Baichuan-13B-Base
[Baichuan2-13B-Base]:https://huggingface.co/baichuan-inc/Baichuan2-13B-Base
[Baichuan2-13B-Chat]:https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat
[Baichuan2-13B-Chat-4bits]:https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat-4bits
[通用]:https://github.com/baichuan-inc/Baichuan2#%E9%80%9A%E7%94%A8%E9%A2%86%E5%9F%9F
[法律]:https://github.com/baichuan-inc/Baichuan2#%E6%B3%95%E5%BE%8B%E5%8C%BB%E7%96%97
[医疗]:https://github.com/baichuan-inc/Baichuan2#%E6%B3%95%E5%BE%8B%E5%8C%BB%E7%96%97
[数学]:https://github.com/baichuan-inc/Baichuan2#%E6%95%B0%E5%AD%A6%E4%BB%A3%E7%A0%81
[代码]:https://github.com/baichuan-inc/Baichuan2#%E6%95%B0%E5%AD%A6%E4%BB%A3%E7%A0%81
[多语言翻译]:https://github.com/baichuan-inc/Baichuan2#%E5%A4%9A%E8%AF%AD%E8%A8%80%E7%BF%BB%E8%AF%91
[《Baichuan 2 模型社区许可协议》]:https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Baichuan%202%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf
[邮件申请]: mailto:opensource@baichuan-inc.com
[Email]: mailto:opensource@baichuan-inc.com
[opensource@baichuan-inc.com]: mailto:opensource@baichuan-inc.com
[训练过程heckpoint下载]: https://huggingface.co/baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
[百川智能]: https://www.baichuan-ai.com
| 13,199 | [
[
-0.025482177734375,
-0.052642822265625,
0.001922607421875,
0.028839111328125,
-0.0191497802734375,
-0.0032138824462890625,
-0.0219879150390625,
-0.030059814453125,
0.020233154296875,
0.0079803466796875,
-0.034515380859375,
-0.0369873046875,
-0.047393798828125,
-0.00354766845703125,
0.006313323974609375,
0.067626953125,
-0.0013475418090820312,
0.002227783203125,
0.017669677734375,
-0.01004791259765625,
-0.04437255859375,
-0.0218658447265625,
-0.0596923828125,
-0.01605224609375,
0.0191802978515625,
0.020965576171875,
0.052825927734375,
0.046234130859375,
0.052703857421875,
0.0186920166015625,
-0.017669677734375,
0.01788330078125,
-0.030242919921875,
-0.01488494873046875,
0.0234527587890625,
-0.034942626953125,
-0.057220458984375,
0.0014562606811523438,
0.027069091796875,
0.0272369384765625,
-0.0027332305908203125,
0.01983642578125,
0.02203369140625,
0.03692626953125,
-0.0250396728515625,
0.025054931640625,
-0.018463134765625,
-0.00553131103515625,
-0.0142974853515625,
-0.0009737014770507812,
-0.018829345703125,
-0.0255279541015625,
0.00733184814453125,
-0.044281005859375,
0.009796142578125,
0.00443267822265625,
0.1116943359375,
-0.004558563232421875,
-0.027984619140625,
-0.00881195068359375,
-0.0217437744140625,
0.06719970703125,
-0.08087158203125,
0.0144500732421875,
0.0276336669921875,
0.01605224609375,
-0.01139068603515625,
-0.06256103515625,
-0.036285400390625,
-0.004375457763671875,
-0.0377197265625,
0.027923583984375,
-0.01678466796875,
-0.0137481689453125,
0.0051422119140625,
0.032745361328125,
-0.052093505859375,
0.001285552978515625,
-0.043670654296875,
-0.01232147216796875,
0.0615234375,
0.0189361572265625,
0.0232696533203125,
-0.03558349609375,
-0.03729248046875,
-0.00362396240234375,
-0.037872314453125,
0.0284271240234375,
0.001857757568359375,
0.011322021484375,
-0.04681396484375,
0.025421142578125,
-0.006282806396484375,
0.035247802734375,
0.013580322265625,
-0.0150299072265625,
0.041839599609375,
-0.045745849609375,
-0.0245819091796875,
-0.0230712890625,
0.0936279296875,
0.040924072265625,
-0.0157318115234375,
0.0136260986328125,
-0.0139007568359375,
-0.01947021484375,
-0.0263671875,
-0.06787109375,
-0.0304412841796875,
0.043548583984375,
-0.058868408203125,
-0.030059814453125,
0.01214599609375,
-0.057373046875,
-0.0017976760864257812,
-0.0019855499267578125,
0.034423828125,
-0.04705810546875,
-0.044097900390625,
-0.00447845458984375,
-0.003917694091796875,
0.0223388671875,
0.0196990966796875,
-0.06622314453125,
0.016845703125,
0.038665771484375,
0.08197021484375,
-0.00791168212890625,
-0.030517578125,
-0.0091552734375,
-0.0018815994262695312,
-0.0311279296875,
0.041717529296875,
-0.000698089599609375,
-0.0265655517578125,
-0.01336669921875,
0.024017333984375,
-0.01465606689453125,
-0.0304412841796875,
0.0269622802734375,
-0.016326904296875,
0.01262664794921875,
-0.0335693359375,
-0.02972412109375,
-0.0150299072265625,
0.030731201171875,
-0.045379638671875,
0.08514404296875,
0.00446319580078125,
-0.066162109375,
0.0179443359375,
-0.040924072265625,
-0.0225372314453125,
-0.0149078369140625,
0.0035915374755859375,
-0.040374755859375,
-0.0318603515625,
0.0260772705078125,
0.037139892578125,
-0.03546142578125,
0.01099395751953125,
-0.01032257080078125,
-0.02484130859375,
0.0115814208984375,
-0.0240020751953125,
0.091796875,
0.0303497314453125,
-0.04638671875,
0.016448974609375,
-0.050506591796875,
-0.00006109476089477539,
0.034149169921875,
-0.022247314453125,
0.003963470458984375,
-0.00959014892578125,
0.0055389404296875,
0.02679443359375,
0.0285797119140625,
-0.01456451416015625,
0.00801849365234375,
-0.034149169921875,
0.052337646484375,
0.0634765625,
0.006961822509765625,
0.0207061767578125,
-0.049835205078125,
0.0262298583984375,
0.02642822265625,
0.03240966796875,
-0.0227813720703125,
-0.0526123046875,
-0.07763671875,
-0.0235748291015625,
0.022674560546875,
0.045654296875,
-0.0400390625,
0.0516357421875,
-0.0121917724609375,
-0.050048828125,
-0.038543701171875,
-0.004367828369140625,
0.0300140380859375,
0.0290069580078125,
0.027374267578125,
-0.0070953369140625,
-0.043487548828125,
-0.054931640625,
0.00975799560546875,
-0.0215301513671875,
0.004627227783203125,
0.0290679931640625,
0.055419921875,
-0.009033203125,
0.0526123046875,
-0.040374755859375,
-0.0196380615234375,
-0.027374267578125,
-0.00494384765625,
0.037139892578125,
0.043060302734375,
0.053375244140625,
-0.0506591796875,
-0.061279296875,
0.01552581787109375,
-0.0614013671875,
0.01139068603515625,
-0.00811767578125,
-0.0290069580078125,
0.0290679931640625,
0.01139068603515625,
-0.04815673828125,
0.037628173828125,
0.04608154296875,
-0.026214599609375,
0.05718994140625,
-0.0182037353515625,
0.023284912109375,
-0.09271240234375,
0.017974853515625,
-0.00431060791015625,
0.00267791748046875,
-0.043365478515625,
0.0051116943359375,
0.016357421875,
0.0129547119140625,
-0.033111572265625,
0.056854248046875,
-0.04925537109375,
0.0263214111328125,
0.00470733642578125,
0.0245819091796875,
0.007053375244140625,
0.0501708984375,
0.0006003379821777344,
0.05743408203125,
0.049957275390625,
-0.046142578125,
0.03778076171875,
0.030517578125,
-0.024627685546875,
0.00431060791015625,
-0.0540771484375,
-0.0026187896728515625,
0.013275146484375,
0.018707275390625,
-0.0828857421875,
-0.0155792236328125,
0.0401611328125,
-0.0589599609375,
0.0182342529296875,
-0.01256561279296875,
-0.020843505859375,
-0.051025390625,
-0.045196533203125,
0.007625579833984375,
0.04046630859375,
-0.03594970703125,
0.0229949951171875,
0.013336181640625,
-0.0016336441040039062,
-0.04547119140625,
-0.058258056640625,
-0.0137939453125,
-0.016937255859375,
-0.06695556640625,
0.0225982666015625,
-0.00295257568359375,
-0.00464630126953125,
-0.004009246826171875,
0.0018711090087890625,
-0.0029315948486328125,
0.00476837158203125,
0.0092315673828125,
0.042755126953125,
-0.022125244140625,
-0.01410675048828125,
-0.0088348388671875,
0.0002567768096923828,
-0.0008063316345214844,
-0.010498046875,
0.05303955078125,
-0.00679779052734375,
0.001148223876953125,
-0.0438232421875,
0.0029621124267578125,
0.032806396484375,
-0.038177490234375,
0.0740966796875,
0.047760009765625,
-0.0269622802734375,
0.0102081298828125,
-0.03460693359375,
-0.01381683349609375,
-0.03485107421875,
0.0271759033203125,
-0.027740478515625,
-0.0439453125,
0.062286376953125,
0.0251617431640625,
0.0239105224609375,
0.05291748046875,
0.0506591796875,
-0.0030117034912109375,
0.066162109375,
0.014251708984375,
-0.01128387451171875,
0.029876708984375,
-0.057952880859375,
0.007659912109375,
-0.063232421875,
-0.036712646484375,
-0.028900146484375,
-0.0209197998046875,
-0.044525146484375,
-0.0316162109375,
0.025482177734375,
0.006992340087890625,
-0.033203125,
0.041259765625,
-0.0374755859375,
-0.00004881620407104492,
0.05181884765625,
0.0234832763671875,
0.0038299560546875,
-0.01410675048828125,
-0.00569915771484375,
-0.0020999908447265625,
-0.0452880859375,
-0.0236968994140625,
0.0889892578125,
0.0306396484375,
0.045074462890625,
0.01995849609375,
0.036102294921875,
0.0066375732421875,
0.0120086669921875,
-0.044036865234375,
0.0260467529296875,
-0.003078460693359375,
-0.063232421875,
-0.014862060546875,
-0.035919189453125,
-0.07208251953125,
0.0257568359375,
-0.01122283935546875,
-0.063232421875,
0.009246826171875,
0.0010633468627929688,
-0.039886474609375,
0.027587890625,
-0.054931640625,
0.0687255859375,
-0.0295562744140625,
-0.0394287109375,
-0.0006732940673828125,
-0.06011962890625,
0.042022705078125,
0.008209228515625,
0.0200347900390625,
-0.007190704345703125,
0.01247406005859375,
0.06634521484375,
-0.049652099609375,
0.044281005859375,
-0.01323699951171875,
-0.0026836395263671875,
0.0411376953125,
0.002994537353515625,
0.05267333984375,
0.01381683349609375,
-0.00966644287109375,
0.0252227783203125,
0.00832366943359375,
-0.03668212890625,
-0.03228759765625,
0.047637939453125,
-0.067138671875,
-0.047149658203125,
-0.0396728515625,
-0.0313720703125,
0.0113067626953125,
0.0270538330078125,
0.044677734375,
0.0234832763671875,
0.007785797119140625,
0.0167083740234375,
0.035308837890625,
-0.0276947021484375,
0.043670654296875,
0.0283660888671875,
-0.017364501953125,
-0.043365478515625,
0.05859375,
0.01226806640625,
0.031951904296875,
0.024200439453125,
0.0165863037109375,
-0.0186767578125,
-0.0275726318359375,
-0.03460693359375,
0.0267181396484375,
-0.032196044921875,
-0.02032470703125,
-0.044342041015625,
-0.033905029296875,
-0.0677490234375,
-0.0034637451171875,
-0.02362060546875,
-0.02099609375,
-0.02044677734375,
-0.01139068603515625,
0.0297698974609375,
0.0277557373046875,
-0.01467132568359375,
0.0197296142578125,
-0.05877685546875,
0.01512908935546875,
0.00484466552734375,
0.0087738037109375,
0.011810302734375,
-0.05487060546875,
-0.038604736328125,
0.026336669921875,
-0.04052734375,
-0.055328369140625,
0.04638671875,
-0.0000015497207641601562,
0.04022216796875,
0.045654296875,
0.0017366409301757812,
0.0565185546875,
-0.0196380615234375,
0.08258056640625,
0.026336669921875,
-0.058258056640625,
0.049652099609375,
-0.033172607421875,
-0.0007824897766113281,
0.01617431640625,
0.02593994140625,
-0.0472412109375,
-0.0184173583984375,
-0.043731689453125,
-0.0596923828125,
0.07733154296875,
0.039031982421875,
-0.0010471343994140625,
0.0085906982421875,
0.01352691650390625,
-0.01300811767578125,
0.00368499755859375,
-0.060791015625,
-0.0589599609375,
-0.0247039794921875,
-0.005672454833984375,
0.005870819091796875,
-0.01468658447265625,
-0.003917694091796875,
-0.02630615234375,
0.0634765625,
0.01544952392578125,
0.03436279296875,
0.0179901123046875,
-0.0008177757263183594,
0.0032520294189453125,
-0.007579803466796875,
0.03485107421875,
0.041656494140625,
-0.032440185546875,
-0.0196075439453125,
0.01343536376953125,
-0.0465087890625,
-0.0005183219909667969,
0.01194000244140625,
-0.02734375,
0.003292083740234375,
0.03076171875,
0.0634765625,
0.00579833984375,
-0.02679443359375,
0.043243408203125,
-0.002010345458984375,
-0.017608642578125,
-0.0178070068359375,
0.005878448486328125,
0.00431060791015625,
0.0170745849609375,
0.0188751220703125,
-0.001979827880859375,
-0.001056671142578125,
-0.0390625,
0.0098876953125,
0.016448974609375,
-0.017578125,
-0.019744873046875,
0.0718994140625,
0.015625,
0.00026416778564453125,
0.0406494140625,
-0.01318359375,
-0.043548583984375,
0.06634521484375,
0.03173828125,
0.0478515625,
-0.0238037109375,
0.01041412353515625,
0.07403564453125,
0.026275634765625,
-0.011688232421875,
0.00684356689453125,
0.0156707763671875,
-0.041473388671875,
0.004734039306640625,
-0.0293121337890625,
0.0029621124267578125,
0.0189361572265625,
-0.044677734375,
0.043060302734375,
-0.033905029296875,
-0.029693603515625,
-0.006805419921875,
0.032470703125,
-0.036346435546875,
0.0267181396484375,
0.0048065185546875,
0.0703125,
-0.044769287109375,
0.0634765625,
0.034515380859375,
-0.056732177734375,
-0.0838623046875,
-0.01006317138671875,
0.006633758544921875,
-0.0570068359375,
0.032440185546875,
0.0102996826171875,
0.0217437744140625,
-0.00775909423828125,
-0.0374755859375,
-0.07244873046875,
0.1138916015625,
0.0007543563842773438,
-0.034088134765625,
-0.00771331787109375,
-0.00030517578125,
0.03167724609375,
0.000728607177734375,
0.04656982421875,
0.048126220703125,
0.03521728515625,
0.008026123046875,
-0.0814208984375,
0.0184173583984375,
-0.043487548828125,
-0.006633758544921875,
-0.0055694580078125,
-0.10455322265625,
0.09808349609375,
-0.0178680419921875,
-0.00505828857421875,
0.01555633544921875,
0.05584716796875,
0.036590576171875,
0.01343536376953125,
0.01666259765625,
0.03070068359375,
0.051300048828125,
-0.0285186767578125,
0.06353759765625,
-0.033233642578125,
0.057464599609375,
0.06427001953125,
0.004909515380859375,
0.04681396484375,
0.0081329345703125,
-0.041046142578125,
0.035430908203125,
0.071533203125,
-0.0206451416015625,
0.035430908203125,
-0.01023101806640625,
-0.014739990234375,
-0.004993438720703125,
0.01593017578125,
-0.0506591796875,
0.01275634765625,
0.019683837890625,
-0.020416259765625,
0.007598876953125,
-0.01551055908203125,
0.034393310546875,
-0.025299072265625,
-0.010101318359375,
0.038818359375,
0.003978729248046875,
-0.049285888671875,
0.06719970703125,
0.0158843994140625,
0.06939697265625,
-0.0545654296875,
0.007598876953125,
-0.042327880859375,
0.01287841796875,
-0.023773193359375,
-0.054595947265625,
-0.0016260147094726562,
-0.001178741455078125,
-0.001491546630859375,
0.0193634033203125,
0.03887939453125,
-0.02056884765625,
-0.034912109375,
0.03082275390625,
0.0136871337890625,
0.01039886474609375,
0.01461029052734375,
-0.06683349609375,
0.000957489013671875,
0.01385498046875,
-0.0439453125,
0.01403045654296875,
0.0360107421875,
0.0026416778564453125,
0.05328369140625,
0.0472412109375,
0.003238677978515625,
0.019012451171875,
-0.0112457275390625,
0.06585693359375,
-0.047149658203125,
-0.0338134765625,
-0.06329345703125,
0.05181884765625,
-0.010986328125,
-0.0357666015625,
0.072265625,
0.06146240234375,
0.053741455078125,
0.001956939697265625,
0.066650390625,
-0.040924072265625,
0.0281829833984375,
-0.03448486328125,
0.073486328125,
-0.053955078125,
0.0088653564453125,
-0.0242462158203125,
-0.037628173828125,
-0.01837158203125,
0.051422119140625,
-0.0178070068359375,
0.0116119384765625,
0.04901123046875,
0.06878662109375,
0.007640838623046875,
-0.009918212890625,
0.00841522216796875,
0.033905029296875,
0.038787841796875,
0.070068359375,
0.035858154296875,
-0.07611083984375,
0.05609130859375,
-0.04864501953125,
-0.017364501953125,
-0.029083251953125,
-0.028717041015625,
-0.07305908203125,
-0.04248046875,
-0.0207672119140625,
-0.05242919921875,
-0.0136260986328125,
0.0709228515625,
0.058746337890625,
-0.070556640625,
-0.0290069580078125,
0.006488800048828125,
0.00402069091796875,
-0.0299835205078125,
-0.018463134765625,
0.0596923828125,
-0.020599365234375,
-0.067626953125,
-0.00014472007751464844,
0.0021495819091796875,
0.01082611083984375,
0.0037746429443359375,
-0.0311126708984375,
-0.0304718017578125,
0.0006327629089355469,
0.03271484375,
0.01515960693359375,
-0.052886962890625,
-0.00298309326171875,
0.0200347900390625,
-0.023956298828125,
0.0154266357421875,
0.018829345703125,
-0.0233154296875,
0.018646240234375,
0.040191650390625,
0.00974273681640625,
0.03851318359375,
-0.0012912750244140625,
0.0185699462890625,
-0.0250091552734375,
0.02685546875,
-0.00914764404296875,
0.035369873046875,
0.004566192626953125,
-0.023101806640625,
0.04791259765625,
0.0284881591796875,
-0.034912109375,
-0.0594482421875,
-0.02288818359375,
-0.0762939453125,
-0.021942138671875,
0.09991455078125,
-0.035888671875,
-0.025421142578125,
0.0122528076171875,
-0.0322265625,
0.039398193359375,
-0.0306396484375,
0.051727294921875,
0.0576171875,
0.006618499755859375,
-0.013336181640625,
-0.044281005859375,
0.0279998779296875,
0.019500732421875,
-0.05999755859375,
0.002651214599609375,
0.0163421630859375,
0.0274658203125,
0.0074310302734375,
0.052337646484375,
-0.01201629638671875,
0.0290069580078125,
0.006641387939453125,
0.0038299560546875,
-0.006999969482421875,
-0.002986907958984375,
-0.0009632110595703125,
-0.021942138671875,
-0.013275146484375,
-0.03369140625
]
] |
facebook/wmt19-en-de | 2023-09-15T13:03:30.000Z | [
"transformers",
"pytorch",
"fsmt",
"text2text-generation",
"translation",
"wmt19",
"facebook",
"en",
"de",
"dataset:wmt19",
"arxiv:1907.06616",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | translation | facebook | null | null | facebook/wmt19-en-de | 18 | 38,098 | transformers | 2022-03-02T23:29:05 | ---
language:
- en
- de
tags:
- translation
- wmt19
- facebook
license: apache-2.0
datasets:
- wmt19
metrics:
- bleu
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
---
# FSMT
## Model description
This is a ported version of [fairseq wmt19 transformer](https://github.com/pytorch/fairseq/blob/master/examples/wmt19/README.md) for en-de.
For more details, please see, [Facebook FAIR's WMT19 News Translation Task Submission](https://arxiv.org/abs/1907.06616).
The abbreviation FSMT stands for FairSeqMachineTranslation
All four models are available:
* [wmt19-en-ru](https://huggingface.co/facebook/wmt19-en-ru)
* [wmt19-ru-en](https://huggingface.co/facebook/wmt19-ru-en)
* [wmt19-en-de](https://huggingface.co/facebook/wmt19-en-de)
* [wmt19-de-en](https://huggingface.co/facebook/wmt19-de-en)
## Intended uses & limitations
#### How to use
```python
from transformers import FSMTForConditionalGeneration, FSMTTokenizer
mname = "facebook/wmt19-en-de"
tokenizer = FSMTTokenizer.from_pretrained(mname)
model = FSMTForConditionalGeneration.from_pretrained(mname)
input = "Machine learning is great, isn't it?"
input_ids = tokenizer.encode(input, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded) # Maschinelles Lernen ist großartig, oder?
```
#### Limitations and bias
- The original (and this ported model) doesn't seem to handle well inputs with repeated sub-phrases, [content gets truncated](https://discuss.huggingface.co/t/issues-with-translating-inputs-containing-repeated-phrases/981)
## Training data
Pretrained weights were left identical to the original model released by fairseq. For more details, please, see the [paper](https://arxiv.org/abs/1907.06616).
## Eval results
pair | fairseq | transformers
-------|---------|----------
en-de | [43.1](http://matrix.statmt.org/matrix/output/1909?run_id=6862) | 42.83
The score is slightly below the score reported by `fairseq`, since `transformers`` currently doesn't support:
- model ensemble, therefore the best performing checkpoint was ported (``model4.pt``).
- re-ranking
The score was calculated using this code:
```bash
git clone https://github.com/huggingface/transformers
cd transformers
export PAIR=en-de
export DATA_DIR=data/$PAIR
export SAVE_DIR=data/$PAIR
export BS=8
export NUM_BEAMS=15
mkdir -p $DATA_DIR
sacrebleu -t wmt19 -l $PAIR --echo src > $DATA_DIR/val.source
sacrebleu -t wmt19 -l $PAIR --echo ref > $DATA_DIR/val.target
echo $PAIR
PYTHONPATH="src:examples/seq2seq" python examples/seq2seq/run_eval.py facebook/wmt19-$PAIR $DATA_DIR/val.source $SAVE_DIR/test_translations.txt --reference_path $DATA_DIR/val.target --score_path $SAVE_DIR/test_bleu.json --bs $BS --task translation --num_beams $NUM_BEAMS
```
note: fairseq reports using a beam of 50, so you should get a slightly higher score if re-run with `--num_beams 50`.
## Data Sources
- [training, etc.](http://www.statmt.org/wmt19/)
- [test set](http://matrix.statmt.org/test_sets/newstest2019.tgz?1556572561)
### BibTeX entry and citation info
```bibtex
@inproceedings{...,
year={2020},
title={Facebook FAIR's WMT19 News Translation Task Submission},
author={Ng, Nathan and Yee, Kyra and Baevski, Alexei and Ott, Myle and Auli, Michael and Edunov, Sergey},
booktitle={Proc. of WMT},
}
```
## TODO
- port model ensemble (fairseq uses 4 model checkpoints)
| 3,431 | [
[
-0.02838134765625,
-0.044586181640625,
0.02557373046875,
0.027557373046875,
-0.01959228515625,
-0.0011739730834960938,
-0.00897979736328125,
-0.02484130859375,
0.00391387939453125,
0.01200103759765625,
-0.06451416015625,
-0.0237579345703125,
-0.05609130859375,
0.01239013671875,
-0.0382080078125,
0.07000732421875,
-0.0195159912109375,
0.025787353515625,
-0.0013942718505859375,
-0.0188140869140625,
-0.0125732421875,
-0.0106353759765625,
-0.038299560546875,
-0.02899169921875,
0.01042938232421875,
0.006275177001953125,
0.04522705078125,
0.0197601318359375,
0.043609619140625,
0.033203125,
-0.0150146484375,
-0.0007610321044921875,
-0.034698486328125,
-0.0165557861328125,
-0.0201263427734375,
-0.0267181396484375,
-0.02838134765625,
0.00212860107421875,
0.04669189453125,
0.045013427734375,
-0.0028591156005859375,
0.043701171875,
0.007572174072265625,
0.035186767578125,
-0.009185791015625,
0.01385498046875,
-0.047607421875,
0.0144500732421875,
-0.01491546630859375,
-0.00335693359375,
-0.035064697265625,
-0.020965576171875,
-0.013702392578125,
-0.031951904296875,
0.010162353515625,
0.00569915771484375,
0.102294921875,
0.017669677734375,
-0.04681396484375,
0.0231781005859375,
-0.0389404296875,
0.07867431640625,
-0.057159423828125,
0.056121826171875,
0.0040130615234375,
0.0297698974609375,
-0.0146484375,
-0.080322265625,
-0.028472900390625,
0.0079803466796875,
-0.0025272369384765625,
0.02288818359375,
-0.035308837890625,
-0.01509857177734375,
0.033538818359375,
0.0309600830078125,
-0.046051025390625,
-0.0153656005859375,
-0.052032470703125,
-0.040679931640625,
0.050506591796875,
0.01146697998046875,
0.004894256591796875,
-0.0229339599609375,
-0.04046630859375,
-0.021331787109375,
-0.021331787109375,
0.01505279541015625,
-0.000881195068359375,
0.0227813720703125,
-0.0083465576171875,
0.044952392578125,
-0.042510986328125,
0.04046630859375,
0.026519775390625,
-0.01123046875,
0.06524658203125,
-0.03997802734375,
-0.006221771240234375,
-0.02178955078125,
0.08197021484375,
0.036865234375,
-0.0012531280517578125,
-0.00785064697265625,
-0.035125732421875,
-0.022186279296875,
0.007904052734375,
-0.08197021484375,
0.016693115234375,
0.006237030029296875,
-0.051788330078125,
-0.01611328125,
0.02069091796875,
-0.049072265625,
0.0164337158203125,
-0.0180511474609375,
0.0687255859375,
-0.03759765625,
-0.0012903213500976562,
0.0000286102294921875,
-0.022613525390625,
0.02423095703125,
0.014739990234375,
-0.0223846435546875,
0.006359100341796875,
0.02337646484375,
0.07244873046875,
-0.010528564453125,
-0.0308990478515625,
-0.045989990234375,
-0.01372528076171875,
-0.0170440673828125,
0.0299072265625,
-0.005336761474609375,
-0.015533447265625,
-0.01155853271484375,
0.048553466796875,
-0.0179595947265625,
-0.025543212890625,
0.05120849609375,
-0.036285400390625,
0.042083740234375,
-0.021697998046875,
-0.028167724609375,
-0.01540374755859375,
0.004749298095703125,
-0.03173828125,
0.08416748046875,
0.034698486328125,
-0.056976318359375,
0.0095367431640625,
-0.037628173828125,
-0.036895751953125,
-0.011199951171875,
0.00383758544921875,
-0.0308074951171875,
0.01129150390625,
0.0081329345703125,
0.030242919921875,
-0.01340484619140625,
0.0384521484375,
-0.01507568359375,
-0.044586181640625,
0.0207977294921875,
-0.036834716796875,
0.0716552734375,
0.037353515625,
-0.036102294921875,
0.017608642578125,
-0.049957275390625,
-0.0008616447448730469,
0.0207366943359375,
-0.0279083251953125,
0.01788330078125,
-0.0169830322265625,
0.01110076904296875,
0.048004150390625,
0.03302001953125,
-0.043304443359375,
-0.007549285888671875,
-0.04046630859375,
0.034210205078125,
0.060455322265625,
-0.006893157958984375,
0.02935791015625,
-0.05029296875,
0.035400390625,
0.01117706298828125,
0.02093505859375,
0.00836944580078125,
-0.0516357421875,
-0.04803466796875,
-0.00455474853515625,
0.0182952880859375,
0.0450439453125,
-0.07373046875,
0.032989501953125,
-0.034576416015625,
-0.060577392578125,
-0.035858154296875,
-0.017669677734375,
0.0228271484375,
0.0256195068359375,
0.047210693359375,
-0.0253448486328125,
-0.045196533203125,
-0.07220458984375,
-0.03533935546875,
0.0009293556213378906,
-0.0007615089416503906,
0.001590728759765625,
0.04443359375,
-0.038299560546875,
0.052154541015625,
-0.0270538330078125,
-0.01666259765625,
-0.0168304443359375,
-0.00679779052734375,
0.04254150390625,
0.050994873046875,
0.048004150390625,
-0.045806884765625,
-0.03192138671875,
-0.01053619384765625,
-0.039337158203125,
-0.00806427001953125,
0.00012755393981933594,
-0.02911376953125,
0.0156402587890625,
0.029296875,
-0.058135986328125,
0.0261993408203125,
0.034881591796875,
-0.03704833984375,
0.03460693359375,
0.0179595947265625,
0.0396728515625,
-0.10858154296875,
0.0086517333984375,
-0.0035858154296875,
-0.040985107421875,
-0.0290679931640625,
-0.006610870361328125,
0.005931854248046875,
-0.0048065185546875,
-0.051422119140625,
0.0528564453125,
-0.01247406005859375,
0.00457000732421875,
-0.00731658935546875,
-0.0034332275390625,
0.008453369140625,
0.045318603515625,
-0.027618408203125,
0.0391845703125,
0.032623291015625,
-0.036224365234375,
0.0222930908203125,
0.039764404296875,
-0.025482177734375,
0.0268096923828125,
-0.040008544921875,
-0.01123809814453125,
0.0033416748046875,
0.0269012451171875,
-0.068359375,
-0.01186370849609375,
0.02874755859375,
-0.05328369140625,
0.0233001708984375,
-0.00685882568359375,
-0.036865234375,
-0.04766845703125,
-0.0217742919921875,
0.0202789306640625,
0.055328369140625,
-0.0367431640625,
0.0380859375,
0.011383056640625,
0.00524139404296875,
-0.0433349609375,
-0.075927734375,
-0.02215576171875,
-0.02154541015625,
-0.053131103515625,
0.045318603515625,
-0.0086212158203125,
0.00472259521484375,
-0.0017538070678710938,
-0.0299224853515625,
0.00402069091796875,
0.00371551513671875,
0.01751708984375,
0.0125885009765625,
-0.01354217529296875,
-0.0014972686767578125,
0.0240936279296875,
-0.01448822021484375,
0.003147125244140625,
-0.033538818359375,
0.05340576171875,
-0.029632568359375,
-0.0182342529296875,
-0.053558349609375,
0.00516510009765625,
0.03961181640625,
-0.02203369140625,
0.064208984375,
0.08966064453125,
-0.03582763671875,
0.0104522705078125,
-0.029998779296875,
-0.030120849609375,
-0.04071044921875,
0.04638671875,
-0.037139892578125,
-0.07122802734375,
0.040252685546875,
-0.001979827880859375,
0.01277923583984375,
0.072509765625,
0.052154541015625,
0.002475738525390625,
0.0904541015625,
0.0124664306640625,
0.005130767822265625,
0.052825927734375,
-0.0238494873046875,
0.007137298583984375,
-0.039947509765625,
-0.0006680488586425781,
-0.0384521484375,
-0.037628173828125,
-0.0574951171875,
-0.04449462890625,
0.01079559326171875,
0.0037784576416015625,
-0.043060302734375,
0.04296875,
-0.034912109375,
0.0026378631591796875,
0.041107177734375,
0.004718780517578125,
0.0199127197265625,
-0.0025806427001953125,
-0.01238250732421875,
-0.012847900390625,
-0.042022705078125,
-0.0241546630859375,
0.076171875,
0.0250244140625,
0.03619384765625,
0.002857208251953125,
0.06243896484375,
0.0005311965942382812,
0.0167694091796875,
-0.04656982421875,
0.04833984375,
-0.003360748291015625,
-0.053192138671875,
-0.009552001953125,
-0.06463623046875,
-0.0699462890625,
0.031951904296875,
-0.007167816162109375,
-0.0635986328125,
0.0068817138671875,
-0.0124664306640625,
-0.005474090576171875,
0.0175628662109375,
-0.0384521484375,
0.08587646484375,
-0.00904083251953125,
-0.016326904296875,
-0.0112762451171875,
-0.050567626953125,
0.0303955078125,
-0.01143646240234375,
0.038299560546875,
-0.01776123046875,
0.02001953125,
0.0758056640625,
-0.03033447265625,
0.040985107421875,
-0.0210113525390625,
0.01076507568359375,
0.0232391357421875,
0.0018949508666992188,
0.0421142578125,
-0.00007587671279907227,
-0.0179595947265625,
0.0224456787109375,
0.035125732421875,
-0.0308380126953125,
-0.01427459716796875,
0.053955078125,
-0.05914306640625,
-0.03961181640625,
-0.033966064453125,
-0.042510986328125,
-0.0133209228515625,
0.037139892578125,
0.045501708984375,
0.03533935546875,
-0.009918212890625,
0.027679443359375,
0.0193023681640625,
-0.014129638671875,
0.034698486328125,
0.027618408203125,
-0.040191650390625,
-0.0309600830078125,
0.0694580078125,
0.01525115966796875,
0.0218658447265625,
0.022003173828125,
0.01519775390625,
-0.0297698974609375,
-0.0254669189453125,
-0.039520263671875,
0.0184478759765625,
-0.053802490234375,
-0.037872314453125,
-0.058135986328125,
-0.021240234375,
-0.043365478515625,
0.01042938232421875,
-0.044189453125,
-0.061065673828125,
-0.006977081298828125,
-0.0134124755859375,
0.0308074951171875,
0.0163726806640625,
-0.0174102783203125,
0.016326904296875,
-0.0704345703125,
0.01788330078125,
-0.0005908012390136719,
0.0187835693359375,
-0.01178741455078125,
-0.07550048828125,
-0.027435302734375,
0.023193359375,
-0.05230712890625,
-0.07562255859375,
0.025146484375,
0.00726318359375,
0.055572509765625,
0.01390838623046875,
0.0191802978515625,
0.04437255859375,
-0.034576416015625,
0.060455322265625,
0.0125732421875,
-0.08099365234375,
0.03265380859375,
-0.023101806640625,
0.0248870849609375,
0.04583740234375,
0.024322509765625,
-0.04168701171875,
-0.046142578125,
-0.06292724609375,
-0.06524658203125,
0.078369140625,
0.03253173828125,
0.016845703125,
0.0047454833984375,
0.005748748779296875,
-0.00060272216796875,
0.0186920166015625,
-0.06964111328125,
-0.0188751220703125,
-0.0311737060546875,
-0.033905029296875,
-0.0018100738525390625,
0.0096588134765625,
-0.01210784912109375,
-0.03424072265625,
0.076171875,
-0.005519866943359375,
0.037261962890625,
0.0159454345703125,
-0.0158233642578125,
-0.01541900634765625,
0.01366424560546875,
0.020050048828125,
0.037384033203125,
-0.00855255126953125,
-0.004528045654296875,
0.034210205078125,
-0.0177001953125,
0.0028095245361328125,
0.037872314453125,
-0.01393890380859375,
0.01496124267578125,
0.01715087890625,
0.0609130859375,
0.01338958740234375,
-0.04559326171875,
0.058441162109375,
-0.0025386810302734375,
-0.029144287109375,
-0.01116943359375,
-0.004302978515625,
0.01117706298828125,
0.04766845703125,
0.031890869140625,
0.021636962890625,
0.0184478759765625,
-0.028167724609375,
0.032470703125,
0.0215911865234375,
-0.05712890625,
-0.0286712646484375,
0.0694580078125,
0.0026187896728515625,
-0.01390838623046875,
0.03533935546875,
-0.041046142578125,
-0.04266357421875,
0.0394287109375,
0.039337158203125,
0.05279541015625,
-0.0138092041015625,
0.0152435302734375,
0.059173583984375,
0.0322265625,
-0.026336669921875,
0.02752685546875,
0.00893402099609375,
-0.04827880859375,
-0.034698486328125,
-0.0662841796875,
0.006504058837890625,
-0.007904052734375,
-0.062469482421875,
0.0321044921875,
0.0003025531768798828,
-0.0272674560546875,
-0.0243377685546875,
-0.0021800994873046875,
-0.062744140625,
0.01299285888671875,
-0.00688934326171875,
0.064208984375,
-0.06097412109375,
0.054534912109375,
0.058837890625,
-0.033782958984375,
-0.06280517578125,
-0.003520965576171875,
0.00238800048828125,
-0.044921875,
0.019500732421875,
0.032867431640625,
0.0221405029296875,
0.018096923828125,
-0.03076171875,
-0.0806884765625,
0.09893798828125,
0.01959228515625,
-0.037750244140625,
0.0081939697265625,
0.00457000732421875,
0.031463623046875,
-0.00015497207641601562,
0.022613525390625,
0.0286712646484375,
0.044219970703125,
0.006633758544921875,
-0.088623046875,
0.0298919677734375,
-0.0224761962890625,
-0.00897979736328125,
0.01629638671875,
-0.066650390625,
0.06793212890625,
-0.005832672119140625,
-0.018341064453125,
0.0182342529296875,
0.061126708984375,
0.034698486328125,
0.033966064453125,
0.037384033203125,
0.03314208984375,
0.04180908203125,
-0.03009033203125,
0.05999755859375,
-0.0160675048828125,
0.06494140625,
0.052337646484375,
0.00983428955078125,
0.047454833984375,
0.039337158203125,
-0.03271484375,
0.02569580078125,
0.049774169921875,
-0.0167694091796875,
0.03411865234375,
0.01036834716796875,
0.0219879150390625,
-0.02044677734375,
0.004917144775390625,
-0.049530029296875,
0.028839111328125,
0.0005135536193847656,
-0.0226287841796875,
-0.0166015625,
0.0160675048828125,
0.007480621337890625,
-0.01216888427734375,
-0.007305145263671875,
0.0277557373046875,
0.0234375,
-0.0439453125,
0.046142578125,
0.0245361328125,
0.05523681640625,
-0.03741455078125,
0.0230712890625,
-0.01959228515625,
0.0218963623046875,
-0.01202392578125,
-0.045166015625,
0.041748046875,
-0.008270263671875,
-0.00438690185546875,
-0.029632568359375,
0.0384521484375,
-0.0271148681640625,
-0.05267333984375,
0.0265045166015625,
0.04656982421875,
0.01357269287109375,
-0.01226806640625,
-0.066162109375,
0.006473541259765625,
0.0246124267578125,
-0.04803466796875,
0.0277557373046875,
0.038909912109375,
-0.0101776123046875,
0.02960205078125,
0.039825439453125,
-0.032012939453125,
0.0102996826171875,
0.0031585693359375,
0.05828857421875,
-0.056671142578125,
-0.02276611328125,
-0.04925537109375,
0.0528564453125,
0.0013914108276367188,
-0.023681640625,
0.055084228515625,
0.058380126953125,
0.06939697265625,
-0.01105499267578125,
0.037384033203125,
-0.023406982421875,
0.03314208984375,
-0.028656005859375,
0.057220458984375,
-0.07427978515625,
-0.004817962646484375,
-0.0316162109375,
-0.07171630859375,
0.005931854248046875,
0.046234130859375,
-0.00864410400390625,
0.01702880859375,
0.052398681640625,
0.059356689453125,
-0.009674072265625,
-0.0050201416015625,
0.01390838623046875,
0.03399658203125,
0.0260772705078125,
0.051544189453125,
0.06671142578125,
-0.07470703125,
0.06591796875,
-0.034820556640625,
-0.013397216796875,
-0.0174560546875,
-0.03509521484375,
-0.055633544921875,
-0.0548095703125,
-0.03070068359375,
-0.0526123046875,
-0.021881103515625,
0.06512451171875,
0.0361328125,
-0.056884765625,
-0.0023097991943359375,
0.006256103515625,
0.001857757568359375,
-0.03509521484375,
-0.02215576171875,
0.0200347900390625,
-0.02197265625,
-0.07745361328125,
0.033233642578125,
-0.009552001953125,
0.00356292724609375,
0.017242431640625,
-0.014251708984375,
-0.01541900634765625,
0.0004668235778808594,
0.03521728515625,
-0.0121002197265625,
-0.041534423828125,
-0.0252532958984375,
0.0188140869140625,
-0.0184173583984375,
-0.0019273757934570312,
0.0138397216796875,
-0.0377197265625,
0.006908416748046875,
0.05401611328125,
0.033355712890625,
0.05999755859375,
-0.002285003662109375,
0.030029296875,
-0.04150390625,
0.0226593017578125,
0.00839996337890625,
0.04632568359375,
0.00922393798828125,
-0.004520416259765625,
0.03875732421875,
0.0430908203125,
-0.040863037109375,
-0.0716552734375,
0.0060577392578125,
-0.08935546875,
-0.023712158203125,
0.08856201171875,
0.005268096923828125,
-0.0137176513671875,
0.01800537109375,
-0.01617431640625,
0.042236328125,
-0.0235443115234375,
0.038360595703125,
0.04620361328125,
0.00995635986328125,
0.007663726806640625,
-0.05194091796875,
0.017303466796875,
0.035003662109375,
-0.03643798828125,
-0.036102294921875,
0.0187835693359375,
0.028533935546875,
0.01395416259765625,
0.047821044921875,
-0.0278778076171875,
0.0217742919921875,
-0.013671875,
0.00684356689453125,
0.002513885498046875,
0.00670623779296875,
-0.007015228271484375,
-0.0078277587890625,
-0.00791168212890625,
-0.0259857177734375
]
] |
Helsinki-NLP/opus-mt-en-it | 2023-08-16T11:30:05.000Z | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"en",
"it",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-en-it | 8 | 38,089 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-en-it
* source languages: en
* target languages: it
* OPUS readme: [en-it](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/en-it/README.md)
* dataset: opus
* model: transformer
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2019-12-04.zip](https://object.pouta.csc.fi/OPUS-MT-models/en-it/opus-2019-12-04.zip)
* test set translations: [opus-2019-12-04.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-it/opus-2019-12-04.test.txt)
* test set scores: [opus-2019-12-04.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/en-it/opus-2019-12-04.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| newssyscomb2009.en.it | 30.9 | 0.606 |
| newstest2009.en.it | 31.9 | 0.604 |
| Tatoeba.en.it | 48.2 | 0.695 |
| 895 | [
[
-0.0222930908203125,
-0.0270843505859375,
0.0164031982421875,
0.03411865234375,
-0.035919189453125,
-0.024078369140625,
-0.034698486328125,
-0.002147674560546875,
0.001476287841796875,
0.034393310546875,
-0.047607421875,
-0.044708251953125,
-0.044281005859375,
0.0163116455078125,
-0.01383209228515625,
0.05169677734375,
-0.0114593505859375,
0.034210205078125,
0.018951416015625,
-0.0296478271484375,
-0.0273284912109375,
-0.0311737060546875,
-0.036712646484375,
-0.0225372314453125,
0.01528167724609375,
0.033111572265625,
0.02880859375,
0.0297393798828125,
0.068115234375,
0.01983642578125,
-0.0070648193359375,
-0.0041351318359375,
-0.031707763671875,
-0.01157379150390625,
0.005126953125,
-0.04205322265625,
-0.051361083984375,
-0.01256561279296875,
0.08294677734375,
0.031982421875,
-0.0016078948974609375,
0.030181884765625,
-0.0004868507385253906,
0.0721435546875,
-0.0243988037109375,
0.00839996337890625,
-0.0452880859375,
0.006328582763671875,
-0.029388427734375,
-0.0294647216796875,
-0.05218505859375,
-0.014404296875,
0.006259918212890625,
-0.046051025390625,
-0.001667022705078125,
0.01369476318359375,
0.1065673828125,
0.0220489501953125,
-0.0256195068359375,
-0.0071258544921875,
-0.047607421875,
0.078125,
-0.062164306640625,
0.0460205078125,
0.03253173828125,
0.0217132568359375,
0.0213470458984375,
-0.0421142578125,
-0.0182647705078125,
0.0017805099487304688,
-0.0158233642578125,
0.01477813720703125,
-0.011566162109375,
-0.0197296142578125,
0.023834228515625,
0.06134033203125,
-0.0548095703125,
-0.00461578369140625,
-0.052337646484375,
0.001007080078125,
0.050872802734375,
0.01151275634765625,
0.00858306884765625,
-0.007049560546875,
-0.0265350341796875,
-0.042633056640625,
-0.060089111328125,
0.010955810546875,
0.0230865478515625,
0.0202484130859375,
-0.030487060546875,
0.05157470703125,
-0.014129638671875,
0.050018310546875,
-0.00617218017578125,
0.0015850067138671875,
0.0753173828125,
-0.029296875,
-0.0243682861328125,
-0.01425933837890625,
0.088623046875,
0.0301513671875,
0.01070404052734375,
0.0018310546875,
-0.0161285400390625,
-0.01459503173828125,
0.01332855224609375,
-0.0728759765625,
-0.0043182373046875,
0.0159912109375,
-0.0306396484375,
-0.002902984619140625,
-0.0010662078857421875,
-0.043853759765625,
0.0173187255859375,
-0.0288848876953125,
0.044830322265625,
-0.04925537109375,
-0.0252838134765625,
0.0281219482421875,
0.00032329559326171875,
0.0204010009765625,
-0.007411956787109375,
-0.041015625,
0.0163726806640625,
0.0239715576171875,
0.052276611328125,
-0.03363037109375,
-0.0212860107421875,
-0.034210205078125,
-0.0167083740234375,
-0.00977325439453125,
0.05133056640625,
-0.00930023193359375,
-0.032806396484375,
-0.004047393798828125,
0.03277587890625,
-0.031341552734375,
-0.0300445556640625,
0.1024169921875,
-0.0204010009765625,
0.05145263671875,
-0.033172607421875,
-0.044036865234375,
-0.0273895263671875,
0.03900146484375,
-0.044891357421875,
0.091552734375,
0.007232666015625,
-0.06451416015625,
0.01702880859375,
-0.05865478515625,
-0.014801025390625,
-0.004791259765625,
0.005859375,
-0.045196533203125,
0.007617950439453125,
0.00899505615234375,
0.0292510986328125,
-0.035064697265625,
0.0227508544921875,
0.0007424354553222656,
-0.0263519287109375,
-0.0006761550903320312,
-0.021728515625,
0.077880859375,
0.0242462158203125,
-0.02471923828125,
0.02130126953125,
-0.075439453125,
0.003231048583984375,
0.00033545494079589844,
-0.039215087890625,
-0.0100250244140625,
0.0093841552734375,
0.0217742919921875,
0.007129669189453125,
0.01959228515625,
-0.047943115234375,
0.0178680419921875,
-0.04498291015625,
0.0162353515625,
0.048675537109375,
-0.02081298828125,
0.029754638671875,
-0.033294677734375,
0.01641845703125,
0.006832122802734375,
0.013580322265625,
0.00067901611328125,
-0.032806396484375,
-0.06304931640625,
-0.0244293212890625,
0.0418701171875,
0.0787353515625,
-0.055511474609375,
0.06011962890625,
-0.046417236328125,
-0.0584716796875,
-0.055419921875,
-0.01105499267578125,
0.0258636474609375,
0.0263519287109375,
0.03759765625,
-0.0106353759765625,
-0.03271484375,
-0.07958984375,
-0.01558685302734375,
-0.0134735107421875,
-0.0178375244140625,
0.00833892822265625,
0.04547119140625,
-0.013702392578125,
0.0302276611328125,
-0.032135009765625,
-0.03619384765625,
-0.00933074951171875,
0.00647735595703125,
0.042724609375,
0.048004150390625,
0.037750244140625,
-0.06280517578125,
-0.04443359375,
-0.0046539306640625,
-0.052825927734375,
-0.01073455810546875,
0.01025390625,
-0.01092529296875,
-0.0007948875427246094,
0.005283355712890625,
-0.0186004638671875,
0.006710052490234375,
0.046783447265625,
-0.049591064453125,
0.036041259765625,
-0.00855255126953125,
0.0282745361328125,
-0.09857177734375,
0.00841522216796875,
-0.01141357421875,
-0.00350189208984375,
-0.03594970703125,
0.005542755126953125,
0.0213470458984375,
0.0119476318359375,
-0.053955078125,
0.0450439453125,
-0.0184783935546875,
-0.01027679443359375,
0.01959228515625,
-0.0026111602783203125,
0.0037059783935546875,
0.052276611328125,
-0.002704620361328125,
0.061798095703125,
0.06097412109375,
-0.043365478515625,
0.00872802734375,
0.03765869140625,
-0.03216552734375,
0.032440185546875,
-0.060089111328125,
-0.0220947265625,
0.0286102294921875,
-0.015655517578125,
-0.045074462890625,
0.01107025146484375,
0.0208740234375,
-0.0445556640625,
0.027587890625,
-0.00028967857360839844,
-0.061279296875,
-0.006877899169921875,
-0.0251312255859375,
0.032928466796875,
0.050384521484375,
-0.0120697021484375,
0.047760009765625,
0.0053253173828125,
0.00022804737091064453,
-0.030487060546875,
-0.07025146484375,
-0.003997802734375,
-0.029510498046875,
-0.062255859375,
0.0180511474609375,
-0.0389404296875,
-0.01033782958984375,
0.0024509429931640625,
0.0242462158203125,
-0.01374053955078125,
0.00434112548828125,
0.006221771240234375,
0.01580810546875,
-0.034454345703125,
0.0097503662109375,
-0.0023136138916015625,
-0.01324462890625,
-0.01335906982421875,
-0.01151275634765625,
0.043182373046875,
-0.031768798828125,
-0.0194244384765625,
-0.0430908203125,
0.00739288330078125,
0.040618896484375,
-0.0310211181640625,
0.056976318359375,
0.04046630859375,
-0.006488800048828125,
0.015228271484375,
-0.0290374755859375,
0.0036716461181640625,
-0.033843994140625,
0.00733184814453125,
-0.040863037109375,
-0.057159423828125,
0.040283203125,
0.007366180419921875,
0.040802001953125,
0.0628662109375,
0.050201416015625,
0.007366180419921875,
0.052001953125,
0.027618408203125,
-0.0034809112548828125,
0.035919189453125,
-0.038665771484375,
-0.014129638671875,
-0.07366943359375,
0.0090484619140625,
-0.05615234375,
-0.0222015380859375,
-0.0635986328125,
-0.019744873046875,
0.0248260498046875,
0.0032100677490234375,
-0.022308349609375,
0.0516357421875,
-0.042144775390625,
0.01444244384765625,
0.0452880859375,
-0.01043701171875,
0.030670166015625,
0.005435943603515625,
-0.038787841796875,
-0.0210723876953125,
-0.0335693359375,
-0.035003662109375,
0.09771728515625,
0.0249786376953125,
0.0234375,
0.01369476318359375,
0.037200927734375,
0.0031299591064453125,
0.0211181640625,
-0.04229736328125,
0.0305938720703125,
-0.022216796875,
-0.054534912109375,
-0.0179901123046875,
-0.04327392578125,
-0.056793212890625,
0.03448486328125,
-0.01461029052734375,
-0.045654296875,
0.010986328125,
0.00049591064453125,
-0.0024166107177734375,
0.034942626953125,
-0.048492431640625,
0.08087158203125,
-0.0025539398193359375,
-0.01020050048828125,
0.0142822265625,
-0.024078369140625,
0.0166015625,
0.004116058349609375,
0.0222015380859375,
-0.0129241943359375,
0.01128387451171875,
0.04669189453125,
-0.0066680908203125,
0.0252227783203125,
-0.0011167526245117188,
-0.004825592041015625,
0.006534576416015625,
0.009613037109375,
0.029296875,
-0.01010894775390625,
-0.0406494140625,
0.034271240234375,
0.002193450927734375,
-0.03607177734375,
-0.0032329559326171875,
0.03741455078125,
-0.051055908203125,
-0.006832122802734375,
-0.0282745361328125,
-0.052459716796875,
-0.00038361549377441406,
0.0247955322265625,
0.05950927734375,
0.049896240234375,
-0.0160980224609375,
0.042938232421875,
0.0604248046875,
-0.0216522216796875,
0.0286102294921875,
0.057403564453125,
-0.0169830322265625,
-0.0374755859375,
0.06488037109375,
0.00754547119140625,
0.0260467529296875,
0.0421142578125,
0.00780487060546875,
-0.005985260009765625,
-0.057403564453125,
-0.05523681640625,
0.0155181884765625,
-0.0263519287109375,
-0.00870513916015625,
-0.04486083984375,
-0.00664520263671875,
-0.01332855224609375,
0.0184478759765625,
-0.0438232421875,
-0.0396728515625,
-0.00836181640625,
-0.01535797119140625,
0.016448974609375,
0.0191650390625,
-0.004718780517578125,
0.0380859375,
-0.0738525390625,
0.01824951171875,
-0.013214111328125,
0.0276641845703125,
-0.04217529296875,
-0.0628662109375,
-0.0290374755859375,
0.0002846717834472656,
-0.04400634765625,
-0.05316162109375,
0.03802490234375,
0.01187896728515625,
0.0207061767578125,
0.0233001708984375,
0.01090240478515625,
0.0220184326171875,
-0.054962158203125,
0.07403564453125,
-0.00868988037109375,
-0.0538330078125,
0.031494140625,
-0.0288238525390625,
0.03631591796875,
0.06573486328125,
0.0182952880859375,
-0.02313232421875,
-0.04559326171875,
-0.0526123046875,
-0.06219482421875,
0.059234619140625,
0.05712890625,
-0.0118408203125,
0.0185089111328125,
-0.01250457763671875,
-0.0021190643310546875,
0.0174713134765625,
-0.08160400390625,
-0.031646728515625,
0.0054473876953125,
-0.02386474609375,
-0.0160064697265625,
-0.0199432373046875,
-0.01812744140625,
-0.018768310546875,
0.0804443359375,
0.0097198486328125,
0.0200042724609375,
0.0248260498046875,
-0.01239776611328125,
-0.0163116455078125,
0.02716064453125,
0.06817626953125,
0.042572021484375,
-0.040985107421875,
-0.01080322265625,
0.019775390625,
-0.0264129638671875,
-0.0124969482421875,
0.0099334716796875,
-0.032318115234375,
0.025787353515625,
0.033843994140625,
0.081787109375,
0.01108551025390625,
-0.0460205078125,
0.031890869140625,
-0.02960205078125,
-0.03271484375,
-0.045654296875,
-0.00908660888671875,
0.00966644287109375,
0.007781982421875,
0.0194244384765625,
0.011566162109375,
0.020294189453125,
-0.0183868408203125,
0.0115203857421875,
0.006198883056640625,
-0.043365478515625,
-0.040130615234375,
0.033477783203125,
0.00765228271484375,
-0.0249786376953125,
0.034027099609375,
-0.029998779296875,
-0.04461669921875,
0.031494140625,
0.01085662841796875,
0.08099365234375,
-0.0198211669921875,
-0.01248931884765625,
0.06219482421875,
0.04974365234375,
-0.0202178955078125,
0.041717529296875,
0.0033092498779296875,
-0.05023193359375,
-0.036346435546875,
-0.054901123046875,
-0.0120086669921875,
0.00829315185546875,
-0.058929443359375,
0.0273895263671875,
0.01904296875,
0.004924774169921875,
-0.022735595703125,
0.01407623291015625,
-0.0455322265625,
0.0085601806640625,
-0.024688720703125,
0.083740234375,
-0.0677490234375,
0.06170654296875,
0.035858154296875,
-0.01947021484375,
-0.0592041015625,
-0.0172271728515625,
-0.0173187255859375,
-0.033477783203125,
0.047515869140625,
0.01012420654296875,
0.02838134765625,
-0.00772857666015625,
-0.015533447265625,
-0.0621337890625,
0.0802001953125,
0.0149078369140625,
-0.04815673828125,
0.00609588623046875,
0.013214111328125,
0.03594970703125,
-0.026458740234375,
0.01496124267578125,
0.03350830078125,
0.057037353515625,
0.004913330078125,
-0.08514404296875,
-0.0207366943359375,
-0.0455322265625,
-0.0289459228515625,
0.035247802734375,
-0.042236328125,
0.082275390625,
0.031280517578125,
-0.0118560791015625,
0.003753662109375,
0.034820556640625,
0.0206756591796875,
0.02117919921875,
0.042633056640625,
0.081787109375,
0.0290679931640625,
-0.03533935546875,
0.0802001953125,
-0.02947998046875,
0.035430908203125,
0.09002685546875,
-0.0028057098388671875,
0.06719970703125,
0.0209808349609375,
-0.00914764404296875,
0.032989501953125,
0.049285888671875,
-0.0206298828125,
0.037017822265625,
0.005504608154296875,
0.0112457275390625,
-0.00980377197265625,
0.01690673828125,
-0.052001953125,
0.0131072998046875,
0.016265869140625,
-0.0190277099609375,
-0.0036525726318359375,
-0.0024280548095703125,
0.0011234283447265625,
-0.0035247802734375,
-0.0127105712890625,
0.048614501953125,
-0.0013828277587890625,
-0.043914794921875,
0.05963134765625,
-0.0029773712158203125,
0.046905517578125,
-0.0516357421875,
0.01073455810546875,
-0.00591278076171875,
0.0218048095703125,
0.0012989044189453125,
-0.0447998046875,
0.035675048828125,
0.00614166259765625,
-0.0180816650390625,
-0.031402587890625,
0.0181732177734375,
-0.03558349609375,
-0.06573486328125,
0.0328369140625,
0.031036376953125,
0.0230255126953125,
-0.00849151611328125,
-0.0673828125,
0.00927734375,
0.0125885009765625,
-0.049652099609375,
-0.001285552978515625,
0.049957275390625,
0.018402099609375,
0.0391845703125,
0.0384521484375,
0.0176544189453125,
0.020782470703125,
-0.0008687973022460938,
0.05438232421875,
-0.0343017578125,
-0.031951904296875,
-0.056976318359375,
0.06427001953125,
-0.01416015625,
-0.047149658203125,
0.052276611328125,
0.07000732421875,
0.0772705078125,
-0.007694244384765625,
0.019439697265625,
-0.0067596435546875,
0.050201416015625,
-0.0438232421875,
0.037841796875,
-0.06976318359375,
0.023712158203125,
-0.00749969482421875,
-0.07269287109375,
-0.01044464111328125,
0.0214691162109375,
-0.01486968994140625,
-0.0270233154296875,
0.061187744140625,
0.04754638671875,
-0.010101318359375,
-0.01212310791015625,
0.0261688232421875,
0.026641845703125,
0.0175323486328125,
0.0447998046875,
0.0311279296875,
-0.0745849609375,
0.038360595703125,
-0.02667236328125,
-0.007106781005859375,
0.0004315376281738281,
-0.051422119140625,
-0.066650390625,
-0.04925537109375,
-0.01507568359375,
-0.0166473388671875,
-0.0218505859375,
0.06402587890625,
0.038177490234375,
-0.07110595703125,
-0.04443359375,
-0.000011265277862548828,
0.00881195068359375,
-0.01558685302734375,
-0.019256591796875,
0.040679931640625,
-0.0244903564453125,
-0.0721435546875,
0.03265380859375,
0.007770538330078125,
-0.017242431640625,
-0.00019109249114990234,
-0.01971435546875,
-0.034088134765625,
-0.004634857177734375,
0.0202484130859375,
0.00048041343688964844,
-0.035614013671875,
0.010223388671875,
0.0120086669921875,
-0.005634307861328125,
0.032257080078125,
0.02923583984375,
-0.0185394287109375,
0.02166748046875,
0.06103515625,
0.0273895263671875,
0.03826904296875,
-0.0210418701171875,
0.038909912109375,
-0.056121826171875,
0.0249786376953125,
0.0145721435546875,
0.0462646484375,
0.031341552734375,
-0.0022563934326171875,
0.06658935546875,
0.013458251953125,
-0.044769287109375,
-0.0792236328125,
0.004154205322265625,
-0.08282470703125,
-0.003360748291015625,
0.07220458984375,
-0.0205078125,
-0.021636962890625,
0.0276947021484375,
-0.014495849609375,
0.010223388671875,
-0.0259552001953125,
0.034210205078125,
0.06207275390625,
0.030914306640625,
0.004215240478515625,
-0.06231689453125,
0.0285186767578125,
0.03790283203125,
-0.060791015625,
-0.01511383056640625,
0.01444244384765625,
0.01369476318359375,
0.03338623046875,
0.043701171875,
-0.02105712890625,
0.0079345703125,
-0.0170440673828125,
0.0307159423828125,
-0.0030574798583984375,
-0.01300048828125,
-0.018951416015625,
0.0026836395263671875,
-0.003391265869140625,
-0.0225677490234375
]
] |
timm/mnasnet_100.rmsp_in1k | 2023-04-27T21:14:03.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1807.11626",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/mnasnet_100.rmsp_in1k | 0 | 38,080 | timm | 2022-12-13T00:00:04 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for mnasnet_100.rmsp_in1k
A MNasNet image classification model. Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* A simple RmsProp based recipe without RandAugment. Using RandomErasing, mixup, dropout, standard random-resize-crop augmentation.
* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
* Step (exponential decay w/ staircase) LR schedule with warmup
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 4.4
- GMACs: 0.3
- Activations (M): 5.5
- Image size: 224 x 224
- **Papers:**
- MnasNet: Platform-Aware Neural Architecture Search for Mobi: https://arxiv.org/abs/1807.11626
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('mnasnet_100.rmsp_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'mnasnet_100.rmsp_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 16, 112, 112])
# torch.Size([1, 24, 56, 56])
# torch.Size([1, 40, 28, 28])
# torch.Size([1, 96, 14, 14])
# torch.Size([1, 320, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'mnasnet_100.rmsp_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@inproceedings{tan2019mnasnet,
title={Mnasnet: Platform-aware neural architecture search for mobile},
author={Tan, Mingxing and Chen, Bo and Pang, Ruoming and Vasudevan, Vijay and Sandler, Mark and Howard, Andrew and Le, Quoc V},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={2820--2828},
year={2019}
}
```
| 4,367 | [
[
-0.036407470703125,
-0.02972412109375,
-0.0017757415771484375,
0.013153076171875,
-0.0235443115234375,
-0.0328369140625,
-0.0093231201171875,
-0.0231475830078125,
0.034149169921875,
0.035614013671875,
-0.0391845703125,
-0.054443359375,
-0.0517578125,
-0.012237548828125,
-0.01009368896484375,
0.0645751953125,
-0.00439453125,
0.0031280517578125,
-0.01904296875,
-0.043121337890625,
-0.014678955078125,
-0.033447265625,
-0.06890869140625,
-0.0297393798828125,
0.02093505859375,
0.011749267578125,
0.039337158203125,
0.048858642578125,
0.04412841796875,
0.03656005859375,
-0.016510009765625,
0.01128387451171875,
-0.005523681640625,
-0.01448822021484375,
0.0308685302734375,
-0.048370361328125,
-0.039947509765625,
0.0178070068359375,
0.04766845703125,
0.0243377685546875,
-0.0009288787841796875,
0.0357666015625,
0.005828857421875,
0.0467529296875,
-0.0212249755859375,
0.0028514862060546875,
-0.03472900390625,
0.02581787109375,
-0.00841522216796875,
-0.0027637481689453125,
-0.0209197998046875,
-0.0253143310546875,
0.011199951171875,
-0.0316162109375,
0.0300445556640625,
-0.0023403167724609375,
0.0958251953125,
0.01666259765625,
-0.0036106109619140625,
-0.007549285888671875,
-0.01348876953125,
0.0594482421875,
-0.06524658203125,
0.01088714599609375,
0.0295867919921875,
0.01552581787109375,
-0.00440216064453125,
-0.072265625,
-0.03955078125,
-0.01502227783203125,
-0.00995635986328125,
-0.00661468505859375,
-0.010589599609375,
-0.0031681060791015625,
0.020904541015625,
0.0225677490234375,
-0.039947509765625,
0.00449371337890625,
-0.037872314453125,
-0.01593017578125,
0.043914794921875,
0.0039043426513671875,
0.0283203125,
-0.02276611328125,
-0.041839599609375,
-0.0274200439453125,
-0.0292510986328125,
0.0192718505859375,
0.016693115234375,
0.0200042724609375,
-0.045440673828125,
0.036651611328125,
0.0153045654296875,
0.04180908203125,
0.00039267539978027344,
-0.0232391357421875,
0.04669189453125,
0.005859375,
-0.034332275390625,
-0.004550933837890625,
0.0826416015625,
0.0266571044921875,
0.01519775390625,
0.01153564453125,
-0.01959228515625,
-0.02606201171875,
-0.000522613525390625,
-0.0860595703125,
-0.0213775634765625,
0.0287322998046875,
-0.05389404296875,
-0.033172607421875,
0.0172271728515625,
-0.042266845703125,
-0.0116119384765625,
-0.006229400634765625,
0.046875,
-0.038543701171875,
-0.02716064453125,
0.0023975372314453125,
-0.018646240234375,
0.018829345703125,
0.004726409912109375,
-0.04486083984375,
0.018798828125,
0.0222930908203125,
0.09136962890625,
0.007236480712890625,
-0.036956787109375,
-0.017181396484375,
-0.026885986328125,
-0.0229034423828125,
0.0316162109375,
-0.0015687942504882812,
-0.013580322265625,
-0.026885986328125,
0.019622802734375,
-0.0166015625,
-0.0595703125,
0.0208587646484375,
-0.015533447265625,
0.0196990966796875,
-0.0058135986328125,
-0.017669677734375,
-0.034423828125,
0.023590087890625,
-0.03466796875,
0.09771728515625,
0.0205230712890625,
-0.05975341796875,
0.02099609375,
-0.050262451171875,
-0.01300048828125,
-0.026397705078125,
-0.004802703857421875,
-0.0772705078125,
-0.004150390625,
0.019866943359375,
0.059326171875,
-0.016632080078125,
-0.00093841552734375,
-0.03607177734375,
-0.0178070068359375,
0.02752685546875,
-0.0035247802734375,
0.08038330078125,
0.0140533447265625,
-0.036865234375,
0.0207061767578125,
-0.048126220703125,
0.0159912109375,
0.044403076171875,
-0.016448974609375,
-0.0030460357666015625,
-0.041168212890625,
0.0149383544921875,
0.03033447265625,
0.007781982421875,
-0.038055419921875,
0.016387939453125,
-0.01342010498046875,
0.0361328125,
0.0509033203125,
-0.0089874267578125,
0.026092529296875,
-0.0325927734375,
0.022003173828125,
0.028839111328125,
0.0201568603515625,
-0.008087158203125,
-0.04351806640625,
-0.0650634765625,
-0.03955078125,
0.033203125,
0.03302001953125,
-0.03656005859375,
0.0399169921875,
-0.00925445556640625,
-0.056365966796875,
-0.038360595703125,
0.00911712646484375,
0.040679931640625,
0.039947509765625,
0.0244903564453125,
-0.0443115234375,
-0.043182373046875,
-0.06878662109375,
0.005229949951171875,
0.00955963134765625,
-0.00524139404296875,
0.028106689453125,
0.051177978515625,
-0.00487518310546875,
0.048126220703125,
-0.031097412109375,
-0.027252197265625,
-0.0140380859375,
0.0080718994140625,
0.029205322265625,
0.0643310546875,
0.0665283203125,
-0.0565185546875,
-0.035400390625,
-0.0125732421875,
-0.0750732421875,
0.0157318115234375,
-0.0087738037109375,
-0.01390838623046875,
0.026947021484375,
0.01328277587890625,
-0.05621337890625,
0.044769287109375,
0.0185699462890625,
-0.0232086181640625,
0.0325927734375,
-0.0149993896484375,
0.018096923828125,
-0.0926513671875,
0.0103759765625,
0.032440185546875,
-0.00823974609375,
-0.0295562744140625,
0.0081634521484375,
0.0007619857788085938,
-0.01238250732421875,
-0.041259765625,
0.048980712890625,
-0.042999267578125,
-0.0200347900390625,
-0.00882720947265625,
-0.01448822021484375,
0.00003534555435180664,
0.05828857421875,
-0.0055389404296875,
0.03271484375,
0.062469482421875,
-0.043731689453125,
0.0301361083984375,
0.0284423828125,
-0.01284027099609375,
0.0284881591796875,
-0.0513916015625,
0.01461029052734375,
0.0003070831298828125,
0.0167999267578125,
-0.069580078125,
-0.01012420654296875,
0.0265655517578125,
-0.04840087890625,
0.047576904296875,
-0.04205322265625,
-0.0347900390625,
-0.03546142578125,
-0.03509521484375,
0.0251312255859375,
0.04931640625,
-0.053131103515625,
0.043548583984375,
0.0218658447265625,
0.02032470703125,
-0.04351806640625,
-0.0653076171875,
-0.01226043701171875,
-0.029083251953125,
-0.051422119140625,
0.030029296875,
0.00916290283203125,
0.0098876953125,
0.00689697265625,
-0.0087738037109375,
-0.00804901123046875,
-0.0105438232421875,
0.0478515625,
0.028656005859375,
-0.03302001953125,
-0.00936126708984375,
-0.0244293212890625,
-0.006542205810546875,
0.0032062530517578125,
-0.0251312255859375,
0.054107666015625,
-0.0223541259765625,
-0.01433563232421875,
-0.06622314453125,
-0.00738525390625,
0.04296875,
-0.01358795166015625,
0.06634521484375,
0.07745361328125,
-0.0439453125,
-0.0030689239501953125,
-0.029083251953125,
-0.021636962890625,
-0.036865234375,
0.0293121337890625,
-0.038482666015625,
-0.0228271484375,
0.06378173828125,
0.0021514892578125,
0.00380706787109375,
0.0546875,
0.0240020751953125,
-0.004550933837890625,
0.059967041015625,
0.04302978515625,
0.00853729248046875,
0.049041748046875,
-0.07373046875,
-0.0187530517578125,
-0.06378173828125,
-0.037994384765625,
-0.03076171875,
-0.047332763671875,
-0.0460205078125,
-0.0280609130859375,
0.0303802490234375,
0.008758544921875,
-0.0280609130859375,
0.04132080078125,
-0.06494140625,
0.008636474609375,
0.05364990234375,
0.04986572265625,
-0.02978515625,
0.0219879150390625,
-0.026458740234375,
-0.0018110275268554688,
-0.061004638671875,
-0.022735595703125,
0.08282470703125,
0.037109375,
0.037872314453125,
-0.01364898681640625,
0.054718017578125,
-0.01540374755859375,
0.02545166015625,
-0.04437255859375,
0.05108642578125,
-0.01175689697265625,
-0.0328369140625,
-0.01114654541015625,
-0.035308837890625,
-0.07220458984375,
0.0147247314453125,
-0.0255889892578125,
-0.05126953125,
0.00847625732421875,
0.00921630859375,
-0.012298583984375,
0.06268310546875,
-0.061737060546875,
0.0697021484375,
-0.0158843994140625,
-0.0224609375,
0.005519866943359375,
-0.05029296875,
0.0196533203125,
0.020477294921875,
-0.0172271728515625,
-0.00656890869140625,
0.01172637939453125,
0.07965087890625,
-0.044769287109375,
0.06378173828125,
-0.03765869140625,
0.029632568359375,
0.035675048828125,
-0.0070648193359375,
0.0198974609375,
-0.01506805419921875,
-0.01461029052734375,
0.0306549072265625,
0.004688262939453125,
-0.0408935546875,
-0.041015625,
0.045440673828125,
-0.0673828125,
-0.020660400390625,
-0.026947021484375,
-0.03363037109375,
0.01430511474609375,
0.006229400634765625,
0.041717529296875,
0.052154541015625,
0.0142364501953125,
0.01540374755859375,
0.046905517578125,
-0.032745361328125,
0.031463623046875,
-0.01265716552734375,
-0.0223541259765625,
-0.03692626953125,
0.06414794921875,
0.01514434814453125,
0.0060882568359375,
0.012359619140625,
0.01348876953125,
-0.0238189697265625,
-0.039642333984375,
-0.0322265625,
0.0250091552734375,
-0.049835205078125,
-0.03515625,
-0.0452880859375,
-0.041351318359375,
-0.029998779296875,
-0.003948211669921875,
-0.03936767578125,
-0.032470703125,
-0.02972412109375,
0.0191192626953125,
0.0465087890625,
0.04193115234375,
-0.006855010986328125,
0.04180908203125,
-0.042633056640625,
0.012359619140625,
0.0033016204833984375,
0.03656005859375,
-0.004680633544921875,
-0.065673828125,
-0.01471710205078125,
-0.002704620361328125,
-0.034820556640625,
-0.052734375,
0.042083740234375,
0.0120086669921875,
0.0372314453125,
0.030029296875,
-0.019775390625,
0.0565185546875,
-0.0030422210693359375,
0.042266845703125,
0.0311279296875,
-0.048370361328125,
0.053375244140625,
0.0034999847412109375,
0.015777587890625,
0.00348663330078125,
0.033966064453125,
-0.0191802978515625,
0.003559112548828125,
-0.072021484375,
-0.052947998046875,
0.0606689453125,
0.01062774658203125,
0.0018892288208007812,
0.026153564453125,
0.05181884765625,
-0.0045318603515625,
0.005084991455078125,
-0.05230712890625,
-0.03662109375,
-0.023956298828125,
-0.021514892578125,
-0.0005908012390136719,
-0.004749298095703125,
-0.00919342041015625,
-0.048980712890625,
0.0550537109375,
-0.00009548664093017578,
0.05816650390625,
0.0260009765625,
-0.001857757568359375,
-0.00716400146484375,
-0.03375244140625,
0.043426513671875,
0.0246429443359375,
-0.02606201171875,
0.005680084228515625,
0.0158538818359375,
-0.045989990234375,
0.0026950836181640625,
0.006931304931640625,
0.0011339187622070312,
0.01052093505859375,
0.02716064453125,
0.06964111328125,
0.0023040771484375,
-0.002166748046875,
0.028656005859375,
-0.005855560302734375,
-0.033203125,
-0.0223846435546875,
0.00959014892578125,
0.00044918060302734375,
0.0306854248046875,
0.0288848876953125,
0.03485107421875,
-0.0147705078125,
-0.02117919921875,
0.02313232421875,
0.045318603515625,
-0.02081298828125,
-0.021392822265625,
0.048492431640625,
-0.0193939208984375,
-0.02362060546875,
0.06256103515625,
-0.003936767578125,
-0.0416259765625,
0.0869140625,
0.034637451171875,
0.0672607421875,
-0.00965118408203125,
0.005336761474609375,
0.059234619140625,
0.020843505859375,
0.0023250579833984375,
0.01343536376953125,
0.01081085205078125,
-0.0535888671875,
0.01323699951171875,
-0.0469970703125,
0.0031642913818359375,
0.0295867919921875,
-0.040191650390625,
0.02471923828125,
-0.060089111328125,
-0.03460693359375,
0.0157318115234375,
0.02191162109375,
-0.06451416015625,
0.0228424072265625,
-0.00545501708984375,
0.07135009765625,
-0.054107666015625,
0.05194091796875,
0.06707763671875,
-0.044342041015625,
-0.0703125,
-0.0061187744140625,
0.00820159912109375,
-0.07379150390625,
0.04315185546875,
0.036468505859375,
0.01346588134765625,
-0.0005726814270019531,
-0.061126708984375,
-0.0450439453125,
0.10736083984375,
0.037872314453125,
0.0005464553833007812,
0.0213165283203125,
-0.0024776458740234375,
0.0172576904296875,
-0.03802490234375,
0.031463623046875,
0.007221221923828125,
0.021575927734375,
0.024810791015625,
-0.053680419921875,
0.02008056640625,
-0.028472900390625,
0.010986328125,
0.016265869140625,
-0.05535888671875,
0.0653076171875,
-0.0357666015625,
-0.0103302001953125,
0.00655364990234375,
0.0521240234375,
0.023590087890625,
0.022430419921875,
0.037811279296875,
0.0650634765625,
0.038238525390625,
-0.01508331298828125,
0.066162109375,
-0.003650665283203125,
0.040008544921875,
0.043243408203125,
0.0279693603515625,
0.052886962890625,
0.0305023193359375,
-0.02191162109375,
0.027587890625,
0.08599853515625,
-0.02294921875,
0.020477294921875,
0.0181121826171875,
-0.00003713369369506836,
-0.00262451171875,
0.00998687744140625,
-0.033966064453125,
0.040863037109375,
0.0142822265625,
-0.04913330078125,
-0.0096588134765625,
0.0023136138916015625,
-0.0009260177612304688,
-0.0237274169921875,
-0.01739501953125,
0.03326416015625,
0.007572174072265625,
-0.0279388427734375,
0.0693359375,
0.01136016845703125,
0.06988525390625,
-0.0335693359375,
0.0023670196533203125,
-0.02337646484375,
0.0124053955078125,
-0.029205322265625,
-0.05535888671875,
0.023681640625,
-0.025787353515625,
-0.0022792816162109375,
0.0021800994873046875,
0.050445556640625,
-0.0197906494140625,
-0.03271484375,
0.00861358642578125,
0.023529052734375,
0.04345703125,
-0.003849029541015625,
-0.09393310546875,
0.01070404052734375,
0.0004324913024902344,
-0.04949951171875,
0.033660888671875,
0.028778076171875,
0.01226043701171875,
0.06268310546875,
0.0479736328125,
-0.005401611328125,
0.0108184814453125,
-0.0212860107421875,
0.0611572265625,
-0.038818359375,
-0.0197906494140625,
-0.059326171875,
0.04644775390625,
-0.0109710693359375,
-0.049530029296875,
0.037445068359375,
0.047637939453125,
0.060272216796875,
-0.0078887939453125,
0.028228759765625,
-0.0192718505859375,
-0.00595855712890625,
-0.040496826171875,
0.061004638671875,
-0.057952880859375,
0.0034732818603515625,
-0.00762939453125,
-0.0550537109375,
-0.0225372314453125,
0.054718017578125,
-0.01323699951171875,
0.036224365234375,
0.036163330078125,
0.08172607421875,
-0.0325927734375,
-0.021636962890625,
0.01605224609375,
0.00496673583984375,
-0.00658416748046875,
0.0239715576171875,
0.0220489501953125,
-0.0643310546875,
0.02215576171875,
-0.048309326171875,
-0.01506805419921875,
-0.00925445556640625,
-0.0489501953125,
-0.07403564453125,
-0.0750732421875,
-0.03955078125,
-0.055572509765625,
-0.0140380859375,
0.07366943359375,
0.08673095703125,
-0.052490234375,
-0.014984130859375,
0.007328033447265625,
0.0115966796875,
-0.0214691162109375,
-0.017913818359375,
0.049102783203125,
-0.01303863525390625,
-0.052398681640625,
-0.02093505859375,
0.003704071044921875,
0.031890869140625,
-0.0038661956787109375,
-0.0190277099609375,
-0.017547607421875,
-0.014892578125,
0.0248870849609375,
0.0283050537109375,
-0.0447998046875,
0.0019817352294921875,
-0.0156707763671875,
-0.0160369873046875,
0.0309295654296875,
0.03765869140625,
-0.037322998046875,
0.01236724853515625,
0.0215911865234375,
0.031829833984375,
0.065185546875,
-0.0259857177734375,
0.002773284912109375,
-0.0706787109375,
0.041595458984375,
-0.0089569091796875,
0.03521728515625,
0.0294952392578125,
-0.02972412109375,
0.044677734375,
0.033599853515625,
-0.02874755859375,
-0.06707763671875,
-0.0088348388671875,
-0.0814208984375,
-0.01407623291015625,
0.06341552734375,
-0.0236663818359375,
-0.041412353515625,
0.040863037109375,
-0.003574371337890625,
0.045501708984375,
-0.0033245086669921875,
0.042205810546875,
0.0183258056640625,
-0.01165771484375,
-0.053314208984375,
-0.0452880859375,
0.0318603515625,
0.021575927734375,
-0.0517578125,
-0.043121337890625,
-0.0035648345947265625,
0.048309326171875,
0.022369384765625,
0.040374755859375,
-0.0161590576171875,
0.0068817138671875,
0.012908935546875,
0.0384521484375,
-0.029083251953125,
-0.0069732666015625,
-0.0254974365234375,
0.00463104248046875,
-0.01180267333984375,
-0.05230712890625
]
] |
Yntec/nuipenimix2 | 2023-09-28T17:39:27.000Z | [
"diffusers",
"Anime",
"Cute",
"Animals",
"McSionnaigh",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Yntec | null | null | Yntec/nuipenimix2 | 3 | 38,025 | diffusers | 2023-09-28T16:58:20 | ---
license: creativeml-openrail-m
library_name: diffusers
pipeline_tag: text-to-image
tags:
- Anime
- Cute
- Animals
- McSionnaigh
- stable-diffusion
- stable-diffusion-diffusers
- diffusers
- text-to-image
---
# nuipenimix 2
fp16 no-ema version of this model. Original page: https://civitai.com/models/81937?modelVersionId=139841
Sample and prompt:
icon of cute little red panda, round frame, blue glow, purple background | 661 | [
[
-0.03717041015625,
-0.032684326171875,
0.01113128662109375,
0.0517578125,
-0.04559326171875,
0.0016994476318359375,
0.03558349609375,
-0.0150299072265625,
0.089111328125,
0.032867431640625,
-0.04534912109375,
-0.0216064453125,
-0.016510009765625,
0.027862548828125,
0.00644683837890625,
0.03680419921875,
0.0062255859375,
0.016021728515625,
0.007843017578125,
-0.003765106201171875,
-0.01885986328125,
0.002399444580078125,
-0.039947509765625,
-0.0333251953125,
0.027313232421875,
0.050567626953125,
0.040985107421875,
0.0265350341796875,
0.0205535888671875,
0.01247406005859375,
-0.028839111328125,
-0.015625,
0.0001882314682006836,
-0.009857177734375,
0.017730712890625,
-0.053863525390625,
-0.0655517578125,
0.006153106689453125,
0.041534423828125,
0.027313232421875,
0.00995635986328125,
0.024505615234375,
0.01232147216796875,
0.02239990234375,
-0.04107666015625,
0.00301361083984375,
-0.006053924560546875,
0.0233612060546875,
-0.0010061264038085938,
0.0006017684936523438,
-0.0027217864990234375,
-0.034912109375,
-0.0239410400390625,
-0.0738525390625,
-0.0183258056640625,
-0.0090484619140625,
0.08477783203125,
0.0235748291015625,
-0.0243072509765625,
-0.006526947021484375,
-0.0141143798828125,
0.04913330078125,
-0.0325927734375,
0.004779815673828125,
0.024871826171875,
0.02490234375,
-0.01401519775390625,
-0.04107666015625,
-0.02783203125,
0.01184844970703125,
0.017730712890625,
0.0034942626953125,
-0.038238525390625,
-0.0341796875,
0.021270751953125,
-0.001964569091796875,
-0.0428466796875,
0.009185791015625,
-0.03692626953125,
0.01273345947265625,
0.0252532958984375,
0.004245758056640625,
0.0469970703125,
-0.0034465789794921875,
-0.04449462890625,
0.00799560546875,
-0.07135009765625,
0.0018024444580078125,
0.014862060546875,
0.001972198486328125,
-0.0633544921875,
0.045196533203125,
-0.01279449462890625,
0.0367431640625,
0.038726806640625,
0.0273284912109375,
0.043060302734375,
-0.01385498046875,
-0.01715087890625,
-0.0035724639892578125,
0.049285888671875,
0.045867919921875,
0.0038909912109375,
0.0269012451171875,
-0.001964569091796875,
-0.0137481689453125,
-0.0093841552734375,
-0.11639404296875,
-0.02264404296875,
0.03240966796875,
-0.04534912109375,
-0.038726806640625,
0.0058746337890625,
-0.09454345703125,
-0.00746917724609375,
0.005817413330078125,
0.008087158203125,
-0.0231475830078125,
-0.06396484375,
-0.01253509521484375,
-0.005039215087890625,
0.043487548828125,
0.0219268798828125,
-0.07330322265625,
0.0015106201171875,
0.049652099609375,
0.06927490234375,
0.055908203125,
0.01221466064453125,
-0.0311737060546875,
-0.0007104873657226562,
-0.044769287109375,
0.069091796875,
-0.060272216796875,
-0.042022705078125,
-0.0117340087890625,
0.0131378173828125,
0.00392913818359375,
-0.040069580078125,
0.0261077880859375,
-0.006404876708984375,
-0.0187225341796875,
-0.03582763671875,
0.0028858184814453125,
-0.024169921875,
0.0080413818359375,
-0.0552978515625,
0.06805419921875,
0.01898193359375,
-0.05169677734375,
0.051727294921875,
-0.0743408203125,
0.0092010498046875,
0.020050048828125,
-0.020538330078125,
-0.0367431640625,
-0.002079010009765625,
-0.00930023193359375,
0.0262603759765625,
0.005847930908203125,
-0.0256805419921875,
-0.0789794921875,
-0.0328369140625,
0.034454345703125,
0.005863189697265625,
0.0919189453125,
0.040008544921875,
-0.0249481201171875,
0.0032482147216796875,
-0.0736083984375,
-0.0009303092956542969,
0.03424072265625,
-0.005435943603515625,
-0.025482177734375,
-0.0648193359375,
0.0113983154296875,
0.03729248046875,
0.04534912109375,
-0.059783935546875,
0.0232391357421875,
-0.00011354684829711914,
0.0347900390625,
0.023590087890625,
0.01611328125,
0.028106689453125,
-0.03472900390625,
0.06866455078125,
0.0013093948364257812,
0.041748046875,
0.002681732177734375,
-0.04791259765625,
-0.05145263671875,
-0.041748046875,
0.03662109375,
0.024383544921875,
-0.050048828125,
0.0379638671875,
0.00539398193359375,
-0.0684814453125,
-0.041473388671875,
0.005352020263671875,
0.01036834716796875,
-0.0086669921875,
-0.010406494140625,
-0.0360107421875,
-0.04461669921875,
-0.0628662109375,
0.00928497314453125,
0.001255035400390625,
-0.031768798828125,
0.0333251953125,
0.050750732421875,
-0.0218658447265625,
0.045074462890625,
-0.01253509521484375,
-0.0222320556640625,
-0.02264404296875,
0.0121612548828125,
0.040496826171875,
0.03936767578125,
0.0833740234375,
-0.07110595703125,
-0.03887939453125,
-0.01947021484375,
-0.052642822265625,
-0.0304718017578125,
0.00662994384765625,
-0.002216339111328125,
0.002285003662109375,
0.002323150634765625,
-0.0352783203125,
0.042724609375,
0.041656494140625,
-0.050140380859375,
0.016143798828125,
-0.03045654296875,
0.0246124267578125,
-0.0872802734375,
0.03509521484375,
0.0255889892578125,
0.00450897216796875,
-0.0226593017578125,
0.0287017822265625,
0.0267181396484375,
-0.0222015380859375,
-0.05169677734375,
0.045013427734375,
-0.0531005859375,
-0.00864410400390625,
-0.0209197998046875,
0.0020771026611328125,
0.0190277099609375,
0.0148468017578125,
-0.01021575927734375,
0.044647216796875,
0.0307159423828125,
-0.033447265625,
0.00428009033203125,
0.042144775390625,
-0.025054931640625,
0.049896240234375,
-0.071533203125,
-0.00174713134765625,
0.0165557861328125,
0.0186309814453125,
-0.05908203125,
-0.02606201171875,
0.04901123046875,
-0.047515869140625,
0.0225067138671875,
-0.0106964111328125,
-0.044708251953125,
-0.00600433349609375,
-0.045074462890625,
0.0380859375,
0.042724609375,
-0.0518798828125,
0.037384033203125,
0.030975341796875,
-0.0176544189453125,
-0.01373291015625,
-0.056854248046875,
0.00612640380859375,
-0.033203125,
-0.0400390625,
0.0215606689453125,
-0.0013971328735351562,
-0.024993896484375,
-0.03143310546875,
0.0128936767578125,
-0.048736572265625,
0.01299285888671875,
0.046478271484375,
0.02838134765625,
-0.016082763671875,
-0.0268707275390625,
0.0191192626953125,
-0.0170745849609375,
0.00864410400390625,
0.0679931640625,
0.05169677734375,
-0.00955963134765625,
0.00495147705078125,
-0.07269287109375,
0.02105712890625,
0.053863525390625,
-0.01320648193359375,
0.0269622802734375,
0.038970947265625,
-0.040252685546875,
-0.002285003662109375,
-0.01111602783203125,
-0.02532958984375,
-0.033111572265625,
-0.02044677734375,
-0.0489501953125,
-0.0107879638671875,
0.0543212890625,
0.00862884521484375,
-0.011688232421875,
0.031341552734375,
0.03350830078125,
0.00768280029296875,
0.08013916015625,
0.043426513671875,
0.01309967041015625,
0.05224609375,
-0.043060302734375,
0.00033092498779296875,
-0.08447265625,
-0.03955078125,
-0.0421142578125,
-0.0184478759765625,
-0.03692626953125,
-0.0166015625,
-0.0011692047119140625,
0.006328582763671875,
-0.041473388671875,
0.04730224609375,
-0.034576416015625,
0.01079559326171875,
0.02960205078125,
0.0276641845703125,
0.00844573974609375,
-0.007781982421875,
-0.00789642333984375,
-0.024627685546875,
-0.045867919921875,
-0.046630859375,
0.06756591796875,
0.0235748291015625,
0.033843994140625,
0.017913818359375,
0.0638427734375,
-0.004306793212890625,
0.02337646484375,
-0.0232391357421875,
0.0438232421875,
0.001087188720703125,
-0.046783447265625,
0.012939453125,
0.0041961669921875,
-0.066162109375,
0.0294952392578125,
-0.0250244140625,
-0.038543701171875,
0.056549072265625,
0.006988525390625,
-0.048858642578125,
0.017669677734375,
-0.0277252197265625,
0.05426025390625,
-0.00926971435546875,
-0.0216827392578125,
-0.0020389556884765625,
-0.0235748291015625,
0.01983642578125,
0.00588226318359375,
0.006023406982421875,
-0.02166748046875,
-0.0362548828125,
0.04425048828125,
-0.04229736328125,
0.0767822265625,
-0.0180511474609375,
0.002994537353515625,
0.0222015380859375,
-0.004436492919921875,
0.01247406005859375,
0.029754638671875,
-0.02117919921875,
0.01161956787109375,
0.0023651123046875,
-0.0217437744140625,
-0.023193359375,
0.047821044921875,
-0.03826904296875,
-0.006549835205078125,
-0.04833984375,
0.01715087890625,
0.03594970703125,
0.0144195556640625,
0.032623291015625,
0.021331787109375,
-0.02191162109375,
0.033477783203125,
0.034942626953125,
-0.01018524169921875,
0.0231475830078125,
0.0426025390625,
-0.03302001953125,
-0.0301971435546875,
0.053924560546875,
0.005680084228515625,
0.005382537841796875,
0.027862548828125,
0.01151275634765625,
-0.0146636962890625,
-0.007373809814453125,
-0.03662109375,
0.029205322265625,
-0.01126861572265625,
-0.01142120361328125,
-0.035858154296875,
0.008270263671875,
-0.03924560546875,
-0.0143585205078125,
-0.0230865478515625,
-0.03228759765625,
-0.08349609375,
0.0088348388671875,
0.037322998046875,
0.03363037109375,
-0.043975830078125,
0.0216217041015625,
-0.0360107421875,
0.0261993408203125,
0.030059814453125,
0.01397705078125,
-0.031005859375,
-0.0426025390625,
0.034088134765625,
0.0229339599609375,
-0.05010986328125,
-0.053955078125,
0.052947998046875,
0.0008039474487304688,
0.0234527587890625,
0.048614501953125,
0.005115509033203125,
0.043121337890625,
-0.0174560546875,
0.049530029296875,
0.03662109375,
-0.0499267578125,
0.050140380859375,
-0.031463623046875,
0.00789642333984375,
0.03778076171875,
0.01806640625,
-0.0233154296875,
-0.013916015625,
-0.0677490234375,
-0.0469970703125,
0.01025390625,
-0.0015316009521484375,
-0.00687408447265625,
0.0162200927734375,
0.0238494873046875,
-0.000782012939453125,
0.0133514404296875,
-0.0364990234375,
-0.014678955078125,
-0.036529541015625,
0.004825592041015625,
0.0290679931640625,
-0.030609130859375,
-0.0048828125,
-0.0240936279296875,
0.044158935546875,
-0.0267486572265625,
0.0364990234375,
0.0009369850158691406,
0.01043701171875,
-0.02362060546875,
0.004940032958984375,
0.05120849609375,
0.0635986328125,
-0.042388916015625,
-0.04974365234375,
-0.0137176513671875,
-0.01136016845703125,
-0.00960540771484375,
0.00199127197265625,
-0.034942626953125,
0.0311279296875,
-0.01175689697265625,
0.045166015625,
0.06365966796875,
-0.0240936279296875,
0.06341552734375,
-0.01898193359375,
-0.007274627685546875,
-0.04815673828125,
0.012237548828125,
-0.008392333984375,
0.0301361083984375,
0.028076171875,
-0.0025005340576171875,
0.02862548828125,
-0.0292816162109375,
0.01299285888671875,
0.0312042236328125,
-0.0254669189453125,
-0.0467529296875,
0.07464599609375,
0.02410888671875,
-0.041229248046875,
0.03387451171875,
-0.0104522705078125,
-0.025054931640625,
0.0887451171875,
0.03875732421875,
0.07122802734375,
-0.040130615234375,
0.048614501953125,
0.039764404296875,
0.01384735107421875,
0.01593017578125,
0.07745361328125,
-0.0009322166442871094,
-0.023773193359375,
0.0255279541015625,
-0.03192138671875,
-0.05938720703125,
0.00717926025390625,
-0.0809326171875,
0.050506591796875,
-0.07373046875,
-0.0012369155883789062,
0.01172637939453125,
0.0190277099609375,
-0.040252685546875,
0.0232696533203125,
-0.0119781494140625,
0.097412109375,
-0.07086181640625,
0.053680419921875,
0.04278564453125,
-0.050994873046875,
-0.042144775390625,
-0.0313720703125,
-0.00033092498779296875,
-0.0760498046875,
0.03668212890625,
0.044097900390625,
0.033111572265625,
-0.0308074951171875,
-0.05633544921875,
-0.0516357421875,
0.083984375,
0.01253509521484375,
-0.03509521484375,
0.02447509765625,
-0.01454925537109375,
0.018768310546875,
-0.054779052734375,
0.0204010009765625,
0.0224609375,
0.040069580078125,
0.023834228515625,
-0.0533447265625,
0.01303863525390625,
-0.0498046875,
0.010284423828125,
0.007579803466796875,
-0.0872802734375,
0.069580078125,
-0.034912109375,
-0.014251708984375,
0.058135986328125,
0.04827880859375,
0.04998779296875,
0.0271759033203125,
0.03826904296875,
0.02923583984375,
0.00891876220703125,
-0.009033203125,
0.054229736328125,
-0.0185394287109375,
0.0215301513671875,
0.0570068359375,
-0.031982421875,
0.06927490234375,
0.047027587890625,
-0.007610321044921875,
0.036224365234375,
0.0760498046875,
-0.0428466796875,
0.037139892578125,
-0.00926971435546875,
-0.019317626953125,
-0.005645751953125,
-0.0193634033203125,
-0.046600341796875,
0.042236328125,
0.027374267578125,
-0.031707763671875,
-0.0101165771484375,
-0.01343536376953125,
0.000972747802734375,
-0.004180908203125,
-0.0281219482421875,
0.050201416015625,
0.0169525146484375,
-0.017059326171875,
0.02923583984375,
-0.0170440673828125,
0.04803466796875,
-0.0281219482421875,
-0.03521728515625,
-0.0215911865234375,
0.0109710693359375,
-0.029632568359375,
-0.047576904296875,
0.01018524169921875,
-0.0021533966064453125,
0.01029205322265625,
-0.017425537109375,
0.036712646484375,
-0.0065155029296875,
-0.055023193359375,
0.016815185546875,
-0.00463104248046875,
0.03753662109375,
0.00739288330078125,
-0.0758056640625,
0.0207672119140625,
-0.00402069091796875,
-0.00971221923828125,
0.025421142578125,
0.0238189697265625,
0.0246124267578125,
0.05816650390625,
0.0269012451171875,
0.00624847412109375,
0.004119873046875,
-0.0212860107421875,
0.050506591796875,
-0.030975341796875,
-0.061553955078125,
-0.034088134765625,
0.0299224853515625,
-0.0276336669921875,
-0.052825927734375,
0.048065185546875,
0.05426025390625,
0.035797119140625,
-0.0216217041015625,
0.03216552734375,
0.00112152099609375,
0.0305938720703125,
-0.0232391357421875,
0.0660400390625,
-0.056060791015625,
-0.0169525146484375,
-0.01050567626953125,
-0.051055908203125,
-0.016326904296875,
0.08367919921875,
0.0191650390625,
0.0077362060546875,
0.013458251953125,
0.06890869140625,
-0.0047607421875,
0.0223236083984375,
0.01358795166015625,
0.01207733154296875,
0.016693115234375,
0.02703857421875,
0.038848876953125,
-0.046539306640625,
0.016754150390625,
-0.03955078125,
-0.049652099609375,
-0.0518798828125,
-0.056365966796875,
-0.06317138671875,
-0.02264404296875,
-0.038726806640625,
-0.03289794921875,
-0.03094482421875,
0.06640625,
0.039886474609375,
-0.04974365234375,
-0.006687164306640625,
0.018829345703125,
0.005542755126953125,
0.00246429443359375,
-0.0141754150390625,
0.001522064208984375,
0.0440673828125,
-0.0643310546875,
0.00995635986328125,
0.0223846435546875,
0.04241943359375,
-0.01515960693359375,
0.008392333984375,
-0.0085601806640625,
-0.0071258544921875,
0.004367828369140625,
0.060699462890625,
-0.034698486328125,
-0.0220794677734375,
-0.00800323486328125,
0.0053558349609375,
0.019744873046875,
0.040191650390625,
-0.016693115234375,
0.0003426074981689453,
0.02935791015625,
0.005157470703125,
0.0137176513671875,
-0.0238189697265625,
0.030548095703125,
-0.007717132568359375,
0.0265960693359375,
0.01178741455078125,
0.060821533203125,
0.0157318115234375,
-0.01352691650390625,
0.0419921875,
0.0056610107421875,
-0.031646728515625,
-0.06988525390625,
0.002590179443359375,
-0.103515625,
-0.005596160888671875,
0.08819580078125,
-0.00513458251953125,
-0.06103515625,
0.01165771484375,
-0.0197601318359375,
0.01397705078125,
-0.0487060546875,
0.04638671875,
0.0210723876953125,
0.005985260009765625,
-0.018096923828125,
-0.01678466796875,
-0.0034503936767578125,
0.01161956787109375,
-0.06011962890625,
-0.035858154296875,
0.018341064453125,
0.049530029296875,
0.028411865234375,
0.0259246826171875,
-0.02862548828125,
0.05169677734375,
0.0237579345703125,
0.0180816650390625,
-0.007053375244140625,
-0.0223846435546875,
-0.04052734375,
0.0033740997314453125,
-0.0122528076171875,
-0.06341552734375
]
] |
timm/mixnet_l.ft_in1k | 2023-04-27T21:13:39.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1907.09595",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/mixnet_l.ft_in1k | 0 | 38,009 | timm | 2022-12-12T23:59:31 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for mixnet_l.ft_in1k
A MixNet image classification model. Fine-tuned on ImageNet-1k from original Tensorflow "SAME" padding weights for use in PyTorch.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 7.3
- GMACs: 0.6
- Activations (M): 10.8
- Image size: 224 x 224
- **Papers:**
- MixConv: Mixed Depthwise Convolutional Kernels: https://arxiv.org/abs/1907.09595
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('mixnet_l.ft_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'mixnet_l.ft_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 32, 112, 112])
# torch.Size([1, 40, 56, 56])
# torch.Size([1, 56, 28, 28])
# torch.Size([1, 160, 14, 14])
# torch.Size([1, 264, 7, 7])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'mixnet_l.ft_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1536, 7, 7) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@misc{tan2019mixconv,
title={MixConv: Mixed Depthwise Convolutional Kernels},
author={Mingxing Tan and Quoc V. Le},
year={2019},
eprint={1907.09595},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
| 3,920 | [
[
-0.04473876953125,
-0.041748046875,
-0.0064849853515625,
0.0155181884765625,
-0.02764892578125,
-0.023040771484375,
-0.01187896728515625,
-0.033447265625,
0.0299530029296875,
0.0258026123046875,
-0.034027099609375,
-0.051788330078125,
-0.0535888671875,
-0.015289306640625,
-0.017852783203125,
0.07977294921875,
-0.01500701904296875,
0.0004925727844238281,
-0.01154327392578125,
-0.0433349609375,
-0.01081085205078125,
-0.0188140869140625,
-0.056427001953125,
-0.03961181640625,
0.0297698974609375,
0.01251220703125,
0.047515869140625,
0.0367431640625,
0.0377197265625,
0.0343017578125,
-0.0187225341796875,
0.0029811859130859375,
-0.0210418701171875,
-0.0142669677734375,
0.03369140625,
-0.039093017578125,
-0.03521728515625,
0.021728515625,
0.05084228515625,
0.039459228515625,
0.0015773773193359375,
0.0212554931640625,
0.0100250244140625,
0.03497314453125,
-0.02081298828125,
-0.004180908203125,
-0.023895263671875,
0.0200347900390625,
0.0017261505126953125,
0.003841400146484375,
-0.011016845703125,
-0.0286102294921875,
0.0235748291015625,
-0.042236328125,
0.0355224609375,
-0.006855010986328125,
0.092529296875,
0.01165771484375,
-0.0006632804870605469,
-0.00568389892578125,
-0.015838623046875,
0.052642822265625,
-0.06439208984375,
0.0175933837890625,
0.021087646484375,
0.011016845703125,
-0.009918212890625,
-0.07281494140625,
-0.046051025390625,
-0.007671356201171875,
-0.0164642333984375,
0.0027923583984375,
-0.00673675537109375,
0.002964019775390625,
0.01934814453125,
0.038665771484375,
-0.033355712890625,
-0.0005364418029785156,
-0.044921875,
-0.0210723876953125,
0.044708251953125,
-0.0008182525634765625,
0.029266357421875,
-0.01050567626953125,
-0.03656005859375,
-0.038177490234375,
-0.0184478759765625,
0.0233612060546875,
0.0253448486328125,
0.0113372802734375,
-0.05780029296875,
0.0386962890625,
0.01157379150390625,
0.04156494140625,
0.005947113037109375,
-0.0262603759765625,
0.04547119140625,
-0.0007352828979492188,
-0.037628173828125,
-0.00392913818359375,
0.08282470703125,
0.025970458984375,
0.0121002197265625,
0.007564544677734375,
-0.0110931396484375,
-0.0234222412109375,
-0.00936126708984375,
-0.09039306640625,
-0.0277252197265625,
0.035003662109375,
-0.04156494140625,
-0.03143310546875,
0.023712158203125,
-0.045867919921875,
-0.01258087158203125,
-0.003353118896484375,
0.05029296875,
-0.037750244140625,
-0.037933349609375,
0.0057830810546875,
-0.019744873046875,
0.0272674560546875,
0.0190277099609375,
-0.032745361328125,
0.01885986328125,
0.0223846435546875,
0.08795166015625,
0.0031890869140625,
-0.0404052734375,
-0.01194000244140625,
-0.034576416015625,
-0.022369384765625,
0.0246124267578125,
-0.0006279945373535156,
-0.0124053955078125,
-0.0227203369140625,
0.0218353271484375,
-0.00969696044921875,
-0.05792236328125,
0.016571044921875,
-0.00992584228515625,
0.02459716796875,
0.0040740966796875,
-0.020782470703125,
-0.033203125,
0.02398681640625,
-0.031707763671875,
0.10125732421875,
0.03216552734375,
-0.07330322265625,
0.0303802490234375,
-0.036346435546875,
-0.01763916015625,
-0.0199432373046875,
-0.0027027130126953125,
-0.078857421875,
-0.01157379150390625,
0.0164337158203125,
0.0570068359375,
-0.01116943359375,
0.00548553466796875,
-0.047332763671875,
-0.0198516845703125,
0.0278472900390625,
0.0085906982421875,
0.0819091796875,
0.01204681396484375,
-0.0301666259765625,
0.0261077880859375,
-0.041839599609375,
0.0064239501953125,
0.03460693359375,
-0.022552490234375,
-0.003620147705078125,
-0.05218505859375,
0.0206756591796875,
0.0281219482421875,
0.00713348388671875,
-0.045379638671875,
0.0160369873046875,
-0.01439666748046875,
0.027374267578125,
0.041229248046875,
-0.0106964111328125,
0.023834228515625,
-0.031158447265625,
0.0247039794921875,
0.03839111328125,
0.0113372802734375,
-0.0078277587890625,
-0.04541015625,
-0.06890869140625,
-0.04412841796875,
0.0283660888671875,
0.0267181396484375,
-0.03851318359375,
0.04071044921875,
-0.00839996337890625,
-0.0546875,
-0.04913330078125,
0.0086669921875,
0.027557373046875,
0.04058837890625,
0.0242462158203125,
-0.03863525390625,
-0.03765869140625,
-0.06719970703125,
0.0062713623046875,
0.01265716552734375,
-0.0017309188842773438,
0.0249176025390625,
0.056793212890625,
-0.0147247314453125,
0.04998779296875,
-0.02349853515625,
-0.01073455810546875,
-0.0178070068359375,
0.00856781005859375,
0.03546142578125,
0.06585693359375,
0.060211181640625,
-0.04510498046875,
-0.03607177734375,
-0.00540924072265625,
-0.07257080078125,
0.0154266357421875,
-0.00228118896484375,
-0.0226287841796875,
0.012664794921875,
0.0055694580078125,
-0.047149658203125,
0.046600341796875,
0.0186004638671875,
-0.032440185546875,
0.029998779296875,
-0.0160675048828125,
0.0196685791015625,
-0.0853271484375,
0.007427215576171875,
0.033294677734375,
-0.017669677734375,
-0.031646728515625,
0.00533294677734375,
-0.0026111602783203125,
-0.005023956298828125,
-0.04144287109375,
0.05133056640625,
-0.035736083984375,
-0.018096923828125,
-0.00966644287109375,
-0.0208587646484375,
0.0021343231201171875,
0.052215576171875,
-0.0066070556640625,
0.0241546630859375,
0.068115234375,
-0.038482666015625,
0.036285400390625,
0.0271759033203125,
-0.0154876708984375,
0.0330810546875,
-0.05645751953125,
0.0144805908203125,
-0.0014963150024414062,
0.0216217041015625,
-0.07342529296875,
-0.020904541015625,
0.028900146484375,
-0.040679931640625,
0.04669189453125,
-0.039764404296875,
-0.03375244140625,
-0.030731201171875,
-0.03759765625,
0.032012939453125,
0.052276611328125,
-0.05340576171875,
0.0361328125,
0.0178375244140625,
0.0247039794921875,
-0.03912353515625,
-0.071533203125,
-0.025726318359375,
-0.028839111328125,
-0.063720703125,
0.026885986328125,
0.0015382766723632812,
0.0086517333984375,
0.010589599609375,
-0.0145721435546875,
-0.0084228515625,
-0.012054443359375,
0.03466796875,
0.0246124267578125,
-0.0286102294921875,
-0.0257720947265625,
-0.0169219970703125,
0.002574920654296875,
-0.0006694793701171875,
-0.022003173828125,
0.042938232421875,
-0.0152740478515625,
-0.007808685302734375,
-0.055389404296875,
-0.0016851425170898438,
0.036590576171875,
0.003177642822265625,
0.06573486328125,
0.08526611328125,
-0.040069580078125,
-0.01016998291015625,
-0.0298614501953125,
-0.0263214111328125,
-0.034759521484375,
0.0273284912109375,
-0.0272369384765625,
-0.04132080078125,
0.07415771484375,
0.008087158203125,
0.00908660888671875,
0.049652099609375,
0.03204345703125,
-0.00872802734375,
0.046112060546875,
0.035736083984375,
0.01035308837890625,
0.05096435546875,
-0.07342529296875,
-0.0213623046875,
-0.058685302734375,
-0.03375244140625,
-0.020904541015625,
-0.054656982421875,
-0.0506591796875,
-0.0236053466796875,
0.03314208984375,
0.018341064453125,
-0.0263671875,
0.032867431640625,
-0.06085205078125,
0.00984954833984375,
0.05242919921875,
0.0474853515625,
-0.029876708984375,
0.02020263671875,
-0.0285491943359375,
0.004856109619140625,
-0.05841064453125,
-0.00707244873046875,
0.08038330078125,
0.039031982421875,
0.04547119140625,
-0.0154266357421875,
0.0582275390625,
-0.01641845703125,
0.0255126953125,
-0.0428466796875,
0.03729248046875,
0.00019371509552001953,
-0.03436279296875,
-0.00441741943359375,
-0.036376953125,
-0.07562255859375,
0.0208587646484375,
-0.02392578125,
-0.052093505859375,
0.01235198974609375,
0.00997161865234375,
-0.01104736328125,
0.054901123046875,
-0.061370849609375,
0.07513427734375,
-0.008941650390625,
-0.0361328125,
0.011871337890625,
-0.052001953125,
0.0238800048828125,
0.0247955322265625,
-0.01316070556640625,
-0.004192352294921875,
0.01739501953125,
0.08233642578125,
-0.048065185546875,
0.062744140625,
-0.03533935546875,
0.024169921875,
0.0372314453125,
-0.0009427070617675781,
0.0164642333984375,
-0.01055908203125,
-0.00026702880859375,
0.0279998779296875,
0.01157379150390625,
-0.0423583984375,
-0.037078857421875,
0.0506591796875,
-0.0794677734375,
-0.00917816162109375,
-0.0272369384765625,
-0.039703369140625,
0.01338958740234375,
0.0038127899169921875,
0.03955078125,
0.0450439453125,
0.01407623291015625,
0.019805908203125,
0.043975830078125,
-0.034454345703125,
0.02880859375,
-0.0154876708984375,
-0.0235137939453125,
-0.0450439453125,
0.059417724609375,
0.009307861328125,
0.0111846923828125,
-0.0005040168762207031,
0.021331787109375,
-0.021728515625,
-0.0404052734375,
-0.02679443359375,
0.026092529296875,
-0.053924560546875,
-0.026458740234375,
-0.044219970703125,
-0.036529541015625,
-0.028839111328125,
-0.01238250732421875,
-0.03778076171875,
-0.0276947021484375,
-0.0243988037109375,
0.0170745849609375,
0.05047607421875,
0.044342041015625,
-0.0025424957275390625,
0.044952392578125,
-0.03582763671875,
0.01334381103515625,
0.00408172607421875,
0.04522705078125,
-0.00909423828125,
-0.068603515625,
-0.018798828125,
-0.002445220947265625,
-0.0316162109375,
-0.0550537109375,
0.036590576171875,
0.0052947998046875,
0.038421630859375,
0.022186279296875,
-0.0249786376953125,
0.055908203125,
0.01291656494140625,
0.035888671875,
0.0284423828125,
-0.044830322265625,
0.04608154296875,
-0.00774383544921875,
0.01702880859375,
0.00791168212890625,
0.0278778076171875,
-0.022369384765625,
-0.005832672119140625,
-0.078125,
-0.06231689453125,
0.07135009765625,
0.020904541015625,
-0.00455474853515625,
0.0350341796875,
0.0489501953125,
0.00829315185546875,
0.0088958740234375,
-0.06451416015625,
-0.039703369140625,
-0.0302734375,
-0.02825927734375,
0.0018100738525390625,
0.0013256072998046875,
-0.01006317138671875,
-0.057586669921875,
0.0494384765625,
-0.0030956268310546875,
0.0535888671875,
0.031524658203125,
-0.00347900390625,
-0.01171112060546875,
-0.031219482421875,
0.0386962890625,
0.0216827392578125,
-0.0307159423828125,
0.007183074951171875,
0.01326751708984375,
-0.039947509765625,
0.00113677978515625,
0.012969970703125,
-0.0008664131164550781,
0.0022945404052734375,
0.03753662109375,
0.06982421875,
0.005229949951171875,
0.00414276123046875,
0.03143310546875,
0.002651214599609375,
-0.03564453125,
-0.01288604736328125,
0.012176513671875,
0.000835418701171875,
0.0303802490234375,
0.01739501953125,
0.0213165283203125,
-0.01097869873046875,
-0.0209808349609375,
0.021148681640625,
0.04010009765625,
-0.0187835693359375,
-0.0260162353515625,
0.0467529296875,
-0.01629638671875,
-0.0048370361328125,
0.05853271484375,
-0.00189208984375,
-0.036590576171875,
0.08050537109375,
0.032562255859375,
0.06793212890625,
-0.002048492431640625,
-0.0012941360473632812,
0.061859130859375,
0.0185394287109375,
0.0033931732177734375,
0.0160064697265625,
0.007568359375,
-0.06256103515625,
0.00862884521484375,
-0.048919677734375,
-0.0012407302856445312,
0.03350830078125,
-0.033233642578125,
0.02642822265625,
-0.06072998046875,
-0.0218658447265625,
0.01447296142578125,
0.0197296142578125,
-0.0703125,
0.020782470703125,
0.00330352783203125,
0.05810546875,
-0.05877685546875,
0.052642822265625,
0.06640625,
-0.047943115234375,
-0.075439453125,
-0.0166168212890625,
0.0010862350463867188,
-0.06304931640625,
0.03485107421875,
0.031646728515625,
0.01239776611328125,
-0.002521514892578125,
-0.06671142578125,
-0.036590576171875,
0.10162353515625,
0.037200927734375,
0.0006642341613769531,
0.0260467529296875,
-0.00028586387634277344,
0.0181121826171875,
-0.038787841796875,
0.0447998046875,
0.01702880859375,
0.02752685546875,
0.03375244140625,
-0.051116943359375,
0.01488494873046875,
-0.0289459228515625,
0.0003845691680908203,
0.0149383544921875,
-0.052276611328125,
0.0718994140625,
-0.0242919921875,
-0.004695892333984375,
-0.008453369140625,
0.052398681640625,
0.0239410400390625,
0.0172271728515625,
0.03863525390625,
0.066650390625,
0.033905029296875,
-0.0235748291015625,
0.06829833984375,
0.004268646240234375,
0.0479736328125,
0.038818359375,
0.0271453857421875,
0.03314208984375,
0.03216552734375,
-0.0225677490234375,
0.02392578125,
0.0860595703125,
-0.0224456787109375,
0.01824951171875,
0.0134735107421875,
0.002330780029296875,
-0.0026264190673828125,
0.01454925537109375,
-0.032989501953125,
0.0278472900390625,
0.01280975341796875,
-0.03985595703125,
-0.0151519775390625,
-0.0035686492919921875,
0.0038661956787109375,
-0.03582763671875,
-0.01134490966796875,
0.038177490234375,
0.003429412841796875,
-0.029052734375,
0.068115234375,
0.007110595703125,
0.07562255859375,
-0.031341552734375,
0.0011701583862304688,
-0.025909423828125,
0.0157928466796875,
-0.03375244140625,
-0.0675048828125,
0.0204925537109375,
-0.026702880859375,
0.00809478759765625,
0.006000518798828125,
0.04791259765625,
-0.036956787109375,
-0.036895751953125,
0.0232696533203125,
0.0238189697265625,
0.038421630859375,
0.004528045654296875,
-0.09375,
0.0154876708984375,
0.0006017684936523438,
-0.0482177734375,
0.0281524658203125,
0.031280517578125,
0.0158538818359375,
0.048431396484375,
0.047027587890625,
-0.0047149658203125,
0.0194549560546875,
-0.012420654296875,
0.06524658203125,
-0.037811279296875,
-0.0290069580078125,
-0.05810546875,
0.057586669921875,
-0.006317138671875,
-0.049407958984375,
0.03253173828125,
0.046661376953125,
0.0733642578125,
-0.00021207332611083984,
0.0357666015625,
-0.01995849609375,
-0.006755828857421875,
-0.030517578125,
0.05322265625,
-0.059417724609375,
-0.00702667236328125,
-0.0186004638671875,
-0.055511474609375,
-0.0264129638671875,
0.055755615234375,
-0.0097808837890625,
0.0439453125,
0.035980224609375,
0.071533203125,
-0.04205322265625,
-0.0212554931640625,
0.01326751708984375,
0.008514404296875,
0.001033782958984375,
0.023193359375,
0.03375244140625,
-0.0592041015625,
0.016265869140625,
-0.058319091796875,
-0.01374053955078125,
-0.013885498046875,
-0.04547119140625,
-0.0733642578125,
-0.060943603515625,
-0.05126953125,
-0.059417724609375,
-0.025726318359375,
0.0709228515625,
0.08709716796875,
-0.06011962890625,
-0.0205230712890625,
0.0029315948486328125,
0.008148193359375,
-0.01251983642578125,
-0.0186614990234375,
0.03961181640625,
-0.0027866363525390625,
-0.052337646484375,
-0.0240325927734375,
-0.003086090087890625,
0.036041259765625,
-0.0037708282470703125,
-0.0235137939453125,
-0.0180816650390625,
-0.0209197998046875,
0.01495361328125,
0.0211181640625,
-0.052337646484375,
-0.005268096923828125,
-0.0229034423828125,
-0.0106658935546875,
0.036346435546875,
0.038421630859375,
-0.032073974609375,
0.0237579345703125,
0.0357666015625,
0.0309600830078125,
0.07373046875,
-0.0253753662109375,
0.0007843971252441406,
-0.06573486328125,
0.04962158203125,
-0.006443023681640625,
0.04266357421875,
0.03619384765625,
-0.0225830078125,
0.039642333984375,
0.032135009765625,
-0.0258941650390625,
-0.057586669921875,
-0.014984130859375,
-0.086669921875,
-0.00922393798828125,
0.06353759765625,
-0.0247344970703125,
-0.037872314453125,
0.0341796875,
-0.0063323974609375,
0.050628662109375,
-0.0097503662109375,
0.029693603515625,
0.026824951171875,
-0.00908660888671875,
-0.053070068359375,
-0.038421630859375,
0.0269927978515625,
0.014678955078125,
-0.0504150390625,
-0.038726806640625,
0.004825592041015625,
0.057403564453125,
0.0128173828125,
0.037322998046875,
-0.01178741455078125,
0.0038280487060546875,
0.01421356201171875,
0.04302978515625,
-0.0246734619140625,
-0.00787353515625,
-0.0242462158203125,
0.004100799560546875,
-0.01258087158203125,
-0.04180908203125
]
] |
moussaKam/frugalscore_tiny_bert-base_bert-score | 2022-02-01T10:50:21.000Z | [
"transformers",
"pytorch",
"bert",
"text-classification",
"arxiv:2110.08559",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | moussaKam | null | null | moussaKam/frugalscore_tiny_bert-base_bert-score | 0 | 37,932 | transformers | 2022-03-02T23:29:05 | # FrugalScore
FrugalScore is an approach to learn a fixed, low cost version of any expensive NLG metric, while retaining most of its original performance
Paper: https://arxiv.org/abs/2110.08559?context=cs
Project github: https://github.com/moussaKam/FrugalScore
The pretrained checkpoints presented in the paper :
| FrugalScore | Student | Teacher | Method |
|----------------------------------------------------|-------------|----------------|------------|
| [moussaKam/frugalscore_tiny_bert-base_bert-score](https://huggingface.co/moussaKam/frugalscore_tiny_bert-base_bert-score) | BERT-tiny | BERT-Base | BERTScore |
| [moussaKam/frugalscore_small_bert-base_bert-score](https://huggingface.co/moussaKam/frugalscore_small_bert-base_bert-score) | BERT-small | BERT-Base | BERTScore |
| [moussaKam/frugalscore_medium_bert-base_bert-score](https://huggingface.co/moussaKam/frugalscore_medium_bert-base_bert-score) | BERT-medium | BERT-Base | BERTScore |
| [moussaKam/frugalscore_tiny_roberta_bert-score](https://huggingface.co/moussaKam/frugalscore_tiny_roberta_bert-score) | BERT-tiny | RoBERTa-Large | BERTScore |
| [moussaKam/frugalscore_small_roberta_bert-score](https://huggingface.co/moussaKam/frugalscore_small_roberta_bert-score) | BERT-small | RoBERTa-Large | BERTScore |
| [moussaKam/frugalscore_medium_roberta_bert-score](https://huggingface.co/moussaKam/frugalscore_medium_roberta_bert-score) | BERT-medium | RoBERTa-Large | BERTScore |
| [moussaKam/frugalscore_tiny_deberta_bert-score](https://huggingface.co/moussaKam/frugalscore_tiny_deberta_bert-score) | BERT-tiny | DeBERTa-XLarge | BERTScore |
| [moussaKam/frugalscore_small_deberta_bert-score](https://huggingface.co/moussaKam/frugalscore_small_deberta_bert-score) | BERT-small | DeBERTa-XLarge | BERTScore |
| [moussaKam/frugalscore_medium_deberta_bert-score](https://huggingface.co/moussaKam/frugalscore_medium_deberta_bert-score) | BERT-medium | DeBERTa-XLarge | BERTScore |
| [moussaKam/frugalscore_tiny_bert-base_mover-score](https://huggingface.co/moussaKam/frugalscore_tiny_bert-base_mover-score) | BERT-tiny | BERT-Base | MoverScore |
| [moussaKam/frugalscore_small_bert-base_mover-score](https://huggingface.co/moussaKam/frugalscore_small_bert-base_mover-score) | BERT-small | BERT-Base | MoverScore |
| [moussaKam/frugalscore_medium_bert-base_mover-score](https://huggingface.co/moussaKam/frugalscore_medium_bert-base_mover-score) | BERT-medium | BERT-Base | MoverScore | | 2,592 | [
[
-0.0293731689453125,
-0.0239410400390625,
-0.0001239776611328125,
0.03375244140625,
-0.01517486572265625,
0.01393890380859375,
-0.003955841064453125,
-0.0235748291015625,
0.042724609375,
0.0185394287109375,
-0.0648193359375,
-0.0413818359375,
-0.024505615234375,
-0.01526641845703125,
0.01189422607421875,
0.0755615234375,
0.01276397705078125,
-0.01422882080078125,
-0.00569915771484375,
-0.033843994140625,
-0.032745361328125,
-0.018829345703125,
-0.049591064453125,
-0.026885986328125,
0.045928955078125,
0.054534912109375,
0.0543212890625,
0.01326751708984375,
0.034912109375,
0.0180206298828125,
-0.012298583984375,
0.00844573974609375,
-0.0289306640625,
-0.014617919921875,
0.018829345703125,
-0.03546142578125,
-0.0592041015625,
0.010528564453125,
0.0168609619140625,
0.026824951171875,
-0.0284271240234375,
0.0552978515625,
0.023468017578125,
0.07958984375,
-0.046051025390625,
0.0184478759765625,
-0.031402587890625,
0.004405975341796875,
0.01070404052734375,
0.0227203369140625,
-0.00199127197265625,
-0.047698974609375,
-0.004543304443359375,
-0.037384033203125,
0.0147857666015625,
-0.0018587112426757812,
0.08349609375,
0.0193634033203125,
0.00453948974609375,
-0.066162109375,
-0.0202789306640625,
0.08367919921875,
-0.057220458984375,
0.02734375,
0.0264434814453125,
-0.0017528533935546875,
-0.0008130073547363281,
-0.0285797119140625,
-0.03472900390625,
-0.0029850006103515625,
-0.0203094482421875,
0.0406494140625,
-0.046478271484375,
-0.030120849609375,
0.0175323486328125,
0.032867431640625,
-0.047607421875,
-0.00933074951171875,
-0.0295562744140625,
0.0195770263671875,
0.053253173828125,
0.01495361328125,
0.01114654541015625,
-0.035430908203125,
-0.04156494140625,
-0.0160064697265625,
-0.0239715576171875,
0.0283355712890625,
0.0120697021484375,
0.00946807861328125,
-0.039154052734375,
0.04034423828125,
-0.004138946533203125,
0.03173828125,
0.0282440185546875,
-0.04083251953125,
0.037017822265625,
-0.032867431640625,
-0.0206146240234375,
-0.005748748779296875,
0.0257720947265625,
0.046417236328125,
0.0007123947143554688,
0.01189422607421875,
-0.020782470703125,
-0.018310546875,
0.00868988037109375,
-0.04052734375,
-0.043914794921875,
0.00339508056640625,
-0.051910400390625,
-0.021331787109375,
-0.004730224609375,
-0.061248779296875,
0.0028057098388671875,
-0.0131988525390625,
0.030181884765625,
-0.051177978515625,
-0.006114959716796875,
0.01192474365234375,
-0.003002166748046875,
0.014617919921875,
0.02813720703125,
-0.049163818359375,
0.018798828125,
0.0283355712890625,
0.07696533203125,
0.02301025390625,
0.0086822509765625,
-0.00661468505859375,
0.00899505615234375,
-0.029815673828125,
0.04510498046875,
-0.00417327880859375,
-0.04852294921875,
-0.0034809112548828125,
0.000006556510925292969,
-0.0059356689453125,
-0.0262451171875,
0.059967041015625,
0.01169586181640625,
0.021331787109375,
-0.048980712890625,
-0.03326416015625,
-0.0232696533203125,
0.0291595458984375,
-0.061187744140625,
0.1009521484375,
0.0245208740234375,
-0.041107177734375,
0.03912353515625,
-0.058135986328125,
-0.00836181640625,
0.0020904541015625,
0.0330810546875,
-0.0293731689453125,
0.0213623046875,
-0.000522613525390625,
0.03887939453125,
-0.0236663818359375,
-0.0119171142578125,
0.0005216598510742188,
-0.01029205322265625,
-0.0133056640625,
-0.0010595321655273438,
0.075439453125,
0.037322998046875,
-0.00797271728515625,
0.01009368896484375,
-0.06475830078125,
0.006839752197265625,
0.03509521484375,
-0.035247802734375,
-0.022552490234375,
-0.0092620849609375,
0.0110626220703125,
0.01259613037109375,
0.04962158203125,
-0.0167694091796875,
0.016571044921875,
0.0015087127685546875,
0.0283355712890625,
0.062347412109375,
-0.01519775390625,
0.01593017578125,
-0.0675048828125,
0.0423583984375,
-0.00823211669921875,
0.041748046875,
0.0278167724609375,
-0.03521728515625,
-0.05596923828125,
-0.04071044921875,
0.0061187744140625,
0.0491943359375,
-0.031890869140625,
0.07977294921875,
-0.005588531494140625,
-0.06427001953125,
-0.0207366943359375,
0.0094757080078125,
0.033294677734375,
0.041748046875,
0.03936767578125,
-0.01087188720703125,
-0.01381683349609375,
-0.0577392578125,
-0.0239410400390625,
-0.0098876953125,
-0.00846099853515625,
0.052581787109375,
0.042633056640625,
0.00446319580078125,
0.04998779296875,
-0.06561279296875,
-0.0406494140625,
-0.0215606689453125,
0.0113525390625,
0.056396484375,
0.0560302734375,
0.07904052734375,
-0.0474853515625,
-0.03497314453125,
-0.03302001953125,
-0.004276275634765625,
0.0172882080078125,
-0.016265869140625,
0.01198577880859375,
0.0264434814453125,
0.01496124267578125,
-0.0423583984375,
0.0236663818359375,
0.058074951171875,
-0.041717529296875,
0.043365478515625,
-0.0309600830078125,
-0.0027561187744140625,
-0.07470703125,
0.0110931396484375,
0.01273345947265625,
0.00020945072174072266,
-0.0157470703125,
0.005855560302734375,
-0.00479888916015625,
0.0174560546875,
-0.0237884521484375,
0.042999267578125,
-0.0299224853515625,
0.005603790283203125,
0.03680419921875,
-0.00933074951171875,
-0.006988525390625,
0.0556640625,
-0.027740478515625,
0.062408447265625,
0.0100555419921875,
-0.02362060546875,
0.00888824462890625,
0.021240234375,
-0.036376953125,
0.0280914306640625,
-0.044036865234375,
-0.00007522106170654297,
-0.0063629150390625,
0.0261688232421875,
-0.0867919921875,
-0.001529693603515625,
0.018890380859375,
-0.0289306640625,
0.0017547607421875,
-0.00689697265625,
-0.048095703125,
-0.03021240234375,
-0.041473388671875,
0.0135345458984375,
0.05438232421875,
-0.039764404296875,
0.033111572265625,
0.03662109375,
-0.006565093994140625,
-0.026336669921875,
-0.04986572265625,
-0.0283966064453125,
-0.0279083251953125,
-0.0283966064453125,
0.0268096923828125,
-0.032440185546875,
-0.00522613525390625,
0.0081787109375,
-0.0301361083984375,
0.0018186569213867188,
0.005146026611328125,
0.00811004638671875,
0.039825439453125,
-0.012664794921875,
0.00528717041015625,
-0.0224151611328125,
-0.0010881423950195312,
-0.00893402099609375,
-0.004405975341796875,
0.057037353515625,
-0.035491943359375,
0.0224456787109375,
-0.0024967193603515625,
0.0222625732421875,
0.0236358642578125,
0.0011568069458007812,
0.055084228515625,
0.05419921875,
-0.043701171875,
0.00565338134765625,
-0.06170654296875,
0.005962371826171875,
-0.031585693359375,
-0.0083770751953125,
-0.04339599609375,
-0.077392578125,
0.054412841796875,
0.0066375732421875,
0.0273590087890625,
0.045806884765625,
0.0302886962890625,
-0.01239776611328125,
0.07354736328125,
0.02423095703125,
-0.006153106689453125,
0.050323486328125,
-0.031402587890625,
0.00232696533203125,
-0.036865234375,
-0.02197265625,
-0.045989990234375,
-0.041168212890625,
-0.04547119140625,
-0.04071044921875,
0.0305938720703125,
0.030364990234375,
-0.0389404296875,
0.051055908203125,
-0.058746337890625,
0.039794921875,
0.058135986328125,
0.0306854248046875,
-0.0208282470703125,
-0.004894256591796875,
-0.0325927734375,
-0.01328277587890625,
-0.06658935546875,
-0.01329803466796875,
0.06256103515625,
0.0167999267578125,
0.0277099609375,
0.023223876953125,
0.062347412109375,
0.0308990478515625,
0.01678466796875,
-0.06298828125,
0.051513671875,
-0.042510986328125,
-0.04705810546875,
-0.010772705078125,
-0.0450439453125,
-0.051513671875,
-0.005970001220703125,
-0.0201873779296875,
-0.0718994140625,
0.024017333984375,
0.02557373046875,
-0.047760009765625,
0.0170440673828125,
-0.0506591796875,
0.06536865234375,
-0.0301513671875,
-0.0408935546875,
-0.032501220703125,
-0.02923583984375,
0.0290374755859375,
0.0023097991943359375,
0.01242828369140625,
-0.047393798828125,
-0.003948211669921875,
0.07177734375,
-0.045013427734375,
0.042388916015625,
-0.0222625732421875,
0.0042877197265625,
0.0263214111328125,
-0.0000476837158203125,
0.041107177734375,
0.007781982421875,
0.004730224609375,
0.00411224365234375,
0.0012493133544921875,
-0.05279541015625,
-0.008880615234375,
0.0682373046875,
-0.040283203125,
-0.013641357421875,
-0.04827880859375,
-0.033538818359375,
-0.024139404296875,
0.03106689453125,
0.0162353515625,
0.004459381103515625,
-0.01390838623046875,
0.0172882080078125,
0.043426513671875,
-0.0193634033203125,
0.0297698974609375,
0.008941650390625,
-0.002933502197265625,
-0.048126220703125,
0.06787109375,
0.0129241943359375,
-0.009674072265625,
0.02862548828125,
0.05242919921875,
-0.0275726318359375,
-0.025054931640625,
-0.00527191162109375,
0.0217437744140625,
-0.0307769775390625,
-0.031280517578125,
-0.036590576171875,
0.00890350341796875,
-0.041595458984375,
-0.039825439453125,
-0.03936767578125,
-0.0487060546875,
-0.0208587646484375,
-0.0185699462890625,
0.03826904296875,
0.0286407470703125,
-0.050201416015625,
0.019683837890625,
-0.0650634765625,
0.016357421875,
0.032379150390625,
0.01497650146484375,
-0.004428863525390625,
-0.0008625984191894531,
-0.020172119140625,
-0.014801025390625,
-0.01161956787109375,
-0.044403076171875,
0.04595947265625,
-0.011688232421875,
0.0247802734375,
0.029754638671875,
0.0110931396484375,
0.07733154296875,
-0.00659942626953125,
0.0767822265625,
0.08245849609375,
-0.06878662109375,
0.0139923095703125,
-0.0239410400390625,
0.0288848876953125,
0.051666259765625,
0.0247650146484375,
-0.0277099609375,
0.00791168212890625,
-0.0701904296875,
-0.09033203125,
0.045654296875,
0.0151214599609375,
0.006107330322265625,
0.00502777099609375,
-0.007122039794921875,
-0.0010690689086914062,
0.032867431640625,
-0.039642333984375,
-0.03485107421875,
-0.0240325927734375,
-0.015899658203125,
-0.004180908203125,
-0.038604736328125,
-0.013031005859375,
-0.05206298828125,
0.0540771484375,
-0.006702423095703125,
0.032806396484375,
0.01434326171875,
0.018585205078125,
-0.0017547607421875,
-0.00957489013671875,
0.07061767578125,
0.046173095703125,
-0.058624267578125,
-0.032928466796875,
0.006805419921875,
-0.044647216796875,
-0.020599365234375,
0.006866455078125,
-0.007289886474609375,
0.015533447265625,
0.01335906982421875,
0.04583740234375,
0.050201416015625,
-0.04705810546875,
0.0125732421875,
-0.0013437271118164062,
-0.0279998779296875,
-0.07000732421875,
0.0019483566284179688,
0.0208892822265625,
0.007480621337890625,
0.0160980224609375,
0.024871826171875,
-0.0007619857788085938,
-0.048004150390625,
0.01483154296875,
0.0396728515625,
-0.04095458984375,
-0.007904052734375,
0.03955078125,
0.00817108154296875,
-0.010009765625,
0.03485107421875,
-0.01568603515625,
-0.034759521484375,
0.05279541015625,
0.0218658447265625,
0.07366943359375,
-0.029541015625,
0.013092041015625,
0.0694580078125,
0.03497314453125,
-0.0103302001953125,
0.04852294921875,
-0.01380157470703125,
-0.050323486328125,
0.01059722900390625,
-0.058685302734375,
-0.0306854248046875,
-0.0030765533447265625,
-0.07037353515625,
0.0275115966796875,
-0.048065185546875,
-0.01467132568359375,
0.00579071044921875,
0.036376953125,
-0.0679931640625,
0.0361328125,
0.0029888153076171875,
0.08856201171875,
-0.035614013671875,
0.055908203125,
0.0419921875,
-0.0347900390625,
-0.0789794921875,
-0.015228271484375,
0.0108489990234375,
-0.08599853515625,
0.034088134765625,
-0.01377105712890625,
-0.00646209716796875,
-0.00968170166015625,
-0.02435302734375,
-0.07611083984375,
0.083984375,
-0.00374603271484375,
-0.041290283203125,
-0.022491455078125,
-0.0165557861328125,
0.0056304931640625,
-0.0223236083984375,
0.0234832763671875,
0.050689697265625,
0.0540771484375,
0.027313232421875,
-0.052642822265625,
0.00685882568359375,
-0.0172119140625,
-0.023529052734375,
0.01131439208984375,
-0.081787109375,
0.0887451171875,
-0.0142974853515625,
-0.005046844482421875,
0.01076507568359375,
0.0265960693359375,
0.0245208740234375,
0.027374267578125,
0.07177734375,
0.0693359375,
0.047149658203125,
-0.00550079345703125,
0.06298828125,
-0.0198974609375,
0.05340576171875,
0.06390380859375,
-0.0004298686981201172,
0.045928955078125,
0.02557373046875,
-0.0249786376953125,
0.0283050537109375,
0.038238525390625,
-0.0178375244140625,
0.036407470703125,
0.0213165283203125,
0.0012722015380859375,
-0.0276336669921875,
-0.001903533935546875,
-0.017120361328125,
0.024017333984375,
0.033966064453125,
-0.021636962890625,
-0.023712158203125,
-0.033782958984375,
0.039764404296875,
-0.0186767578125,
-0.028656005859375,
0.05731201171875,
0.0007052421569824219,
-0.030029296875,
0.05157470703125,
-0.0177764892578125,
0.051727294921875,
-0.06414794921875,
0.0023632049560546875,
-0.0297393798828125,
0.03173828125,
-0.0118865966796875,
-0.038909912109375,
0.016876220703125,
0.015533447265625,
-0.026458740234375,
-0.028045654296875,
0.0421142578125,
0.00920867919921875,
-0.08087158203125,
0.009674072265625,
0.040985107421875,
0.00305938720703125,
0.0177459716796875,
-0.08929443359375,
-0.01081085205078125,
0.0128936767578125,
-0.037872314453125,
0.02911376953125,
0.002017974853515625,
0.0164642333984375,
0.03466796875,
0.0631103515625,
-0.00641632080078125,
0.0016422271728515625,
-0.0249786376953125,
0.047637939453125,
-0.056488037109375,
-0.04681396484375,
-0.041046142578125,
0.0406494140625,
-0.015899658203125,
-0.049591064453125,
0.06317138671875,
0.056549072265625,
0.050933837890625,
-0.0225830078125,
0.038116455078125,
-0.0201416015625,
0.05560302734375,
-0.036376953125,
0.06756591796875,
-0.075439453125,
-0.004489898681640625,
-0.038970947265625,
-0.05352783203125,
-0.024932861328125,
0.0645751953125,
-0.008880615234375,
-0.01184844970703125,
0.0263214111328125,
0.0251922607421875,
0.0051727294921875,
0.0082855224609375,
0.00962066650390625,
-0.005046844482421875,
0.0095367431640625,
0.037322998046875,
0.0294189453125,
-0.01238250732421875,
0.032928466796875,
-0.047454833984375,
-0.0177001953125,
-0.0297698974609375,
-0.06744384765625,
-0.03973388671875,
-0.0268402099609375,
-0.029815673828125,
-0.025238037109375,
0.0021533966064453125,
0.08697509765625,
0.0489501953125,
-0.07177734375,
-0.03369140625,
-0.0018320083618164062,
0.01849365234375,
-0.04974365234375,
-0.0245513916015625,
0.03778076171875,
-0.00603485107421875,
-0.055938720703125,
0.0197906494140625,
-0.00434112548828125,
-0.006687164306640625,
0.020477294921875,
-0.0022296905517578125,
-0.0257720947265625,
0.037384033203125,
0.044891357421875,
0.01258087158203125,
-0.038482666015625,
-0.0293426513671875,
0.00995635986328125,
0.000408172607421875,
-0.001148223876953125,
0.04681396484375,
-0.03662109375,
-0.02435302734375,
0.04296875,
0.00029087066650390625,
0.041778564453125,
0.01038360595703125,
-0.0029087066650390625,
-0.045928955078125,
0.009033203125,
0.037933349609375,
0.0394287109375,
-0.0009431838989257812,
-0.0131683349609375,
0.05780029296875,
0.00737762451171875,
-0.036224365234375,
-0.0648193359375,
0.01042938232421875,
-0.099609375,
-0.0281829833984375,
0.045989990234375,
-0.0188140869140625,
-0.0143585205078125,
0.023895263671875,
-0.01300811767578125,
0.0023860931396484375,
-0.055572509765625,
0.053985595703125,
0.03857421875,
-0.0285797119140625,
-0.0185089111328125,
-0.023651123046875,
0.035491943359375,
0.047821044921875,
-0.033294677734375,
-0.01085662841796875,
0.046173095703125,
0.01558685302734375,
0.044677734375,
0.047943115234375,
0.011322021484375,
0.0023326873779296875,
0.015228271484375,
-0.0017910003662109375,
0.00572967529296875,
0.0015277862548828125,
0.01375579833984375,
0.009918212890625,
-0.0253448486328125,
-0.0517578125
]
] |
philschmid/distilbert-onnx | 2022-02-16T14:51:05.000Z | [
"transformers",
"onnx",
"distilbert",
"question-answering",
"en",
"dataset:squad",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | question-answering | philschmid | null | null | philschmid/distilbert-onnx | 2 | 37,821 | transformers | 2022-03-02T23:29:05 | ---
language: "en"
datasets:
- squad
metrics:
- squad
license: apache-2.0
---
# ONNX Conversion of [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad)
# DistilBERT base cased distilled SQuAD
This model is a fine-tune checkpoint of [DistilBERT-base-cased](https://huggingface.co/distilbert-base-cased), fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1.
This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).
| 557 | [
[
-0.0269012451171875,
-0.039093017578125,
0.038360595703125,
0.041778564453125,
-0.0294342041015625,
0.0325927734375,
0.018341064453125,
-0.0009937286376953125,
0.01055145263671875,
0.03009033203125,
-0.08038330078125,
-0.038604736328125,
-0.03466796875,
0.0027256011962890625,
-0.017913818359375,
0.0927734375,
-0.00264739990234375,
0.010772705078125,
0.00846099853515625,
-0.008941650390625,
-0.0168914794921875,
-0.051513671875,
-0.051361083984375,
-0.022064208984375,
0.023712158203125,
0.0299072265625,
0.019317626953125,
0.0251922607421875,
0.050933837890625,
0.01824951171875,
-0.0216827392578125,
-0.02294921875,
-0.07073974609375,
0.00989532470703125,
-0.00035309791564941406,
-0.02642822265625,
-0.05596923828125,
0.00592803955078125,
-0.0032329559326171875,
0.045806884765625,
-0.016876220703125,
0.0189056396484375,
-0.0165863037109375,
0.05902099609375,
-0.0247650146484375,
0.0237579345703125,
-0.0556640625,
0.0037441253662109375,
0.00879669189453125,
0.00351715087890625,
-0.03179931640625,
-0.01824951171875,
0.02838134765625,
-0.055450439453125,
0.0369873046875,
0.0019044876098632812,
0.040496826171875,
0.0270843505859375,
-0.01666259765625,
0.000926971435546875,
-0.031280517578125,
0.0704345703125,
-0.040069580078125,
0.01094818115234375,
0.02886962890625,
0.047027587890625,
-0.0175933837890625,
-0.052764892578125,
-0.021820068359375,
0.00494384765625,
0.01374053955078125,
0.00927734375,
-0.0134429931640625,
0.00792694091796875,
0.018096923828125,
0.033355712890625,
-0.016204833984375,
-0.0208740234375,
-0.05047607421875,
-0.0126953125,
0.052703857421875,
0.006626129150390625,
-0.0115509033203125,
0.015716552734375,
-0.0548095703125,
-0.0040283203125,
-0.050262451171875,
-0.00009059906005859375,
0.003353118896484375,
0.032196044921875,
-0.01456451416015625,
0.03082275390625,
-0.043670654296875,
0.0347900390625,
0.056671142578125,
0.00299072265625,
0.0243377685546875,
-0.050750732421875,
-0.0289459228515625,
0.04644775390625,
0.0180816650390625,
0.042877197265625,
0.03192138671875,
-0.01001739501953125,
-0.034515380859375,
-0.01666259765625,
0.0257415771484375,
-0.0992431640625,
-0.031982421875,
0.0020656585693359375,
-0.032257080078125,
-0.053131103515625,
0.0197906494140625,
-0.004116058349609375,
-0.0017709732055664062,
-0.0019989013671875,
0.0267486572265625,
-0.0281829833984375,
-0.0273590087890625,
-0.002399444580078125,
-0.0439453125,
0.0169830322265625,
0.042510986328125,
-0.06292724609375,
0.0007162094116210938,
0.03582763671875,
0.061920166015625,
-0.0009632110595703125,
0.012298583984375,
-0.0164031982421875,
0.00414276123046875,
-0.02197265625,
0.03363037109375,
-0.00347137451171875,
-0.0447998046875,
-0.0130462646484375,
0.0133209228515625,
0.023040771484375,
-0.042694091796875,
0.030548095703125,
-0.037811279296875,
-0.0233612060546875,
-0.04681396484375,
-0.035369873046875,
-0.02020263671875,
0.035308837890625,
-0.052001953125,
0.0635986328125,
0.05364990234375,
-0.019866943359375,
0.059906005859375,
-0.0499267578125,
-0.0206756591796875,
0.01097869873046875,
0.0294342041015625,
-0.023956298828125,
0.017181396484375,
-0.01519775390625,
0.0310821533203125,
0.004253387451171875,
0.00960540771484375,
-0.047821044921875,
-0.0130615234375,
-0.00804901123046875,
-0.004405975341796875,
0.0836181640625,
0.0164947509765625,
-0.0160369873046875,
-0.007488250732421875,
-0.06109619140625,
0.027984619140625,
-0.01367950439453125,
-0.0340576171875,
-0.0263824462890625,
-0.0214080810546875,
0.007587432861328125,
0.0232086181640625,
0.024261474609375,
-0.039031982421875,
0.0223388671875,
-0.005420684814453125,
0.036956787109375,
0.034332275390625,
0.00865936279296875,
0.0252685546875,
-0.0389404296875,
0.0131988525390625,
0.0205230712890625,
0.0195770263671875,
0.01849365234375,
-0.05584716796875,
-0.06536865234375,
-0.032318115234375,
0.0219573974609375,
0.032989501953125,
-0.04345703125,
0.0545654296875,
0.016326904296875,
-0.0589599609375,
-0.015716552734375,
0.01482391357421875,
0.039825439453125,
0.028289794921875,
0.0309906005859375,
-0.01861572265625,
-0.04339599609375,
-0.0654296875,
0.0302581787109375,
-0.047943115234375,
0.00408935546875,
-0.02001953125,
0.05401611328125,
-0.011688232421875,
0.059906005859375,
-0.01154327392578125,
-0.01922607421875,
-0.0299072265625,
0.01006317138671875,
0.033050537109375,
0.050567626953125,
0.07257080078125,
-0.050811767578125,
-0.05218505859375,
0.00794219970703125,
-0.03948974609375,
-0.0030460357666015625,
0.0211944580078125,
-0.023040771484375,
0.007289886474609375,
0.039031982421875,
-0.02593994140625,
0.059112548828125,
0.019866943359375,
-0.0478515625,
0.0217742919921875,
-0.00423431396484375,
0.0318603515625,
-0.08599853515625,
-0.00021970272064208984,
0.0021038055419921875,
-0.037353515625,
-0.0562744140625,
0.004726409912109375,
0.0014495849609375,
0.01763916015625,
-0.0506591796875,
0.01084136962890625,
-0.0308074951171875,
0.0036773681640625,
-0.00109100341796875,
-0.044189453125,
0.0102386474609375,
0.026885986328125,
-0.01226806640625,
0.04071044921875,
0.020050048828125,
-0.04449462890625,
0.04876708984375,
0.034454345703125,
-0.02484130859375,
0.05108642578125,
-0.068359375,
0.0023403167724609375,
0.00780487060546875,
0.01294708251953125,
-0.077392578125,
-0.0030517578125,
-0.0097503662109375,
-0.0159454345703125,
0.018310546875,
-0.029693603515625,
-0.02593994140625,
-0.0004425048828125,
-0.0123291015625,
0.045196533203125,
0.039398193359375,
-0.029510498046875,
0.00678253173828125,
0.0115509033203125,
-0.0013589859008789062,
-0.003566741943359375,
-0.06610107421875,
-0.03778076171875,
-0.020782470703125,
-0.051910400390625,
0.055511474609375,
-0.01422119140625,
-0.041534423828125,
-0.0111541748046875,
-0.0263214111328125,
-0.04412841796875,
0.008758544921875,
0.022674560546875,
0.035003662109375,
-0.04608154296875,
-0.015716552734375,
0.0185546875,
0.00982666015625,
0.00675201416015625,
0.0121612548828125,
0.033050537109375,
-0.010223388671875,
0.00019681453704833984,
-0.0244903564453125,
0.026031494140625,
0.066650390625,
0.0279693603515625,
0.056671142578125,
0.009368896484375,
-0.030426025390625,
-0.023162841796875,
-0.0288543701171875,
-0.03875732421875,
-0.032989501953125,
0.0206451416015625,
-0.04986572265625,
-0.045684814453125,
0.05706787109375,
0.00887298583984375,
0.0021572113037109375,
0.06512451171875,
0.03955078125,
-0.01387786865234375,
0.0760498046875,
0.05511474609375,
-0.0055389404296875,
0.00884246826171875,
-0.0343017578125,
-0.0040130615234375,
-0.032867431640625,
-0.0261688232421875,
-0.03204345703125,
-0.03558349609375,
-0.0220184326171875,
-0.0196533203125,
0.0261077880859375,
0.04119873046875,
-0.04620361328125,
0.048828125,
-0.038116455078125,
0.038818359375,
0.03668212890625,
0.02276611328125,
0.038421630859375,
-0.00397491455078125,
-0.0033740997314453125,
-0.006832122802734375,
-0.0404052734375,
-0.00812530517578125,
0.07489013671875,
0.0258636474609375,
0.03564453125,
0.02752685546875,
0.048370361328125,
0.04412841796875,
0.01898193359375,
-0.0533447265625,
0.02593994140625,
-0.0111236572265625,
-0.08935546875,
-0.01904296875,
-0.021331787109375,
-0.0206146240234375,
-0.0178070068359375,
-0.010772705078125,
-0.0214080810546875,
0.0036373138427734375,
0.0082244873046875,
-0.04620361328125,
-0.0008120536804199219,
-0.058319091796875,
0.0802001953125,
-0.0205535888671875,
-0.01171112060546875,
-0.01471710205078125,
-0.04296875,
0.037750244140625,
-0.01531982421875,
-0.026214599609375,
-0.018951416015625,
0.018341064453125,
0.02972412109375,
-0.0694580078125,
0.043060302734375,
-0.02642822265625,
0.004100799560546875,
0.028289794921875,
0.0034160614013671875,
0.0201568603515625,
0.0256195068359375,
-0.032440185546875,
0.0191192626953125,
0.01309967041015625,
-0.0291290283203125,
-0.020904541015625,
0.050506591796875,
-0.04534912109375,
-0.0287322998046875,
-0.03472900390625,
-0.0214080810546875,
-0.007598876953125,
0.004238128662109375,
0.038787841796875,
0.017547607421875,
-0.04876708984375,
0.0330810546875,
0.06884765625,
0.00844573974609375,
0.0267486572265625,
0.039764404296875,
-0.024658203125,
-0.004489898681640625,
0.0313720703125,
-0.00789642333984375,
0.05999755859375,
0.0276947021484375,
0.00010883808135986328,
-0.0430908203125,
-0.044677734375,
-0.06390380859375,
-0.0135040283203125,
-0.04925537109375,
-0.0213470458984375,
-0.0109710693359375,
-0.044525146484375,
-0.0416259765625,
-0.01027679443359375,
-0.030242919921875,
-0.049346923828125,
-0.0416259765625,
-0.0211029052734375,
0.055908203125,
0.052947998046875,
0.00959014892578125,
0.0228729248046875,
-0.0423583984375,
0.0007519721984863281,
0.028961181640625,
0.0146484375,
-0.051483154296875,
-0.05731201171875,
0.0017061233520507812,
0.0149993896484375,
-0.02392578125,
-0.0718994140625,
0.0233154296875,
0.029510498046875,
0.037933349609375,
0.039093017578125,
0.0216827392578125,
0.059112548828125,
-0.0223236083984375,
0.0251312255859375,
0.023681640625,
-0.055572509765625,
0.051055908203125,
-0.0286865234375,
0.0186920166015625,
0.0931396484375,
0.037750244140625,
0.00940704345703125,
-0.0102691650390625,
-0.04595947265625,
-0.0399169921875,
0.052703857421875,
0.0262451171875,
-0.0096893310546875,
0.0223388671875,
0.02490234375,
0.01291656494140625,
0.032501220703125,
-0.027923583984375,
-0.039215087890625,
-0.029388427734375,
-0.006099700927734375,
0.01103973388671875,
-0.00687408447265625,
-0.0024471282958984375,
-0.053070068359375,
0.05877685546875,
-0.00492095947265625,
0.0022716522216796875,
0.01467132568359375,
0.0117034912109375,
0.0016870498657226562,
-0.016387939453125,
0.052215576171875,
0.044830322265625,
-0.0640869140625,
-0.0269012451171875,
0.01116943359375,
-0.0325927734375,
0.0196533203125,
-0.01032257080078125,
-0.0079193115234375,
0.0207366943359375,
0.0021915435791015625,
0.06890869140625,
0.01039886474609375,
-0.0157318115234375,
0.036163330078125,
-0.0014066696166992188,
-0.0416259765625,
-0.03375244140625,
0.0225372314453125,
-0.0016117095947265625,
0.024566650390625,
0.03167724609375,
0.016876220703125,
0.0184783935546875,
-0.06951904296875,
0.0195465087890625,
0.02899169921875,
-0.0577392578125,
-0.02471923828125,
0.03863525390625,
0.036285400390625,
-0.015411376953125,
0.0416259765625,
-0.042999267578125,
-0.047119140625,
0.06463623046875,
0.0343017578125,
0.068115234375,
-0.020111083984375,
0.022186279296875,
0.050201416015625,
0.01259613037109375,
-0.0250701904296875,
0.032501220703125,
-0.0091094970703125,
-0.043670654296875,
-0.006805419921875,
-0.0684814453125,
-0.0181884765625,
0.0018901824951171875,
-0.058197021484375,
0.0306396484375,
-0.058685302734375,
-0.030242919921875,
0.01233673095703125,
-0.0053863525390625,
-0.0404052734375,
0.0215606689453125,
-0.00940704345703125,
0.07879638671875,
-0.04296875,
0.077880859375,
0.054779052734375,
-0.0213623046875,
-0.056549072265625,
-0.0210113525390625,
0.00548553466796875,
-0.05755615234375,
0.07861328125,
0.01678466796875,
0.01264190673828125,
0.014404296875,
-0.024627685546875,
-0.04461669921875,
0.08599853515625,
0.0204620361328125,
-0.061126708984375,
0.00321197509765625,
0.00832366943359375,
0.03436279296875,
-0.0484619140625,
0.02691650390625,
0.053131103515625,
0.039093017578125,
0.02783203125,
-0.09576416015625,
-0.00457763671875,
-0.034027099609375,
-0.00025773048400878906,
0.005985260009765625,
-0.045257568359375,
0.08551025390625,
-0.022369384765625,
0.002727508544921875,
0.01495361328125,
0.0284423828125,
0.0340576171875,
0.0213623046875,
0.045562744140625,
0.05853271484375,
0.01495361328125,
-0.03887939453125,
0.04412841796875,
-0.00853729248046875,
0.0206756591796875,
0.053558349609375,
-0.0295867919921875,
0.053009033203125,
0.047515869140625,
-0.0240631103515625,
0.04022216796875,
0.0364990234375,
0.001537322998046875,
0.07745361328125,
0.03289794921875,
-0.033538818359375,
-0.037628173828125,
0.0213165283203125,
-0.038970947265625,
0.0379638671875,
0.0235137939453125,
-0.039581298828125,
-0.01349639892578125,
-0.031280517578125,
-0.020355224609375,
-0.007965087890625,
-0.046142578125,
0.06768798828125,
-0.0005784034729003906,
-0.0557861328125,
0.0518798828125,
-0.0001628398895263672,
0.046844482421875,
-0.0426025390625,
-0.01358795166015625,
-0.01824951171875,
0.03753662109375,
-0.0029697418212890625,
-0.047210693359375,
0.03948974609375,
-0.002628326416015625,
-0.054718017578125,
-0.02593994140625,
0.03973388671875,
-0.0292205810546875,
-0.07110595703125,
0.01177215576171875,
0.038116455078125,
0.0042724609375,
-0.0296478271484375,
-0.055084228515625,
0.0021305084228515625,
0.0225677490234375,
-0.005153656005859375,
0.0218505859375,
0.049774169921875,
0.0035915374755859375,
0.03082275390625,
0.0435791015625,
-0.018218994140625,
0.0165252685546875,
-0.00832366943359375,
0.058502197265625,
-0.039093017578125,
-0.030242919921875,
-0.061126708984375,
0.042083740234375,
-0.0242462158203125,
-0.06707763671875,
0.033721923828125,
0.055908203125,
0.06671142578125,
-0.029998779296875,
0.066650390625,
-0.017608642578125,
0.0291900634765625,
-0.0287933349609375,
0.08331298828125,
-0.047271728515625,
-0.0033397674560546875,
-0.00982666015625,
-0.0640869140625,
0.01053619384765625,
0.068603515625,
0.023712158203125,
-0.00482940673828125,
0.0312042236328125,
0.05340576171875,
-0.015960693359375,
0.0115966796875,
0.0285797119140625,
-0.0009722709655761719,
0.006595611572265625,
0.045806884765625,
0.04449462890625,
-0.049530029296875,
0.035736083984375,
-0.04296875,
-0.0259246826171875,
-0.028289794921875,
-0.076171875,
-0.0963134765625,
-0.03125,
-0.030731201171875,
-0.045074462890625,
0.0115966796875,
0.053009033203125,
0.06719970703125,
-0.0843505859375,
-0.01264190673828125,
-0.0296173095703125,
-0.0172119140625,
-0.00494384765625,
-0.016082763671875,
-0.02496337890625,
-0.004016876220703125,
-0.047515869140625,
0.03594970703125,
0.01554107666015625,
0.01366424560546875,
-0.0321044921875,
-0.01459503173828125,
-0.0104217529296875,
-0.01337432861328125,
0.03790283203125,
0.00939178466796875,
-0.041290283203125,
-0.022247314453125,
0.0184326171875,
-0.0286102294921875,
0.005634307861328125,
0.042816162109375,
-0.0389404296875,
0.004482269287109375,
0.05352783203125,
0.0266265869140625,
0.04595947265625,
0.006473541259765625,
0.061614990234375,
-0.071533203125,
0.0228424072265625,
0.0191802978515625,
0.03619384765625,
0.0162811279296875,
-0.0137786865234375,
0.03985595703125,
0.030242919921875,
-0.03704833984375,
-0.05902099609375,
0.01055908203125,
-0.1090087890625,
-0.0021228790283203125,
0.07952880859375,
-0.020599365234375,
-0.0207366943359375,
-0.0162200927734375,
-0.0173797607421875,
0.0186614990234375,
-0.048828125,
0.04986572265625,
0.0550537109375,
0.01947021484375,
0.0113372802734375,
-0.029083251953125,
0.051422119140625,
0.0193328857421875,
-0.048492431640625,
-0.0269927978515625,
0.0252838134765625,
0.0330810546875,
0.0258026123046875,
0.032806396484375,
0.005352020263671875,
0.03350830078125,
0.0029582977294921875,
0.0008940696716308594,
-0.003917694091796875,
-0.0177154541015625,
0.023590087890625,
-0.00437164306640625,
-0.0173797607421875,
-0.0242462158203125
]
] |
philschmid/flan-t5-xxl-sharded-fp16 | 2023-03-08T15:30:42.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"endpoints-template",
"arxiv:2210.11416",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text2text-generation | philschmid | null | null | philschmid/flan-t5-xxl-sharded-fp16 | 47 | 37,658 | transformers | 2023-01-27T15:05:31 | ---
license: apache-2.0
tags:
- endpoints-template
---
# FORK of FLAN-T5 XXL
> This is a fork of google/flan-t5-xxl implementing a custom `handler.py` as an example for how to use t5-11b with inference-endpoints on a single NVIDIA A10G.
You can deploy the flan-t5-xxl with a [1-click](https://ui.endpoints.huggingface.co/new?repository=philschmid/flan-t5-xxl-sharded-fp16).
Since we are using the "quantized" version, we can switch our instance type to **"GPU [medium] · 1x Nvidia A10G"**.
# TL;DR
If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages.
As mentioned in the first few lines of the abstract :
> Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints,1 which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
**Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the [T5 model card](https://huggingface.co/t5-large).
# Model Details
## Model Description
- **Model type:** Language model
- **Language(s) (NLP):** English, Spanish, Japanese, Persian, Hindi, French, Chinese, Bengali, Gujarati, German, Telugu, Italian, Arabic, Polish, Tamil, Marathi, Malayalam, Oriya, Panjabi, Portuguese, Urdu, Galician, Hebrew, Korean, Catalan, Thai, Dutch, Indonesian, Vietnamese, Bulgarian, Filipino, Central Khmer, Lao, Turkish, Russian, Croatian, Swedish, Yoruba, Kurdish, Burmese, Malay, Czech, Finnish, Somali, Tagalog, Swahili, Sinhala, Kannada, Zhuang, Igbo, Xhosa, Romanian, Haitian, Estonian, Slovak, Lithuanian, Greek, Nepali, Assamese, Norwegian
- **License:** Apache 2.0
- **Related Models:** [All FLAN-T5 Checkpoints](https://huggingface.co/models?search=flan-t5)
- **Original Checkpoints:** [All Original FLAN-T5 Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#flan-t5-checkpoints)
- **Resources for more information:**
- [Research paper](https://arxiv.org/pdf/2210.11416.pdf)
- [GitHub Repo](https://github.com/google-research/t5x)
- [Hugging Face FLAN-T5 Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/t5)
| 2,524 | [
[
-0.049468994140625,
-0.052703857421875,
0.0268402099609375,
0.00811767578125,
-0.01239013671875,
-0.0042266845703125,
-0.01136016845703125,
-0.049652099609375,
0.0171966552734375,
0.0229339599609375,
-0.04986572265625,
-0.046722412109375,
-0.03564453125,
-0.0016756057739257812,
-0.0293731689453125,
0.08245849609375,
-0.0098724365234375,
-0.0054473876953125,
0.017974853515625,
-0.020965576171875,
0.0010175704956054688,
-0.0194244384765625,
-0.0697021484375,
-0.01508331298828125,
0.040008544921875,
0.0244598388671875,
0.0491943359375,
0.050018310546875,
0.0238189697265625,
0.019622802734375,
-0.0171966552734375,
-0.0169677734375,
-0.0244140625,
-0.032684326171875,
-0.00562286376953125,
-0.0240478515625,
-0.054290771484375,
-0.0152130126953125,
0.033782958984375,
0.027557373046875,
-0.0174560546875,
0.022247314453125,
-0.0174713134765625,
0.036407470703125,
-0.052581787109375,
0.006015777587890625,
-0.002017974853515625,
0.007137298583984375,
-0.035919189453125,
0.0209503173828125,
-0.004604339599609375,
-0.029449462890625,
0.0183563232421875,
-0.0614013671875,
0.0255279541015625,
-0.00450897216796875,
0.10650634765625,
0.01195526123046875,
-0.0179595947265625,
-0.01279449462890625,
-0.036376953125,
0.05328369140625,
-0.070556640625,
0.027496337890625,
0.0102691650390625,
0.046844482421875,
-0.001102447509765625,
-0.0633544921875,
-0.04376220703125,
-0.01003265380859375,
0.00604248046875,
0.0005087852478027344,
0.0018138885498046875,
0.023345947265625,
0.0357666015625,
0.05792236328125,
-0.037139892578125,
-0.004642486572265625,
-0.0394287109375,
-0.01241302490234375,
0.044403076171875,
-0.003021240234375,
0.042266845703125,
-0.00992584228515625,
-0.031982421875,
-0.020782470703125,
-0.0399169921875,
0.00945281982421875,
0.0185394287109375,
0.01222991943359375,
-0.0462646484375,
0.00830078125,
-0.0173187255859375,
0.04327392578125,
0.017578125,
-0.0163726806640625,
0.0277099609375,
-0.01432037353515625,
-0.027435302734375,
-0.01276397705078125,
0.0673828125,
0.0120849609375,
0.0132904052734375,
0.0058135986328125,
-0.0318603515625,
-0.006748199462890625,
0.01387786865234375,
-0.06805419921875,
-0.022979736328125,
0.038726806640625,
-0.0277862548828125,
-0.03704833984375,
0.01227569580078125,
-0.058807373046875,
-0.00921630859375,
0.00775146484375,
0.032684326171875,
-0.046417236328125,
-0.044647216796875,
-0.0118408203125,
-0.01364898681640625,
0.034515380859375,
0.03228759765625,
-0.08843994140625,
0.0282135009765625,
0.057098388671875,
0.06817626953125,
0.00980377197265625,
-0.0162811279296875,
-0.0299224853515625,
0.0082244873046875,
-0.02178955078125,
0.04052734375,
-0.03668212890625,
-0.0226593017578125,
0.01123809814453125,
0.01434326171875,
-0.00859832763671875,
-0.04315185546875,
0.054840087890625,
-0.03179931640625,
0.0279693603515625,
-0.04473876953125,
-0.044830322265625,
-0.049102783203125,
0.01427459716796875,
-0.057373046875,
0.07550048828125,
0.0212249755859375,
-0.05029296875,
0.032745361328125,
-0.06268310546875,
-0.034149169921875,
0.0034027099609375,
0.0012693405151367188,
-0.035064697265625,
0.007633209228515625,
0.0189056396484375,
0.0167236328125,
-0.014556884765625,
0.0044708251953125,
-0.038970947265625,
-0.0233612060546875,
-0.026702880859375,
0.01183319091796875,
0.0772705078125,
0.0323486328125,
-0.061187744140625,
0.0338134765625,
-0.0433349609375,
-0.0015726089477539062,
0.00899505615234375,
-0.007434844970703125,
-0.007015228271484375,
-0.01885986328125,
0.0288848876953125,
0.027679443359375,
0.0189971923828125,
-0.0347900390625,
0.01532745361328125,
-0.0274810791015625,
0.03277587890625,
0.042144775390625,
-0.006103515625,
0.0268096923828125,
-0.033477783203125,
0.048553466796875,
0.02252197265625,
0.034423828125,
-0.01409912109375,
-0.0302276611328125,
-0.0841064453125,
-0.0093231201171875,
0.0089569091796875,
0.049224853515625,
-0.056243896484375,
0.01120758056640625,
-0.026519775390625,
-0.0330810546875,
-0.028472900390625,
0.01538848876953125,
0.048919677734375,
0.026153564453125,
0.0262908935546875,
-0.021514892578125,
-0.025634765625,
-0.0545654296875,
-0.01371002197265625,
0.0008168220520019531,
0.0101318359375,
0.01166534423828125,
0.050506591796875,
0.0008068084716796875,
0.029327392578125,
-0.0190582275390625,
-0.034454345703125,
-0.024261474609375,
-0.00020825862884521484,
0.005168914794921875,
0.044586181640625,
0.077880859375,
-0.0435791015625,
-0.042205810546875,
0.008453369140625,
-0.057769775390625,
0.0078887939453125,
0.0078887939453125,
-0.012786865234375,
0.0479736328125,
0.01483917236328125,
-0.027374267578125,
0.0240020751953125,
0.04864501953125,
-0.028564453125,
0.032928466796875,
-0.0126800537109375,
0.0139923095703125,
-0.097900390625,
0.019287109375,
0.0118560791015625,
-0.0184783935546875,
-0.047088623046875,
0.03448486328125,
0.0104827880859375,
-0.0017719268798828125,
-0.04022216796875,
0.06243896484375,
-0.03240966796875,
0.0004100799560546875,
-0.0185089111328125,
-0.003875732421875,
-0.008056640625,
0.0318603515625,
0.005962371826171875,
0.05908203125,
0.047149658203125,
-0.051910400390625,
0.0178375244140625,
0.0100250244140625,
-0.0145111083984375,
0.041595458984375,
-0.062255859375,
0.0009126663208007812,
0.003368377685546875,
0.0255279541015625,
-0.047393798828125,
-0.0419921875,
0.031524658203125,
-0.0178680419921875,
0.019775390625,
-0.0255279541015625,
-0.0240325927734375,
-0.031341552734375,
-0.02435302734375,
0.0186309814453125,
0.052154541015625,
-0.05303955078125,
0.045806884765625,
0.020355224609375,
0.01837158203125,
-0.034637451171875,
-0.0653076171875,
-0.001338958740234375,
-0.039764404296875,
-0.06414794921875,
0.0270538330078125,
0.00311279296875,
-0.0033721923828125,
-0.01087188720703125,
-0.0086822509765625,
-0.0227203369140625,
-0.0023651123046875,
0.0165863037109375,
-0.0006966590881347656,
-0.0259246826171875,
-0.017120361328125,
0.006908416748046875,
-0.01021575927734375,
0.0020275115966796875,
-0.041046142578125,
0.02630615234375,
-0.0206451416015625,
-0.002227783203125,
-0.057342529296875,
0.0045166015625,
0.0413818359375,
-0.03179931640625,
0.06695556640625,
0.08026123046875,
-0.04400634765625,
-0.00460052490234375,
-0.054962158203125,
-0.0182342529296875,
-0.0380859375,
-0.013641357421875,
-0.044281005859375,
-0.0570068359375,
0.0723876953125,
0.007808685302734375,
0.0352783203125,
0.04510498046875,
0.01459503173828125,
0.0027923583984375,
0.053436279296875,
0.048919677734375,
-0.018798828125,
0.0657958984375,
-0.036834716796875,
-0.0005207061767578125,
-0.048553466796875,
-0.0033473968505859375,
-0.0228271484375,
-0.01357269287109375,
-0.045867919921875,
-0.0241851806640625,
0.02923583984375,
0.012054443359375,
-0.033355712890625,
0.0242156982421875,
-0.0201568603515625,
0.01560211181640625,
0.045257568359375,
0.008758544921875,
0.0021495819091796875,
0.007762908935546875,
-0.0171051025390625,
0.006195068359375,
-0.041351318359375,
-0.0367431640625,
0.07562255859375,
0.017333984375,
0.0335693359375,
0.0256500244140625,
0.0673828125,
0.004558563232421875,
0.012542724609375,
-0.02508544921875,
0.028411865234375,
-0.0228729248046875,
-0.06182861328125,
-0.005481719970703125,
-0.023681640625,
-0.04815673828125,
0.0057525634765625,
0.003849029541015625,
-0.06048583984375,
0.0016260147094726562,
0.0267333984375,
-0.04278564453125,
0.038665771484375,
-0.06854248046875,
0.1033935546875,
-0.01146697998046875,
-0.036285400390625,
-0.0238494873046875,
-0.0367431640625,
0.05615234375,
0.01317596435546875,
0.0116729736328125,
-0.0038776397705078125,
-0.0029468536376953125,
0.04443359375,
-0.0740966796875,
0.05401611328125,
-0.036834716796875,
-0.019561767578125,
0.02874755859375,
-0.00177001953125,
0.03521728515625,
0.005611419677734375,
-0.0108184814453125,
0.018585205078125,
0.0284576416015625,
-0.051361083984375,
-0.05120849609375,
0.07305908203125,
-0.060699462890625,
-0.033599853515625,
-0.036712646484375,
-0.00949859619140625,
0.017181396484375,
0.0296478271484375,
0.0215911865234375,
0.0389404296875,
-0.007190704345703125,
-0.0171661376953125,
0.04730224609375,
-0.0228729248046875,
0.043975830078125,
0.020050048828125,
-0.03729248046875,
-0.04132080078125,
0.06988525390625,
-0.00206756591796875,
0.034271240234375,
0.0283966064453125,
0.01385498046875,
-0.0198211669921875,
-0.023651123046875,
-0.061553955078125,
0.015106201171875,
-0.04449462890625,
0.01013946533203125,
-0.0309906005859375,
-0.007114410400390625,
-0.033203125,
-0.01131439208984375,
-0.041290283203125,
-0.035797119140625,
-0.0162506103515625,
0.0017175674438476562,
0.035003662109375,
0.05389404296875,
0.0019550323486328125,
0.034698486328125,
-0.0531005859375,
0.02276611328125,
-0.0031719207763671875,
0.040252685546875,
0.012237548828125,
-0.04766845703125,
-0.010650634765625,
0.01392364501953125,
-0.027069091796875,
-0.0545654296875,
0.0133819580078125,
0.0264892578125,
0.031097412109375,
0.0645751953125,
-0.0013303756713867188,
0.06634521484375,
-0.01654052734375,
0.068603515625,
-0.0027790069580078125,
-0.0775146484375,
0.05059814453125,
-0.05072021484375,
0.0355224609375,
0.038360595703125,
0.0267333984375,
-0.043548583984375,
-0.0160675048828125,
-0.0648193359375,
-0.051055908203125,
0.058502197265625,
0.00980377197265625,
0.0012121200561523438,
0.0088653564453125,
0.032073974609375,
-0.007053375244140625,
0.0032138824462890625,
-0.04730224609375,
-0.0277862548828125,
-0.028839111328125,
-0.01087188720703125,
-0.0001494884490966797,
-0.02056884765625,
-0.01451873779296875,
-0.016937255859375,
0.056854248046875,
-0.00679779052734375,
0.0153961181640625,
0.01385498046875,
-0.007762908935546875,
-0.013580322265625,
0.0035572052001953125,
0.069580078125,
0.040863037109375,
-0.0175628662109375,
-0.01004791259765625,
0.0230865478515625,
-0.039093017578125,
-0.01528167724609375,
0.0054779052734375,
-0.0256805419921875,
-0.004901885986328125,
0.026580810546875,
0.07672119140625,
0.02850341796875,
-0.025390625,
0.032501220703125,
-0.0021610260009765625,
-0.020660400390625,
-0.048797607421875,
0.027984619140625,
0.00736236572265625,
0.0192718505859375,
0.01140594482421875,
-0.01059722900390625,
0.0027408599853515625,
-0.0293121337890625,
0.004138946533203125,
0.0156402587890625,
-0.0275115966796875,
-0.039642333984375,
0.074462890625,
0.0286712646484375,
0.0003714561462402344,
0.045257568359375,
-0.0294647216796875,
-0.037811279296875,
0.03533935546875,
0.0186920166015625,
0.0810546875,
-0.0258026123046875,
0.01568603515625,
0.06298828125,
0.01806640625,
-0.006221771240234375,
0.0472412109375,
-0.007526397705078125,
-0.0295867919921875,
-0.010833740234375,
-0.052154541015625,
-0.020599365234375,
0.00992584228515625,
-0.045135498046875,
0.0273284912109375,
-0.069580078125,
-0.004734039306640625,
-0.0037631988525390625,
0.021728515625,
-0.043487548828125,
0.0220947265625,
0.018768310546875,
0.07537841796875,
-0.0487060546875,
0.0703125,
0.0736083984375,
-0.061553955078125,
-0.07391357421875,
-0.004322052001953125,
0.0250244140625,
-0.031768798828125,
0.0198211669921875,
0.01136016845703125,
0.01092529296875,
-0.0023937225341796875,
-0.0252838134765625,
-0.06439208984375,
0.0924072265625,
0.0271453857421875,
-0.0338134765625,
0.0008015632629394531,
0.00804901123046875,
0.036041259765625,
-0.0128936767578125,
0.049896240234375,
0.0430908203125,
0.04315185546875,
0.0219879150390625,
-0.0921630859375,
0.029022216796875,
-0.021514892578125,
0.00844573974609375,
0.01015472412109375,
-0.0745849609375,
0.0634765625,
-0.0263519287109375,
-0.0128631591796875,
0.009735107421875,
0.0677490234375,
0.0249481201171875,
0.01165771484375,
0.04339599609375,
0.049224853515625,
0.055694580078125,
-0.022979736328125,
0.09332275390625,
-0.044525146484375,
0.03289794921875,
0.05523681640625,
0.01751708984375,
0.058135986328125,
0.02545166015625,
-0.01097869873046875,
0.05059814453125,
0.06707763671875,
0.0073089599609375,
0.01538848876953125,
-0.0038394927978515625,
-0.036285400390625,
-0.0126953125,
-0.0003559589385986328,
-0.0360107421875,
0.00861358642578125,
0.028411865234375,
-0.025726318359375,
-0.0215606689453125,
-0.00830078125,
0.0232391357421875,
-0.0220947265625,
-0.0188446044921875,
0.04193115234375,
0.01071929931640625,
-0.051849365234375,
0.07073974609375,
0.0097198486328125,
0.057403564453125,
-0.053192138671875,
0.00875091552734375,
-0.0347900390625,
0.0242462158203125,
-0.038330078125,
-0.0286407470703125,
0.022125244140625,
-0.00362396240234375,
-0.0014553070068359375,
-0.0097808837890625,
0.0281219482421875,
-0.0305328369140625,
-0.03533935546875,
0.01507568359375,
0.003398895263671875,
0.020721435546875,
-0.005126953125,
-0.060882568359375,
0.03228759765625,
0.006786346435546875,
-0.024322509765625,
0.017852783203125,
0.0147705078125,
-0.021820068359375,
0.057403564453125,
0.03204345703125,
-0.016937255859375,
0.031402587890625,
0.022369384765625,
0.054290771484375,
-0.057098388671875,
-0.045257568359375,
-0.037078857421875,
0.039031982421875,
-0.004253387451171875,
-0.042938232421875,
0.050445556640625,
0.05023193359375,
0.07928466796875,
-0.0141754150390625,
0.06719970703125,
-0.034942626953125,
0.0201263427734375,
-0.03472900390625,
0.059844970703125,
-0.06634521484375,
0.0009927749633789062,
-0.0379638671875,
-0.0576171875,
-0.00775146484375,
0.051361083984375,
-0.028900146484375,
0.036529541015625,
0.052764892578125,
0.048370361328125,
-0.0290679931640625,
0.0167083740234375,
0.0163116455078125,
0.0056610107421875,
0.0443115234375,
0.060211181640625,
0.020904541015625,
-0.05841064453125,
0.038360595703125,
-0.051910400390625,
-0.006656646728515625,
-0.0165863037109375,
-0.05401611328125,
-0.072265625,
-0.043060302734375,
-0.0290985107421875,
-0.023040771484375,
0.01097869873046875,
0.055877685546875,
0.0631103515625,
-0.0782470703125,
-0.02410888671875,
-0.02130126953125,
0.00386810302734375,
-0.0205230712890625,
-0.01947021484375,
0.025634765625,
-0.036468505859375,
-0.0772705078125,
0.01004791259765625,
0.004405975341796875,
0.0150146484375,
-0.02606201171875,
-0.0162811279296875,
-0.01374053955078125,
-0.0282135009765625,
0.020782470703125,
0.04864501953125,
-0.07452392578125,
-0.03228759765625,
-0.016510009765625,
-0.0094146728515625,
-0.004852294921875,
0.0355224609375,
-0.032196044921875,
0.023956298828125,
0.033599853515625,
0.03460693359375,
0.048431396484375,
-0.0015916824340820312,
0.0526123046875,
-0.029022216796875,
0.028564453125,
-0.0158233642578125,
0.0189208984375,
0.0208892822265625,
-0.007640838623046875,
0.037689208984375,
0.0214385986328125,
-0.02362060546875,
-0.041748046875,
0.006015777587890625,
-0.07025146484375,
0.00836181640625,
0.08294677734375,
-0.0298614501953125,
-0.035614013671875,
0.017059326171875,
-0.003963470458984375,
0.023284912109375,
-0.033355712890625,
0.0452880859375,
0.056915283203125,
0.00921630859375,
-0.037933349609375,
-0.057281494140625,
0.059783935546875,
0.038116455078125,
-0.06585693359375,
-0.01535797119140625,
0.02691650390625,
0.051055908203125,
0.0005822181701660156,
0.038848876953125,
-0.00222015380859375,
0.029022216796875,
0.0013303756713867188,
0.0222320556640625,
-0.01050567626953125,
-0.0102081298828125,
-0.027557373046875,
-0.004352569580078125,
0.0007071495056152344,
-0.0189056396484375
]
] |
deepset/sentence_bert | 2021-05-19T15:34:03.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | deepset | null | null | deepset/sentence_bert | 19 | 37,466 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
---
This is an upload of the bert-base-nli-stsb-mean-tokens pretrained model from the Sentence Transformers Repo (https://github.com/UKPLab/sentence-transformers)
| 188 | [
[
-0.00308990478515625,
-0.025421142578125,
0.031158447265625,
0.016998291015625,
-0.025909423828125,
-0.005207061767578125,
-0.0026874542236328125,
-0.01157379150390625,
0.04522705078125,
0.06268310546875,
-0.0777587890625,
-0.019134521484375,
-0.02288818359375,
-0.004894256591796875,
-0.052276611328125,
0.08587646484375,
0.015899658203125,
0.0430908203125,
-0.003963470458984375,
0.01465606689453125,
-0.034881591796875,
-0.034698486328125,
-0.034454345703125,
-0.01654052734375,
0.031280517578125,
0.0134735107421875,
0.05108642578125,
0.00597381591796875,
0.042388916015625,
0.01611328125,
-0.004734039306640625,
-0.05279541015625,
-0.01526641845703125,
-0.02374267578125,
-0.01123809814453125,
-0.0240020751953125,
-0.033477783203125,
0.00853729248046875,
0.0562744140625,
0.0289154052734375,
-0.027069091796875,
0.031097412109375,
-0.029937744140625,
0.03070068359375,
-0.021575927734375,
-0.00803375244140625,
-0.032073974609375,
-0.006702423095703125,
-0.0177001953125,
0.0201416015625,
-0.03033447265625,
-0.0192108154296875,
0.018035888671875,
-0.055816650390625,
0.016998291015625,
0.00452423095703125,
0.07977294921875,
0.0234832763671875,
-0.0325927734375,
-0.04058837890625,
-0.0253753662109375,
0.049530029296875,
-0.042938232421875,
0.034576416015625,
-0.002399444580078125,
0.033447265625,
-0.01375579833984375,
-0.078857421875,
-0.041259765625,
-0.01434326171875,
-0.02593994140625,
0.01271820068359375,
-0.01140594482421875,
0.00487518310546875,
0.0072021484375,
0.029449462890625,
-0.044952392578125,
0.0008902549743652344,
-0.048919677734375,
-0.01557159423828125,
0.0228271484375,
-0.013916015625,
0.0246124267578125,
-0.0501708984375,
-0.0255126953125,
-0.018890380859375,
-0.05181884765625,
-0.00664520263671875,
0.03082275390625,
0.0166473388671875,
-0.032989501953125,
0.058807373046875,
0.0251617431640625,
0.052337646484375,
-0.0203094482421875,
0.048126220703125,
0.042083740234375,
-0.0262908935546875,
-0.0026302337646484375,
-0.0089111328125,
0.0231170654296875,
0.02117919921875,
0.035614013671875,
-0.00603485107421875,
-0.0214385986328125,
-0.007419586181640625,
0.044036865234375,
-0.04705810546875,
-0.0227203369140625,
0.0092620849609375,
-0.055450439453125,
-0.0236053466796875,
0.0310211181640625,
-0.035552978515625,
0.01059722900390625,
-0.0301055908203125,
0.0297698974609375,
-0.036895751953125,
-0.01131439208984375,
0.004425048828125,
-0.020599365234375,
0.006755828857421875,
-0.01110076904296875,
-0.0560302734375,
0.01163482666015625,
0.02716064453125,
0.05322265625,
0.0218963623046875,
-0.03009033203125,
-0.0205230712890625,
0.0025539398193359375,
-0.0030975341796875,
0.028839111328125,
-0.019134521484375,
-0.03936767578125,
0.00647735595703125,
0.003932952880859375,
-0.005340576171875,
-0.01100921630859375,
0.049652099609375,
-0.0479736328125,
0.0296478271484375,
-0.004825592041015625,
-0.048583984375,
-0.00246429443359375,
0.0190582275390625,
-0.056121826171875,
0.09442138671875,
0.03668212890625,
-0.05145263671875,
0.0198822021484375,
-0.09735107421875,
-0.0108642578125,
0.00502777099609375,
-0.005306243896484375,
-0.021148681640625,
0.01393890380859375,
0.00583648681640625,
0.023712158203125,
0.00655364990234375,
0.035003662109375,
-0.009735107421875,
-0.0247344970703125,
0.035919189453125,
0.0015964508056640625,
0.08056640625,
0.0389404296875,
0.006290435791015625,
0.035614013671875,
-0.08721923828125,
0.00188446044921875,
0.0096282958984375,
-0.0230255126953125,
-0.0210113525390625,
0.006259918212890625,
0.013336181640625,
0.014556884765625,
0.0340576171875,
-0.053558349609375,
0.0186614990234375,
-0.02056884765625,
0.0548095703125,
0.051513671875,
-0.011260986328125,
0.0212249755859375,
-0.018096923828125,
0.009246826171875,
0.01393890380859375,
0.035919189453125,
-0.007083892822265625,
-0.0265350341796875,
-0.051422119140625,
-0.030853271484375,
0.044769287109375,
0.0278472900390625,
-0.0382080078125,
0.06170654296875,
-0.0229339599609375,
-0.034423828125,
-0.035675048828125,
-0.002521514892578125,
0.007457733154296875,
0.006870269775390625,
0.0242919921875,
-0.0208282470703125,
-0.072265625,
-0.0733642578125,
0.013519287109375,
-0.039703369140625,
-0.0305633544921875,
-0.0012445449829101562,
0.068115234375,
-0.038330078125,
0.07476806640625,
-0.0360107421875,
-0.00632476806640625,
-0.0308990478515625,
0.032958984375,
0.035736083984375,
0.059844970703125,
0.07879638671875,
-0.03076171875,
-0.0034732818603515625,
-0.052490234375,
-0.01523590087890625,
-0.0131683349609375,
-0.0102996826171875,
-0.0265045166015625,
-0.0233306884765625,
0.03497314453125,
-0.0670166015625,
0.01561737060546875,
0.043182373046875,
-0.04180908203125,
0.046112060546875,
-0.01300048828125,
0.0043792724609375,
-0.111328125,
0.0178070068359375,
-0.01397705078125,
-0.0255889892578125,
-0.0289306640625,
0.014678955078125,
0.01458740234375,
-0.01532745361328125,
-0.03985595703125,
0.0162506103515625,
-0.02569580078125,
-0.0171051025390625,
0.01418304443359375,
-0.00765228271484375,
-0.020050048828125,
0.01470947265625,
-0.0037689208984375,
0.0645751953125,
0.04638671875,
-0.01971435546875,
0.02239990234375,
0.05157470703125,
-0.02227783203125,
0.00989532470703125,
-0.06591796875,
0.0259552001953125,
0.0126800537109375,
0.01187896728515625,
-0.053009033203125,
-0.0289459228515625,
0.00537109375,
-0.04010009765625,
0.0012979507446289062,
0.0030193328857421875,
-0.054962158203125,
-0.058563232421875,
-0.0160064697265625,
0.0136566162109375,
0.0445556640625,
-0.05194091796875,
0.051025390625,
0.0228729248046875,
-0.0126800537109375,
-0.043701171875,
-0.052093505859375,
-0.0005583763122558594,
0.0077667236328125,
-0.02410888671875,
0.0276641845703125,
-0.01319122314453125,
-0.00905609130859375,
0.012481689453125,
0.03759765625,
-0.01076507568359375,
-0.0027923583984375,
0.0176544189453125,
0.04693603515625,
-0.0244140625,
0.00910186767578125,
0.0008587837219238281,
0.0135498046875,
0.0184478759765625,
-0.0031528472900390625,
0.0543212890625,
-0.0122222900390625,
-0.0171661376953125,
-0.020660400390625,
0.029541015625,
0.0274658203125,
0.01074981689453125,
0.047515869140625,
0.0258636474609375,
-0.01812744140625,
-0.01168060302734375,
-0.0316162109375,
-0.02093505859375,
-0.0313720703125,
0.029022216796875,
-0.017974853515625,
-0.0584716796875,
0.027496337890625,
0.0003342628479003906,
0.0014362335205078125,
0.035736083984375,
0.0293731689453125,
-0.02203369140625,
0.05169677734375,
0.043060302734375,
-0.017913818359375,
0.050750732421875,
-0.01904296875,
-0.009735107421875,
-0.01953125,
0.00815582275390625,
-0.041412353515625,
-0.01149749755859375,
-0.0249481201171875,
-0.01320648193359375,
-0.0213165283203125,
0.00910186767578125,
-0.03826904296875,
0.040191650390625,
-0.033966064453125,
0.047515869140625,
0.07928466796875,
0.0167999267578125,
-0.0123138427734375,
-0.0303497314453125,
-0.008209228515625,
-0.005950927734375,
-0.03521728515625,
-0.041656494140625,
0.09014892578125,
0.034912109375,
0.04046630859375,
0.004375457763671875,
0.040985107421875,
0.040802001953125,
0.0264434814453125,
-0.0272369384765625,
0.052581787109375,
-0.03338623046875,
-0.0804443359375,
-0.007457733154296875,
-0.0129547119140625,
-0.05718994140625,
-0.020751953125,
-0.0350341796875,
-0.035308837890625,
-0.0224456787109375,
0.004131317138671875,
-0.01421356201171875,
0.01580810546875,
-0.06915283203125,
0.0760498046875,
-0.0283966064453125,
0.05096435546875,
-0.0296783447265625,
-0.0736083984375,
0.0081634521484375,
0.0008654594421386719,
-0.0048065185546875,
0.0199737548828125,
0.03570556640625,
0.06817626953125,
-0.0304412841796875,
0.06793212890625,
-0.020599365234375,
0.01126861572265625,
0.03668212890625,
-0.0194854736328125,
0.020172119140625,
-0.01163482666015625,
0.01262664794921875,
0.01727294921875,
-0.0058441162109375,
-0.0268707275390625,
-0.029937744140625,
0.014739990234375,
-0.07269287109375,
-0.0030841827392578125,
-0.0246124267578125,
-0.029571533203125,
0.0110015869140625,
0.034210205078125,
0.012359619140625,
0.031463623046875,
-0.0390625,
0.027618408203125,
0.0234375,
-0.0009007453918457031,
0.033447265625,
0.02587890625,
-0.03271484375,
-0.029266357421875,
0.0382080078125,
-0.0162353515625,
-0.0051727294921875,
0.0308990478515625,
-0.005733489990234375,
-0.03387451171875,
-0.059326171875,
-0.0141448974609375,
0.0258636474609375,
-0.049835205078125,
-0.0040283203125,
-0.012176513671875,
-0.0413818359375,
-0.045440673828125,
-0.018768310546875,
-0.0209503173828125,
-0.04254150390625,
-0.0467529296875,
-0.03753662109375,
0.0283203125,
0.06475830078125,
-0.0180816650390625,
0.06109619140625,
-0.0712890625,
0.0196990966796875,
0.0217132568359375,
0.0205841064453125,
-0.036956787109375,
-0.037567138671875,
-0.023345947265625,
-0.006732940673828125,
-0.0198211669921875,
-0.051788330078125,
0.031829833984375,
0.0024509429931640625,
0.058380126953125,
0.0163421630859375,
-0.01812744140625,
0.031524658203125,
-0.047576904296875,
0.0791015625,
0.04913330078125,
-0.07965087890625,
0.0611572265625,
-0.0224609375,
0.01297760009765625,
0.051361083984375,
0.0275726318359375,
-0.015960693359375,
-0.0284271240234375,
-0.049224853515625,
-0.05718994140625,
0.0391845703125,
0.0233306884765625,
0.0205841064453125,
-0.020050048828125,
0.027069091796875,
0.004375457763671875,
0.020233154296875,
-0.08197021484375,
-0.01235198974609375,
-0.05499267578125,
-0.058380126953125,
-0.004611968994140625,
-0.036285400390625,
-0.004566192626953125,
-0.00841522216796875,
0.065185546875,
0.00440216064453125,
0.036163330078125,
0.004375457763671875,
-0.049346923828125,
0.01007080078125,
0.036529541015625,
0.035980224609375,
0.036712646484375,
-0.056549072265625,
-0.012847900390625,
0.00415802001953125,
-0.056396484375,
-0.004505157470703125,
0.0286407470703125,
-0.0076751708984375,
0.02020263671875,
0.0198974609375,
0.06451416015625,
0.0400390625,
-0.048583984375,
0.05157470703125,
-0.01058197021484375,
-0.01953125,
-0.054107666015625,
-0.01016998291015625,
-0.003696441650390625,
0.0183563232421875,
0.03619384765625,
0.0128936767578125,
0.00647735595703125,
-0.02044677734375,
0.03717041015625,
0.00727081298828125,
-0.038970947265625,
-0.04364013671875,
0.045654296875,
0.043426513671875,
-0.032318115234375,
0.07293701171875,
-0.01158905029296875,
-0.03582763671875,
0.0106964111328125,
0.040435791015625,
0.052093505859375,
0.00650787353515625,
0.02716064453125,
0.0258636474609375,
0.0184783935546875,
0.003826141357421875,
0.038848876953125,
0.00884246826171875,
-0.060455322265625,
-0.03839111328125,
-0.039398193359375,
-0.025726318359375,
0.0164031982421875,
-0.060546875,
0.042724609375,
-0.0210418701171875,
-0.02593994140625,
0.0011339187622070312,
-0.01739501953125,
-0.03204345703125,
0.03521728515625,
0.0298309326171875,
0.08758544921875,
-0.055999755859375,
0.07366943359375,
0.059356689453125,
-0.0316162109375,
-0.05059814453125,
-0.01812744140625,
-0.013580322265625,
-0.061065673828125,
0.07183837890625,
0.01580810546875,
0.003997802734375,
0.02288818359375,
-0.045623779296875,
-0.057373046875,
0.0697021484375,
0.02886962890625,
-0.04693603515625,
-0.03375244140625,
0.011688232421875,
0.04058837890625,
-0.0310821533203125,
0.0274658203125,
0.0258026123046875,
0.01160430908203125,
-0.008636474609375,
-0.043426513671875,
-0.00530242919921875,
-0.03857421875,
0.0023136138916015625,
0.0037784576416015625,
-0.0303497314453125,
0.060760498046875,
0.0031528472900390625,
0.005817413330078125,
0.032989501953125,
0.06927490234375,
0.037689208984375,
-0.01910400390625,
0.06427001953125,
0.061279296875,
0.01654052734375,
-0.01494598388671875,
0.060028076171875,
-0.0257720947265625,
0.04168701171875,
0.08807373046875,
-0.01258087158203125,
0.0714111328125,
0.055023193359375,
-0.002765655517578125,
0.0731201171875,
0.04901123046875,
-0.0207672119140625,
0.04217529296875,
0.024627685546875,
0.0128021240234375,
0.0024547576904296875,
0.015869140625,
-0.0158233642578125,
0.0268707275390625,
0.015380859375,
-0.03125,
-0.012939453125,
-0.003192901611328125,
-0.02716064453125,
-0.01227569580078125,
-0.0260772705078125,
0.040130615234375,
-0.01560211181640625,
-0.042388916015625,
0.0089263916015625,
-0.034393310546875,
0.053314208984375,
-0.07281494140625,
0.005519866943359375,
0.0272369384765625,
0.00799560546875,
0.0205535888671875,
-0.07196044921875,
0.0352783203125,
0.0038776397705078125,
-0.015289306640625,
-0.03277587890625,
0.0560302734375,
-0.0123138427734375,
-0.0440673828125,
0.036529541015625,
0.019439697265625,
0.0143890380859375,
0.0308990478515625,
-0.08935546875,
-0.0273895263671875,
-0.006114959716796875,
-0.0352783203125,
-0.0034351348876953125,
0.004306793212890625,
0.0080413818359375,
0.02294921875,
0.034698486328125,
0.01526641845703125,
0.0206756591796875,
0.05755615234375,
0.057220458984375,
-0.06109619140625,
-0.05010986328125,
-0.0296478271484375,
0.0628662109375,
-0.028839111328125,
-0.0484619140625,
0.03558349609375,
0.04998779296875,
0.057220458984375,
-0.056121826171875,
0.0306549072265625,
-0.0195465087890625,
0.05963134765625,
-0.049591064453125,
0.05621337890625,
-0.0231475830078125,
-0.01546478271484375,
-0.0104522705078125,
-0.0521240234375,
-0.02764892578125,
0.041748046875,
-0.0024890899658203125,
-0.007476806640625,
0.054840087890625,
0.051788330078125,
-0.0011615753173828125,
0.01016998291015625,
0.007537841796875,
0.01904296875,
-0.0016565322875976562,
0.0016956329345703125,
0.0826416015625,
-0.0254058837890625,
0.038848876953125,
-0.006313323974609375,
0.0009522438049316406,
-0.00021326541900634766,
-0.06292724609375,
-0.076904296875,
-0.040557861328125,
-0.0157623291015625,
-0.027069091796875,
0.006626129150390625,
0.0843505859375,
0.06689453125,
-0.0855712890625,
-0.0232696533203125,
-0.041351318359375,
-0.0223541259765625,
0.01018524169921875,
-0.014678955078125,
0.0202484130859375,
-0.02984619140625,
-0.041717529296875,
0.0204925537109375,
-0.0184478759765625,
0.043975830078125,
-0.006023406982421875,
0.0046234130859375,
-0.0447998046875,
0.021728515625,
0.0279693603515625,
-0.01313018798828125,
-0.028228759765625,
-0.045440673828125,
0.0137786865234375,
-0.00452423095703125,
-0.00439453125,
0.07916259765625,
-0.0254058837890625,
0.002506256103515625,
0.0187225341796875,
0.02545166015625,
0.034423828125,
-0.0034008026123046875,
0.050079345703125,
-0.09637451171875,
0.0209808349609375,
0.003299713134765625,
0.05963134765625,
0.0170745849609375,
-0.01451873779296875,
0.04437255859375,
0.0184783935546875,
-0.03399658203125,
-0.063720703125,
-0.0010538101196289062,
-0.09716796875,
-0.030853271484375,
0.046539306640625,
-0.00980377197265625,
-0.04058837890625,
0.0128936767578125,
-0.02899169921875,
0.03839111328125,
-0.027069091796875,
0.0550537109375,
0.056915283203125,
0.02801513671875,
-0.0176544189453125,
-0.01459503173828125,
0.01360321044921875,
0.0312347412109375,
-0.042633056640625,
-0.0178680419921875,
0.0302734375,
0.00981903076171875,
0.0440673828125,
0.03948974609375,
-0.01181793212890625,
0.01015472412109375,
0.002685546875,
0.039825439453125,
0.00839996337890625,
-0.0214691162109375,
-0.01549530029296875,
-0.0142822265625,
-0.0168914794921875,
-0.028289794921875
]
] |
timm/tinynet_a.in1k | 2023-04-27T21:50:19.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2010.14819",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/tinynet_a.in1k | 0 | 37,356 | timm | 2022-12-13T00:21:58 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for tinynet_a.in1k
A TinyNet image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 6.2
- GMACs: 0.3
- Activations (M): 5.4
- Image size: 192 x 192
- **Papers:**
- Model rubik's cube: Twisting resolution, depth and width for tinynets: https://arxiv.org/abs/2010.14819v2
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('tinynet_a.in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tinynet_a.in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 16, 96, 96])
# torch.Size([1, 24, 48, 48])
# torch.Size([1, 40, 24, 24])
# torch.Size([1, 112, 12, 12])
# torch.Size([1, 320, 6, 6])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'tinynet_a.in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 6, 6) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@article{han2020model,
title={Model rubik’s cube: Twisting resolution, depth and width for tinynets},
author={Han, Kai and Wang, Yunhe and Zhang, Qiulin and Zhang, Wei and Xu, Chunjing and Zhang, Tong},
journal={Advances in Neural Information Processing Systems},
volume={33},
pages={19353--19364},
year={2020}
}
```
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
| 3,930 | [
[
-0.03326416015625,
-0.03704833984375,
0.003955841064453125,
-0.00018525123596191406,
-0.0204010009765625,
-0.02862548828125,
-0.019317626953125,
-0.02728271484375,
0.019744873046875,
0.02667236328125,
-0.03131103515625,
-0.04327392578125,
-0.045623779296875,
-0.01318359375,
-0.00722503662109375,
0.074462890625,
0.007244110107421875,
-0.0019140243530273438,
-0.0192108154296875,
-0.03399658203125,
-0.005458831787109375,
-0.00518035888671875,
-0.06298828125,
-0.0343017578125,
0.0257568359375,
0.025115966796875,
0.052490234375,
0.0504150390625,
0.037139892578125,
0.0364990234375,
-0.015960693359375,
0.004810333251953125,
-0.01163482666015625,
-0.033233642578125,
0.03143310546875,
-0.05059814453125,
-0.0380859375,
0.0206146240234375,
0.049652099609375,
0.03790283203125,
0.006256103515625,
0.03955078125,
0.0083160400390625,
0.041534423828125,
-0.005794525146484375,
0.00048828125,
-0.0273284912109375,
0.0180511474609375,
-0.001789093017578125,
0.0172271728515625,
-0.0210113525390625,
-0.03424072265625,
0.01488494873046875,
-0.03680419921875,
0.034423828125,
0.007656097412109375,
0.09417724609375,
0.01025390625,
-0.00586700439453125,
-0.00543975830078125,
-0.01331329345703125,
0.055755615234375,
-0.060394287109375,
0.0078277587890625,
0.0222015380859375,
0.016448974609375,
-0.004093170166015625,
-0.0740966796875,
-0.042999267578125,
-0.014373779296875,
-0.0225372314453125,
-0.01438140869140625,
-0.0146026611328125,
-0.003757476806640625,
0.0207672119140625,
0.0223388671875,
-0.03399658203125,
0.01256561279296875,
-0.04736328125,
-0.01318359375,
0.043548583984375,
0.011444091796875,
0.0257415771484375,
-0.032135009765625,
-0.030792236328125,
-0.031341552734375,
-0.0219268798828125,
0.03265380859375,
0.022735595703125,
0.024993896484375,
-0.05316162109375,
0.035186767578125,
0.01261138916015625,
0.039154052734375,
0.0104217529296875,
-0.0288848876953125,
0.0411376953125,
0.002429962158203125,
-0.035675048828125,
-0.0148468017578125,
0.08892822265625,
0.01849365234375,
0.0050201416015625,
0.0115814208984375,
-0.00634765625,
-0.033050537109375,
-0.002162933349609375,
-0.08404541015625,
-0.0433349609375,
0.031402587890625,
-0.0521240234375,
-0.03656005859375,
0.014251708984375,
-0.044891357421875,
-0.015411376953125,
-0.0008740425109863281,
0.047210693359375,
-0.03594970703125,
-0.0265655517578125,
-0.00249481201171875,
-0.01036834716796875,
0.00885772705078125,
0.01555633544921875,
-0.03875732421875,
0.0176849365234375,
0.029449462890625,
0.08721923828125,
0.01177215576171875,
-0.03265380859375,
-0.01486968994140625,
-0.032073974609375,
-0.02215576171875,
0.03485107421875,
0.00348663330078125,
-0.00494384765625,
-0.030029296875,
0.0204315185546875,
-0.01142120361328125,
-0.054931640625,
0.00848388671875,
-0.01311492919921875,
0.018524169921875,
0.0158843994140625,
-0.01442718505859375,
-0.03533935546875,
0.0245361328125,
-0.036041259765625,
0.08404541015625,
0.0175933837890625,
-0.060577392578125,
0.0186920166015625,
-0.040802001953125,
-0.00792694091796875,
-0.021392822265625,
-0.00652313232421875,
-0.09039306640625,
-0.0008950233459472656,
0.0125885009765625,
0.0555419921875,
-0.0182647705078125,
-0.002841949462890625,
-0.04449462890625,
-0.01318359375,
0.03216552734375,
0.00527191162109375,
0.0858154296875,
0.0048065185546875,
-0.02593994140625,
0.0236663818359375,
-0.04473876953125,
0.0190582275390625,
0.040252685546875,
-0.02313232421875,
-0.005710601806640625,
-0.0428466796875,
0.01177978515625,
0.0279693603515625,
0.0084991455078125,
-0.042877197265625,
0.02801513671875,
-0.01678466796875,
0.0306243896484375,
0.052459716796875,
-0.01383209228515625,
0.030059814453125,
-0.0291900634765625,
0.0165557861328125,
0.03045654296875,
0.0198822021484375,
0.00713348388671875,
-0.051025390625,
-0.06317138671875,
-0.037261962890625,
0.0380859375,
0.0228271484375,
-0.045196533203125,
0.0301666259765625,
-0.02203369140625,
-0.056793212890625,
-0.042449951171875,
0.015899658203125,
0.034423828125,
0.032501220703125,
0.019744873046875,
-0.0291900634765625,
-0.03240966796875,
-0.0712890625,
0.00829315185546875,
-0.002933502197265625,
-0.0110321044921875,
0.032745361328125,
0.056640625,
-0.0067596435546875,
0.049072265625,
-0.03289794921875,
-0.0263519287109375,
-0.0182342529296875,
0.0167388916015625,
0.040618896484375,
0.063232421875,
0.0545654296875,
-0.0499267578125,
-0.04473876953125,
-0.0042724609375,
-0.0592041015625,
0.0236968994140625,
-0.01161956787109375,
-0.0113983154296875,
0.0196075439453125,
0.00612640380859375,
-0.05169677734375,
0.04730224609375,
0.0164794921875,
-0.034454345703125,
0.036590576171875,
-0.017608642578125,
0.01087188720703125,
-0.07598876953125,
0.0080108642578125,
0.021697998046875,
-0.0137481689453125,
-0.034515380859375,
0.0013780593872070312,
0.0079803466796875,
-0.00804901123046875,
-0.041778564453125,
0.047760009765625,
-0.0447998046875,
-0.01491546630859375,
-0.0109100341796875,
-0.00879669189453125,
-0.0004968643188476562,
0.05621337890625,
-0.011871337890625,
0.0231781005859375,
0.0621337890625,
-0.03948974609375,
0.038299560546875,
0.032623291015625,
-0.0176544189453125,
0.02532958984375,
-0.045684814453125,
0.01708984375,
0.00708770751953125,
0.004688262939453125,
-0.07452392578125,
-0.01067352294921875,
0.0254364013671875,
-0.0513916015625,
0.047576904296875,
-0.0465087890625,
-0.035980224609375,
-0.045257568359375,
-0.044525146484375,
0.02996826171875,
0.052978515625,
-0.054473876953125,
0.034515380859375,
0.0204620361328125,
0.0243682861328125,
-0.027587890625,
-0.070068359375,
-0.020965576171875,
-0.0240020751953125,
-0.05975341796875,
0.017364501953125,
0.003307342529296875,
0.00823974609375,
0.017852783203125,
-0.00353240966796875,
-0.006343841552734375,
-0.01007080078125,
0.04058837890625,
0.02691650390625,
-0.0305023193359375,
-0.01319122314453125,
-0.0264129638671875,
-0.0047607421875,
0.00249481201171875,
-0.0223388671875,
0.038238525390625,
-0.02850341796875,
-0.00493621826171875,
-0.058868408203125,
-0.01064300537109375,
0.0262908935546875,
0.01025390625,
0.0684814453125,
0.0819091796875,
-0.036773681640625,
-0.00879669189453125,
-0.0226898193359375,
-0.0259552001953125,
-0.038482666015625,
0.024078369140625,
-0.033416748046875,
-0.034088134765625,
0.063232421875,
0.0085601806640625,
-0.0031871795654296875,
0.045684814453125,
0.02325439453125,
-0.0162506103515625,
0.058013916015625,
0.051300048828125,
0.0137939453125,
0.045562744140625,
-0.0792236328125,
-0.00922393798828125,
-0.06689453125,
-0.031524658203125,
-0.0282135009765625,
-0.05169677734375,
-0.0518798828125,
-0.0306396484375,
0.036102294921875,
0.0167236328125,
-0.02325439453125,
0.03350830078125,
-0.056884765625,
0.00861358642578125,
0.051483154296875,
0.048370361328125,
-0.0259552001953125,
0.0213165283203125,
-0.0289764404296875,
-0.0012054443359375,
-0.0640869140625,
-0.0181427001953125,
0.0804443359375,
0.03173828125,
0.044586181640625,
-0.005374908447265625,
0.046478271484375,
-0.01390838623046875,
0.0206451416015625,
-0.047821044921875,
0.04901123046875,
-0.007396697998046875,
-0.03619384765625,
-0.01374053955078125,
-0.036041259765625,
-0.08001708984375,
0.012969970703125,
-0.0220184326171875,
-0.06719970703125,
0.0106658935546875,
0.01314544677734375,
-0.029876708984375,
0.06671142578125,
-0.059539794921875,
0.0755615234375,
-0.0040740966796875,
-0.03173828125,
0.00513458251953125,
-0.047515869140625,
0.028045654296875,
0.0196075439453125,
-0.010284423828125,
-0.007572174072265625,
0.00635528564453125,
0.08502197265625,
-0.0457763671875,
0.0684814453125,
-0.0286407470703125,
0.037506103515625,
0.04058837890625,
0.003326416015625,
0.0199127197265625,
-0.004047393798828125,
-0.002727508544921875,
0.030914306640625,
0.004238128662109375,
-0.037628173828125,
-0.035430908203125,
0.048797607421875,
-0.07818603515625,
-0.028564453125,
-0.025970458984375,
-0.03558349609375,
0.0144195556640625,
0.01122283935546875,
0.031036376953125,
0.042205810546875,
0.01934814453125,
0.021820068359375,
0.04052734375,
-0.028900146484375,
0.03497314453125,
-0.006465911865234375,
-0.024139404296875,
-0.0335693359375,
0.06512451171875,
0.01406097412109375,
0.00908660888671875,
0.0031414031982421875,
0.025299072265625,
-0.01383209228515625,
-0.04376220703125,
-0.03131103515625,
0.033477783203125,
-0.042022705078125,
-0.0421142578125,
-0.0421142578125,
-0.03326416015625,
-0.035369873046875,
-0.00238800048828125,
-0.043212890625,
-0.035308837890625,
-0.034210205078125,
0.0192413330078125,
0.049224853515625,
0.04644775390625,
-0.022613525390625,
0.03961181640625,
-0.044342041015625,
0.01934814453125,
0.0157318115234375,
0.03741455078125,
-0.0013980865478515625,
-0.06927490234375,
-0.0296630859375,
-0.005336761474609375,
-0.035247802734375,
-0.0487060546875,
0.0347900390625,
0.0107269287109375,
0.0303497314453125,
0.0301513671875,
-0.014862060546875,
0.055145263671875,
-0.005573272705078125,
0.0433349609375,
0.030303955078125,
-0.044403076171875,
0.051300048828125,
-0.001220703125,
0.01393890380859375,
0.000537872314453125,
0.02496337890625,
-0.0196075439453125,
-0.0007691383361816406,
-0.08087158203125,
-0.0509033203125,
0.0828857421875,
0.0142059326171875,
-0.00804901123046875,
0.032684326171875,
0.045654296875,
-0.0009870529174804688,
0.0009975433349609375,
-0.06060791015625,
-0.03582763671875,
-0.01358795166015625,
-0.0195465087890625,
0.002262115478515625,
-0.007442474365234375,
-0.01050567626953125,
-0.050689697265625,
0.056640625,
-0.00980377197265625,
0.06903076171875,
0.0129241943359375,
-0.0011053085327148438,
-0.01517486572265625,
-0.03466796875,
0.03204345703125,
0.020904541015625,
-0.0235443115234375,
0.0064544677734375,
0.0093536376953125,
-0.04376220703125,
0.0029582977294921875,
0.00665283203125,
-0.006710052490234375,
-0.0025177001953125,
0.0288543701171875,
0.06158447265625,
0.00119781494140625,
0.0064544677734375,
0.03466796875,
-0.0066070556640625,
-0.026275634765625,
-0.0134735107421875,
0.01326751708984375,
0.0019989013671875,
0.036590576171875,
0.0212249755859375,
0.0301666259765625,
-0.0090484619140625,
-0.0174560546875,
0.01629638671875,
0.042388916015625,
-0.0175933837890625,
-0.030364990234375,
0.044464111328125,
-0.0205230712890625,
-0.01824951171875,
0.0648193359375,
-0.009429931640625,
-0.033843994140625,
0.0882568359375,
0.028900146484375,
0.0648193359375,
0.003032684326171875,
0.007541656494140625,
0.061676025390625,
0.02685546875,
0.011138916015625,
0.00806427001953125,
0.0094757080078125,
-0.0552978515625,
0.01708984375,
-0.04022216796875,
0.0007128715515136719,
0.0302886962890625,
-0.03955078125,
0.0239410400390625,
-0.0614013671875,
-0.028106689453125,
0.0188140869140625,
0.03558349609375,
-0.071533203125,
0.01358795166015625,
0.005748748779296875,
0.06341552734375,
-0.055816650390625,
0.06439208984375,
0.0706787109375,
-0.037872314453125,
-0.07855224609375,
-0.013519287109375,
0.01263427734375,
-0.06689453125,
0.040496826171875,
0.033782958984375,
0.01558685302734375,
-0.0012636184692382812,
-0.066650390625,
-0.0469970703125,
0.103515625,
0.0228424072265625,
0.005847930908203125,
0.0242919921875,
-0.0021686553955078125,
0.0157470703125,
-0.034637451171875,
0.03399658203125,
0.016204833984375,
0.0239715576171875,
0.01149749755859375,
-0.055450439453125,
0.0157623291015625,
-0.0268096923828125,
0.0143585205078125,
0.0138397216796875,
-0.05853271484375,
0.07275390625,
-0.043731689453125,
-0.01277923583984375,
0.01189422607421875,
0.053070068359375,
0.0158233642578125,
0.012451171875,
0.04144287109375,
0.05755615234375,
0.036834716796875,
-0.0229949951171875,
0.06475830078125,
0.0079803466796875,
0.051300048828125,
0.046661376953125,
0.040435791015625,
0.044036865234375,
0.0305023193359375,
-0.025421142578125,
0.0301055908203125,
0.0758056640625,
-0.0260467529296875,
0.0217742919921875,
0.00701904296875,
0.01122283935546875,
-0.00391387939453125,
0.01259613037109375,
-0.0244140625,
0.02960205078125,
0.0191650390625,
-0.0302886962890625,
-0.00672149658203125,
0.01059722900390625,
-0.0025272369384765625,
-0.0267791748046875,
-0.0252227783203125,
0.037261962890625,
0.0038700103759765625,
-0.015625,
0.059661865234375,
0.01117706298828125,
0.06854248046875,
-0.0247650146484375,
0.01087188720703125,
-0.022491455078125,
0.0222320556640625,
-0.030059814453125,
-0.06158447265625,
0.018524169921875,
-0.022705078125,
-0.0014123916625976562,
0.00807952880859375,
0.0516357421875,
-0.0239410400390625,
-0.0369873046875,
0.01059722900390625,
0.022247314453125,
0.03955078125,
0.0106048583984375,
-0.09747314453125,
0.00827789306640625,
0.006999969482421875,
-0.0560302734375,
0.0281982421875,
0.0377197265625,
0.01904296875,
0.05743408203125,
0.041534423828125,
-0.004230499267578125,
0.0189971923828125,
-0.026702880859375,
0.06402587890625,
-0.042572021484375,
-0.027252197265625,
-0.056427001953125,
0.05572509765625,
-0.00885009765625,
-0.03887939453125,
0.041961669921875,
0.04229736328125,
0.06591796875,
-0.01128387451171875,
0.020965576171875,
-0.0286407470703125,
0.0009112358093261719,
-0.032196044921875,
0.058624267578125,
-0.05877685546875,
-0.0037746429443359375,
-0.00589752197265625,
-0.041015625,
-0.026611328125,
0.05426025390625,
-0.02423095703125,
0.032318115234375,
0.0386962890625,
0.07647705078125,
-0.03778076171875,
-0.0234527587890625,
0.020477294921875,
0.02239990234375,
0.0008149147033691406,
0.03326416015625,
0.028350830078125,
-0.0679931640625,
0.032196044921875,
-0.06353759765625,
-0.01163482666015625,
-0.0202484130859375,
-0.049224853515625,
-0.0792236328125,
-0.0582275390625,
-0.05316162109375,
-0.052825927734375,
-0.0284576416015625,
0.0679931640625,
0.0826416015625,
-0.05877685546875,
-0.0157318115234375,
0.01885986328125,
0.0238037109375,
-0.020904541015625,
-0.0182342529296875,
0.04974365234375,
-0.005268096923828125,
-0.052978515625,
-0.02642822265625,
-0.0011091232299804688,
0.032257080078125,
0.0028553009033203125,
-0.0202178955078125,
-0.020416259765625,
-0.0209808349609375,
0.01265716552734375,
0.0275726318359375,
-0.0474853515625,
-0.01438140869140625,
-0.026153564453125,
-0.0196990966796875,
0.033599853515625,
0.033050537109375,
-0.042388916015625,
0.0170440673828125,
0.0272064208984375,
0.0232696533203125,
0.0621337890625,
-0.034515380859375,
-0.01312255859375,
-0.06597900390625,
0.0465087890625,
-0.00789642333984375,
0.034088134765625,
0.031646728515625,
-0.03045654296875,
0.039337158203125,
0.0295257568359375,
-0.03179931640625,
-0.06396484375,
-0.01410675048828125,
-0.077392578125,
-0.014801025390625,
0.05755615234375,
-0.02777099609375,
-0.049957275390625,
0.0333251953125,
0.0038242340087890625,
0.040435791015625,
-0.00444793701171875,
0.039825439453125,
0.0099334716796875,
-0.01558685302734375,
-0.0501708984375,
-0.03558349609375,
0.03204345703125,
0.01139068603515625,
-0.04327392578125,
-0.037994384765625,
0.0018606185913085938,
0.05096435546875,
0.0293426513671875,
0.03289794921875,
-0.0059967041015625,
0.01369476318359375,
0.0164642333984375,
0.0357666015625,
-0.03369140625,
-0.0168914794921875,
-0.0311279296875,
0.00799560546875,
-0.005405426025390625,
-0.04388427734375
]
] |
timm/botnet26t_256.c1_in1k | 2023-04-26T16:09:11.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2110.00476",
"arxiv:2101.11605",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/botnet26t_256.c1_in1k | 0 | 37,334 | timm | 2023-04-26T16:08:51 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for botnet26t_256.c1_in1k
A BotNet image classification model (, based on ResNet architecture). Trained on ImageNet-1k in `timm` by Ross Wightman.
NOTE: this model did not adhere to any specific paper configuration, it was tuned for reasonable training times and reduced frequency of self-attention blocks.
Recipe details:
* Based on [ResNet Strikes Back](https://arxiv.org/abs/2110.00476) `C` recipes
* SGD (w/ Nesterov) optimizer and AGC (adaptive gradient clipping).
* Cosine LR schedule with warmup
This model architecture is implemented using `timm`'s flexible [BYOBNet (Bring-Your-Own-Blocks Network)](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/byobnet.py).
BYOB (with BYOANet attention specific blocks) allows configuration of:
* block / stage layout
* block-type interleaving
* stem layout
* output stride (dilation)
* activation and norm layers
* channel and spatial / self-attention layers
...and also includes `timm` features common to many other architectures, including:
* stochastic depth
* gradient checkpointing
* layer-wise LR decay
* per-stage feature extraction
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 12.5
- GMACs: 3.3
- Activations (M): 12.0
- Image size: 256 x 256
- **Papers:**
- Bottleneck Transformers for Visual Recognition: https://arxiv.org/abs/2101.11605
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- **Dataset:** ImageNet-1k
## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('botnet26t_256.c1_in1k', pretrained=True)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```
### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'botnet26t_256.c1_in1k',
pretrained=True,
features_only=True,
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
for o in output:
# print shape of each feature map in output
# e.g.:
# torch.Size([1, 64, 128, 128])
# torch.Size([1, 256, 64, 64])
# torch.Size([1, 512, 32, 32])
# torch.Size([1, 1024, 16, 16])
# torch.Size([1, 2048, 8, 8])
print(o.shape)
```
### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'botnet26t_256.c1_in1k',
pretrained=True,
num_classes=0, # remove classifier nn.Linear
)
model = model.eval()
# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
# or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 2048, 8, 8) shaped tensor
output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```
## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
## Citation
```bibtex
@misc{rw2019timm,
author = {Ross Wightman},
title = {PyTorch Image Models},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
doi = {10.5281/zenodo.4414861},
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@article{Srinivas2021BottleneckTF,
title={Bottleneck Transformers for Visual Recognition},
author={A. Srinivas and Tsung-Yi Lin and Niki Parmar and Jonathon Shlens and P. Abbeel and Ashish Vaswani},
journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2021},
pages={16514-16524}
}
```
```bibtex
@inproceedings{wightman2021resnet,
title={ResNet strikes back: An improved training procedure in timm},
author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
```
| 5,328 | [
[
-0.034820556640625,
-0.036468505859375,
-0.0031299591064453125,
0.0038394927978515625,
-0.01861572265625,
-0.01873779296875,
-0.0182647705078125,
-0.027069091796875,
0.016754150390625,
0.040130615234375,
-0.0374755859375,
-0.0469970703125,
-0.050750732421875,
-0.0046234130859375,
-0.011810302734375,
0.06787109375,
-0.00209808349609375,
-0.002681732177734375,
-0.0093231201171875,
-0.037750244140625,
-0.025909423828125,
-0.0274658203125,
-0.07379150390625,
-0.028228759765625,
0.032196044921875,
0.0133514404296875,
0.035675048828125,
0.0509033203125,
0.0552978515625,
0.037261962890625,
-0.003864288330078125,
0.00826263427734375,
-0.017974853515625,
-0.0142669677734375,
0.0180816650390625,
-0.04736328125,
-0.03363037109375,
0.0206298828125,
0.04571533203125,
0.018829345703125,
0.0027256011962890625,
0.032867431640625,
0.0019378662109375,
0.04608154296875,
-0.016571044921875,
0.003795623779296875,
-0.03948974609375,
0.017059326171875,
-0.0171051025390625,
-0.0008401870727539062,
-0.031219482421875,
-0.0180206298828125,
0.0153045654296875,
-0.031494140625,
0.040283203125,
0.010528564453125,
0.10028076171875,
0.0201416015625,
0.004413604736328125,
0.004852294921875,
-0.0168609619140625,
0.059814453125,
-0.056304931640625,
0.0220947265625,
0.01605224609375,
0.0223388671875,
-0.009857177734375,
-0.073974609375,
-0.04254150390625,
-0.015594482421875,
-0.0062713623046875,
0.005474090576171875,
-0.021087646484375,
0.00043582916259765625,
0.0258026123046875,
0.01715087890625,
-0.036376953125,
0.007354736328125,
-0.04595947265625,
-0.0161285400390625,
0.03912353515625,
0.0011453628540039062,
0.023193359375,
-0.023468017578125,
-0.043426513671875,
-0.029632568359375,
-0.024627685546875,
0.0192413330078125,
0.0223846435546875,
0.0181427001953125,
-0.04486083984375,
0.0247955322265625,
0.0128021240234375,
0.043212890625,
0.0008111000061035156,
-0.019805908203125,
0.042022705078125,
0.004299163818359375,
-0.031402587890625,
-0.018951416015625,
0.0838623046875,
0.0253143310546875,
0.0265350341796875,
0.008209228515625,
-0.0172882080078125,
-0.027618408203125,
0.01107025146484375,
-0.0772705078125,
-0.032501220703125,
0.0244140625,
-0.05157470703125,
-0.03143310546875,
0.018402099609375,
-0.047760009765625,
-0.01409912109375,
0.0014696121215820312,
0.041015625,
-0.047027587890625,
-0.0252838134765625,
-0.00006288290023803711,
-0.021636962890625,
0.0217437744140625,
0.02215576171875,
-0.031768798828125,
0.0162200927734375,
0.02215576171875,
0.0902099609375,
-0.0011396408081054688,
-0.031005859375,
-0.017333984375,
-0.0285797119140625,
-0.0179443359375,
0.03778076171875,
-0.000675201416015625,
-0.001605987548828125,
-0.02655029296875,
0.025360107421875,
-0.0104522705078125,
-0.057159423828125,
0.003818511962890625,
-0.0242919921875,
0.019378662109375,
0.006134033203125,
-0.0157470703125,
-0.0430908203125,
0.028533935546875,
-0.040374755859375,
0.08465576171875,
0.023468017578125,
-0.06439208984375,
0.0190887451171875,
-0.047393798828125,
-0.01265716552734375,
-0.01444244384765625,
-0.00382232666015625,
-0.08380126953125,
-0.006465911865234375,
0.01232147216796875,
0.05413818359375,
-0.025726318359375,
-0.0007882118225097656,
-0.041107177734375,
-0.0184173583984375,
0.034210205078125,
-0.011993408203125,
0.0819091796875,
0.01326751708984375,
-0.0304412841796875,
0.0207672119140625,
-0.044097900390625,
0.007476806640625,
0.048980712890625,
-0.0142669677734375,
0.004550933837890625,
-0.042144775390625,
0.0110931396484375,
0.0220489501953125,
0.0106201171875,
-0.042327880859375,
0.016387939453125,
-0.0164642333984375,
0.04034423828125,
0.055023193359375,
-0.00847625732421875,
0.01690673828125,
-0.034912109375,
0.0264129638671875,
0.02349853515625,
0.0248565673828125,
-0.00899505615234375,
-0.042572021484375,
-0.06390380859375,
-0.044708251953125,
0.031280517578125,
0.033416748046875,
-0.04034423828125,
0.034942626953125,
-0.0133819580078125,
-0.0509033203125,
-0.039642333984375,
0.00830841064453125,
0.040863037109375,
0.043548583984375,
0.02716064453125,
-0.0455322265625,
-0.041473388671875,
-0.0706787109375,
0.004058837890625,
0.003665924072265625,
0.005352020263671875,
0.026336669921875,
0.050933837890625,
-0.0043792724609375,
0.0545654296875,
-0.0278167724609375,
-0.0248260498046875,
-0.024139404296875,
0.0079193115234375,
0.03216552734375,
0.060546875,
0.059600830078125,
-0.047576904296875,
-0.040679931640625,
-0.00891876220703125,
-0.06414794921875,
0.0140228271484375,
-0.01032257080078125,
-0.00966644287109375,
0.0283355712890625,
0.01102447509765625,
-0.039947509765625,
0.050445556640625,
0.01222991943359375,
-0.00848388671875,
0.0308685302734375,
-0.0169830322265625,
0.0163116455078125,
-0.0853271484375,
0.00841522216796875,
0.027069091796875,
-0.019989013671875,
-0.03131103515625,
0.006134033203125,
0.0035839080810546875,
-0.00838470458984375,
-0.038665771484375,
0.051177978515625,
-0.040130615234375,
-0.0136871337890625,
-0.0121002197265625,
-0.0137176513671875,
-0.0035724639892578125,
0.06439208984375,
-0.00449371337890625,
0.03656005859375,
0.061004638671875,
-0.032318115234375,
0.041015625,
0.020172119140625,
-0.00984954833984375,
0.031982421875,
-0.052337646484375,
0.02001953125,
0.0011167526245117188,
0.01450347900390625,
-0.0845947265625,
-0.016876220703125,
0.038482666015625,
-0.052978515625,
0.0513916015625,
-0.040130615234375,
-0.035125732421875,
-0.04791259765625,
-0.035797119140625,
0.0301361083984375,
0.057952880859375,
-0.05438232421875,
0.036285400390625,
0.016571044921875,
0.029632568359375,
-0.040191650390625,
-0.060333251953125,
-0.01189422607421875,
-0.032501220703125,
-0.047393798828125,
0.01861572265625,
0.01171112060546875,
0.0115814208984375,
0.005931854248046875,
-0.00907135009765625,
-0.006351470947265625,
-0.006931304931640625,
0.04534912109375,
0.0284881591796875,
-0.018096923828125,
-0.006832122802734375,
-0.0357666015625,
-0.003482818603515625,
-0.001068115234375,
-0.0237274169921875,
0.053802490234375,
-0.0196380615234375,
-0.01233673095703125,
-0.070068359375,
-0.005298614501953125,
0.035369873046875,
-0.01432037353515625,
0.056976318359375,
0.0799560546875,
-0.03900146484375,
-0.002716064453125,
-0.040008544921875,
-0.0226287841796875,
-0.03790283203125,
0.036285400390625,
-0.0274200439453125,
-0.0301361083984375,
0.06536865234375,
-0.0013151168823242188,
-0.00264739990234375,
0.0484619140625,
0.027740478515625,
-0.013427734375,
0.049285888671875,
0.04669189453125,
0.0081634521484375,
0.061187744140625,
-0.07098388671875,
-0.0166015625,
-0.06549072265625,
-0.03314208984375,
-0.0218048095703125,
-0.04888916015625,
-0.052276611328125,
-0.027862548828125,
0.033233642578125,
0.0050506591796875,
-0.0318603515625,
0.04327392578125,
-0.0638427734375,
0.002048492431640625,
0.058746337890625,
0.050201416015625,
-0.0301361083984375,
0.0223388671875,
-0.01239776611328125,
0.00040984153747558594,
-0.063720703125,
-0.01708984375,
0.08575439453125,
0.037353515625,
0.04736328125,
-0.01503753662109375,
0.057220458984375,
-0.004238128662109375,
0.0303955078125,
-0.042083740234375,
0.049652099609375,
-0.0106353759765625,
-0.040313720703125,
-0.01377105712890625,
-0.03363037109375,
-0.08453369140625,
-0.002346038818359375,
-0.0180816650390625,
-0.0611572265625,
0.0030670166015625,
0.0137176513671875,
-0.017791748046875,
0.059906005859375,
-0.06329345703125,
0.070556640625,
-0.0118255615234375,
-0.0299530029296875,
-0.0036144256591796875,
-0.05926513671875,
0.01947021484375,
0.01345062255859375,
-0.020538330078125,
-0.007354736328125,
0.01390838623046875,
0.08074951171875,
-0.045166015625,
0.06988525390625,
-0.0285491943359375,
0.029632568359375,
0.038818359375,
-0.01104736328125,
0.0211334228515625,
-0.01233673095703125,
-0.002803802490234375,
0.036041259765625,
-0.0037384033203125,
-0.036956787109375,
-0.04248046875,
0.0357666015625,
-0.07403564453125,
-0.034820556640625,
-0.0283966064453125,
-0.03875732421875,
0.0206451416015625,
0.01093292236328125,
0.0384521484375,
0.05084228515625,
0.0235137939453125,
0.01464080810546875,
0.042999267578125,
-0.0379638671875,
0.031402587890625,
-0.0036258697509765625,
-0.01090240478515625,
-0.0430908203125,
0.07000732421875,
0.020355224609375,
0.01457977294921875,
0.01910400390625,
0.013427734375,
-0.0174102783203125,
-0.037017822265625,
-0.0204620361328125,
0.028900146484375,
-0.049285888671875,
-0.043304443359375,
-0.03887939453125,
-0.044921875,
-0.0343017578125,
-0.0022411346435546875,
-0.03814697265625,
-0.0210113525390625,
-0.0220794677734375,
0.027313232421875,
0.059234619140625,
0.04290771484375,
-0.00670623779296875,
0.04852294921875,
-0.03900146484375,
0.015350341796875,
0.004192352294921875,
0.03900146484375,
-0.002880096435546875,
-0.06964111328125,
-0.0185089111328125,
-0.0115966796875,
-0.036956787109375,
-0.05975341796875,
0.036041259765625,
0.006145477294921875,
0.03729248046875,
0.02471923828125,
-0.01502227783203125,
0.05413818359375,
-0.0090484619140625,
0.035675048828125,
0.0323486328125,
-0.043060302734375,
0.0469970703125,
0.00009894371032714844,
0.01214599609375,
0.0014028549194335938,
0.0223236083984375,
-0.0218353271484375,
-0.00818634033203125,
-0.0772705078125,
-0.046905517578125,
0.0706787109375,
0.007175445556640625,
-0.00701904296875,
0.022247314453125,
0.053070068359375,
0.0032787322998046875,
0.004528045654296875,
-0.05780029296875,
-0.031402587890625,
-0.0218963623046875,
-0.0216827392578125,
0.006130218505859375,
0.00211334228515625,
-0.003932952880859375,
-0.046844482421875,
0.04522705078125,
0.002376556396484375,
0.06298828125,
0.0253753662109375,
-0.00251007080078125,
-0.001728057861328125,
-0.035186767578125,
0.031341552734375,
0.01702880859375,
-0.026458740234375,
0.00902557373046875,
0.0192413330078125,
-0.04266357421875,
0.0023365020751953125,
0.005069732666015625,
0.001033782958984375,
-0.002635955810546875,
0.0391845703125,
0.0653076171875,
-0.009429931640625,
-0.004467010498046875,
0.032257080078125,
0.0002510547637939453,
-0.024261474609375,
-0.0196533203125,
0.01678466796875,
-0.01511383056640625,
0.039306640625,
0.0182342529296875,
0.03466796875,
-0.0161895751953125,
-0.0200958251953125,
0.0233154296875,
0.04449462890625,
-0.0198974609375,
-0.0251617431640625,
0.052520751953125,
-0.01702880859375,
-0.0288543701171875,
0.0675048828125,
-0.0061798095703125,
-0.04327392578125,
0.0845947265625,
0.033538818359375,
0.0748291015625,
-0.00196075439453125,
-0.00107574462890625,
0.055816650390625,
0.02294921875,
0.0080108642578125,
0.015350341796875,
0.01058197021484375,
-0.055023193359375,
0.00943756103515625,
-0.0313720703125,
0.0029506683349609375,
0.0293121337890625,
-0.03375244140625,
0.0269012451171875,
-0.06494140625,
-0.040283203125,
0.00823211669921875,
0.0226287841796875,
-0.0789794921875,
0.0200653076171875,
-0.0034999847412109375,
0.06640625,
-0.04608154296875,
0.057159423828125,
0.06365966796875,
-0.04638671875,
-0.06646728515625,
-0.004367828369140625,
0.0017976760864257812,
-0.08172607421875,
0.04608154296875,
0.0352783203125,
0.0095367431640625,
0.007694244384765625,
-0.06915283203125,
-0.044830322265625,
0.1031494140625,
0.036407470703125,
-0.0078277587890625,
0.02252197265625,
-0.00856781005859375,
0.017791748046875,
-0.0287017822265625,
0.034088134765625,
0.00786590576171875,
0.0214080810546875,
0.018341064453125,
-0.05072021484375,
0.0214080810546875,
-0.0205078125,
0.00890350341796875,
0.00966644287109375,
-0.06982421875,
0.06707763671875,
-0.036865234375,
-0.01458740234375,
0.00742340087890625,
0.051727294921875,
0.0164642333984375,
0.012115478515625,
0.038360595703125,
0.058197021484375,
0.0372314453125,
-0.0198822021484375,
0.0675048828125,
-0.007450103759765625,
0.0421142578125,
0.047821044921875,
0.0301666259765625,
0.041961669921875,
0.0272369384765625,
-0.0225982666015625,
0.0223846435546875,
0.0814208984375,
-0.0338134765625,
0.023345947265625,
0.0227813720703125,
0.01306915283203125,
-0.0115966796875,
0.00537872314453125,
-0.028076171875,
0.035888671875,
0.0095062255859375,
-0.03668212890625,
-0.01110076904296875,
0.0082550048828125,
-0.0057220458984375,
-0.0219268798828125,
-0.01026153564453125,
0.03631591796875,
-0.00014281272888183594,
-0.02545166015625,
0.0631103515625,
0.00775146484375,
0.06317138671875,
-0.0283203125,
0.0026493072509765625,
-0.022674560546875,
0.0150299072265625,
-0.018585205078125,
-0.062744140625,
0.0163421630859375,
-0.0178375244140625,
-0.00177001953125,
-0.0001785755157470703,
0.052825927734375,
-0.0162506103515625,
-0.0299224853515625,
0.01450347900390625,
0.0222625732421875,
0.0455322265625,
0.001392364501953125,
-0.0914306640625,
0.017303466796875,
-0.0026416778564453125,
-0.04071044921875,
0.0183868408203125,
0.037322998046875,
0.004299163818359375,
0.064697265625,
0.039581298828125,
-0.0035495758056640625,
0.0121002197265625,
-0.013641357421875,
0.060333251953125,
-0.042724609375,
-0.01538848876953125,
-0.0631103515625,
0.041900634765625,
-0.01220703125,
-0.04071044921875,
0.03955078125,
0.04144287109375,
0.06976318359375,
-0.00817108154296875,
0.033538818359375,
-0.0195465087890625,
-0.0017528533935546875,
-0.028167724609375,
0.05255126953125,
-0.060089111328125,
-0.0022335052490234375,
-0.0133819580078125,
-0.04571533203125,
-0.0275115966796875,
0.05340576171875,
-0.018951416015625,
0.0341796875,
0.034423828125,
0.0740966796875,
-0.024871826171875,
-0.036102294921875,
0.0160980224609375,
0.0092620849609375,
0.0070648193359375,
0.036865234375,
0.034088134765625,
-0.0594482421875,
0.0259246826171875,
-0.041961669921875,
-0.01377105712890625,
-0.01544189453125,
-0.0455322265625,
-0.08306884765625,
-0.06817626953125,
-0.048004150390625,
-0.049530029296875,
-0.00746917724609375,
0.07171630859375,
0.08355712890625,
-0.051605224609375,
-0.01241302490234375,
0.0021648406982421875,
0.017303466796875,
-0.023284912109375,
-0.0174407958984375,
0.0416259765625,
-0.021270751953125,
-0.055206298828125,
-0.028167724609375,
0.01158905029296875,
0.0300445556640625,
-0.002773284912109375,
-0.01432037353515625,
-0.0178985595703125,
-0.01739501953125,
0.0100860595703125,
0.0273284912109375,
-0.055999755859375,
-0.01995849609375,
-0.0115966796875,
-0.01209259033203125,
0.0374755859375,
0.0347900390625,
-0.043670654296875,
0.0244293212890625,
0.0289764404296875,
0.032928466796875,
0.05609130859375,
-0.0228271484375,
0.004512786865234375,
-0.06744384765625,
0.0408935546875,
-0.0142669677734375,
0.03521728515625,
0.029510498046875,
-0.0254974365234375,
0.045074462890625,
0.044097900390625,
-0.0290985107421875,
-0.06451416015625,
-0.0025691986083984375,
-0.08795166015625,
-0.01253509521484375,
0.060455322265625,
-0.0255126953125,
-0.044769287109375,
0.0316162109375,
-0.00804901123046875,
0.0562744140625,
-0.00910186767578125,
0.04449462890625,
0.0185699462890625,
-0.007175445556640625,
-0.05499267578125,
-0.040924072265625,
0.0269775390625,
0.01293182373046875,
-0.042938232421875,
-0.0307159423828125,
-0.004817962646484375,
0.0506591796875,
0.02215576171875,
0.0367431640625,
-0.009429931640625,
0.0097198486328125,
0.005855560302734375,
0.042022705078125,
-0.030975341796875,
-0.0206451416015625,
-0.0217742919921875,
0.0014362335205078125,
-0.0113677978515625,
-0.055816650390625
]
] |
hassanblend/HassanBlend1.5.1.2 | 2023-07-01T22:25:00.000Z | [
"diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | hassanblend | null | null | hassanblend/HassanBlend1.5.1.2 | 211 | 37,320 | diffusers | 2023-01-05T23:57:46 | ---
title: Hassanblend1.5.1.2
emoji: 📚
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: 3.11.0
app_file: app.py
pinned: false
thumbnail: https://i.imgur.com/PVThZvk.png
license: creativeml-openrail-m
tags:
- text-to-image
inference: true
---
# HassanBlend1.5
I am hassan, I created HassansBlend, the latest version currently is 1.5.1.2 I continue to iterate and improve on this model over time. Feel free to check out our discord or rentry page for more examples with prompts and outputs generated.
This blend is finetuned over SD1.5 with thousands of images included in the dataset it was trained with. Along with that there are some minor merges added in just to soften it up and increase the creativity.
I have also some custom created content such as enhancement hypernetworks/embeddings etc for patreons or KoFi subscribers only on my pages below
<b> Links </b><br>
<b>Patreon</b>
<a href="https://www.patreon.com/sd_hassan" target="_blank"><img src="https://i.imgur.com/sR32SqJ.jpg"></img></a>
<b>KoFi</b>
<a href="https://ko-fi.com/sdhassan" target="_blank"><img src="https://i.imgur.com/0P7CTN4.png"></img></a>
<b>Discord</b>
<a href="https://discord.gg/sdmodelers" target="_blank"><img src="https://i.imgur.com/HC1iHwg.png"></img></a>
### Quicklinks:
* [Latest Setup](https://rentry.org/sdhassan#current-setup)
* [HassanBlend Model Finetune Updates](https://rentry.org/sdhassan#hassanblend-finetuning-updates)
* [Latest Patreon Posts](https://rentry.org/sdhassan#patreon-posts)
* [Models](https://rentry.org/sdhassan#models)
* [HassanBlend1.5](https://rentry.org/sdhassan#hassanblend15-downloads)
* [HassanBlend1.4](https://rentry.org/sdhassan#hassanblend14-downloads)
* [Prompts](https://rentry.org/sdhassan#prompts)
* [Photorealistic Tips](https://rentry.org/sdhassan#tips-for-photorealistic-images)
* [Embeddings](https://rentry.org/sdhassan#embeddings)
* [Hypernetworks](https://rentry.org/sdhassan#hypernetworks)
* [Wildcards](https://rentry.org/sdhassan#wildcards-i-made)
* [MyTools](https://rentry.org/sdhassan#my-tools)
* [Settings I use](https://rentry.org/sdhassan#settings)
Model details and examples with sample prompts: https://rentry.org/sdhassan | 2,190 | [
[
-0.052398681640625,
-0.037994384765625,
0.03582763671875,
0.02117919921875,
-0.032257080078125,
-0.00516510009765625,
0.010101318359375,
-0.01995849609375,
0.043487548828125,
0.053863525390625,
-0.07568359375,
-0.05938720703125,
-0.036224365234375,
0.0007576942443847656,
-0.01340484619140625,
0.06195068359375,
0.00640106201171875,
-0.009613037109375,
-0.006351470947265625,
-0.01947021484375,
-0.03643798828125,
-0.007511138916015625,
-0.055755615234375,
-0.0220489501953125,
0.051300048828125,
0.0239715576171875,
0.075439453125,
0.051025390625,
0.03143310546875,
0.0236053466796875,
-0.0029144287109375,
0.002819061279296875,
-0.051605224609375,
0.0015783309936523438,
-0.01519012451171875,
0.01132965087890625,
-0.034271240234375,
-0.0030269622802734375,
0.0389404296875,
0.0208282470703125,
-0.00704193115234375,
0.029510498046875,
-0.020172119140625,
0.07470703125,
-0.041290283203125,
0.002574920654296875,
-0.007518768310546875,
0.00714111328125,
-0.007595062255859375,
-0.0048065185546875,
0.006496429443359375,
-0.03472900390625,
-0.0028476715087890625,
-0.065673828125,
0.0115203857421875,
0.017486572265625,
0.07196044921875,
0.0164337158203125,
-0.03607177734375,
0.004611968994140625,
-0.048614501953125,
0.06048583984375,
-0.054962158203125,
0.044525146484375,
0.0269622802734375,
0.053924560546875,
-0.0193023681640625,
-0.0682373046875,
-0.035125732421875,
0.0012674331665039062,
0.01239013671875,
0.0311279296875,
-0.03521728515625,
0.002124786376953125,
0.03778076171875,
0.0460205078125,
-0.045257568359375,
-0.0229644775390625,
-0.040802001953125,
-0.0008001327514648438,
0.056549072265625,
0.01049041748046875,
0.01145172119140625,
-0.01183319091796875,
-0.031768798828125,
-0.0238494873046875,
-0.037933349609375,
0.0201416015625,
0.06500244140625,
-0.0013341903686523438,
-0.04437255859375,
0.055145263671875,
-0.0216522216796875,
0.05670166015625,
0.01178741455078125,
-0.00852203369140625,
0.0146484375,
-0.0206451416015625,
-0.01470184326171875,
-0.0125579833984375,
0.05377197265625,
0.04248046875,
0.009979248046875,
0.0256195068359375,
-0.0187835693359375,
-0.0094146728515625,
0.0253448486328125,
-0.0740966796875,
-0.0450439453125,
0.033966064453125,
-0.06573486328125,
-0.04217529296875,
0.003662109375,
-0.04425048828125,
-0.034454345703125,
-0.0164337158203125,
0.0303497314453125,
-0.0275726318359375,
-0.0286712646484375,
0.01541900634765625,
-0.0176239013671875,
0.01119232177734375,
0.036651611328125,
-0.02752685546875,
0.031768798828125,
0.01438140869140625,
0.049713134765625,
0.0222320556640625,
0.0159149169921875,
-0.01236724853515625,
-0.0038204193115234375,
-0.03582763671875,
0.055328369140625,
-0.0215911865234375,
-0.04571533203125,
0.01195526123046875,
0.0216217041015625,
0.0182342529296875,
-0.039276123046875,
0.047393798828125,
-0.04833984375,
-0.019775390625,
-0.031707763671875,
-0.04595947265625,
-0.02947998046875,
0.004291534423828125,
-0.06732177734375,
0.060760498046875,
0.0214385986328125,
-0.04681396484375,
-0.00732421875,
-0.057220458984375,
0.003650665283203125,
0.00936126708984375,
0.00020253658294677734,
-0.037628173828125,
0.00494384765625,
-0.004673004150390625,
0.0215606689453125,
-0.003292083740234375,
-0.005767822265625,
-0.04864501953125,
-0.03387451171875,
0.02252197265625,
-0.01666259765625,
0.062347412109375,
0.0309295654296875,
-0.00447845458984375,
0.00408935546875,
-0.081787109375,
0.0144805908203125,
0.03350830078125,
-0.0039215087890625,
0.0169219970703125,
-0.01366424560546875,
0.03753662109375,
0.034454345703125,
0.006397247314453125,
-0.043304443359375,
0.01366424560546875,
-0.005680084228515625,
-0.005420684814453125,
0.059295654296875,
0.0281524658203125,
0.01201629638671875,
-0.061126708984375,
0.06610107421875,
0.01003265380859375,
0.01021575927734375,
-0.01336669921875,
-0.037139892578125,
-0.041900634765625,
-0.032318115234375,
0.0088348388671875,
0.014801025390625,
-0.042877197265625,
0.0193023681640625,
-0.004207611083984375,
-0.045318603515625,
-0.040924072265625,
0.007190704345703125,
0.032012939453125,
0.01514434814453125,
0.020904541015625,
-0.0328369140625,
-0.04046630859375,
-0.09326171875,
0.008544921875,
0.00789642333984375,
0.007610321044921875,
0.03607177734375,
0.032318115234375,
-0.01885986328125,
0.052490234375,
-0.046234130859375,
0.005237579345703125,
-0.00482177734375,
-0.006580352783203125,
0.034515380859375,
0.061859130859375,
0.053924560546875,
-0.08074951171875,
-0.03631591796875,
-0.00746917724609375,
-0.037139892578125,
0.0124664306640625,
0.0008435249328613281,
-0.0264434814453125,
-0.013763427734375,
0.01971435546875,
-0.04730224609375,
0.04168701171875,
0.035552978515625,
-0.0302734375,
0.06451416015625,
0.00762939453125,
0.0225677490234375,
-0.099365234375,
0.0016956329345703125,
0.03057861328125,
-0.03759765625,
-0.026397705078125,
0.012359619140625,
-0.0313720703125,
-0.0251312255859375,
-0.0504150390625,
0.056549072265625,
-0.0177764892578125,
-0.0029506683349609375,
-0.0050201416015625,
-0.02484130859375,
0.0032806396484375,
0.04541015625,
-0.02154541015625,
0.0384521484375,
0.0491943359375,
-0.0350341796875,
0.050628662109375,
0.032012939453125,
-0.027862548828125,
0.038360595703125,
-0.08489990234375,
0.0226287841796875,
-0.02508544921875,
0.035369873046875,
-0.09161376953125,
-0.03900146484375,
0.052978515625,
-0.0311737060546875,
0.0209503173828125,
-0.03399658203125,
-0.0408935546875,
-0.0322265625,
-0.0297088623046875,
0.046417236328125,
0.059112548828125,
-0.037322998046875,
0.024322509765625,
0.01192474365234375,
-0.0025005340576171875,
-0.0251312255859375,
-0.0171966552734375,
-0.0087738037109375,
-0.0010814666748046875,
-0.050018310546875,
0.04046630859375,
-0.0203094482421875,
-0.02154541015625,
0.0302886962890625,
-0.0138092041015625,
-0.0189971923828125,
-0.02099609375,
0.04541015625,
0.020050048828125,
-0.01812744140625,
-0.01568603515625,
0.00580596923828125,
0.0100250244140625,
-0.00487518310546875,
-0.0321044921875,
0.034637451171875,
-0.0261993408203125,
-0.0367431640625,
-0.076904296875,
0.0258026123046875,
0.046051025390625,
-0.0014314651489257812,
0.041473388671875,
0.061370849609375,
-0.025909423828125,
-0.00504302978515625,
-0.043365478515625,
-0.0071258544921875,
-0.03948974609375,
0.0105743408203125,
-0.02008056640625,
-0.061370849609375,
0.05426025390625,
-0.020599365234375,
0.01552581787109375,
0.04779052734375,
0.026336669921875,
-0.034454345703125,
0.09808349609375,
0.038818359375,
0.01751708984375,
0.041748046875,
-0.06689453125,
0.0028285980224609375,
-0.052490234375,
-0.0261993408203125,
-0.0231475830078125,
-0.038970947265625,
-0.06732177734375,
-0.02886962890625,
0.021636962890625,
0.0005960464477539062,
-0.0286865234375,
0.038330078125,
-0.0229339599609375,
0.036865234375,
0.025146484375,
0.033935546875,
0.0034236907958984375,
0.0022335052490234375,
-0.005260467529296875,
-0.0037097930908203125,
-0.059600830078125,
-0.0260467529296875,
0.056396484375,
0.02008056640625,
0.0592041015625,
0.0117645263671875,
0.058349609375,
0.039398193359375,
-0.00859832763671875,
-0.05712890625,
0.043243408203125,
0.000705718994140625,
-0.05169677734375,
0.01171112060546875,
-0.0170745849609375,
-0.05120849609375,
0.0058135986328125,
-0.03778076171875,
-0.034271240234375,
0.0281219482421875,
0.0272216796875,
-0.03350830078125,
0.0239715576171875,
-0.0231781005859375,
0.0662841796875,
0.0102996826171875,
-0.03753662109375,
-0.0171661376953125,
-0.0555419921875,
0.028900146484375,
0.0117034912109375,
0.016998291015625,
-0.025604248046875,
0.0189971923828125,
0.044158935546875,
-0.049591064453125,
0.063720703125,
-0.00384521484375,
0.004123687744140625,
0.042694091796875,
0.00356292724609375,
0.0286102294921875,
0.004047393798828125,
0.0027179718017578125,
0.0013637542724609375,
0.009063720703125,
-0.059112548828125,
-0.04034423828125,
0.06353759765625,
-0.061370849609375,
-0.0186614990234375,
-0.02130126953125,
-0.040679931640625,
-0.004779815673828125,
0.01435089111328125,
0.031280517578125,
0.07708740234375,
-0.01216888427734375,
0.0218505859375,
0.056427001953125,
-0.01885986328125,
0.019012451171875,
-0.016632080078125,
-0.031982421875,
-0.039794921875,
0.077880859375,
-0.01415252685546875,
0.0130462646484375,
-0.0166778564453125,
0.0087432861328125,
-0.0277557373046875,
-0.0253143310546875,
-0.044891357421875,
0.021453857421875,
-0.049591064453125,
-0.0160064697265625,
-0.033416748046875,
-0.028961181640625,
-0.03802490234375,
-0.032470703125,
-0.041351318359375,
-0.046844482421875,
-0.024444580078125,
0.0036334991455078125,
0.0384521484375,
0.07073974609375,
0.0017747879028320312,
0.0290679931640625,
-0.05023193359375,
0.0269317626953125,
0.0152435302734375,
0.0191497802734375,
-0.0010662078857421875,
-0.03875732421875,
-0.018829345703125,
0.00972747802734375,
-0.0306396484375,
-0.05682373046875,
0.028961181640625,
0.004886627197265625,
0.03411865234375,
0.02752685546875,
-0.0007824897766113281,
0.05078125,
-0.024139404296875,
0.056793212890625,
0.0290069580078125,
-0.0347900390625,
0.042144775390625,
-0.069091796875,
0.041748046875,
0.05078125,
0.052276611328125,
-0.03778076171875,
-0.0196990966796875,
-0.06719970703125,
-0.0509033203125,
0.0286102294921875,
0.0269317626953125,
0.0208740234375,
0.00946044921875,
0.0264434814453125,
-0.00768280029296875,
0.0199432373046875,
-0.039794921875,
-0.0389404296875,
-0.031280517578125,
-0.0160369873046875,
0.01470184326171875,
-0.0154876708984375,
-0.015777587890625,
-0.048797607421875,
0.08489990234375,
-0.0011730194091796875,
0.0255126953125,
0.0172271728515625,
0.0287017822265625,
-0.022857666015625,
-0.01230621337890625,
0.03753662109375,
0.06353759765625,
-0.02410888671875,
-0.010589599609375,
-0.0282135009765625,
-0.016998291015625,
0.0016574859619140625,
0.00048065185546875,
-0.0091705322265625,
0.0227813720703125,
0.0110931396484375,
0.0791015625,
0.03594970703125,
-0.03277587890625,
0.0345458984375,
-0.002895355224609375,
-0.0308837890625,
-0.040802001953125,
0.012969970703125,
0.0021648406982421875,
0.04620361328125,
0.0028533935546875,
0.032470703125,
0.025604248046875,
-0.0248870849609375,
0.0114898681640625,
0.0145416259765625,
-0.040618896484375,
-0.032958984375,
0.04376220703125,
-0.00916290283203125,
-0.020843505859375,
0.027069091796875,
-0.0389404296875,
-0.0262451171875,
0.06732177734375,
0.05401611328125,
0.062469482421875,
0.00908660888671875,
0.045562744140625,
0.05755615234375,
-0.01300048828125,
-0.00452423095703125,
0.044647216796875,
-0.00640106201171875,
-0.0299835205078125,
-0.01166534423828125,
-0.053375244140625,
-0.039947509765625,
0.017730712890625,
-0.050506591796875,
0.0384521484375,
-0.062347412109375,
-0.0219268798828125,
0.01776123046875,
0.00736236572265625,
-0.05633544921875,
0.0200347900390625,
0.0030975341796875,
0.072998046875,
-0.053924560546875,
0.043243408203125,
0.07379150390625,
-0.0247344970703125,
-0.063720703125,
-0.012542724609375,
0.0302734375,
-0.034637451171875,
0.028900146484375,
-0.0046234130859375,
-0.0149383544921875,
0.0386962890625,
-0.08197021484375,
-0.074462890625,
0.076904296875,
0.0020904541015625,
-0.0282135009765625,
0.03240966796875,
-0.0250091552734375,
0.0236358642578125,
-0.040283203125,
-0.0168304443359375,
0.007171630859375,
0.0272674560546875,
0.055450439453125,
-0.0238037109375,
0.003662109375,
-0.042938232421875,
0.028900146484375,
0.0097808837890625,
-0.046478271484375,
0.05218505859375,
-0.0198516845703125,
-0.00290679931640625,
0.041595458984375,
0.048736572265625,
0.0279541015625,
0.025054931640625,
0.04901123046875,
0.0677490234375,
0.025909423828125,
0.01151275634765625,
0.0958251953125,
-0.01433563232421875,
0.03961181640625,
0.068359375,
0.00849151611328125,
0.0257415771484375,
0.0158538818359375,
-0.0160064697265625,
0.044921875,
0.062347412109375,
-0.0228424072265625,
0.054534912109375,
0.0233612060546875,
-0.03314208984375,
-0.026214599609375,
-0.044464111328125,
-0.03778076171875,
0.0152740478515625,
-0.00482940673828125,
-0.015655517578125,
-0.0189056396484375,
-0.006832122802734375,
-0.011016845703125,
-0.0070037841796875,
-0.022125244140625,
0.032501220703125,
0.00848388671875,
-0.0104217529296875,
0.043975830078125,
-0.006805419921875,
0.0264434814453125,
-0.044464111328125,
-0.031524658203125,
0.00670623779296875,
0.0017328262329101562,
-0.0247344970703125,
-0.04827880859375,
0.01049041748046875,
-0.0112152099609375,
-0.00415802001953125,
-0.022918701171875,
0.08251953125,
-0.0255889892578125,
-0.0626220703125,
0.0045166015625,
0.0218505859375,
0.01348114013671875,
0.01251220703125,
-0.06988525390625,
0.03497314453125,
-0.00951385498046875,
-0.01097869873046875,
-0.0021724700927734375,
-0.00455474853515625,
0.00821685791015625,
0.03228759765625,
0.066162109375,
0.00937652587890625,
-0.00457000732421875,
0.0139617919921875,
0.07098388671875,
-0.0341796875,
-0.03704833984375,
-0.043304443359375,
0.03369140625,
-0.01448822021484375,
-0.03546142578125,
0.047088623046875,
0.042266845703125,
0.07330322265625,
-0.0275726318359375,
0.0428466796875,
-0.01007843017578125,
0.005802154541015625,
-0.0196075439453125,
0.061248779296875,
-0.068359375,
-0.0202789306640625,
-0.037384033203125,
-0.07659912109375,
0.0032596588134765625,
0.048736572265625,
0.0194244384765625,
0.01351165771484375,
0.01812744140625,
0.06298828125,
-0.0158538818359375,
0.01593017578125,
0.0231781005859375,
0.0094146728515625,
0.0056304931640625,
0.00637054443359375,
0.06536865234375,
-0.052581787109375,
0.006572723388671875,
-0.060760498046875,
0.0011205673217773438,
-0.019744873046875,
-0.053863525390625,
-0.05096435546875,
-0.05657958984375,
-0.040496826171875,
-0.03839111328125,
0.016357421875,
0.095703125,
0.078369140625,
-0.0543212890625,
-0.023162841796875,
0.004848480224609375,
0.01435089111328125,
-0.01271820068359375,
-0.01190185546875,
-0.00597381591796875,
0.0201416015625,
-0.04473876953125,
0.0208740234375,
0.012115478515625,
0.0273895263671875,
0.00142669677734375,
-0.005313873291015625,
-0.029754638671875,
0.00604248046875,
0.038055419921875,
0.0396728515625,
-0.03265380859375,
-0.0240020751953125,
-0.0046539306640625,
0.00007343292236328125,
0.00033020973205566406,
0.04534912109375,
-0.037200927734375,
0.01776123046875,
0.03271484375,
0.042205810546875,
0.053924560546875,
0.01242828369140625,
0.0194244384765625,
-0.045257568359375,
0.0009326934814453125,
0.01410675048828125,
0.022918701171875,
0.0176849365234375,
-0.0208282470703125,
0.0372314453125,
0.03387451171875,
-0.037384033203125,
-0.03759765625,
0.02752685546875,
-0.103515625,
0.0003814697265625,
0.06756591796875,
0.00350189208984375,
-0.024169921875,
0.0034465789794921875,
-0.0283050537109375,
0.017486572265625,
-0.0282440185546875,
0.0276947021484375,
0.045257568359375,
-0.006412506103515625,
-0.005893707275390625,
-0.062744140625,
0.024169921875,
0.01519012451171875,
-0.04058837890625,
-0.036956787109375,
0.072265625,
0.0214385986328125,
0.0081634521484375,
0.052886962890625,
-0.0255126953125,
0.037933349609375,
-0.005340576171875,
0.0017747879028320312,
-0.0233154296875,
-0.0297088623046875,
-0.03472900390625,
-0.0111236572265625,
-0.016265869140625,
-0.0286712646484375
]
] |
BM-K/KoSimCSE-roberta | 2023-03-24T00:48:01.000Z | [
"transformers",
"pytorch",
"safetensors",
"roberta",
"feature-extraction",
"korean",
"ko",
"endpoints_compatible",
"region:us"
] | feature-extraction | BM-K | null | null | BM-K/KoSimCSE-roberta | 2 | 37,314 | transformers | 2022-04-05T13:59:27 | ---
language: ko
tags:
- korean
---
https://github.com/BM-K/Sentence-Embedding-is-all-you-need
# Korean-Sentence-Embedding
🍭 Korean sentence embedding repository. You can download the pre-trained models and inference right away, also it provides environments where individuals can train models.
## Quick tour
```python
import torch
from transformers import AutoModel, AutoTokenizer
def cal_score(a, b):
if len(a.shape) == 1: a = a.unsqueeze(0)
if len(b.shape) == 1: b = b.unsqueeze(0)
a_norm = a / a.norm(dim=1)[:, None]
b_norm = b / b.norm(dim=1)[:, None]
return torch.mm(a_norm, b_norm.transpose(0, 1)) * 100
model = AutoModel.from_pretrained('BM-K/KoSimCSE-roberta')
tokenizer = AutoTokenizer.from_pretrained('BM-K/KoSimCSE-roberta')
sentences = ['치타가 들판을 가로 질러 먹이를 쫓는다.',
'치타 한 마리가 먹이 뒤에서 달리고 있다.',
'원숭이 한 마리가 드럼을 연주한다.']
inputs = tokenizer(sentences, padding=True, truncation=True, return_tensors="pt")
embeddings, _ = model(**inputs, return_dict=False)
score01 = cal_score(embeddings[0][0], embeddings[1][0])
score02 = cal_score(embeddings[0][0], embeddings[2][0])
```
## Performance
- Semantic Textual Similarity test set results <br>
| Model | AVG | Cosine Pearson | Cosine Spearman | Euclidean Pearson | Euclidean Spearman | Manhattan Pearson | Manhattan Spearman | Dot Pearson | Dot Spearman |
|------------------------|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|
| KoSBERT<sup>†</sup><sub>SKT</sub> | 77.40 | 78.81 | 78.47 | 77.68 | 77.78 | 77.71 | 77.83 | 75.75 | 75.22 |
| KoSBERT | 80.39 | 82.13 | 82.25 | 80.67 | 80.75 | 80.69 | 80.78 | 77.96 | 77.90 |
| KoSRoBERTa | 81.64 | 81.20 | 82.20 | 81.79 | 82.34 | 81.59 | 82.20 | 80.62 | 81.25 |
| | | | | | | | | |
| KoSentenceBART | 77.14 | 79.71 | 78.74 | 78.42 | 78.02 | 78.40 | 78.00 | 74.24 | 72.15 |
| KoSentenceT5 | 77.83 | 80.87 | 79.74 | 80.24 | 79.36 | 80.19 | 79.27 | 72.81 | 70.17 |
| | | | | | | | | |
| KoSimCSE-BERT<sup>†</sup><sub>SKT</sub> | 81.32 | 82.12 | 82.56 | 81.84 | 81.63 | 81.99 | 81.74 | 79.55 | 79.19 |
| KoSimCSE-BERT | 83.37 | 83.22 | 83.58 | 83.24 | 83.60 | 83.15 | 83.54 | 83.13 | 83.49 |
| KoSimCSE-RoBERTa | 83.65 | 83.60 | 83.77 | 83.54 | 83.76 | 83.55 | 83.77 | 83.55 | 83.64 |
| | | | | | | | | | |
| KoSimCSE-BERT-multitask | 85.71 | 85.29 | 86.02 | 85.63 | 86.01 | 85.57 | 85.97 | 85.26 | 85.93 |
| KoSimCSE-RoBERTa-multitask | 85.77 | 85.08 | 86.12 | 85.84 | 86.12 | 85.83 | 86.12 | 85.03 | 85.99 | | 2,583 | [
[
-0.020782470703125,
-0.046417236328125,
0.03497314453125,
0.02215576171875,
-0.0270538330078125,
0.00518798828125,
-0.02044677734375,
0.0017633438110351562,
0.0247802734375,
0.0280609130859375,
-0.0499267578125,
-0.055389404296875,
-0.047454833984375,
0.0063323974609375,
0.005329132080078125,
0.05267333984375,
-0.0150146484375,
0.00856781005859375,
0.007358551025390625,
-0.0099334716796875,
-0.04266357421875,
-0.01236724853515625,
-0.02362060546875,
-0.02325439453125,
0.00832366943359375,
0.037994384765625,
0.050872802734375,
0.02581787109375,
0.0200653076171875,
0.032440185546875,
0.004627227783203125,
0.00010353326797485352,
-0.011566162109375,
0.01568603515625,
0.006134033203125,
-0.040069580078125,
-0.0234222412109375,
0.0011796951293945312,
0.03369140625,
0.033203125,
0.0007476806640625,
0.01043701171875,
0.005523681640625,
0.0521240234375,
-0.0303802490234375,
0.012786865234375,
-0.0206146240234375,
0.023345947265625,
0.004055023193359375,
-0.01538848876953125,
-0.0286712646484375,
-0.03466796875,
0.011962890625,
-0.04913330078125,
0.0010080337524414062,
0.0037746429443359375,
0.10400390625,
0.0182952880859375,
-0.047393798828125,
-0.03509521484375,
-0.0241546630859375,
0.07110595703125,
-0.06341552734375,
0.031982421875,
0.02117919921875,
0.01092529296875,
-0.01202392578125,
-0.05419921875,
-0.038238525390625,
-0.0029277801513671875,
-0.02587890625,
0.044189453125,
0.00020515918731689453,
0.003818511962890625,
0.020111083984375,
0.024993896484375,
-0.054107666015625,
-0.0163116455078125,
-0.024566650390625,
-0.01531219482421875,
0.05010986328125,
0.01273345947265625,
0.035064697265625,
-0.0517578125,
-0.037017822265625,
-0.0188140869140625,
-0.00864410400390625,
0.007465362548828125,
0.0252227783203125,
0.005748748779296875,
-0.00824737548828125,
0.058441162109375,
-0.020294189453125,
0.03070068359375,
0.0160369873046875,
-0.007720947265625,
0.052764892578125,
-0.035919189453125,
-0.0283050537109375,
0.007305145263671875,
0.0693359375,
0.035614013671875,
0.017364501953125,
-0.0021991729736328125,
-0.005435943603515625,
0.0092315673828125,
0.0014190673828125,
-0.061126708984375,
-0.04486083984375,
0.021514892578125,
-0.0293731689453125,
-0.0139617919921875,
0.0210113525390625,
-0.05706787109375,
0.0120697021484375,
-0.024810791015625,
0.06329345703125,
-0.037261962890625,
-0.0158233642578125,
0.0160980224609375,
-0.0162353515625,
0.0199127197265625,
-0.0020751953125,
-0.0455322265625,
0.0120086669921875,
0.01751708984375,
0.06280517578125,
0.00473785400390625,
-0.017425537109375,
0.002658843994140625,
-0.0025730133056640625,
-0.0318603515625,
0.036102294921875,
-0.0003809928894042969,
-0.0240936279296875,
0.00007939338684082031,
0.023101806640625,
-0.030364990234375,
-0.00908660888671875,
0.045440673828125,
-0.0135650634765625,
0.030548095703125,
-0.0161895751953125,
-0.06292724609375,
-0.0155181884765625,
0.0225982666015625,
-0.040985107421875,
0.10369873046875,
0.011138916015625,
-0.06878662109375,
0.034942626953125,
-0.04840087890625,
-0.017578125,
-0.005199432373046875,
0.0009946823120117188,
-0.052734375,
-0.0005364418029785156,
0.0300750732421875,
0.05596923828125,
0.0163421630859375,
0.008026123046875,
-0.018463134765625,
-0.0245208740234375,
-0.00016105175018310547,
-0.01152801513671875,
0.07318115234375,
0.0162200927734375,
-0.0301666259765625,
0.0123291015625,
-0.07403564453125,
0.0384521484375,
0.0164031982421875,
-0.02001953125,
-0.02703857421875,
-0.037078857421875,
0.00046181678771972656,
0.0318603515625,
0.01369476318359375,
-0.043609619140625,
0.01107025146484375,
-0.04620361328125,
0.034027099609375,
0.056884765625,
0.0159149169921875,
0.034576416015625,
-0.0253753662109375,
0.04315185546875,
0.01104736328125,
0.0035266876220703125,
-0.007793426513671875,
-0.0311737060546875,
-0.041748046875,
-0.04302978515625,
0.0280303955078125,
0.05133056640625,
-0.058929443359375,
0.06658935546875,
-0.0197601318359375,
-0.04522705078125,
-0.054962158203125,
0.002880096435546875,
0.01953125,
0.0235748291015625,
0.01934814453125,
0.018707275390625,
-0.057586669921875,
-0.06768798828125,
-0.0266571044921875,
0.00811004638671875,
0.004512786865234375,
0.038238525390625,
0.06597900390625,
-0.0016431808471679688,
0.06585693359375,
-0.061553955078125,
-0.0179595947265625,
-0.0295562744140625,
-0.00734710693359375,
0.047027587890625,
0.04217529296875,
0.0469970703125,
-0.05181884765625,
-0.0848388671875,
-0.003192901611328125,
-0.05889892578125,
-0.00959014892578125,
-0.0022220611572265625,
-0.016143798828125,
0.02191162109375,
0.03466796875,
-0.0650634765625,
0.06109619140625,
0.04443359375,
-0.06072998046875,
0.0682373046875,
-0.0260772705078125,
0.0265045166015625,
-0.11724853515625,
0.004985809326171875,
-0.0190887451171875,
-0.0252685546875,
-0.042877197265625,
-0.0021457672119140625,
0.01093292236328125,
0.0012044906616210938,
-0.0199127197265625,
0.05279541015625,
-0.0362548828125,
0.0073699951171875,
-0.004230499267578125,
0.01177215576171875,
0.007556915283203125,
0.048492431640625,
-0.00067138671875,
0.051605224609375,
0.0369873046875,
-0.0372314453125,
0.020050048828125,
0.0238037109375,
-0.04913330078125,
0.0268707275390625,
-0.04913330078125,
-0.004962921142578125,
0.0105438232421875,
0.0255126953125,
-0.10809326171875,
-0.02044677734375,
0.03546142578125,
-0.05035400390625,
0.004741668701171875,
-0.016510009765625,
-0.043701171875,
-0.048553466796875,
-0.04156494140625,
0.0102386474609375,
0.039093017578125,
-0.0277252197265625,
0.033111572265625,
0.005771636962890625,
-0.01548004150390625,
-0.045074462890625,
-0.051177978515625,
-0.018951416015625,
-0.017364501953125,
-0.044952392578125,
0.033355712890625,
-0.00545501708984375,
0.0006985664367675781,
0.0206298828125,
-0.01169586181640625,
-0.0084228515625,
0.0049896240234375,
0.01364898681640625,
0.034637451171875,
-0.025665283203125,
0.0017242431640625,
0.01316070556640625,
-0.0179901123046875,
-0.004169464111328125,
-0.01166534423828125,
0.060882568359375,
-0.006687164306640625,
-0.01812744140625,
-0.05157470703125,
0.0090484619140625,
0.0328369140625,
0.00797271728515625,
0.063232421875,
0.0614013671875,
-0.0262908935546875,
-0.0017366409301757812,
-0.0295867919921875,
-0.0067596435546875,
-0.037628173828125,
0.03424072265625,
-0.048492431640625,
-0.06451416015625,
0.056121826171875,
-0.00815582275390625,
-0.01212310791015625,
0.056854248046875,
0.042633056640625,
-0.01412200927734375,
0.08551025390625,
0.021148681640625,
0.006526947021484375,
0.021575927734375,
-0.0435791015625,
0.021087646484375,
-0.059417724609375,
-0.0228729248046875,
-0.0294036865234375,
-0.02569580078125,
-0.0516357421875,
0.00127410888671875,
0.01526641845703125,
0.0166778564453125,
-0.040313720703125,
0.035003662109375,
-0.050323486328125,
0.035888671875,
0.04144287109375,
0.0240020751953125,
-0.002460479736328125,
-0.0200347900390625,
-0.04669189453125,
-0.024688720703125,
-0.05426025390625,
-0.0244140625,
0.0853271484375,
0.01474761962890625,
0.0438232421875,
0.001556396484375,
0.05621337890625,
0.01560211181640625,
-0.00957489013671875,
-0.053802490234375,
0.03228759765625,
0.000050902366638183594,
-0.040802001953125,
-0.0249176025390625,
-0.032073974609375,
-0.0692138671875,
0.0328369140625,
-0.01336669921875,
-0.0689697265625,
-0.002094268798828125,
-0.0117340087890625,
-0.03350830078125,
0.0263824462890625,
-0.055572509765625,
0.07476806640625,
0.0029468536376953125,
-0.004871368408203125,
0.00618743896484375,
-0.046844482421875,
0.0206298828125,
0.0131072998046875,
0.0079193115234375,
-0.0007448196411132812,
0.0003879070281982422,
0.058807373046875,
-0.045989990234375,
0.04156494140625,
-0.0220489501953125,
0.01409912109375,
0.0221405029296875,
0.003810882568359375,
0.0430908203125,
0.0184326171875,
0.01016998291015625,
-0.0152740478515625,
0.0103607177734375,
-0.036224365234375,
-0.0408935546875,
0.06671142578125,
-0.0714111328125,
-0.0298309326171875,
-0.054595947265625,
-0.038330078125,
0.003215789794921875,
0.034576416015625,
0.040557861328125,
0.0158843994140625,
0.00708770751953125,
0.031219482421875,
0.045196533203125,
-0.0231475830078125,
0.042083740234375,
0.016845703125,
-0.015045166015625,
-0.056884765625,
0.046112060546875,
0.0144195556640625,
0.0157318115234375,
0.01427459716796875,
0.0347900390625,
-0.046722412109375,
-0.01331329345703125,
-0.0210113525390625,
0.0144195556640625,
-0.0491943359375,
-0.015777587890625,
-0.051544189453125,
-0.027740478515625,
-0.052490234375,
-0.024871826171875,
-0.031280517578125,
-0.04119873046875,
-0.00806427001953125,
-0.0251007080078125,
0.0204620361328125,
0.046875,
-0.0024471282958984375,
0.0281982421875,
-0.04803466796875,
0.01251983642578125,
0.001682281494140625,
0.01316070556640625,
-0.0011320114135742188,
-0.0487060546875,
-0.01102447509765625,
-0.00435638427734375,
-0.0211639404296875,
-0.0714111328125,
0.04315185546875,
0.00441741943359375,
0.0340576171875,
0.0257415771484375,
0.007534027099609375,
0.057525634765625,
-0.024383544921875,
0.06768798828125,
0.0103607177734375,
-0.0714111328125,
0.040985107421875,
-0.016693115234375,
0.03057861328125,
0.03924560546875,
0.033416748046875,
-0.0458984375,
-0.0159454345703125,
-0.06341552734375,
-0.0753173828125,
0.07257080078125,
0.0362548828125,
0.00589752197265625,
0.005954742431640625,
0.017425537109375,
-0.006565093994140625,
0.0161285400390625,
-0.06475830078125,
-0.0396728515625,
-0.04022216796875,
-0.0361328125,
0.0008916854858398438,
-0.00978851318359375,
0.015380859375,
-0.035125732421875,
0.06671142578125,
0.0104827880859375,
0.0279541015625,
0.025909423828125,
-0.02398681640625,
0.0172119140625,
0.00850677490234375,
0.051849365234375,
0.04461669921875,
-0.0180511474609375,
-0.00662994384765625,
0.0224609375,
-0.04400634765625,
0.0180511474609375,
-0.00826263427734375,
-0.01715087890625,
0.021270751953125,
0.024017333984375,
0.0482177734375,
0.0372314453125,
-0.02764892578125,
0.04278564453125,
0.01126861572265625,
-0.040557861328125,
-0.040252685546875,
-0.016937255859375,
0.0072479248046875,
0.021636962890625,
0.01491546630859375,
-0.0037860870361328125,
-0.015380859375,
-0.032440185546875,
0.0235137939453125,
0.010986328125,
-0.038787841796875,
-0.01454925537109375,
0.037261962890625,
-0.01081085205078125,
-0.0189971923828125,
0.049957275390625,
-0.020782470703125,
-0.0733642578125,
0.053253173828125,
0.04095458984375,
0.05706787109375,
-0.033203125,
0.022979736328125,
0.06378173828125,
0.00943756103515625,
-0.0137176513671875,
0.041412353515625,
0.0159149169921875,
-0.052764892578125,
-0.0160369873046875,
-0.034210205078125,
0.0117034912109375,
0.017242431640625,
-0.048492431640625,
0.01546478271484375,
-0.0184783935546875,
-0.015869140625,
-0.0103302001953125,
0.029022216796875,
-0.04937744140625,
0.021270751953125,
-0.024383544921875,
0.06304931640625,
-0.07403564453125,
0.060394287109375,
0.05462646484375,
-0.0364990234375,
-0.0673828125,
-0.0166015625,
-0.0070648193359375,
-0.060577392578125,
0.042755126953125,
0.013946533203125,
0.031402587890625,
0.006298065185546875,
-0.0260162353515625,
-0.07135009765625,
0.09967041015625,
-0.002597808837890625,
-0.0218658447265625,
0.00807952880859375,
0.01336669921875,
0.030914306640625,
-0.01096343994140625,
0.038360595703125,
0.0272216796875,
0.04315185546875,
0.00408172607421875,
-0.055694580078125,
0.02081298828125,
-0.02142333984375,
-0.00635528564453125,
0.016937255859375,
-0.05767822265625,
0.07977294921875,
-0.0008769035339355469,
0.0036334991455078125,
0.0102386474609375,
0.0439453125,
0.01715087890625,
0.017425537109375,
0.037750244140625,
0.061065673828125,
0.053802490234375,
-0.0117950439453125,
0.061004638671875,
-0.0249176025390625,
0.054901123046875,
0.07598876953125,
0.00754547119140625,
0.04888916015625,
0.0196990966796875,
-0.0227813720703125,
0.034881591796875,
0.050506591796875,
-0.008941650390625,
0.047027587890625,
0.01253509521484375,
-0.006000518798828125,
-0.0270538330078125,
0.025054931640625,
-0.0238037109375,
0.03424072265625,
0.01548004150390625,
-0.02569580078125,
-0.0083770751953125,
0.006397247314453125,
0.0284576416015625,
0.007282257080078125,
-0.01015472412109375,
0.048919677734375,
0.00012600421905517578,
-0.04351806640625,
0.018768310546875,
-0.001094818115234375,
0.047607421875,
-0.05023193359375,
0.00569915771484375,
0.00264739990234375,
0.031402587890625,
-0.01322174072265625,
-0.06634521484375,
0.011993408203125,
-0.01470184326171875,
-0.007598876953125,
0.0008730888366699219,
0.060333251953125,
-0.033172607421875,
-0.0457763671875,
0.01751708984375,
0.0335693359375,
0.0081024169921875,
-0.0008931159973144531,
-0.078125,
-0.01261138916015625,
0.006847381591796875,
-0.0487060546875,
0.0208892822265625,
0.036651611328125,
0.007061004638671875,
0.053436279296875,
0.044097900390625,
0.00304412841796875,
0.0247344970703125,
-0.0007243156433105469,
0.052154541015625,
-0.052947998046875,
-0.05462646484375,
-0.074462890625,
0.0305328369140625,
-0.0218505859375,
-0.041595458984375,
0.07037353515625,
0.0587158203125,
0.051300048828125,
-0.0211639404296875,
0.057373046875,
-0.0195465087890625,
0.0261688232421875,
-0.04022216796875,
0.07818603515625,
-0.046173095703125,
-0.0205230712890625,
-0.0213775634765625,
-0.06256103515625,
-0.018157958984375,
0.06878662109375,
-0.0157012939453125,
0.008697509765625,
0.0655517578125,
0.052703857421875,
-0.005878448486328125,
-0.0000979304313659668,
0.0154571533203125,
0.041015625,
0.0157470703125,
0.04412841796875,
0.03955078125,
-0.05926513671875,
0.048583984375,
-0.038116455078125,
0.0005869865417480469,
-0.0128326416015625,
-0.056793212890625,
-0.07373046875,
-0.04840087890625,
-0.023284912109375,
-0.031402587890625,
-0.007373809814453125,
0.09259033203125,
0.037139892578125,
-0.05841064453125,
-0.003940582275390625,
-0.00644683837890625,
0.00608062744140625,
-0.016876220703125,
-0.0223236083984375,
0.0709228515625,
-0.0280609130859375,
-0.058685302734375,
0.00850677490234375,
-0.00377655029296875,
0.0030460357666015625,
0.006443023681640625,
-0.016510009765625,
-0.04742431640625,
0.0152740478515625,
0.036285400390625,
-0.000507354736328125,
-0.06317138671875,
-0.034271240234375,
0.00011819601058959961,
-0.02313232421875,
0.00495147705078125,
0.0164642333984375,
-0.037994384765625,
0.0285491943359375,
0.04736328125,
0.03375244140625,
0.036590576171875,
-0.0022678375244140625,
0.0206298828125,
-0.045379638671875,
0.0135345458984375,
0.01007080078125,
0.026947021484375,
-0.004001617431640625,
-0.02142333984375,
0.048492431640625,
0.03375244140625,
-0.04766845703125,
-0.06451416015625,
-0.020477294921875,
-0.08209228515625,
-0.02569580078125,
0.0716552734375,
-0.03375244140625,
-0.0228118896484375,
-0.00823974609375,
-0.0306396484375,
0.02227783203125,
-0.02825927734375,
0.045806884765625,
0.07916259765625,
0.00951385498046875,
-0.0008721351623535156,
-0.050750732421875,
0.03961181640625,
0.028350830078125,
-0.041961669921875,
-0.0211181640625,
-0.00881195068359375,
0.03314208984375,
-0.005901336669921875,
0.05047607421875,
-0.0012216567993164062,
0.0209503173828125,
0.0153656005859375,
-0.00164794921875,
-0.00197601318359375,
-0.00643157958984375,
0.0027866363525390625,
-0.0003075599670410156,
-0.0394287109375,
-0.044830322265625
]
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.