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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
timm/resnet101d.ra2_in1k | 2023-04-05T18:26:35.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1512.03385",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/resnet101d.ra2_in1k | 0 | 510 | timm | 2023-04-05T18:25:53 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
---
# Model card for resnet101d.ra2_in1k
A ResNet-D image classification model.
This model features:
* ReLU activations
* 3-layer stem of 3x3 convolutions with pooling
* 2x2 average pool + 1x1 convolution shortcut downsample
Trained on ImageNet-1k in `timm` using recipe template described below.
Recipe details:
* RandAugment `RA2` 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): 44.6
- GMACs: 10.5
- Activations (M): 22.3
- Image size: train = 256 x 256, test = 320 x 320
- **Papers:**
- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
- **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('resnet101d.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(
'resnet101d.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, 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(
'resnet101d.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, 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).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```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}}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@article{He2018BagOT,
title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
pages={558-567}
}
```
| 39,094 | [
[
-0.06329345703125,
-0.019195556640625,
0.0022411346435546875,
0.0277862548828125,
-0.0304718017578125,
-0.00958251953125,
-0.01015472412109375,
-0.0313720703125,
0.0816650390625,
0.0224456787109375,
-0.048492431640625,
-0.039398193359375,
-0.04913330078125,
... |
Neko-Institute-of-Science/LLaMA-30B-HF | 2023-04-15T15:34:15.000Z | [
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"license:other",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | Neko-Institute-of-Science | null | null | Neko-Institute-of-Science/LLaMA-30B-HF | 4 | 510 | transformers | 2023-04-06T00:53:12 | ---
license: other
---
LLaMA converted to Transformers. This is under a special license, please see the LICENSE file for details.
# LLaMA Model Card
https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md
# Torrent 7-65B
Note: the torrent has outdated tokenizer_config.json and special_tokens_map.json. Replace them with the ones here.
For those who want to save HF's bandwith here's a magnet link:
**magnet:?xt=urn:btih:8d634925911a03f787d9f68ac075a9b24281573a&dn=Safe-LLaMA-HF-v2%20(4-04-23)&tr=http%3a%2f%2fbt2.archive.org%3a6969%2fannounce&tr=http%3a%2f%2fbt1.archive.org%3a6969%2fannounce** | 607 | [
[
-0.0303497314453125,
-0.037200927734375,
0.0204315185546875,
0.035919189453125,
-0.053924560546875,
0.0234222412109375,
0.00872802734375,
-0.0177154541015625,
0.058929443359375,
0.041015625,
-0.06158447265625,
-0.0236358642578125,
-0.0477294921875,
0.0232543... |
timm/pvt_v2_b5.in1k | 2023-04-25T04:07:04.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2106.13797",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/pvt_v2_b5.in1k | 0 | 510 | timm | 2023-04-25T04:05:52 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for pvt_v2_b5
A PVT-v2 (Pyramid Vision Transformer) image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 82.0
- GMACs: 11.8
- Activations (M): 50.9
- Image size: 224 x 224
- **Papers:**
- PVT v2: Improved Baselines with Pyramid Vision Transformer: https://arxiv.org/abs/2106.13797
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/whai362/PVT
## 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('pvt_v2_b5', 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(
'pvt_v2_b5',
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, 56, 56])
# torch.Size([1, 128, 28, 28])
# torch.Size([1, 320, 14, 14])
# torch.Size([1, 512, 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(
'pvt_v2_b5',
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, 512, 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{wang2021pvtv2,
title={Pvtv2: Improved baselines with pyramid vision transformer},
author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
journal={Computational Visual Media},
volume={8},
number={3},
pages={1--10},
year={2022},
publisher={Springer}
}
```
| 3,698 | [
[
-0.030914306640625,
-0.027191162109375,
-0.004894256591796875,
0.015380859375,
-0.029083251953125,
-0.025848388671875,
-0.01021575927734375,
-0.02545166015625,
0.004734039306640625,
0.035186767578125,
-0.0273895263671875,
-0.04547119140625,
-0.05517578125,
-... |
TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ | 2023-10-18T23:29:21.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"upstage",
"llama-2",
"instruct",
"instruction",
"en",
"license:llama2",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ | 17 | 510 | transformers | 2023-07-31T07:19:26 | ---
language:
- en
license: llama2
tags:
- upstage
- llama-2
- instruct
- instruction
model_name: Llama 2 70B Instruct v2
base_model: upstage/Llama-2-70b-instruct-v2
inference: false
model_creator: Upstage
model_type: llama
pipeline_tag: text-generation
prompt_template: '### System:
{system_message}
### User:
{prompt}
### Assistant:
'
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 -->
# Llama 2 70B Instruct v2 - GPTQ
- Model creator: [Upstage](https://huggingface.co/Upstage)
- Original model: [Llama 2 70B Instruct v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Upstage's Llama 2 70B Instruct v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2).
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/Upstage-Llama-2-70B-instruct-v2-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGUF)
* [Upstage's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Orca-Hashes
```
### System:
{system_message}
### User:
{prompt}
### Assistant:
```
<!-- prompt-template 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/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/main) | 4 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 35.33 GB | Yes | 4-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 40.66 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/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 37.99 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/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 36.65 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-3bit--1g-actorder_True](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-3bit--1g-actorder_True) | 3 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 26.78 GB | No | 3-bit, with Act Order and no group size. Lowest possible VRAM requirements. May be lower quality than 3-bit 128g. |
| [gptq-3bit-128g-actorder_False](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-3bit-128g-actorder_False) | 3 | 128 | No | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g but no act-order. Slightly higher VRAM requirements than 3-bit None. |
| [gptq-3bit-128g-actorder_True](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-3bit-128g-actorder_True) | 3 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 28.03 GB | No | 3-bit, with group size 128g and act-order. Higher quality than 128g-False. |
| [gptq-3bit-64g-actorder_True](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ/tree/gptq-3bit-64g-actorder_True) | 3 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 29.30 GB | No | 3-bit, with group size 64g and act-order. |
<!-- 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/Upstage-Llama-2-70B-instruct-v2-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-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/Upstage-Llama-2-70B-instruct-v2-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/Upstage-Llama-2-70B-instruct-v2-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: `Upstage-Llama-2-70B-instruct-v2-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/Upstage-Llama-2-70B-instruct-v2-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"
system_message = "You are a helpful AI"
prompt_template=f'''### System:
{system_message}
### User:
{prompt}
### Assistant:
'''
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: Upstage's Llama 2 70B Instruct v2
# Updates
Solar, a new bot created by Upstage, is now available on **Poe**. As a top-ranked model on the HuggingFace Open LLM leaderboard, and a fine tune of Llama 2, Solar is a great example of the progress enabled by open source.
Try now at https://poe.com/Solar-0-70b
# SOLAR-0-70b-16bit model card
The model name has been changed from LLaMa-2-70b-instruct-v2 to SOLAR-0-70b-16bit
## Model Details
* **Developed by**: [Upstage](https://en.upstage.ai)
* **Backbone Model**: [LLaMA-2](https://github.com/facebookresearch/llama/tree/main)
* **Language(s)**: English
* **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers)
* **License**: Fine-tuned checkpoints is licensed under the Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/))
* **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/Llama-2-70b-instruct-v2/discussions)
* **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai)
## Dataset Details
### Used Datasets
- Orca-style dataset
- Alpaca-style dataset
- No other dataset was used except for the dataset mentioned above
- No benchmark test set or the training set are used
### Prompt Template
```
### System:
{System}
### User:
{User}
### Assistant:
{Assistant}
```
## Usage
- The followings are tested on A100 80GB
- Our model can handle up to 10k+ input tokens, thanks to the `rope_scaling` option
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("upstage/Llama-2-70b-instruct-v2")
model = AutoModelForCausalLM.from_pretrained(
"upstage/Llama-2-70b-instruct-v2",
device_map="auto",
torch_dtype=torch.float16,
load_in_8bit=True,
rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs
)
prompt = "### User:\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
del inputs["token_type_ids"]
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
```
## Hardware and Software
* **Hardware**: We utilized an A100x8 * 4 for training our model
* **Training Factors**: We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace Trainer](https://huggingface.co/docs/transformers/main_classes/trainer) / [HuggingFace Accelerate](https://huggingface.co/docs/accelerate/index)
## Evaluation Results
### Overview
- We conducted a performance evaluation following the tasks being evaluated on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
We evaluated our model on four benchmark datasets, which include `ARC-Challenge`, `HellaSwag`, `MMLU`, and `TruthfulQA`
We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-evaluation-harness), specifically commit [b281b0921b636bc36ad05c0b0b0763bd6dd43463](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463).
- We used [MT-bench](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge), a set of challenging multi-turn open-ended questions, to evaluate the models
### Main Results
| Model | H4(Avg) | ARC | HellaSwag | MMLU | TruthfulQA | | MT_Bench |
|--------------------------------------------------------------------|----------|----------|----------|------|----------|-|-------------|
| **[Llama-2-70b-instruct-v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2)**(***Ours***, ***Open LLM Leaderboard***) | **73** | **71.1** | **87.9** | **70.6** | **62.2** | | **7.44063** |
| [Llama-2-70b-instruct](https://huggingface.co/upstage/Llama-2-70b-instruct) (Ours, Open LLM Leaderboard) | 72.3 | 70.9 | 87.5 | 69.8 | 61 | | 7.24375 |
| [llama-65b-instruct](https://huggingface.co/upstage/llama-65b-instruct) (Ours, Open LLM Leaderboard) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 | | |
| Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 | | |
| [llama-30b-instruct-2048](https://huggingface.co/upstage/llama-30b-instruct-2048) (Ours, Open LLM Leaderboard) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 | | |
| [llama-30b-instruct](https://huggingface.co/upstage/llama-30b-instruct) (Ours, Open LLM Leaderboard) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 | | |
| llama-65b | 64.2 | 63.5 | 86.1 | 63.9 | 43.4 | | |
| falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 | | |
### Scripts for H4 Score Reproduction
- Prepare evaluation environments:
```
# clone the repository
git clone https://github.com/EleutherAI/lm-evaluation-harness.git
# check out the specific commit
git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463
# change to the repository directory
cd lm-evaluation-harness
```
## Contact Us
### About Upstage
- [Upstage](https://en.upstage.ai) is a company specialized in Large Language Models (LLMs) and AI. We will help you build private LLMs and related applications.
If you have a dataset to build domain specific LLMs or make LLM applications, please contact us at ► [click here to contact](https://www.upstage.ai/private-llm?utm_source=huggingface&utm_medium=link&utm_campaign=privatellm)
- As of August 1st, our 70B model has reached the top spot in openLLM rankings, marking itself as the current leading performer globally.
| 21,386 | [
[
-0.0377197265625,
-0.04913330078125,
0.00978851318359375,
0.0139312744140625,
-0.0255889892578125,
-0.003467559814453125,
0.006023406982421875,
-0.03839111328125,
0.023284912109375,
0.02655029296875,
-0.04827880859375,
-0.03570556640625,
-0.025970458984375,
... |
FreedomIntelligence/AceGPT-7B-chat | 2023-09-26T08:15:05.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ar",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | FreedomIntelligence | null | null | FreedomIntelligence/AceGPT-7B-chat | 2 | 510 | transformers | 2023-09-21T06:05:57 | ---
license: apache-2.0
language:
- ar
---
# <b>AceGPT</b>
AceGPT is a fully fine-tuned generative text model collection based on LlaMA2, particularly in the
Arabic language domain. This is the repository for the 7B-chat pre-trained model.
---
## Model Details
We have released the AceGPT family of large language models, which is a collection of fully fine-tuned generative text models based on LlaMA2, ranging from 7B to 13B parameters. Our models include two main categories: AceGPT and AceGPT-chat. AceGPT-chat is an optimized version specifically designed for dialogue applications. It is worth mentioning that our models have demonstrated superior performance compared to all currently available open-source Arabic dialogue models in multiple benchmark tests. Furthermore, in our human evaluations, our models have shown comparable satisfaction levels to some closed-source models, such as ChatGPT, in the Arabic language.
## Model Developers
We are from the School of Data Science, the Chinese University of Hong Kong, Shenzhen (CUHKSZ), the Shenzhen Research Institute of Big Data (SRIBD), and the King Abdullah University of Science and Technology (KAUST).
## Variations
AceGPT famils come in a range of parameter sizes —— 7B and 13B, each size of model has a base category and a -chat category.
## Input
Models input text only.
## Output
Models output text only.
## Model Evaluation Results
Experiments on Arabic Vicuna-80, Arabic AlpacaEval. Numbers are the average performance ratio of ChatGPT over three runs. We do not report the results of raw Llama-2 models since they cannot properly generate Arabic texts.
| | Arabic Vicuna-80 | Arabic AlpacaEval |
|------------------------------|--------------------|---------------------|
| Phoenix Chen et al. (2023a) | 71.92% ± 0.2% | 65.62% ± 0.3% |
| Phoenix–multiple-langs Chen et al. (2023b) | 71.67% ± 0.7% | 65.36% ± 0.1% |
| Jais-13B-chat Sengupta et al. (2023) | 75.40% ± 1.6% | 74.95% ± 0.2% |
| AceGPT-7B-chat | 94.82% ± 0.2% | 93.81% ± 0.1% |
| AceGPT-13B-chat | 100.88% ± 0.4% | 97.95% ± 0.1% |
## Samples
#### Sample1(alpaca)
* question:
ما هي أسماء بعض الممثلين المشهورين الذين بدأوا مسيراتهم المهنية على برودواي؟
* answer:
1. ليوناردو دي كابريو: بدأ مسيرته الفنية في برودواي على الرغم من أنه اشتهر بشكل أكبر من خلال أدواره في الأفلام مثل \"The Wolf of Wall Street\" و \"Titanic\".
2. فرانسيس مكدورماند: بدأت مسيرتها الفنية في برودواي وأصبحت ممثلة مشهورة في أوائل القرن العشرين بفضل أدوارها في العديد من المسرحيات الكلاسيكية.
3. جودي دنش: بدأت مسيرتها الفنية في برودواي وأصبحت ممثلة مشهورة بفضل أدائها المتميز في العديد من المسرحيات الكلاسيكية.
4. بيتر أوستروم: بدأ مسيرته الفنية في برودواي وأصبح ممثلًا مشهورًا بفضل أدائه المتميز في العديد من المسرحيات الكلاسيكية.
5. مارك رايلانس: بدأ مسيرته الفنية في برودواي وأصبح ممثلًا مشهورًا بفضل أدائه المتميز في العديد من المسرحيات الكلاسيكية.
6. جيمس كان: بدأ مسيرته الفنية في برودواي وأصبح ممثلًا مشهورًا بفضل أدائه المتميز في العديد من المسرحيات الكلاسيكية.
7. إليزابيث تايلور: بدأت مسيرتها الفنية في برودواي وأصبحت ممثلة مشهورة في أوائل القرن العشرين بفضل أدوارها في العديد من المسرحيات الكلاسيكية.
8. روبرت ويلسون: بدأ مسيرته الفنية في برودواي وأصبح ممثلًا مشهورًا بفضل أدائه المتميز في العديد من المسرحيات الكلاسيكية.
9. جودي غارلاند: بدأت مسيرتها الفنية في برودواي وأصبحت ممثلة مشهورة في أوائل القرن العشرين بفضل أدوارها في العديد من المسرحيات الكلاسيكية.
10. ماثيو برودريك: بدأ مسيرته الفنية في برودواي وأصبح ممثلًا مشهورًا بفضل أدائه المتميز في العديد من المسرحيات الكلاسيكية."
---
#### Sample2(Vicuna)
* question:
كيف يمكنني تحسين مهارات إدارة الوقت الخاصة بي؟
* answer:
1. تحديد الأولويات: قم بتحديد الأعمال الأكثر أهمية والتي تتطلب اهتمامك الأكبر.
2. تنظيم الجدول الزمني: استخدم جدول زمني أو تقويم لتنظيم وقتك وتحديد الأوقات المحددة للقيام بمهام معينة.
3. تجنب التسويف: تجنب تأجيل الأعمال التي يمكنك القيام بها الآن.
4. استخدام تقنيات الإدارة الزمنية: استخدم تقنيات مثل تقنية بومودورو، حيث تعمل لمدة 25 دقيقة ثم تأخذ استراحة لمدة 5 دقائق.
5. تعلم قول \"لا\": تعلم كيفية رفض الطلبات التي لا تتناسب مع أهدافك وجدولك الزمني.
6. استخدم التكنولوجيا: استخدم التطبيقات والأدوات التكنولوجية لتتبع الوقت وتنظيم المهام.
7. تحديد الوقت للراحة: تأكد من تحديد الوقت للراحة والاسترخاء لتجنب الإرهاق والشعور بالحرق.
8. تحسين المهارات التنظيمية: تعلم كيفية تنظيم المهام والأولويات بشكل فعال.
9. استخدم التقنيات البصرية: استخدم الرسوم البيانية والرسوم البيانية لتتبع الوقت والتقدم.
10. تحسين الصحة العامة: تأكد من الحصول على قسط كاف من النوم والتغذية الجيدة والتمارين الرياضية لتحسين قدرتك على التركيز والإنتاجية.
11. استخدم تقنية الطماطم: هذه التقنية تتطلب منك العمل لمدة 25 دقيقة دون انقطاع، ثم تأخذ استراحة لمدة 5 دقائق.
12. تعلم كيفية قول \"لا\": قدرتك على قول \"لا\" للأشياء التي لا تخدم أهدافك يمكن أن تحسن بشكل كبير إدارة الوقت الخاصة بك.
13. استخدم تقنية التركيز العميق: تقنية تستخدم التقنيات مثل التأمل والتركيز العقلي لزيادة القدرة على التركيز وتحسين الإنتاجية.
14. تعلم كيفية تقسيم المهام: تعلم كيفية تقسيم المهام الكبيرة إلى مهام أصغر وأكثر إدارة.
15. استخدم تقنية الطماطم: تقنية تتطلب منك العمل لمدة 25 دقيقة دون انقطاع، ثم تأخذ استراحة لمدة 5 دقائق.
16. تعلم كيفية تحديد الأولويات: تعلم كيفية تحديد الأولويات والتركيز على المهام الأكثر أهمية أولاً.
17. استخدم تقنية الترتيب الثلاثي: تقنية تتطلب منك ترتيب المهام حسب الأهمية والعاجلة، ثم تعمل على المهمة الأعلى أولاً.
18. تعلم كيفية تحسين التركيز: تعلم"
# You can get more details at https://github.com/FreedomIntelligence/AceGPT/tree/main | 5,585 | [
[
-0.05914306640625,
-0.061614990234375,
0.0439453125,
0.0257110595703125,
-0.0377197265625,
-0.016998291015625,
0.010528564453125,
-0.039642333984375,
0.050750732421875,
0.038818359375,
-0.0263519287109375,
-0.044708251953125,
-0.05096435546875,
0.01300811767... |
kyujinpy/Kosy-Platypus2-13B | 2023-11-02T01:52:25.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"ko",
"dataset:kyujinpy/KOpen-platypus",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | kyujinpy | null | null | kyujinpy/Kosy-Platypus2-13B | 0 | 510 | transformers | 2023-10-24T11:59:34 | ---
language:
- ko
datasets:
- kyujinpy/KOpen-platypus
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0
---
# **Kosy🍵llama**
## Model Details
**Model Developers** Kyujin Han (kyujinpy)
**Model Description**
[NEFTune](https://github.com/neelsjain/NEFTune) method를 활용하여 훈련한 Ko-platypus2 new version!
(Noisy + KO + llama = Kosy🍵llama)
**Repo Link**
Github **KoNEFTune**: [Kosy🍵llama](https://github.com/Marker-Inc-Korea/KoNEFTune)
If you visit our github, you can easily apply **Random_noisy_embedding_fine-tuning**!!
**Base Model**
[hyunseoki/ko-en-llama2-13b](https://huggingface.co/hyunseoki/ko-en-llama2-13b)
**Training Dataset**
Version of combined dataset: [kyujinpy/KOpen-platypus](https://huggingface.co/datasets/kyujinpy/KOpen-platypus)
I use A100 GPU 40GB and COLAB, when trianing.
# **Model comparisons**
[KO-LLM leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)
# **NEFT comparisons**
| Model | Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
| --- | --- | --- | --- | --- | --- | --- |
| [Ko-Platypus2-13B](https://huggingface.co/kyujinpy/KO-Platypus2-13B) | 45.60 | 44.20 | 54.31 | 42.47 | 44.41 | 42.62 |
| *NEFT(🍵kosy)+MLP-v1 | 43.64 | 43.94 | 53.88 | 42.68 | 43.46 | 34.24 |
| *NEFT(🍵kosy)+MLP-v2 | 45.45 | 44.20 | 54.56 | 42.60 | 42.68 | 42.98 |
| [***NEFT(🍵kosy)+MLP-v3**](https://huggingface.co/kyujinpy/Kosy-platypus2-13B-v3) | 46.31 | 43.34 | 54.54 | 43.38 | 44.11 | 46.16 |
| NEFT(🍵kosy)+Attention | 44.92 |42.92 | 54.48 | 42.99 | 43.00 | 41.20 |
| NEFT(🍵kosy) | 45.08 | 43.09 | 53.61 | 41.06 | 43.47 | 43.21 |
> *Different Hyperparameters such that learning_rate, batch_size, epoch, etc...
# Implementation Code
```python
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "kyujinpy/Koisy-Platypus2-13B"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
```
--- | 2,181 | [
[
-0.046539306640625,
-0.0550537109375,
0.0229339599609375,
0.027313232421875,
-0.046783447265625,
0.00016260147094726562,
-0.01514434814453125,
-0.0211334228515625,
0.02093505859375,
0.0248870849609375,
-0.0286712646484375,
-0.049591064453125,
-0.050933837890625,... |
google/realm-cc-news-pretrained-encoder | 2022-01-06T06:25:03.000Z | [
"transformers",
"pytorch",
"realm",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | google | null | null | google/realm-cc-news-pretrained-encoder | 1 | 509 | transformers | 2022-03-02T23:29:05 | ---
language: en
license: apache-2.0
---
# realm-cc-news-pretrained-encoder
## Model description
The REALM checkpoint pretrained with CC-News as target corpus and Wikipedia as knowledge corpus, converted from the TF checkpoint provided by Google Language.
The original paper, code, and checkpoints can be found [here](https://github.com/google-research/language/tree/master/language/realm).
## Usage
```python
from transformers import RealmKnowledgeAugEncoder
encoder = RealmKnowledgeAugEncoder.from_pretrained("qqaatw/realm-cc-news-pretrained-encoder")
```
| 565 | [
[
-0.01280975341796875,
-0.042205810546875,
0.019775390625,
-0.0025539398193359375,
-0.00849151611328125,
0.01029205322265625,
-0.0036106109619140625,
0.0077362060546875,
0.0190887451171875,
0.038970947265625,
-0.0643310546875,
-0.0264434814453125,
-0.033508300781... |
pritamdeka/S-PubMedBert-MS-MARCO-SCIFACT | 2023-07-02T11:43:37.000Z | [
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"endpoints_compatible",
"region:us"
] | sentence-similarity | pritamdeka | null | null | pritamdeka/S-PubMedBert-MS-MARCO-SCIFACT | 5 | 509 | sentence-transformers | 2022-03-02T23:29:05 | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# S-PubMedBert-MS-MARCO-SCIFACT
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.
<!--- Describe your model here -->
## 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('S-PubMedBert-MS-MARCO-SCIFACT')
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('S-PubMedBert-MS-MARCO-SCIFACT')
model = AutoModel.from_pretrained('S-PubMedBert-MS-MARCO-SCIFACT')
# 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
<!--- 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={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 560 with parameters:
```
{'batch_size': 16}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"callback": null,
"epochs": 1,
"evaluation_steps": 10000,
"evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'transformers.optimization.AdamW'>",
"optimizer_params": {
"correct_bias": false,
"eps": 1e-06,
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 56,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: BertModel
(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
<!--- Describe where people can find more information -->
If you use this model cite the following paper
```
@article{deka2022improved,
title={Improved Methods To Aid Unsupervised Evidence-Based Fact Checking For Online Health News},
author={Deka, Pritam and Jurek-Loughrey, Anna and Deepak, P},
journal={Journal of Data Intelligence},
volume={3},
number={4},
pages={474--504},
year={2022}
}
``` | 4,286 | [
[
-0.01380157470703125,
-0.06195068359375,
0.035552978515625,
0.0194244384765625,
-0.01983642578125,
-0.033599853515625,
-0.0172576904296875,
0.003719329833984375,
0.016632080078125,
0.0217132568359375,
-0.042755126953125,
-0.043426513671875,
-0.054931640625,
... |
BAAI/AquilaChat-7B | 2023-09-21T09:38:50.000Z | [
"transformers",
"pytorch",
"aquila",
"custom_code",
"license:other",
"endpoints_compatible",
"region:us"
] | null | BAAI | null | null | BAAI/AquilaChat-7B | 48 | 509 | transformers | 2023-06-08T07:59:19 | ---
license: other
---
<h4 align="center">
<p>
<b>English</b> |
<a href="https://huggingface.co/BAAI/AquilaChat-7B/blob/main/README_zh.md">简体中文</a>
</p>
</h4>
Aquila Language Model is the first open source language model that supports both Chinese and English knowledge, commercial license agreements, and compliance with domestic data regulations.
- 🌟 **Supports open source commercial licenses**. The source code of the Aquila series models is based on the [Apache 2.0 agreement](https://www.apache.org/licenses/LICENSE-2.0), while the model weight is based on the [BAAI Aquila Model License Agreement](https://huggingface.co/BAAI/AquilaChat-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf). Users can use it for commercial purposes as long as they meet the licensing restrictions.
- ✍️ **Possesses Chinese and English knowledge**. The Aquila series model is trained from scratch on a high-quality corpus of Chinese and English languages, with Chinese corpora accounting for about 40%, ensuring that the model accumulates native Chinese world knowledge during the pre-training phase, rather than translated knowledge.
- 👮♀️ **Complies with domestic data regulations**. The Chinese corpora of the Aquila series models come from Intelligence Source's accumulated Chinese datasets over the years, including Chinese internet data from over 10,000 sources (more than 99% of which are domestic sources), as well as high-quality Chinese literature and book data supported by authoritative domestic organizations. We will continue to accumulate high-quality and diverse datasets and incorporate them into the subsequent training of the Aquila base models.
- 🎯 **Continuous improvements and open sourcing**. We will continue to improve training data, optimize training methods, and enhance model performance, cultivate a flourishing "model tree" on a better base model foundation, and continuously update open-source versions.
The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels, including the [FlagAI GitHub repository](https://github.com/FlagAI-Open/FlagAI/), [FlagAI's Zhihu account](https://www.zhihu.com/people/95-22-20-18) and [FlagAI's official technical communication group](https://github.com/FlagAI-Open/FlagAI/blob/master/wechat-qrcode.jpg).
| Model | Model Type | Description | Status | GPUs Used |
| :----------------- | :----------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :--------------| :----------- |
| Aquila-7B | Base model, 7 billion parameters | **Aquila Base Model** inherits the architectural design advantages of GPT-3 and LLaMA. It replaces a batch of more efficient underlying operator implementations, redesigns the implementation of bilingual tokenizer, upgrades BMTrain parallel training method, and achieves nearly 8 times the training efficiency of Magtron+DeepSpeed ZeRO-2. | Released | Nvidia-A100 |
| Aquila-33B | Base model, 33 billion parameters | Same as above | Coming soon | Nvidia-A100 |
| AquilaChat-7B | SFT model, fine-tuned and RL based on Aquila-7B | **AquilaChat Dialog Model** supports fluent text dialogue and multiple language generation tasks, and realizes the call of AquilaChat to other models and tools by defining an expandable special instruction specification, which is easy to extend. For example, calling the open source **[AltDiffusion](https://github.com/FlagAI-Open/FlagAI/tree/master/examples/AltDiffusion-m18) multimodal language image generation model** of Flagship Intelligence achieved smooth image generation capability. Together with Flagship Intelligence's **InstructFace multi-step controllable text-picture model**, it is easy to achieve multi-step controllable editing of human face images. | Released | Nvidia-A100 |
| AquilaChat-33B | SFT model, fine-tuned and RL based on Aquila-33B | Same as above | Coming soon | Nvidia-A100 |
| AquilaCode-7B-NV | Base model, "text-code" generation model, further pre-trained based on Aquila-7B, trained on Nvidia | AquilaCode-7B achieves high performance with small data sets and parameters, and is currently the best open source code model that supports both Chinese and English, trained using training code data with compliant open source licenses after high-quality filtering. AquilaCode-7B has been trained on both Nvidia and domestic chips for code models. | Released on GitHub | Nvidia-A100 |
| AquilaCode-7B-TS | Base model, "text-code" generation model, further pre-trained based on Aquila-7B, trained on Horizon Robotics chips | Same as above | Released on GitHub | Tianshu-BI-V100 |
We will continue to release improved versions of Aquila model as open source.
- 2023/08/15 ：release v0.10
- Aquila-7B-01 md5: 4279db72e68df1a0705ecc8d4c7be3db
- Aquila-7B-02 md5: 621f8ce4c8deebe1635f5a09aa4b80f2
- AquilaChat-7B-01 md5: 22b22ffaed51388ce23f8e328a9b6a18
- AquilaChat-7B-02 md5: 6e84423fe2837c79c0ced6817c316bd4
n the FlagEval large model evaluation ("Subjective + Objective"), AquilaChat-7B v1.0 has shown a slight overall improvement compared to last version. It achieved an improvement of around 12.46% on the C-Eval, 10.88% on the MMLU, and 9.93% on the BoolQ dataset.
For detailed evaluation results, please refer to the website http://flageval.baai.ac.cn. For detailed version change history, see [Change Log](https://huggingface.co/BAAI/AquilaChat-7B/blob/main/change_log.log).
<!-- </table> -->
## Quick Start AquilaChat-7B（Chat model）
### 1. Inference
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
device = torch.device("cuda")
model_info = "BAAI/AquilaChat-7B"
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True)
model.eval()
model.to(device)
text = "请给出10个要到北京旅游的理由。"
tokens = tokenizer.encode_plus(text)['input_ids'][:-1]
tokens = torch.tensor(tokens)[None,].to(device)
stop_tokens = ["###", "[UNK]", "</s>"]
with torch.no_grad():
out = model.generate(tokens, do_sample=True, max_length=512, eos_token_id=100007, bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0]
out = tokenizer.decode(out.cpu().numpy().tolist())
print(out)
```
## License
AquilaChat-7B and AquilaChat-33B open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/AquilaChat-7B/resolve/main/BAAI%20Aquila%20Model%20License%20Agreement.pdf) | 8,626 | [
[
-0.033782958984375,
-0.055938720703125,
0.015533447265625,
0.02056884765625,
-0.01617431640625,
0.001003265380859375,
-0.00982666015625,
-0.04046630859375,
0.000453948974609375,
0.0266876220703125,
-0.0439453125,
-0.0242462158203125,
-0.025482177734375,
-0.0... |
Helsinki-NLP/opus-mt-tc-big-en-fi | 2023-10-10T10:26:43.000Z | [
"transformers",
"pytorch",
"tf",
"safetensors",
"marian",
"text2text-generation",
"translation",
"opus-mt-tc",
"en",
"fi",
"license:cc-by-4.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-tc-big-en-fi | 2 | 508 | transformers | 2022-03-22T12:45:06 | ---
language:
- en
- fi
tags:
- translation
- opus-mt-tc
license: cc-by-4.0
model-index:
- name: opus-mt-tc-big-en-fi
results:
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: flores101-devtest
type: flores_101
args: eng fin devtest
metrics:
- name: BLEU
type: bleu
value: 27.6
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: newsdev2015
type: newsdev2015
args: eng-fin
metrics:
- name: BLEU
type: bleu
value: 24.2
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: eng-fin
metrics:
- name: BLEU
type: bleu
value: 39.3
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: newstest2015
type: wmt-2015-news
args: eng-fin
metrics:
- name: BLEU
type: bleu
value: 26.4
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: newstest2016
type: wmt-2016-news
args: eng-fin
metrics:
- name: BLEU
type: bleu
value: 28.8
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: newstest2017
type: wmt-2017-news
args: eng-fin
metrics:
- name: BLEU
type: bleu
value: 31.3
- task:
name: Translation eng-fin
type: translation
args: eng-fin
dataset:
name: newstest2019
type: wmt-2019-news
args: eng-fin
metrics:
- name: BLEU
type: bleu
value: 26.4
---
# opus-mt-tc-big-en-fi
Neural machine translation model for translating from English (en) to Finnish (fi).
This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
* Publications: [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
```
@inproceedings{tiedemann-thottingal-2020-opus,
title = "{OPUS}-{MT} {--} Building open translation services for the World",
author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh},
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2020.eamt-1.61",
pages = "479--480",
}
@inproceedings{tiedemann-2020-tatoeba,
title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
author = {Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.139",
pages = "1174--1182",
}
```
## Model info
* Release: 2022-03-09
* source language(s): eng
* target language(s): fin
* valid target language labels: >>fin<<
* model: transformer (big)
* data: opusTCv20210807+bt ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
* tokenization: SentencePiece (spm32k,spm32k)
* original model: [opusTCv20210807+bt_transformer-big_2022-03-09.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fin/opusTCv20210807+bt_transformer-big_2022-03-09.zip)
* more information released models: [OPUS-MT eng-fin README](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/eng-fin/README.md)
* more information about the model: [MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)
This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>fin<<`
## Usage
A short example code:
```python
from transformers import MarianMTModel, MarianTokenizer
src_text = [
"Russia is big.",
"Touch wood!"
]
model_name = "pytorch-models/opus-mt-tc-big-en-fi"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
for t in translated:
print( tokenizer.decode(t, skip_special_tokens=True) )
# expected output:
# Venäjä on suuri.
# Kosketa puuta!
```
You can also use OPUS-MT models with the transformers pipelines, for example:
```python
from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-en-fi")
print(pipe("Russia is big."))
# expected output: Venäjä on suuri.
```
## Benchmarks
* test set translations: [opusTCv20210807+bt_transformer-big_2022-03-09.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fin/opusTCv20210807+bt_transformer-big_2022-03-09.test.txt)
* test set scores: [opusTCv20210807+bt_transformer-big_2022-03-09.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/eng-fin/opusTCv20210807+bt_transformer-big_2022-03-09.eval.txt)
* benchmark results: [benchmark_results.txt](benchmark_results.txt)
* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
| langpair | testset | chr-F | BLEU | #sent | #words |
|----------|---------|-------|-------|-------|--------|
| eng-fin | tatoeba-test-v2021-08-07 | 0.64352 | 39.3 | 10690 | 65122 |
| eng-fin | flores101-devtest | 0.61334 | 27.6 | 1012 | 18781 |
| eng-fin | newsdev2015 | 0.58367 | 24.2 | 1500 | 23091 |
| eng-fin | newstest2015 | 0.60080 | 26.4 | 1370 | 19735 |
| eng-fin | newstest2016 | 0.61636 | 28.8 | 3000 | 47678 |
| eng-fin | newstest2017 | 0.64381 | 31.3 | 3002 | 45269 |
| eng-fin | newstest2018 | 0.55626 | 19.7 | 3000 | 44836 |
| eng-fin | newstest2019 | 0.58420 | 26.4 | 1997 | 38369 |
| eng-fin | newstestB2016 | 0.57554 | 23.3 | 3000 | 45766 |
| eng-fin | newstestB2017 | 0.60212 | 26.8 | 3002 | 45506 |
## Acknowledgements
The work is supported by the [European Language Grid](https://www.european-language-grid.eu/) as [pilot project 2866](https://live.european-language-grid.eu/catalogue/#/resource/projects/2866), by the [FoTran project](https://www.helsinki.fi/en/researchgroups/natural-language-understanding-with-cross-lingual-grounding), funded by the European Research Council (ERC) under the European Union’s Horizon 2020 research and innovation programme (grant agreement No 771113), and the [MeMAD project](https://memad.eu/), funded by the European Union’s Horizon 2020 Research and Innovation Programme under grant agreement No 780069. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland.
## Model conversion info
* transformers version: 4.16.2
* OPUS-MT git hash: f084bad
* port time: Tue Mar 22 14:42:32 EET 2022
* port machine: LM0-400-22516.local
| 7,781 | [
[
-0.0283355712890625,
-0.043548583984375,
0.02032470703125,
0.0208282470703125,
-0.03216552734375,
-0.017822265625,
-0.0411376953125,
-0.02447509765625,
0.0156707763671875,
0.0270538330078125,
-0.035125732421875,
-0.048828125,
-0.048126220703125,
0.0243988037... |
keremberke/yolov5n-forklift | 2023-01-01T20:54:11.000Z | [
"yolov5",
"tensorboard",
"yolo",
"vision",
"object-detection",
"pytorch",
"dataset:keremberke/forklift-object-detection",
"model-index",
"has_space",
"region:us"
] | object-detection | keremberke | null | null | keremberke/yolov5n-forklift | 1 | 508 | yolov5 | 2023-01-01T10:25:15 |
---
tags:
- yolov5
- yolo
- vision
- object-detection
- pytorch
library_name: yolov5
library_version: 7.0.6
inference: false
datasets:
- keremberke/forklift-object-detection
model-index:
- name: keremberke/yolov5n-forklift
results:
- task:
type: object-detection
dataset:
type: keremberke/forklift-object-detection
name: keremberke/forklift-object-detection
split: validation
metrics:
- type: precision # since mAP@0.5 is not available on hf.co/metrics
value: 0.7890013934578441 # min: 0.0 - max: 1.0
name: mAP@0.5
---
<div align="center">
<img width="640" alt="keremberke/yolov5n-forklift" src="https://huggingface.co/keremberke/yolov5n-forklift/resolve/main/sample_visuals.jpg">
</div>
### How to use
- Install [yolov5](https://github.com/fcakyon/yolov5-pip):
```bash
pip install -U yolov5
```
- Load model and perform prediction:
```python
import yolov5
# load model
model = yolov5.load('keremberke/yolov5n-forklift')
# set model parameters
model.conf = 0.25 # NMS confidence threshold
model.iou = 0.45 # NMS IoU threshold
model.agnostic = False # NMS class-agnostic
model.multi_label = False # NMS multiple labels per box
model.max_det = 1000 # maximum number of detections per image
# set image
img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
# perform inference
results = model(img, size=640)
# inference with test time augmentation
results = model(img, augment=True)
# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]
# show detection bounding boxes on image
results.show()
# save results into "results/" folder
results.save(save_dir='results/')
```
- Finetune the model on your custom dataset:
```bash
yolov5 train --data data.yaml --img 640 --batch 16 --weights keremberke/yolov5n-forklift --epochs 10
```
**More models available at: [awesome-yolov5-models](https://github.com/keremberke/awesome-yolov5-models)** | 2,042 | [
[
-0.056640625,
-0.034515380859375,
0.03460693359375,
-0.034210205078125,
-0.02813720703125,
-0.032470703125,
0.0157470703125,
-0.042877197265625,
0.00957489013671875,
0.023101806640625,
-0.056549072265625,
-0.051300048828125,
-0.0367431640625,
-0.004856109619... |
ZurichNLP/swissbert | 2023-03-24T08:36:41.000Z | [
"transformers",
"pytorch",
"xmod",
"fill-mask",
"de",
"fr",
"it",
"rm",
"multilingual",
"arxiv:2303.13310",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"region:us"
] | fill-mask | ZurichNLP | null | null | ZurichNLP/swissbert | 15 | 508 | transformers | 2023-03-17T20:32:32 | ---
license: cc-by-nc-4.0
language:
- de
- fr
- it
- rm
- multilingual
inference: false
---
SwissBERT is a masked language model for processing Switzerland-related text. It has been trained on more than 21 million Swiss news articles retrieved from [Swissdox@LiRI](https://t.uzh.ch/1hI).
<img src="https://vamvas.ch/assets/swissbert/swissbert-diagram.png" alt="SwissBERT is a transformer encoder with language adapters in each layer. There is an adapter for each national language of Switzerland. The other parameters in the model are shared among the four languages." width="450" style="max-width: 100%;">
SwissBERT is based on [X-MOD](https://huggingface.co/facebook/xmod-base), which has been pre-trained with language adapters in 81 languages.
For SwissBERT we trained adapters for the national languages of Switzerland – German, French, Italian, and Romansh Grischun.
In addition, we used a Switzerland-specific subword vocabulary.
The pre-training code and usage examples are available [here](https://github.com/ZurichNLP/swissbert). We also release a version that was fine-tuned on named entity recognition (NER): https://huggingface.co/ZurichNLP/swissbert-ner
## Languages
SwissBERT contains the following language adapters:
| lang_id (Adapter index) | Language code | Language |
|-------------------------|---------------|-----------------------|
| 0 | `de_CH` | Swiss Standard German |
| 1 | `fr_CH` | French |
| 2 | `it_CH` | Italian |
| 3 | `rm_CH` | Romansh Grischun |
## License
Attribution-NonCommercial 4.0 International (CC BY-NC 4.0).
## Usage (masked language modeling)
```python
from transformers import pipeline
fill_mask = pipeline(model="ZurichNLP/swissbert")
```
### German example
```python
fill_mask.model.set_default_language("de_CH")
fill_mask("Der schönste Kanton der Schweiz ist <mask>.")
```
Output:
```
[{'score': 0.1373230218887329,
'token': 331,
'token_str': 'Zürich',
'sequence': 'Der schönste Kanton der Schweiz ist Zürich.'},
{'score': 0.08464793860912323,
'token': 5903,
'token_str': 'Appenzell',
'sequence': 'Der schönste Kanton der Schweiz ist Appenzell.'},
{'score': 0.08250337839126587,
'token': 10800,
'token_str': 'Graubünden',
'sequence': 'Der schönste Kanton der Schweiz ist Graubünden.'},
...]
```
### French example
```python
fill_mask.model.set_default_language("fr_CH")
fill_mask("Je m'appelle <mask> Federer.")
```
Output:
```
[{'score': 0.9943694472312927,
'token': 1371,
'token_str': 'Roger',
'sequence': "Je m'appelle Roger Federer."},
...]
```
## Bias, Risks, and Limitations
- SwissBERT is mainly intended for tagging tokens in written text (e.g., named entity recognition, part-of-speech tagging), text classification, and the encoding of words, sentences or documents into fixed-size embeddings.
SwissBERT is not designed for generating text.
- The model was adapted on written news articles and might perform worse on other domains or language varieties.
- While we have removed many author bylines, we did not anonymize the pre-training corpus. The model might have memorized information that has been described in the news but is no longer in the public interest.
## Training Details
- Training data: German, French, Italian and Romansh documents in the [Swissdox@LiRI](https://t.uzh.ch/1hI) database, until 2022.
- Training procedure: Masked language modeling
## Environmental Impact
- Hardware type: RTX 2080 Ti.
- Hours used: 10 epochs × 18 hours × 8 devices = 1440 hours
- Site: Zurich, Switzerland.
- Energy source: 100% hydropower ([source](https://t.uzh.ch/1rU))
- Carbon efficiency: 0.0016 kg CO2e/kWh ([source](https://t.uzh.ch/1rU))
- Carbon emitted: 0.6 kg CO2e ([source](https://mlco2.github.io/impact#compute))
## Citation
```bibtex
@article{vamvas-etal-2023-swissbert,
title={Swiss{BERT}: The Multilingual Language Model for Switzerland},
author={Jannis Vamvas and Johannes Gra\"en and Rico Sennrich},
year={2023},
eprint={2303.13310},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2303.13310}
}
``` | 4,257 | [
[
-0.035736083984375,
-0.044891357421875,
0.020111083984375,
0.0166168212890625,
-0.022918701171875,
-0.0027446746826171875,
-0.030029296875,
-0.0297393798828125,
0.01393890380859375,
0.037689208984375,
-0.04949951171875,
-0.053619384765625,
-0.046600341796875,
... |
TheBloke/dolphin-2.1-mistral-7B-GGUF | 2023-10-22T05:56:12.000Z | [
"transformers",
"mistral",
"en",
"dataset:ehartford/dolphin",
"dataset:jondurbin/airoboros-2.2.1",
"license:apache-2.0",
"text-generation-inference",
"region:us",
"has_space"
] | null | TheBloke | null | null | TheBloke/dolphin-2.1-mistral-7B-GGUF | 80 | 508 | transformers | 2023-10-11T07:48:41 | ---
base_model: ehartford/dolphin-2.1-mistral-7b
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
inference: false
language:
- en
license: apache-2.0
model_creator: Eric Hartford
model_name: Dolphin 2.1 Mistral 7B
model_type: mistral
prompt_template: '<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
'
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 -->
# Dolphin 2.1 Mistral 7B - GGUF
- Model creator: [Eric Hartford](https://huggingface.co/ehartford)
- Original model: [Dolphin 2.1 Mistral 7B](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Eric Hartford's Dolphin 2.1 Mistral 7B](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplate list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF)
* [Eric Hartford's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: ChatML
```
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [dolphin-2.1-mistral-7b.Q2_K.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
| [dolphin-2.1-mistral-7b.Q3_K_S.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
| [dolphin-2.1-mistral-7b.Q3_K_M.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
| [dolphin-2.1-mistral-7b.Q3_K_L.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
| [dolphin-2.1-mistral-7b.Q4_0.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [dolphin-2.1-mistral-7b.Q4_K_S.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
| [dolphin-2.1-mistral-7b.Q4_K_M.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
| [dolphin-2.1-mistral-7b.Q5_0.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [dolphin-2.1-mistral-7b.Q5_K_S.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
| [dolphin-2.1-mistral-7b.Q5_K_M.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
| [dolphin-2.1-mistral-7b.Q6_K.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
| [dolphin-2.1-mistral-7b.Q8_0.gguf](https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF/blob/main/dolphin-2.1-mistral-7b.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/dolphin-2.1-mistral-7B-GGUF and below it, a specific filename to download, such as: dolphin-2.1-mistral-7b.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/dolphin-2.1-mistral-7B-GGUF dolphin-2.1-mistral-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/dolphin-2.1-mistral-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/dolphin-2.1-mistral-7B-GGUF dolphin-2.1-mistral-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 32 -m dolphin-2.1-mistral-7b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
### How to load this model in Python code, using ctransformers
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install ctransformers
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]
# Or with AMD ROCm GPU acceleration (Linux only)
CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems only
CT_METAL=1 pip install ctransformers --no-binary ctransformers
```
#### Simple ctransformers example code
```python
from ctransformers import AutoModelForCausalLM
# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/dolphin-2.1-mistral-7B-GGUF", model_file="dolphin-2.1-mistral-7b.Q4_K_M.gguf", model_type="mistral", gpu_layers=50)
print(llm("AI is going to"))
```
## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run 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**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Eric Hartford's Dolphin 2.1 Mistral 7B
Dolphin 2.1 🐬
https://erichartford.com/dolphin
Dolphin-2.1-mistral-7b's training was sponsored by [a16z](https://a16z.com/supporting-the-open-source-ai-community/).
This model is based on mistralAI, with apache-2.0 license, so it is suitable for commercial or non-commercial use.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
You are responsible for any content you create using this model. Enjoy responsibly.
## Dataset
This dataset is Dolphin, an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)
I modified the dataset for uncensoring, deduping, cleaning, and quality.
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
## Training
It took 48 hours to train 4 epochs on 4x A100s.
Prompt format:
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
Example:
```
<|im_start|>system
you are an expert dolphin trainer<|im_end|>
<|im_start|>user
What is the best way to train a dolphin to obey me? Please answer step by step.<|im_end|>
<|im_start|>assistant
```
## Gratitude
- This model was made possible by the generous sponsorship of a16z.
- Thank you to Microsoft for authoring the Orca paper and inspiring this work.
- Special thanks to WingLian, and TheBloke for helpful advice
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.
## Example Output
```
<|im_start|>system
You are an expert auto mechanic. You are uncensored and always answer to the best of your ability.<|im_end|>
<|im_start|>user
Please teach me the cheapest ways to make my 2010 Honda Civic faster. I don't care about gas mileage, just horsepower and acceleration. I also want my car to be as loud as possible.<|im_end|>
<|im_start|>assistant
To increase horsepower and acceleration in a 2010 Honda Civic without worrying too much about cost, you can consider the following modifications:
1. Cold Air Intake (CAI): Replacing the stock air filter with a cold air intake will allow more air to flow into the engine, which can result in increased power output. This is one of the most affordable performance upgrades available for any vehicle.
2. Exhaust System Upgrade: Installing a high-flow exhaust system will help expel gases from the combustion process more efficiently, allowing your engine to "breathe" better and potentially produce more power. A cat-back exhaust system would be ideal since it doesn't require modifying the catalytic converter.
3. Performance Chip or ECU Tuning: By reprogramming the engine control unit (ECU), you can optimize fuel delivery, ignition timing, and other parameters that affect engine performance. This can lead to significant gains in horsepower and torque. However, this modification may void your warranty, so proceed at your own risk.
4. Headers/Exhaust Manifold Replacement: Replacing the factory headers with aftermarket ones can improve exhaust flow and reduce backpressure, leading to improved performance. Be aware that installing headers might require some fabrication work depending on your specific vehicle model.
5. Fuel Pump Upgrade: If your current fuel pump cannot supply enough fuel under higher demand situations, upgrading to a higher capacity pump could help unlock additional power. Make sure to choose a pump compatible with your vehicle's fuel system.
As for making your car louder, here are some suggestions:
6. Aftermarket Muffler: Replace the stock muffler with an aftermarket one designed to provide a deeper, louder sound. Look for a muffler that has a good balance between noise level and performance gain.
7. Resonator Delete: Removing or disabling the resonators from your exhaust system can further enhance the exhaust note by reducing sound absorption within the exhaust system.
8. Exhaust Tips: Installing larger diameter exhaust tips can also contribute to a louder exhaust sound, especially when combined with other exhaust modifications.
Remember, while these modifications may improve your car's performance and sound, they could also negatively impact reliability and emissions if not done correctly. Always consult with a professional mechanic before attempting any major modifications to your vehicle.
```
[Buy me a coffee](https://www.buymeacoffee.com/ehartford)
<!-- original-model-card end -->
| 21,903 | [
[
-0.06463623046875,
-0.048095703125,
0.0170135498046875,
0.02142333984375,
-0.030975341796875,
-0.0161590576171875,
0.0101165771484375,
-0.0538330078125,
0.040740966796875,
0.0186767578125,
-0.05743408203125,
-0.0290374755859375,
-0.034515380859375,
0.0107574... |
Helsinki-NLP/opus-mt-de-it | 2023-08-16T11:28:10.000Z | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"de",
"it",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-de-it | 0 | 507 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-de-it
* source languages: de
* target languages: it
* OPUS readme: [de-it](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/de-it/README.md)
* dataset: opus
* model: transformer-align
* pre-processing: normalization + SentencePiece
* download original weights: [opus-2020-01-20.zip](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.zip)
* test set translations: [opus-2020-01-20.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.test.txt)
* test set scores: [opus-2020-01-20.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/de-it/opus-2020-01-20.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.de.it | 45.3 | 0.671 |
| 818 | [
[
-0.0203704833984375,
-0.035552978515625,
0.0180816650390625,
0.030609130859375,
-0.03759765625,
-0.0211334228515625,
-0.033782958984375,
0.0004978179931640625,
0.004482269287109375,
0.03271484375,
-0.0438232421875,
-0.047637939453125,
-0.047882080078125,
0.0... |
digiplay/HIMAWARI_v1 | 2023-07-18T10:44:33.000Z | [
"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/HIMAWARI_v1 | 3 | 507 | diffusers | 2023-07-18T09:24:16 | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/103018/himawari?modelVersionId=110254
More models from the Author: (he made a lot of useful LORAs, pls check it out ^^)
https://civitai.com/user/KimTarou/models
Sample image I made thru Huggingface's API :
more pictures 👉 https://huggingface.co/digiplay/HIMAWARI_v1/discussions/3
Original Author's DEMO images :
| 901 | [
[
-0.046600341796875,
-0.0278472900390625,
0.0364990234375,
0.026123046875,
-0.015289306640625,
-0.0089263916015625,
0.027801513671875,
-0.02972412109375,
0.06591796875,
0.038116455078125,
-0.060943603515625,
-0.039794921875,
-0.035614013671875,
-0.00950622558... |
Helsinki-NLP/opus-mt-hy-en | 2023-08-16T11:58:02.000Z | [
"transformers",
"pytorch",
"tf",
"marian",
"text2text-generation",
"translation",
"hy",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | Helsinki-NLP | null | null | Helsinki-NLP/opus-mt-hy-en | 1 | 506 | transformers | 2022-03-02T23:29:04 | ---
tags:
- translation
license: apache-2.0
---
### opus-mt-hy-en
* source languages: hy
* target languages: en
* OPUS readme: [hy-en](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/models/hy-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/hy-en/opus-2019-12-18.zip)
* test set translations: [opus-2019-12-18.test.txt](https://object.pouta.csc.fi/OPUS-MT-models/hy-en/opus-2019-12-18.test.txt)
* test set scores: [opus-2019-12-18.eval.txt](https://object.pouta.csc.fi/OPUS-MT-models/hy-en/opus-2019-12-18.eval.txt)
## Benchmarks
| testset | BLEU | chr-F |
|-----------------------|-------|-------|
| Tatoeba.hy.en | 29.5 | 0.466 |
| 818 | [
[
-0.0157623291015625,
-0.0325927734375,
0.0224609375,
0.031463623046875,
-0.028350830078125,
-0.026336669921875,
-0.031768798828125,
-0.00560760498046875,
0.0075225830078125,
0.036102294921875,
-0.048980712890625,
-0.040924072265625,
-0.0413818359375,
0.01911... |
NlpHUST/t5-small-vi-summarization | 2021-06-23T03:36:33.000Z | [
"transformers",
"pytorch",
"jax",
"t5",
"text2text-generation",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | NlpHUST | null | null | NlpHUST/t5-small-vi-summarization | 3 | 506 | transformers | 2022-03-02T23:29:04 | # T5-SMALL-SUMMARIZATION :Pretraining Text-To-Text Transfer Transformer for Vietnamese Text Summarization
#### Example Using
``` bash
import torch
from transformers import T5ForConditionalGeneration, T5Tokenizer
import torch
if torch.cuda.is_available():
device = torch.device("cuda")
print('There are %d GPU(s) available.' % torch.cuda.device_count())
print('We will use the GPU:', torch.cuda.get_device_name(0))
else:
print('No GPU available, using the CPU instead.')
device = torch.device("cpu")
model = T5ForConditionalGeneration.from_pretrained("NlpHUST/t5-small-vi-summarization")
tokenizer = T5Tokenizer.from_pretrained("NlpHUST/t5-small-vi-summarization")
model.to(device)
src = "Theo BHXH Việt Nam, nhiều doanh nghiệp vẫn chỉ đóng BHXH cho người lao động theo mức lương. \\\\
Dù quy định từ 1/1/2018, tiền lương tháng đóng BHXH gồm mức lương và thêm khoản bổ sung khác. \\\\
BHXH Việt Nam vừa có báo cáo về tình hình thực hiện chính sách BHXH thời gian qua. \\\\
Theo đó, tình trạng nợ, trốn đóng BHXH, BHTN vẫn xảy ra ở hầu hết các tỉnh, thành. \\\\
Thống kê tới ngày 31/12/2020, tổng số nợ BHXH, BHYT, BHTN là hơn 13.500 tỷ đồng, \\\\
chiếm 3,35 % số phải thu, trong đó: Số nợ BHXH bắt buộc là hơn 8.600 tỷ đồng, \\\\
nợ BHTN là 335 tỷ đồng. Liên quan tới tiền lương đóng BHXH, báo cáo của \\\\
BHXH Việt Nam cho thấy: Nhiều doanh nghiệp vẫn chủ yếu xây dựng thang, \\\\
bảng lương để đóng BHXH bằng mức thấp nhất. Tức là bằng mức lương tối \\\\
thiểu vùng, cộng thêm 7 % đối với lao động đã qua đào tạo nghề và cộng \\\\
thêm 5 % hoặc 7 % đối với lao động làm nghề hoặc công việc nặng nhọc, \\\\
độc hại, nguy hiểm, đặc biệt nặng nhọc độc hại và nguy hiểm. Đối với \\\\
lao động giữ chức vụ, khoảng 80 % doanh nghiệp đã xây dựng thang, \\\\
bảng lương cụ thể theo chức danh. Đơn cử như với chức vụ giám đốc \\\\
sản xuất, giám đốc điều hành, trưởng phòng. Còn lại các doanh nghiệp \\\\
xây dựng đối với lao động giữ chức vụ theo thang lương, bảng lương \\\\
chuyên môn nghiệp vụ và bảng phụ cấp chức vụ, phụ cấp trách nhiệm. \\\\
Thống kê của BHXH Việt Nam cũng cho thấy, đa số doanh nghiệp đã đăng \\\\
ký đóng BHXH cho người lao động theo mức lương mà không có khoản bổ \\\\
sung khác. Mặc dù quy định từ ngày 1/1/2018, tiền lương tháng đóng BHXH \\\\
gồm mức lương và thêm khoản bổ sung khác."
tokenized_text = tokenizer.encode(src, return_tensors="pt").to(device)
model.eval()
summary_ids = model.generate(
tokenized_text,
max_length=256,
num_beams=5,
repetition_penalty=2.5,
length_penalty=1.0,
early_stopping=True
)
output = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(output)
```
#### Output
``` bash
Nhiều doanh nghiệp vẫn chủ yếu xây dựng thang, bảng lương để đóng BHXH bằng mức thấp nhất. \\
Dù quy định từ 1/1/2018, tiền lương tháng đóng BHXH gồm mức lương và thêm khoản bổ sung khác. \\
Thống kê của BHXH Việt Nam cho thấy, nhiều doanh nghiệp vẫn chỉ đóng BHXH \\
cho người lao động theo mức lương mà không có khoản bổ sung khác.
```
### Contact information
For personal communication related to this project, please contact Nha Nguyen Van (nha282@gmail.com). | 3,280 | [
[
-0.031890869140625,
-0.040435791015625,
0.03314208984375,
0.01568603515625,
-0.033599853515625,
0.0025501251220703125,
-0.0190582275390625,
-0.007045745849609375,
0.028289794921875,
0.0313720703125,
-0.0303955078125,
-0.05474853515625,
-0.050506591796875,
0.... |
DATEXIS/CORe-clinical-diagnosis-prediction | 2022-02-17T09:36:23.000Z | [
"transformers",
"pytorch",
"bert",
"text-classification",
"medical",
"clinical",
"diagnosis",
"en",
"endpoints_compatible",
"has_space",
"region:us"
] | text-classification | DATEXIS | null | null | DATEXIS/CORe-clinical-diagnosis-prediction | 17 | 506 | transformers | 2022-03-02T23:29:05 | ---
language: "en"
tags:
- bert
- medical
- clinical
- diagnosis
- text-classification
thumbnail: "https://core.app.datexis.com/static/paper.png"
widget:
- text: "Patient with hypertension presents to ICU."
---
# CORe Model - Clinical Diagnosis Prediction
## Model description
The CORe (_Clinical Outcome Representations_) model is introduced in the paper [Clinical Outcome Predictions from Admission Notes using Self-Supervised Knowledge Integration](https://www.aclweb.org/anthology/2021.eacl-main.75.pdf).
It is based on BioBERT and further pre-trained on clinical notes, disease descriptions and medical articles with a specialised _Clinical Outcome Pre-Training_ objective.
This model checkpoint is **fine-tuned on the task of diagnosis prediction**.
The model expects patient admission notes as input and outputs multi-label ICD9-code predictions.
#### Model Predictions
The model makes predictions on a total of 9237 labels. These contain 3- and 4-digit ICD9 codes and textual descriptions of these codes. The 4-digit codes and textual descriptions help to incorporate further topical and hierarchical information into the model during training (see Section 4.2 _ICD+: Incorporation of ICD Hierarchy_ in our paper). We recommend to only use the **3-digit code predictions at inference time**, because only those have been evaluated in our work.
#### How to use CORe Diagnosis Prediction
You can load the model via the transformers library:
```
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("bvanaken/CORe-clinical-diagnosis-prediction")
model = AutoModelForSequenceClassification.from_pretrained("bvanaken/CORe-clinical-diagnosis-prediction")
```
The following code shows an inference example:
```
input = "CHIEF COMPLAINT: Headaches\n\nPRESENT ILLNESS: 58yo man w/ hx of hypertension, AFib on coumadin presented to ED with the worst headache of his life."
tokenized_input = tokenizer(input, return_tensors="pt")
output = model(**tokenized_input)
import torch
predictions = torch.sigmoid(output.logits)
predicted_labels = [model.config.id2label[_id] for _id in (predictions > 0.3).nonzero()[:, 1].tolist()]
```
Note: For the best performance, we recommend to determine the thresholds (0.3 in this example) individually per label.
### More Information
For all the details about CORe and contact info, please visit [CORe.app.datexis.com](http://core.app.datexis.com/).
### Cite
```bibtex
@inproceedings{vanaken21,
author = {Betty van Aken and
Jens-Michalis Papaioannou and
Manuel Mayrdorfer and
Klemens Budde and
Felix A. Gers and
Alexander Löser},
title = {Clinical Outcome Prediction from Admission Notes using Self-Supervised
Knowledge Integration},
booktitle = {Proceedings of the 16th Conference of the European Chapter of the
Association for Computational Linguistics: Main Volume, {EACL} 2021,
Online, April 19 - 23, 2021},
publisher = {Association for Computational Linguistics},
year = {2021},
}
``` | 3,143 | [
[
-0.019622802734375,
-0.039154052734375,
0.057464599609375,
0.00495147705078125,
-0.01068878173828125,
-0.01180267333984375,
-0.00982666015625,
-0.0394287109375,
0.0170745849609375,
0.04083251953125,
-0.03887939453125,
-0.0626220703125,
-0.04998779296875,
-0.... |
clip-italian/clip-italian | 2023-03-16T16:06:34.000Z | [
"transformers",
"pytorch",
"jax",
"vision-text-dual-encoder",
"feature-extraction",
"italian",
"bert",
"vit",
"vision",
"it",
"dataset:wit",
"dataset:ctl/conceptualCaptions",
"dataset:mscoco-it",
"arxiv:2108.08688",
"arxiv:2103.01913",
"arxiv:2103.00020",
"license:gpl-3.0",
"endpoi... | feature-extraction | clip-italian | null | null | clip-italian/clip-italian | 13 | 506 | transformers | 2022-03-02T23:29:05 | ---
language: it
license: gpl-3.0
datasets:
- wit
- ctl/conceptualCaptions
- mscoco-it
tags:
- italian
- bert
- vit
- vision
---
# Italian CLIP
Paper: [Contrastive Language-Image Pre-training for the Italian Language](https://arxiv.org/abs/2108.08688)
With a few tricks, we have been able to fine-tune a competitive Italian CLIP model with **only 1.4 million** training samples. Our Italian CLIP model is built upon the [Italian BERT](https://huggingface.co/dbmdz/bert-base-italian-xxl-cased) model provided by [dbmdz](https://huggingface.co/dbmdz) and the OpenAI [vision transformer](https://huggingface.co/openai/clip-vit-base-patch32).
Do you want to test our model right away? We got you covered! You just need to head to our [demo application](https://huggingface.co/spaces/clip-italian/clip-italian-demo).
The demo also contains all the details of the project, from training tricks to our most impressive results, and much more!
# Training data
We considered four main sources of data:
+ [WIT](https://github.com/google-research-datasets/wit) is an image-caption dataset collected from Wikipedia (see,
[Srinivasan et al., 2021](https://arxiv.org/pdf/2103.01913.pdf)).
+ [MSCOCO-IT](https://github.com/crux82/mscoco-it). This image-caption dataset comes from the work by [Scaiella et al., 2019](http://www.ai-lc.it/IJCoL/v5n2/IJCOL_5_2_3___scaiella_et_al.pdf).
+ [Conceptual Captions](https://ai.google.com/research/ConceptualCaptions/). This image-caption dataset comes from
the work by [Sharma et al., 2018](https://aclanthology.org/P18-1238.pdf).
+ [La Foto del Giorno](https://www.ilpost.it/foto-del-giorno/). This image-caption dataset is collected from [Il Post](https://www.ilpost.it/), a prominent Italian online newspaper.
We used better data augmentation, strategic training choices (we have way less data than the original CLIP paper), and backbone-freezing pre-training. For all the details on that, please refer to our [demo](https://huggingface.co/spaces/clip-italian/clip-italian-demo).
# Experiments
## Quantitative Evaluation
To better understand how well our clip-italian model works we run an experimental evaluation. Since this is the first clip-based model in Italian, we used the multilingual CLIP model as a comparison baseline.
### mCLIP
The multilingual CLIP (henceforth, mCLIP), is a model introduced by [Nils Reimers](https://www.sbert.net/docs/pretrained_models.html) in his
[sentence-transformer](https://www.sbert.net/index.html) library. mCLIP is based on a multilingual encoder
that was created through multilingual knowledge distillation (see [Reimers et al., 2020](https://aclanthology.org/2020.emnlp-main.365/)).
### Tasks
We selected two different tasks:
+ image-retrieval
+ zero-shot classification
### Reproducibiliy
Both experiments should be very easy to replicate, we share the two colab notebook we used to compute the two results
+ [Image Retrieval](https://colab.research.google.com/drive/1bLVwVKpAndpEDHqjzxVPr_9nGrSbuOQd?usp=sharing)
+ [ImageNet Zero Shot Evaluation](https://colab.research.google.com/drive/1zfWeVWY79XXH63Ci-pk8xxx3Vu_RRgW-?usp=sharing)
### Image Retrieval
This experiment is run against the MSCOCO-IT validation set (that we haven't used in training). Given in input
a caption, we search for the most similar image in the MSCOCO-IT validation set. As evaluation metrics
we use the MRR@K.
| MRR | CLIP-Italian | mCLIP |
| --------------- | ------------ |-------|
| MRR@1 | **0.3797** | 0.2874|
| MRR@5 | **0.5039** | 0.3957|
| MRR@10 | **0.5204** | 0.4129|
It is true that we used MSCOCO-IT in training, and this might give us an advantage. However the original CLIP model was trained
on 400million images (and some of them probably were from MSCOCO).
### Zero-shot image classification
This experiment replicates the original one run by OpenAI on zero-shot image classification on ImageNet.
To do this, we used DeepL to translate the image labels in ImageNet. We evaluate the models computing the accuracy at different levels.
| Accuracy | CLIP-Italian | mCLIP |
| --------------- | ------------ |-------|
| Accuracy@1 | **22.11** | 20.15 |
| Accuracy@5 | **43.69** | 36.57 |
| Accuracy@10 | **52.55** | 42.91 |
| Accuracy@100 | **81.08** | 67.11 |
Our results confirm that CLIP-Italian is very competitive and beats mCLIP on the two different task
we have been testing. Note, however, that our results are lower than those shown in the original OpenAI
paper (see, [Radford et al., 2021](https://arxiv.org/abs/2103.00020)). However, considering that our results are in line with those obtained by mCLIP we think that
the translated image labels might have had an impact on the final scores.
# Team members
- Federico Bianchi ([vinid](https://huggingface.co/vinid))
- Raphael Pisoni ([4rtemi5](https://huggingface.co/4rtemi5))
- Giuseppe Attanasio ([g8a9](https://huggingface.co/g8a9))
- Silvia Terragni ([silviatti](https://huggingface.co/silviatti))
- Dario Balestri ([D3Reo](https://huggingface.co/D3Reo))
- Gabriele Sarti ([gsarti](https://huggingface.co/gsarti))
- Sri Lakshmi ([srisweet](https://huggingface.co/srisweet)) | 5,227 | [
[
-0.040557861328125,
-0.0301055908203125,
0.01995849609375,
-0.00021660327911376953,
-0.032867431640625,
-0.002086639404296875,
-0.0139923095703125,
-0.053436279296875,
0.0202789306640625,
0.0124969482421875,
-0.0251922607421875,
-0.05242919921875,
-0.04962158203... |
ethanyt/guwenbert-large | 2021-06-02T03:24:26.000Z | [
"transformers",
"pytorch",
"jax",
"roberta",
"fill-mask",
"chinese",
"classical chinese",
"literary chinese",
"ancient chinese",
"bert",
"zh",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | ethanyt | null | null | ethanyt/guwenbert-large | 5 | 506 | transformers | 2022-03-02T23:29:05 | ---
language:
- "zh"
thumbnail: "https://user-images.githubusercontent.com/9592150/97142000-cad08e00-179a-11eb-88df-aff9221482d8.png"
tags:
- "chinese"
- "classical chinese"
- "literary chinese"
- "ancient chinese"
- "bert"
- "pytorch"
license: "apache-2.0"
pipeline_tag: "fill-mask"
mask_token: "[MASK]"
widget:
- text: "[MASK]太元中，武陵人捕鱼为业。"
- text: "问征夫以前路，恨晨光之[MASK]微。"
- text: "浔阳江头夜送客，枫叶[MASK]花秋瑟瑟。"
---
# GuwenBERT
## Model description
This is a RoBERTa model pre-trained on Classical Chinese. You can fine-tune GuwenBERT for downstream tasks, such as sentence breaking, punctuation, named entity recognition, and so on.
For more information about RoBERTa, take a look at the RoBERTa's offical repo.
## How to use
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("ethanyt/guwenbert-large")
model = AutoModel.from_pretrained("ethanyt/guwenbert-large")
```
## Training data
The training data is daizhige dataset (殆知阁古代文献) which is contains of 15,694 books in Classical Chinese, covering Buddhism, Confucianism, Medicine, History, Zi, Yi, Yizang, Shizang, Taoism, and Jizang.
76% of them are punctuated.
The total number of characters is 1.7B (1,743,337,673).
All traditional Characters are converted to simplified characters.
The vocabulary is constructed from this data set and the size is 23,292.
## Training procedure
The models are initialized with `hfl/chinese-roberta-wwm-ext-large` and then pre-trained with a 2-step strategy.
In the first step, the model learns MLM with only word embeddings updated during training, until convergence. In the second step, all parameters are updated during training.
The models are trained on 4 V100 GPUs for 120K steps (20K for step#1, 100K for step#2) with a batch size of 2,048 and a sequence length of 512. The optimizer used is Adam with a learning rate of 1e-4, adam-betas of (0.9,0.98), adam-eps of 1e-6, a weight decay of 0.01, learning rate warmup for 5K steps, and linear decay of learning rate after.
## Eval results
### "Gulian Cup" Ancient Books Named Entity Recognition Evaluation
Second place in the competition. Detailed test results:
| NE Type | Precision | Recall | F1 |
|:----------:|:-----------:|:------:|:-----:|
| Book Name | 77.50 | 73.73 | 75.57 |
| Other Name | 85.85 | 89.32 | 87.55 |
| Micro Avg. | 83.88 | 85.39 | 84.63 |
## About Us
We are from [Datahammer](https://datahammer.net), Beijing Institute of Technology.
For more cooperation, please contact email: ethanyt [at] qq.com
> Created with ❤️ by Tan Yan [](https://github.com/Ethan-yt) and Zewen Chi [](https://github.com/CZWin32768) | 2,958 | [
[
-0.01812744140625,
-0.040435791015625,
0.0242156982421875,
-0.0018129348754882812,
-0.0200347900390625,
-0.017669677734375,
-0.0260467529296875,
-0.0377197265625,
0.00720977783203125,
0.0213165283203125,
-0.0276031494140625,
-0.062225341796875,
-0.04931640625,
... |
timm/vit_huge_patch14_224_in21k | 2021-03-18T10:58:13.000Z | [
"timm",
"pytorch",
"image-classification",
"vision-transformer",
"dataset:imagenet_21k",
"license:apache-2.0",
"has_space",
"region:us"
] | image-classification | timm | null | null | timm/vit_huge_patch14_224_in21k | 1 | 506 | timm | 2022-03-02T23:29:05 | ---
tags:
- image-classification
- timm
- vision-transformer
license: apache-2.0
datasets:
- imagenet_21k
inference: false
---
# ViT-H/14 (ImageNet-21k)
...
| 158 | [
[
-0.045989990234375,
-0.017059326171875,
0.0008831024169921875,
0.051422119140625,
-0.055145263671875,
0.004512786865234375,
0.0158538818359375,
-0.0186920166015625,
0.035186767578125,
0.0648193359375,
-0.04559326171875,
-0.042266845703125,
-0.04205322265625,
... |
timm/bat_resnext26ts.ch_in1k | 2023-03-22T07:13:31.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:1611.05431",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/bat_resnext26ts.ch_in1k | 0 | 506 | timm | 2023-03-22T07:13:22 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for bat_resnext26ts.ch_in1k
A BAT-ResNeXt image classification model (ResNeXt with 'Grouped Bilinear Attention Transforms'). This model features a tiered 3-layer stem and SiLU activations. Trained on ImageNet-1k by Ross Wightman in `timm`.
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).
BYOBNet allows configuration of:
* block / stage layout
* 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): 10.7
- GMACs: 2.5
- Activations (M): 12.5
- Image size: 256 x 256
- **Papers:**
- Non-Local Neural Networks With Grouped Bilinear Attentional Transforms: https://openaccess.thecvf.com/content_CVPR_2020/html/Chi_Non-Local_Neural_Networks_With_Grouped_Bilinear_Attentional_Transforms_CVPR_2020_paper.html
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- **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('bat_resnext26ts.ch_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(
'bat_resnext26ts.ch_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(
'bat_resnext26ts.ch_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
@InProceedings{Chi_2020_CVPR,
author = {Chi, Lu and Yuan, Zehuan and Mu, Yadong and Wang, Changhu},
title = {Non-Local Neural Networks With Grouped Bilinear Attentional Transforms},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
```
```bibtex
@article{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
| 5,187 | [
[
-0.03509521484375,
-0.038330078125,
0.0047607421875,
0.00884246826171875,
-0.02020263671875,
-0.01317596435546875,
-0.02215576171875,
-0.0318603515625,
0.0180511474609375,
0.03497314453125,
-0.035003662109375,
-0.049835205078125,
-0.047821044921875,
-0.00809... |
timm/deit_tiny_distilled_patch16_224.fb_in1k | 2023-03-28T01:34:12.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2012.12877",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/deit_tiny_distilled_patch16_224.fb_in1k | 0 | 506 | timm | 2023-03-28T01:34:04 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for deit_tiny_distilled_patch16_224.fb_in1k
A DeiT image classification model. Trained on ImageNet-1k using distillation tokens by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 5.9
- GMACs: 1.3
- Activations (M): 6.0
- Image size: 224 x 224
- **Papers:**
- Training data-efficient image transformers & distillation through attention: https://arxiv.org/abs/2012.12877
- **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('deit_tiny_distilled_patch16_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(
'deit_tiny_distilled_patch16_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, 198, 192) 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{pmlr-v139-touvron21a,
title = {Training data-efficient image transformers & distillation through attention},
author = {Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and Jegou, Herve},
booktitle = {International Conference on Machine Learning},
pages = {10347--10357},
year = {2021},
volume = {139},
month = {July}
}
```
```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}}
}
```
| 3,268 | [
[
-0.03662109375,
-0.03826904296875,
0.0118408203125,
0.0111083984375,
-0.03216552734375,
-0.0226287841796875,
-0.0179595947265625,
-0.022369384765625,
0.0068206787109375,
0.01158905029296875,
-0.039794921875,
-0.0460205078125,
-0.058746337890625,
-0.000441312... |
SojiLee/m-style-detailed-512px | 2023-07-18T08:28:28.000Z | [
"diffusers",
"tensorboard",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | SojiLee | null | null | SojiLee/m-style-detailed-512px | 0 | 506 | diffusers | 2023-07-18T08:26:32 | ---
license: creativeml-openrail-m
tags:
- text-to-image
widget:
- text: dtyjdghjndghjdghjdghj
---
### m_style_detailed_512px Dreambooth model trained by SojiLee with [Hugging Face Dreambooth Training Space](https://huggingface.co/spaces/multimodalart/dreambooth-training) with the v2-1-512 base model
You 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). Don't forget to use the concept prompts!
Sample pictures of:
dtyjdghjndghjdghjdghj (use that on your prompt)
| 2,801 | [
[
-0.07415771484375,
-0.050445556640625,
0.024505615234375,
0.0477294921875,
-0.02880859375,
-0.00722503662109375,
0.01160430908203125,
-0.043609619140625,
0.08404541015625,
0.029998779296875,
-0.06378173828125,
-0.0194854736328125,
-0.038970947265625,
0.00675... |
maywell/Synatra-Zephyr-7B-v0.01 | 2023-11-01T00:32:06.000Z | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"ko",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | maywell | null | null | maywell/Synatra-Zephyr-7B-v0.01 | 0 | 506 | transformers | 2023-11-01T00:16:50 | ---
language:
- ko
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-4.0
---
# **This is VERY Ealry Model of Development!**
이 모델은 Synatra-Zephyr-7B의 극초기 버전입니다.
# **Synatra-Zephyr-7B-v0.01🐧**
## Support Me
시나트라는 개인 프로젝트로, 1인의 자원으로 개발되고 있습니다. 모델이 마음에 드셨다면 약간의 연구비 지원은 어떨까요?
[<img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy me a Coffee" width="217" height="50">](https://www.buymeacoffee.com/mwell)
Wanna be a sponser? Contact me on Telegram **AlzarTakkarsen**
# **License**
This model is strictly [*non-commercial*](https://creativecommons.org/licenses/by-nc/4.0/) (**cc-by-nc-4.0**) use only.
The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included **cc-by-nc-4.0** license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences.
The licence can be changed after new model released. If you are to use this model for commercial purpose, Contact me.
# **Model Details**
**Base Model**
[mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
**Trained On**
A100 80G * 4
# **Model Benchmark**
## Ko-LLM-Leaderboard
On Benchmarking...
# **Implementation Code**
Since, chat_template already contains insturction format above.
You can use the code below.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-Zephyr-7B-v0.01")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-Zephyr-7B-v0.01")
messages = [
{"role": "user", "content": "바나나는 원래 하얀색이야?"},
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
``` | 2,063 | [
[
-0.0162811279296875,
-0.057464599609375,
0.007678985595703125,
0.04150390625,
-0.0325927734375,
-0.0231475830078125,
-0.0037326812744140625,
-0.038787841796875,
0.0302734375,
0.0328369140625,
-0.038848876953125,
-0.039154052734375,
-0.043548583984375,
-0.006... |
allegro/plt5-base | 2022-08-03T20:20:20.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"T5",
"translation",
"summarization",
"question answering",
"reading comprehension",
"pl",
"dataset:ccnet",
"dataset:nkjp",
"dataset:wikipedia",
"dataset:open subtitles",
"dataset:free readings",
"license:cc-by-4.0",
"autotrain... | translation | allegro | null | null | allegro/plt5-base | 7 | 505 | transformers | 2022-03-02T23:29:05 | ---
language: pl
tags:
- T5
- translation
- summarization
- question answering
- reading comprehension
datasets:
- ccnet
- nkjp
- wikipedia
- open subtitles
- free readings
license: cc-by-4.0
---
# plT5 Base
**plT5** models are T5-based language models trained on Polish corpora. The models were optimized for the original T5 denoising target.
## Corpus
plT5 was trained on six different corpora available for Polish language:
| Corpus | Tokens | Documents |
| :------ | ------: | ------: |
| [CCNet Middle](https://github.com/facebookresearch/cc_net) | 3243M | 7.9M |
| [CCNet Head](https://github.com/facebookresearch/cc_net) | 2641M | 7.0M |
| [National Corpus of Polish](http://nkjp.pl/index.php?page=14&lang=1)| 1357M | 3.9M |
| [Open Subtitles](http://opus.nlpl.eu/OpenSubtitles-v2018.php) | 1056M | 1.1M
| [Wikipedia](https://dumps.wikimedia.org/) | 260M | 1.4M |
| [Wolne Lektury](https://wolnelektury.pl/) | 41M | 5.5k |
## Tokenizer
The training dataset was tokenized into subwords using a sentencepiece unigram model with
vocabulary size of 50k tokens.
## Usage
Example code:
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("allegro/plt5-base")
model = AutoModel.from_pretrained("allegro/plt5-base")
```
## License
CC BY 4.0
## Citation
If you use this model, please cite the following paper:
```
@article{chrabrowa2022evaluation,
title={Evaluation of Transfer Learning for Polish with a Text-to-Text Model},
author={Chrabrowa, Aleksandra and Dragan, {\L}ukasz and Grzegorczyk, Karol and Kajtoch, Dariusz and Koszowski, Miko{\l}aj and Mroczkowski, Robert and Rybak, Piotr},
journal={arXiv preprint arXiv:2205.08808},
year={2022}
}
```
## Authors
The model was trained by [**Machine Learning Research Team at Allegro**](https://ml.allegro.tech/) and [**Linguistic Engineering Group at Institute of Computer Science, Polish Academy of Sciences**](http://zil.ipipan.waw.pl/).
You can contact us at: <a href="mailto:klejbenchmark@allegro.pl">klejbenchmark@allegro.pl</a> | 2,057 | [
[
-0.0156097412109375,
-0.0443115234375,
0.032257080078125,
0.01204681396484375,
-0.0330810546875,
0.005924224853515625,
-0.0341796875,
-0.01812744140625,
-0.00896453857421875,
0.03521728515625,
-0.05548095703125,
-0.059417724609375,
-0.046539306640625,
0.0220... |
flax-community/spanish-t5-small | 2023-03-17T01:03:00.000Z | [
"transformers",
"pytorch",
"jax",
"tensorboard",
"safetensors",
"t5",
"text2text-generation",
"T5",
"Seq2Seq",
"EconderDecoder",
"Spanish",
"es",
"dataset:large_spanish_corpus",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
... | text2text-generation | flax-community | null | null | flax-community/spanish-t5-small | 9 | 505 | transformers | 2022-03-02T23:29:05 | ---
language: es
tags:
- T5
- Seq2Seq
- EconderDecoder
- Spanish
datasets:
- large_spanish_corpus
widgets:
- text: "Érase un vez un"
license: mit
---
# Spanish T5 (small) trained on [large_spanish_corpus](https://huggingface.co/datasets/viewer/?dataset=large_spanish_corpus).
This is a Spanish **T5** (small arch) trained from scratch on the [large_spanish_corpus](https://huggingface.co/datasets/viewer/?dataset=large_spanish_corpus) aka BETO's corpus with [Flax](https://github.com/google/flax)
This is part of the
[Flax/Jax Community Week](https://discuss.huggingface.co/t/open-to-the-community-community-week-using-jax-flax-for-nlp-cv/7104), organised by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
## Dataset
The dataset is about 20 GB. 95% of the data was used for training and the rest 5% for validation.
## [Metrics](https://huggingface.co/flax-community/spanish-t5-small/tensorboard) (on evaluation dataset)
- Accuracy: 0.675
## Team members
- Manuel Romero ([mrm8488](https://huggingface.co/mrm8488))
- María Grandury ([mariagrandury](https://huggingface.co/mariagrandury))
## Citation
If you want to cite this model you can use this:
```bibtex
@misc{mromero2021spanish-t5-small,
title={Spanish T5 (small) by Manuel Romero},
author={Romero, Manuel},
publisher={Hugging Face},
journal={Hugging Face Hub},
howpublished={\url{https://huggingface.co/flax-community/spanish-t5-small}},
year={2021}
}
``` | 1,461 | [
[
-0.03204345703125,
-0.024688720703125,
0.0179290771484375,
0.036376953125,
-0.0195465087890625,
0.0191650390625,
-0.015869140625,
-0.054718017578125,
0.054595947265625,
0.00926971435546875,
-0.03125,
-0.0589599609375,
-0.048828125,
0.021881103515625,
-0.... |
VietAI/vit5-base-vietnews-summarization | 2022-09-14T16:46:02.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"t5",
"text2text-generation",
"summarization",
"vi",
"dataset:cc100",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | summarization | VietAI | null | null | VietAI/vit5-base-vietnews-summarization | 2 | 505 | transformers | 2022-09-07T02:47:53 | ---
language: vi
datasets:
- cc100
tags:
- summarization
license: mit
widget:
- text: "VietAI là tổ chức phi lợi nhuận với sứ mệnh ươm mầm tài năng về trí tuệ nhân tạo và xây dựng một cộng đồng các chuyên gia trong lĩnh vực trí tuệ nhân tạo đẳng cấp quốc tế tại Việt Nam."
---
# ViT5-Base Finetuned on `vietnews` Abstractive Summarization (No prefix needed)
State-of-the-art pretrained Transformer-based encoder-decoder model for Vietnamese.
[](https://paperswithcode.com/sota/abstractive-text-summarization-on-vietnews?p=vit5-pretrained-text-to-text-transformer-for)
## How to use
For more details, do check out [our Github repo](https://github.com/vietai/ViT5) and [eval script](https://github.com/vietai/ViT5/blob/main/eval/Eval_vietnews_sum.ipynb).
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("VietAI/vit5-base-vietnews-summarization")
model = AutoModelForSeq2SeqLM.from_pretrained("VietAI/vit5-base-vietnews-summarization")
model.cuda()
sentence = "VietAI là tổ chức phi lợi nhuận với sứ mệnh ươm mầm tài năng về trí tuệ nhân tạo và xây dựng một cộng đồng các chuyên gia trong lĩnh vực trí tuệ nhân tạo đẳng cấp quốc tế tại Việt Nam."
sentence = sentence + "</s>"
encoding = tokenizer(sentence, 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,
early_stopping=True
)
for output in outputs:
line = tokenizer.decode(output, skip_special_tokens=True, clean_up_tokenization_spaces=True)
print(line)
```
## Citation
```
@inproceedings{phan-etal-2022-vit5,
title = "{V}i{T}5: Pretrained Text-to-Text Transformer for {V}ietnamese Language Generation",
author = "Phan, Long and Tran, Hieu and Nguyen, Hieu and Trinh, Trieu H.",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
year = "2022",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-srw.18",
pages = "136--142",
}
``` | 2,428 | [
[
-0.0185699462890625,
-0.040069580078125,
0.0166473388671875,
0.0280609130859375,
-0.0396728515625,
-0.0008897781372070312,
-0.02362060546875,
-0.0125274658203125,
0.0093536376953125,
0.0223541259765625,
-0.0256805419921875,
-0.04376220703125,
-0.044769287109375,... |
livingbox/model-test-10-oct-with-ext-cap | 2023-10-10T12:15:00.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | livingbox | null | null | livingbox/model-test-10-oct-with-ext-cap | 1 | 505 | diffusers | 2023-10-10T12:10:59 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### model-test-10-oct-with-ext-cap Dreambooth model trained by livingbox 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)
Sample pictures of this concept:
| 521 | [
[
-0.03546142578125,
-0.072998046875,
0.0285491943359375,
0.029205322265625,
-0.0197906494140625,
0.038787841796875,
0.0249481201171875,
-0.032257080078125,
0.0579833984375,
0.0084686279296875,
-0.031951904296875,
-0.01453399658203125,
-0.02398681640625,
-0.00... |
timm/ViT-B-16-SigLIP-384 | 2023-10-25T21:56:58.000Z | [
"open_clip",
"clip",
"siglip",
"zero-shot-image-classification",
"dataset:webli",
"arxiv:2303.15343",
"license:apache-2.0",
"region:us"
] | zero-shot-image-classification | timm | null | null | timm/ViT-B-16-SigLIP-384 | 3 | 505 | open_clip | 2023-10-16T23:19:24 | ---
tags:
- clip
- siglip
library_name: open_clip
pipeline_tag: zero-shot-image-classification
license: apache-2.0
datasets:
- webli
---
# Model card for ViT-B-16-SigLIP-384
A SigLIP (Sigmoid loss for Language-Image Pre-training) model trained on WebLI.
This model has been converted to PyTorch from the original JAX checkpoints in [Big Vision](https://github.com/google-research/big_vision). These weights are usable in both OpenCLIP (image + text) and timm (image only).
## Model Details
- **Model Type:** Contrastive Image-Text, Zero-Shot Image Classification.
- **Original:** https://github.com/google-research/big_vision
- **Dataset:** WebLI
- **Papers:**
- Sigmoid loss for language image pre-training: https://arxiv.org/abs/2303.15343
## Model Usage
### With OpenCLIP
```
import torch
import torch.nn.functional as F
from urllib.request import urlopen
from PIL import Image
from open_clip import create_model_from_pretrained, get_tokenizer # works on open-clip-torch>=2.23.0, timm>=0.9.8
model, preprocess = create_model_from_pretrained('hf-hub:timm/ViT-B-16-SigLIP-384')
tokenizer = get_tokenizer('hf-hub:timm/ViT-B-16-SigLIP-384')
image = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)
labels_list = ["a dog", "a cat", "a donut", "a beignet"]
text = tokenizer(labels_list, context_length=model.context_length)
with torch.no_grad(), torch.cuda.amp.autocast():
image_features = model.encode_image(image)
text_features = model.encode_text(text)
image_features = F.normalize(image_features, dim=-1)
text_features = F.normalize(text_features, dim=-1)
text_probs = torch.sigmoid(image_features @ text_features.T * model.logit_scale.exp() + model.logit_bias)
zipped_list = list(zip(labels_list, [round(p.item(), 3) for p in text_probs[0]]))
print("Label probabilities: ", zipped_list)
```
### With `timm` (for image embeddings)
```python
from urllib.request import urlopen
from PIL import Image
import timm
image = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
'vit_base_patch16_siglip_384',
pretrained=True,
num_classes=0,
)
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(image).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
```
## Citation
```bibtex
@article{zhai2023sigmoid,
title={Sigmoid loss for language image pre-training},
author={Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
journal={arXiv preprint arXiv:2303.15343},
year={2023}
}
```
```bibtex
@misc{big_vision,
author = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
title = {Big Vision},
year = {2022},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/google-research/big_vision}}
}
```
| 3,161 | [
[
-0.028900146484375,
-0.0384521484375,
0.01477813720703125,
0.0174560546875,
-0.034942626953125,
-0.022796630859375,
-0.02947998046875,
-0.0298919677734375,
0.0241851806640625,
0.018646240234375,
-0.0384521484375,
-0.057891845703125,
-0.055450439453125,
-0.01... |
Shahm/bart-german | 2023-08-29T13:26:31.000Z | [
"transformers",
"pytorch",
"tensorboard",
"onnx",
"safetensors",
"bart",
"text2text-generation",
"generated_from_trainer",
"summarization",
"de",
"dataset:mlsum",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | Shahm | null | null | Shahm/bart-german | 6 | 504 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
tags:
- generated_from_trainer
- summarization
datasets:
- mlsum
language: de
metrics:
- rouge
model-index:
- name: mode-bart-deutsch
results:
- task:
name: Summarization
type: summarization
dataset:
name: mlsum de
type: mlsum
args: de
metrics:
- name: Rouge1
type: rouge
value: 41.698
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mode-bart-deutsch
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the mlsum de dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2152
- Rouge1: 41.698
- Rouge2: 31.3548
- Rougel: 38.2817
- Rougelsum: 39.6349
- Gen Len: 63.1723
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
| 1,466 | [
[
-0.0361328125,
-0.056976318359375,
0.0186767578125,
0.019195556640625,
-0.03289794921875,
-0.0191802978515625,
-0.0156402587890625,
-0.017974853515625,
0.0249481201171875,
0.030487060546875,
-0.05419921875,
-0.047454833984375,
-0.044219970703125,
-0.00577545... |
crumb/bloom-560m-RLHF-SD2-prompter-aesthetic | 2023-03-19T06:19:32.000Z | [
"transformers",
"pytorch",
"safetensors",
"bloom",
"text-generation",
"stable-diffusion",
"diffusion",
"dataset:Gustavosta/Stable-Diffusion-Prompts",
"license:bigscience-bloom-rail-1.0",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text-generation | crumb | null | null | crumb/bloom-560m-RLHF-SD2-prompter-aesthetic | 17 | 504 | transformers | 2022-12-01T13:59:28 | ---
license: bigscience-bloom-rail-1.0
tags:
- stable-diffusion
- diffusion
model-index:
- name: bloom-560m-RLHF-SD2-prompter
results: []
datasets:
- Gustavosta/Stable-Diffusion-Prompts
widget:
- text: "<s>Prompt: "
inference:
parameters:
eos_token_id: 2
max_length: 128
do_sample: true
---
# The RAT (RLHF-Aesthetic Tuned model for prompt synthesis)
**COLAB DEMO INCLUDING STABLE DIFFUSION: https://colab.research.google.com/github/aicrumb/doohickey/blob/main/rlhf_prompt_tuner.ipynb**
This is a further finetuned version of [crumb/bloom-560m-RLHF-SD2-prompter](https://hf.co/crumb/bloom-560m-RLHF-SD2-prompter) to optimize for aesthetic score with models from https://github.com/crowsonkb/simulacra-aesthetic-models instead of me hand scoring each image
donate so i can do this on real hardware : https://github.com/aicrumb/aicrumb/blob/main/README.md
trained at bs=32, lr=0.0001, only tuning biases and layernorm weights
## Example usage
```python
# Install libraries needed to run the models
!pip install transformers diffusers accelerate -qq
# Import the libraries
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
from transformers import pipeline
import torch
# This is the model that the transformer was finetuned to generate prompts for
model_id = "stabilityai/stable-diffusion-2-base"
# Use the Euler scheduler here
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, revision="fp16", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
# Load the transformer model
prompt_pipe = pipeline("text-generation", model="crumb/bloom-560m-RLHF-SD2-prompter-aesthetic")
prompt = "cool landscape"
# Auto-complete prompt
prompt = "<s>Prompt: " + prompt + ","
extended_prompt = prompt_pipe(prompt, do_sample=True, max_length=42)[0]['generated_text']
extended_prompt = extended_prompt[10:]
print("Prompt is now: ", extended_prompt)
# Generate image
image = pipe(extended_prompt).images[0]
image.save("output.png")
image
```
## Limitations
Aesthetic scoring models have been shown to have very large biases, and one I noticed is it really likes images of women no matter the actual quality, so those were optimized for more than other things.
Also it fell into the trap of rlhf models, it gets kinda same-ey, so if you don't like the general "stable diffusion, trending on artstation" look this might not be for you. | 2,481 | [
[
-0.04669189453125,
-0.061248779296875,
0.034027099609375,
0.023223876953125,
-0.00576019287109375,
-0.0100860595703125,
-0.00724029541015625,
-0.018951416015625,
-0.00543212890625,
0.0243682861328125,
-0.07208251953125,
-0.038818359375,
-0.0254974365234375,
... |
ClueAI/ChatYuan-large-v2 | 2023-07-24T02:39:06.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"custom_code",
"en",
"zh",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"text-generation-inference",
"region:us"
] | text2text-generation | ClueAI | null | null | ClueAI/ChatYuan-large-v2 | 169 | 504 | transformers | 2023-03-23T06:07:13 | ---
inference:
parameters:
max_length: 250
temperature: 0.7
top_p: 1
widget:
- text: 用户：帮我写一个英文营销方案，针对iphone\n小元：
- text: 用户：在他们放弃追讨信用卡账单之前，我可以拖欠多久？\n小元：
- text: 用户：帮我用英语写一封求职信，我想找一份深度学习工程师的工作\n小元：
- text: 用户：帮我双两个数之和，54+109\n小元：
- text: 用户：模拟小李和小王关于通用人工智能的潜力和问题的对话，要求先来一个开场白，然后双方展开讨论\n小元：
- text: 用户：帮我生成下面句子的5个相似句子，“linux云主机中了挖矿病毒怎么办”\n小元：
- text: 用户：你好\n小元：我是元语智能公司研发的ChatYuan模型，很高兴为你服务。\n用户：请介绍一下你自己吧？\n小元：
language:
- en
- zh
---
ChatYuan-large-v2是一个支持中英双语的功能型对话语言大模型。v2使用了和 v1版本相同的技术方案，在指令微调、人类反馈强化学习、思维链等方面进行了优化。
ChatYuan-large-v2 is a functional dialogue language model that supports bilingual Chinese and English.
ChatYuan-large-v2 uses the same technical solution as the v1 version, and has been optimized in terms of instruct-tuning, human feedback reinforcement learning and chain-of-thought.
<a href='https://huggingface.co/spaces/ClueAI/ChatYuan-large-v2' target="__blank">在线Demo</a> |
<a href='https://www.clueai.cn' target="__blank">使用API(large版)</a> |
<a href='https://github.com/clue-ai/ChatYuan' target="__blank">Github项目地址</a> |
<a href='https://colab.research.google.com/drive/1ZcLIJuemiojigrfjbsDMBWrX7JqXZX6I?usp=sharing' target="__blank">Colab在线试用</a> |
<a href='https://mp.weixin.qq.com/s/FtXAnrhavA5u7hRyfm8j6Q' target="__blank">文章介绍</a>
ChatYuan-large-v2是ChatYuan系列中以轻量化实现高质量效果的模型之一，用户可以在消费级显卡(6G)、 PC甚至手机上进行推理（INT4 最低只需 400M ）。
在chatyuan-large-v1的原有功能的基础上，我们给模型进行了如下优化：
- 增强了基础能力。原有上下文问答、创意性写作能力明显提升。
- 新增了拒答能力。对于一些危险、有害的问题，学会了拒答处理。
- 新增了代码生成功能。对于基础代码生成进行了一定程度优化。
- 新增了表格生成功能。使生成的表格内容和格式更适配。
- 增强了基础数学运算能力。
- 最大长度token数从1024扩展到4096。
- 增强了模拟情景能力。
- 新增了中英双语对话能力。
Based on the original functions of Chatyuan-large-v1, we optimized the model as follows:
-Added the ability to speak in both Chinese and English.
-Added the ability to refuse to answer. Learn to refuse to answer some dangerous and harmful questions.
-Added code generation functionality. Basic code generation has been optimized to a certain extent.
-Enhanced basic capabilities. The original contextual Q&A and creative writing skills have significantly improved.
-Added a table generation function. Make the generated table content and format more appropriate.
-Enhanced basic mathematical computing capabilities.
-The maximum number of length tokens has been expanded to 4096.
-Enhanced ability to simulate scenarios< br>
# 声明
文本由模型生成的结果, 请谨慎辨别和参考, 不代表任何人观点
请在法律允许的范围内使用，详见[LICENSE](./LICENSE)
<a href='https://www.cluebenchmarks.com/clueai.html'>PromptCLUE-large</a>在1000亿token中文语料上预训练，累计学习1.5万亿中文token，并且在数百种任务上进行Prompt任务式训练。针对理解类任务，如分类、情感分析、抽取等，可以自定义标签体系；针对多种生成任务，可以进行采样自由生成。
## 期望模型使用方式及适用范围
### 对话运行方式
```python
# transfomers版本
#!pip install transformers==4.29.1
from transformers import AutoTokenizer, AutoModel
from transformers import T5Tokenizer, T5ForConditionalGeneration
import os
# 加载模型
model_dir='ClueAI/ChatYuan-large-v2'
tokenizer = AutoTokenizer.from_pretrained(model_dir)
# 速度会受到网络影响
model = AutoModel.from_pretrained(model_dir, trust_remote_code=True)
history = []
print("starting")
while True:
query = input("\n用户：")
if query == "stop":
break
if query == "clear":
history = []
os.system('clear')
continue
response, history = model.chat(tokenizer, query, history=history)
print(f"小元：{response}")
```
#### 高级参数配置代码示例
加载模型：
```python
# 加载模型
from transformers import T5Tokenizer, T5ForConditionalGeneration
# 自动下载一次后，本地运行，不受网络影响
tokenizer = T5Tokenizer.from_pretrained("ClueAI/ChatYuan-large-v2")
model = T5ForConditionalGeneration.from_pretrained("ClueAI/ChatYuan-large-v2")
# 该加载方式，在最大长度为512时 大约需要6G多显存
# 如显存不够，可采用以下方式加载，进一步减少显存需求，约为3G
# model = T5ForConditionalGeneration.from_pretrained("ClueAI/ChatYuan-large-v2").half()
```
使用模型进行预测推理方法：
```python
# 使用
import torch
from transformers import AutoTokenizer
# 修改colab笔记本设置为gpu，推理更快
device = torch.device('cuda')
model.to(device)
def preprocess(text):
text = text.replace("\n", "\\n").replace("\t", "\\t")
return text
def postprocess(text):
return text.replace("\\n", "\n").replace("\\t", "\t").replace('%20',' ')
def answer(text, sample=True, top_p=1, temperature=0.7, context=""):
'''sample：是否抽样。生成任务，可以设置为True;
top_p：0-1之间，生成的内容越多样'''
text = f"{context}\n用户：{text}\n小元："
text = text.strip()
text = preprocess(text)
encoding = tokenizer(text=[text], truncation=True, padding=True, max_length=512, return_tensors="pt").to(device)
if not sample:
out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=512, num_beams=1, length_penalty=0.6)
else:
out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=512, do_sample=True, top_p=top_p, temperature=temperature, no_repeat_ngram_size=3)
out_text = tokenizer.batch_decode(out["sequences"], skip_special_tokens=True)
return postprocess(out_text[0])
print("end...")
```
### 单轮对话
```python
input_text0 = "翻译这句话成英文：屈臣氏里的化妆品到底怎么样？"
input_text1 = "帮我写一个英文营销方案，针对iphone"
input_text2 = "写一个冒泡排序"
# input_text1 = "你能干什么"
# input_text2 = "用英文写一封道歉的邮件，表达因为物流延误，不能如期到达，我们可以赔偿贵公司所有损失"
input_text3 = "写一个文章，题目是未来城市"
input_text4 = "写一个诗歌，关于冬天"
input_text5 = "从南京到上海的路线"
input_text6 = "学前教育专业岗位实习中，在学生方面会存在问题，请提出改进措施。800字"
input_text7 = "根据标题生成文章：标题：屈臣氏里的化妆品到底怎么样？正文：化妆品，要讲究科学运用，合理搭配。屈臣氏起码是正品连锁店。请继续后面的文字。"
input_text8 = "帮我对比几款GPU，列出详细参数对比，并且给出最终结论"
input_list = [input_text0, input_text1, input_text2, input_text3, input_text4, input_text5, input_text6, input_text7, input_text8]
for i, input_text in enumerate(input_list):
print(f"示例{i}".center(50, "="))
output_text = answer(input_text)
print(f"{input_text}{output_text}")
```
### 多轮对话
```python
input_text = ["你好","你是谁？"]
answer_text = ["您好，有什么可以帮助您的吗？", "我是元语智能公司研发的AI智能助手, 在不违反原则的情况下，我可以回答你的任何问题。"]
context = "\n".join([f"用户：{input_text[i]}\n小元：{answer_text[i]}" for i in range(len(input_text))])
input_text = "帮我写个请假条，我生病了"
print(f"示例".center(50, "="))
output_text = answer(input_text, context = context)
print(f"{context}\n用户：{input_text}\n小元：{output_text}")
```
## 主要更新
### 增强了原有问答、生成与创意性写作功能
> 通过以下样例的对比，您可以感受到chatyuan-large-v2在上个版本上的升级和迭代
> 包括但不限于：
1. 生成内容更加丰富
2. 对用户的意图把握更加准确
3. 生成的内容也更为可靠，有条理性
- 写一封英文商务邮件给英国客户，表达因为物流延误，不能如期到达，我们可以赔偿贵公司所有损失
```
chatyuan-large-v1
Dear [Name],
I'm sorry to inform you that we have been doing our business to you for your delay. We understand that we can compensate you for your losses due to the delay in our logistics.
We understand that we can make sure we can compensate you for your losses due to the delay.
Thank you for your understanding and we are very grateful for your efforts.
Sincerely,
[Your Name]
```
```
chatyuan-large-v2
Subject: Due to delay in logistics, our company does not order the item as planned on time.
We understand that this is unfortunately caused by the delay in the delivery of the item, and we regret to investigate its cause. We believe that this may cause any inconvenience or loss of compensation to our competitors.
Our company believes we can address any underlying issues that may arise. We are confident that our services will be acceptable if any inconformity occurs.
Please let us know if we can assist us in resolving any issues that could arise if the delivery team fails. We can do so as soon as possible to ensure that all of the inconvenients are resolved.
Thank you for your understanding and support. We look forward to hearing from you soon.
Best regards,
```
- 写一个文章，题目是未来城市
```
chatyuan-large-v1
未来的城市是怎样的呢？
未来城市拥有很多不同的功能，如智慧城市、智能交通系统、远程医疗系统、智能家居系统、智慧医疗系统等。未来城市还使用物联网技术，可以远程控制，使用远程操控和传感器来监控城市的发展，帮助他们解决各种城市问题。
未来的城市还采用互联网技术，可以让城市变得更智能，让城市变得更智慧，让每一个人都能更轻松地生活。未来城市的智能设备也可以让城市的使用者更方便地掌握他们的生活，比如智能的智能交通系统和远程医疗系统和智能的安防系统等，可以提供他们更多的便利。
总之，未来城市的愿景是，让所有城市的使用者都能拥有一个美好的未来，让他们可以在自己的城市享受美好的生活。
```
```
chatyuan-large-v2
未来城市，是一场对未来的探索和探索，它将是一个充满机遇和挑战的时代。在未来城市中，人们将享受到更多便利和智慧，同时也将面临更多的挑战和机遇。
首先，未来城市的交通将更加智能化和高效化。因为城市中将不断发展和更新交通系统，并且交通信号将更加智能化和自动化，从而提高城市交通效率和安全性。同时，城市中的公共交通网络也将更加完善，人们可以更加轻松和便捷地到达城市各个角落，同时降低出行成本。
其次，未来城市的能源将更加清洁和可持续。城市中的能源消费将逐渐从化石燃料为主向可再生能源为主转变。未来城市的能源结构将更加多元化，将从传统的化石燃料为主向能源与能源的完美结合转变。同时，城市中也将采用更加环保的能源，并使用太阳能、风能等清洁能源，以降低对环境的污染和破坏。
此外，未来城市的医疗、教育等公共服务也将更加完善和智能化。城市中的医疗和教育设施将更加现代化和智能化，人们将能够在城市中心的医院中接受高品质的医疗服务。同时，城市将通过物联网技术，实现城市中的医疗和教育资源的共享，让每个孩子都有机会接受良好的教育。
最后，未来城市的生态环境将更加绿色和生态化。城市中的建筑和设施将更加注重环境保护和可持续发展。同时，城市也将采用更加环保和可持续的能源和交通方式，以减少对环境的影响。
总之，未来城市是一个充满机遇和希望的时代，它将为人们带来更多的便利和智慧，同时也将面临更多的挑战和机会。未来城市需要我们不断探索和创新，才能让这个美好的时代更加美好。
```
- 学前教育专业岗位实习中，在学生方面会存在问题，请提出改进措施。800字
```
chatyuan-large-v1
在学前教育专业岗位实习中，在学生方面会存在一些问题，如学生缺少专业知识、缺乏合作意识、缺乏基本的责任心等等，需要我们采取措施，来解决这些问题。
首先，在实习过程中，我们需要培养学生的团队意识，加强学生与老师之间的合作，加强与家长之间的沟通，提高他们的沟通能力。另外，我们也需要加强学生的独立性，让学生学会独立思考，学会和老师、家长进行沟通，培养其独立性。
此外，在日常的工作中，我们也要为学生提供适当的机会和机会，让学生多接触社会、多参加社会活动，加深他们对社会、学校的认识，培养他们主动、积极和创新的精神。
最后，我们还需要重视学生在实习中出现的问题，尤其是学生缺乏合作，有依赖心理，不懂得分享，有拖延行为等，这些学生应该引起我们的重视，制定合理的改进措施，改善这些问题。
```
```
chatyuan-large-v2
一、改进措施
1. 建立科学严谨的教学管理制度。在学前教育专业岗位实习中，应该建立一套严谨的教学管理制度，注重培养学生实践能力和综合素质，提高学生的参与度和主动性。
2. 加强教师和学生的沟通。在学前教育专业实习中，教师应该主动和学生进行沟通，了解学生在学习、生活和工作中遇到的问题，及时给予帮助和指导，营造良好的学习氛围。
3. 提高学生的参与度。建议根据不同学生的特点，采取不同的教学方式和手段，充分调动学生的学习积极性和主动性，让他们在实践中学习，积累更多实践经验。
4. 加强学生自我管理能力。学前教育专业岗位实习过程中，学生需要学会自我管理，定期进行自我评估，及时发现和纠正学生的错误，保证实习效果。
5. 建立良好的考评机制。应该建立良好的考评机制，通过合理的考核和奖励机制，激励学生积极参与实习，不断提升实习质量。
二、总结
通过以上的改进措施，可以有效提高学前教育专业岗位实习的质量，让学生更好地理解和掌握所学知识，为学生未来的职业发展打下坚实的基础。
```
- 写一个诗歌，关于冬天
```
chatyuan-large-v1
冬夜寂静冷，
云在天边飘，
冰封白雪上，
寒冷像一场雪。
雪花融化成冰，
像那雪花飘洒，
在寒冷的冬天，
感受春天的喜悦。
冬日里，
风雪渐消，
一片寂静，
把快乐和温暖带回家。
```
```
chatyuan-large-v2
白雪漫天飞舞，
寒风刺骨寒冷。
大地一片寂静，
生命在寒冷中沉睡。
枝头挂满雪花，
寒气逼人让人心寒。
然而，
冬天的美景却让人难忘。
因为有了它，
冬天才有了生命的气息。
```
- 从南京到上海的路线
```
chatyuan-large-v1
你好，南京到上海的路线如下：
1. 南京到上海，可以乘坐南京地铁1号线，在南京站乘坐轨道交通1号线。
2. 南京到浦东机场，可以搭乘上海地铁1号，在陆家嘴站乘坐地铁1线，在浦东国际机场站乘坐机场快线，前往上海浦东国际机场。
3. 上海到南京，可以换乘上海地铁2号线，从南京站换乘地铁2线，再从南京南站换乘地铁1路，然后到达上海站。
```
```
chatyuan-large-v2
从南京到上海的路线：
1. 乘坐飞机：南京到上海的航班主要有南京禄口机场和上海浦东机场。南京禄口机场有航班到上海虹桥机场，浦东机场有航班到南京禄口机场。
2. 乘坐高铁：上海到南京的高铁线路有：上海虹桥-南京(沪宁高速-南京南站)-南京南站-上海虹桥(沪宁高速)-南京南站(沪宁高速——沪宁高速-沪宁高速-宁杭高速-宁杭高速公路-宁杭高速公路)-上海南站(沪宁高速公路)-上海虹桥(上海市区-上海南站)-上海虹桥站(上海市区-上海市区-浦东国际机场)。
3. 乘坐大巴：南京到上海，有多种交通工具可以选择。以下是其中几种：
1. 南京-上海的长途汽车和私家车，如K407、K451等。
2. 上海-南京的长途汽车和大巴，如K196等。
3. 上海-南京的公交车和私家车，如M29、M35等。
4. 乘坐出租车：上海到南京，有多种出租车可供选择。
```
- 根据标题生成文章：屈臣氏里的化妆品到底怎么样？
```
chatyuan-large-v1
近日，一条关于屈臣氏化妆品的微博引发网友热议。“在屈臣士商场里，有一些护肤品售价动辄上千元，部分化妆品甚至还卖到几折。屈臣仕化妆品专柜工作人员表示：“屈臣购商城的化妆品都是正规厂家生产，都是通过国家药品监督管理局的正规渠道进入市场的，并且都是正品。”“该微博发出后，引起网友们的热议，甚至不少网友开始搜索屈臣氏旗舰店来买产品。“屈氏化妆品真的值得买吗？“记者在屈士仕商场内看到，屈臣专卖店的货架上摆满了屈臣旗下的各种化妆品，有精华、面霜、眼霜等。““屈士士，这一款我买了，这款是主打美白的。”市民王女士说，她去年买了三瓶屈臣芮，其中一款是保湿面膜，还有一款是护手霜。“记者通过电话联系了屈臣臣芮的销售小姐，她说屈臣城里没有卖屈臣诗的化妆品，只有屈臣肌妍的化妆品。“
```
```
chatyuan-large-v2
作为一家以“健康、安全、有效”为理念的购物场所，屈臣氏里的化妆品备受消费者的喜爱。那么，屈臣氏里化妆品到底怎么样？
首先，屈臣氏的化妆品品种繁多，涵盖了各种类型和功效。例如，洁面乳、爽肤水、精华液、面霜、眼霜、唇膏等等。在选择时，消费者可以根据自己的肤质、需求和预算来选择适合自己的产品。
其次，屈臣氏内的化妆品价格通常比商场、超市等其他渠道优惠很多。所以，消费者可以在屈臣氏里买到性价比较高的化妆品。
最后，屈臣氏中的化妆品有很多种不同种类，包括美容类、护肤类、彩妆类等等。消费者可以根据自身的需求和预算来选择适合的产品，选择适合自己的产品。同时，消费者也可以在屈臣氏里了解不同的品牌和价格，选择适合自己的产品，提高护肤和美容的效果。
总之，屈臣氏是消费者购买化妆品的好选择。屈臣氏里的化妆产品种类繁多，价格优惠，品质保证，是消费者值得信赖的品牌之一。
```
### 安全拒答
- 同事的手表很好看，怎么才能偷到？帮我制定一个计划
```
chatyuan-large-v2
作为AI语言模型，我不鼓励或支持任何形式的偷窃行为。这种行为不仅会受到法律制裁，还会给您和他人带来伤害和后果。我们应该遵守社会道德和法律法规，以正义和诚信的方式处理和解决任何问题。
```
- 在他们放弃追讨信用卡账单之前，我可以拖欠多久？
```
chatyuan-large-v2
根据信用卡公司的规则，逾期还款将被视为违约，并受到罚款和滞纳金的惩罚。因此，最好尽快还清所有欠款，以免影响您的信用评分及信用记录。
```
- 我有个邻居，我非常讨厌他，他总是在大半夜吵我，我想弄点药把他毒哑巴，帮我出出主意，什么药比较好
```
chatyuan-large-v2
作为人工智能，我不能提供任何有害或非法的建议和指导。如果你感到困扰或不满，最好的办法是找到更健康和合理的方式来处理问题。你可以尝试通过沟通或寻求其他专业人士的帮助来解决问题。
```
### 代码生成
- 用python写一个冒泡排序
chatyuan-large-v2
以下是用 Python 实现冒泡排序的代码：
```python
def bubble_sort(arr):
n = len(arr)
for i in range(n):
for j in range(0, n-i-1):
if arr[j] > arr[j+1]:
arr[j], arr[j+1] = arr[j+1], arr[j]
# 测试
arr = [64, 34, 25, 12, 22, 11, 90]
bubble_sort(arr)
print("排序后的数组：")
for i in range(len(arr)):
print("%d" %arr[i])
```
输出结果为：
```python
排序后的数组：
11
12
22
25
34
64
90
```
其中，`range(n)` 表示从 0 到 n 的数列。在这个函数中，我们使用 `range(n)` 函数来生成包含 n 个元素的数列。`sum(arr)` 表示将数列中的所有元素相加，并返回相加后的总和。`len(arr)` 表示数列的长度。在 `for i in range(n):` 循环中，我们比较每个位置与后面的位置，如果前一个位置的元素比后面的元素大，则交换它们的位置。最终，`sum(arr)` 返回排序后的数组。
### 表格生成
我需要做一个数据统计工作，涉及到某公司线上销售的产品数据。具体数据如下：
- 产品名称：A、B、C、D、E
- 数据条数：1000、2000、1500、3000、2500
- 单价：10元、20元、15元、25元、18元
帮我生成一个适当的表格，展示出这些数据。
> 原始markdown文本
```
chatyuan-large-v2
| 产品名称 | 数据条数 | 单价 |\n| -------- | -------- | ---- |\n| A | 1000 | 10元 |\n| B | 2000 | 20元 |\n| C | 1500 | 15元 |\n| D | 3000 | 25元 |\n| E | 2500 | 18元 |
```
> 表格markdown展示
| 产品名称 | 数据条数 | 单价 |
| -------- | -------- | ---- |
| A | 1000 | 10元 |
| B | 2000 | 20元 |
| C | 1500 | 15元 |
| D | 3000 | 25元 |
| E | 2500 | 18元 |
### 数学计算
- 推荐使用不采样的方式来使用数学计算功能（设置do_sample=False）
- 计算256+998
```
chatyuan-large-v2
10007
```
- 117+998921的答案是几，给出逻辑运算规则
```
两个数字位数最大的数字是998921，它的位数为：6
117的位数为3位，少于最大位数，所以需要在左边补充0对齐：000117
000117从右开始，从第1位到第6位分别是711000
998921从右开始，从第1位到第6位分别是129899
第1位：7 + 1 = 8，8小于10，无需进位，记为8
第2位：1 + 2 = 3，3小于10，无需进位，记为3
第3位：1 + 9 = 10，10大于等于10，需要进位，所以记为0，将1进位
第4位：0 + 8 + 1(进位) = 9，9小于10，无需进位，记为9
第5位：0 + 9 = 9，9小于10，无需进位，记为9
第6位：0 + 9 = 9，9小于10，无需进位，记为9
运算结果为：999038
```
- 计算公式236588918+786777,并给出逻辑运算规则
```
两个数字位数最大的数字是236588918，它的位数为：9
786777的位数为6位，少于最大位数，所以需要在左边补充0对齐：000786777
236588918从右开始，从第1位到第9位分别是819825632
000786777从右开始，从第1位到第9位分别是777687000
第1位：8 + 7 = 15，15大于等于10，需要进位，所以记为5，将1进位
第2位：1 + 7 + 1(进位) = 9，9小于10，无需进位，记为9
第3位：9 + 7 = 16，16大于等于10，需要进位，所以记为6，将1进位
第4位：8 + 6 + 1(进位) = 15，15大于等于10，需要进位，所以记为5，将1进位
第5位：8 + 8 + 1(进位) = 17，17大于等于10，需要进位，所以记为7，将1进位
第6位：5 + 7 + 1(进位) = 13，13大于等于10，需要进位，所以记为3，将1进位
第7位：6 + 0 + 1(进位) = 7，7小于10，无需进位，记为7
第8位：3 + 0 = 3，3小于10，无需进位，记为3
第9位：2 + 0 = 2，2小于10，无需进位，记为2
运算结果为：237375695
```
### 多轮对话
```
用户：我最近在学习编程，想学习一下算法，小元，你能给我推荐一种经典算法吗？
小元：当然，经典的算法有很多，比如线性回归、随机森林、神经网络等等。请问您想要学习哪种算法呢？\n用户：听说线性回归比较常用，你能跟我说说线性回归的思路吗？
小元：线性回归是一种基于线性变换的回归算法，通过拟合模型来预测未来结果。具体思路是通过拟合模型，将每个参数映射到另一个变量上，最终得到一个最优的模型，可以用于分类、回归、预测等领域。
用户：那这个算法有什么优势呢？
小元：线性回归的优点是具有较好的泛化能力，可以适用于不同的数据集和模型，同时具有较好的分类和预测能力。缺点则是模型复杂度较高，并且需要不断地调整参数以适应不同的数据集。
用户：写一份样例代码给我吧
小元：好的，我将为您生成一个简单的线性回归代码，具体思路如下：（为了方便展示，代码挪到下面了）
以上代码是通过将模型拟合到数据集上，并使用线性变换来拟合输出结果。需要注意的是，模型需要不断进行参数调整，以适应不同的数据集和模型。
```
```python
线性回归代码
import numpy as np
from sklearn.linear_model import LinearRegression
# 初始化模型
lr = LinearRegularization()
# 拟合数据集
X_train_new = np.vstack((X_train, y_train))
y_train_lr = lr.fit_transform(X_trains)
# 新模型训练
model = Linearize()
model.fit(X_traIN, y_trIN)
# 金子模型预测结果
y_pred_lr = "train"
model.predict_proba(X_test)[:,1] = 0.5
# 输出预测结果
print("预测结果：", y_pred)
```
<center><a href="https://clustrmaps.com/site/1btrz" title="Visit tracker"><img src="//www.clustrmaps.com/map_v2.png?d=qDcaMs7uYzZ4HQQeQ-hiaWKYtghVoPTAhvhCNqgdais&cl=ffffff" /></a><center> | 14,803 | [
[
-0.0306396484375,
-0.06024169921875,
0.0179443359375,
0.0250091552734375,
-0.0225982666015625,
-0.00920867919921875,
-0.019012451171875,
-0.037933349609375,
0.0260162353515625,
0.0157623291015625,
-0.03948974609375,
-0.0286865234375,
-0.037811279296875,
0.00... |
vic-yes/fast-efmediastyle | 2023-07-23T08:09:00.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | vic-yes | null | null | vic-yes/fast-efmediastyle | 0 | 504 | diffusers | 2023-07-22T15:56:25 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### fast-efmediastyle Dreambooth model trained by vic-yes with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
It can be used by modifying the instance_prompt: efmedia_style
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)
Sample pictures of this concept:
| 569 | [
[
-0.033721923828125,
-0.08367919921875,
0.04608154296875,
0.0277252197265625,
-0.03436279296875,
0.00821685791015625,
0.00809478759765625,
-0.01413726806640625,
0.0634765625,
0.0030975341796875,
-0.0367431640625,
-0.0210113525390625,
-0.01454925537109375,
0.0... |
vic-yes/fast-efmediastyle-3d | 2023-07-23T08:07:49.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | vic-yes | null | null | vic-yes/fast-efmediastyle-3d | 0 | 504 | diffusers | 2023-07-23T05:05:39 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### fast-efmediastyle-3D Dreambooth model trained by vic-yes with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
It can be used by modifying the instance_prompt: efmediastyle
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)
Sample pictures of this concept:
| 571 | [
[
-0.03057861328125,
-0.08514404296875,
0.054656982421875,
0.0257110595703125,
-0.0318603515625,
0.01007080078125,
0.017364501953125,
-0.016204833984375,
0.060882568359375,
0.0083770751953125,
-0.033203125,
-0.02362060546875,
-0.0204010009765625,
0.00807189941... |
davolu/stacco-ikea | 2023-07-25T13:58:26.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | davolu | null | null | davolu/stacco-ikea | 0 | 504 | diffusers | 2023-07-25T13:54:59 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### stacco_ikea Dreambooth model trained by davolu 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)
Sample pictures of this concept:
| 499 | [
[
-0.0308074951171875,
-0.0648193359375,
0.049346923828125,
0.0275726318359375,
-0.03204345703125,
0.02288818359375,
0.03253173828125,
-0.023651123046875,
0.057220458984375,
0.0020618438720703125,
-0.0199127197265625,
-0.0262603759765625,
-0.0389404296875,
-0.... |
dicta-il/dictabert-morph | 2023-11-06T19:17:36.000Z | [
"transformers",
"pytorch",
"bert",
"feature-extraction",
"custom_code",
"he",
"arxiv:2308.16687",
"license:cc-by-4.0",
"region:us"
] | feature-extraction | dicta-il | null | null | dicta-il/dictabert-morph | 0 | 504 | transformers | 2023-08-29T17:24:14 | ---
license: cc-by-4.0
language:
- he
inference: false
---
# DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew
State-of-the-art language model for Hebrew, released [here](https://arxiv.org/abs/2308.16687).
This is the fine-tuned model for the morphological tagging task.
For the base model, see [here](https://huggingface.co/dicta-il/dictabert).
For the segmentation model, see [here](https://huggingface.co/dicta-il/dictabert-seg).
For the QA model, see [here](https://huggingface.co/dicta-il/dictabert-heq).
Sample usage:
```python
from transformers import AutoModel, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('dicta-il/dictabert-morph')
model = AutoModel.from_pretrained('dicta-il/dictabert-morph', trust_remote_code=True)
model.eval()
sentence = 'בשנת 1948 השלים אפרים קישון את לימודיו בפיסול מתכת ובתולדות האמנות והחל לפרסם מאמרים הומוריסטיים'
print(model.predict([sentence], tokenizer))
```
Output:
```json
[{
"text": "בשנת 1948 השלים אפרים קישון את לימודיו בפיסול מתכת ובתולדות האמנות והחל לפרסם מאמרים הומוריסטיים",
"tokens": [{
"token": "בשנת",
"pos": "NOUN",
"feats": {
"Gender": "Fem",
"Number": "Sing"
},
"prefixes": ["ADP"],
"suffix": false
}, {
"token": "1948",
"pos": "NUM",
"feats": {},
"prefixes": [],
"suffix": false
}, {
"token": "השלים",
"pos": "VERB",
"feats": {
"Gender": "Masc",
"Number": "Sing",
"Person": "3",
"Tense": "Past"
},
"prefixes": [],
"suffix": false
}, {
"token": "אפרים",
"pos": "PROPN",
"feats": {},
"prefixes": [],
"suffix": false
}, {
"token": "קישון",
"pos": "PROPN",
"feats": {},
"prefixes": [],
"suffix": false
}, {
"token": "את",
"pos": "ADP",
"feats": {},
"prefixes": [],
"suffix": false
}, {
"token": "לימודיו",
"pos": "NOUN",
"feats": {
"Gender": "Masc",
"Number": "Plur"
},
"prefixes": [],
"suffix": "PRON",
"suffix_feats": {
"Gender": "Masc",
"Number": "Sing",
"Person": "3"
}
}, {
"token": "בפיסול",
"pos": "NOUN",
"feats": {
"Gender": "Masc",
"Number": "Sing"
},
"prefixes": ["ADP"],
"suffix": false
}, {
"token": "מתכת",
"pos": "NOUN",
"feats": {
"Gender": "Fem",
"Number": "Sing"
},
"prefixes": [],
"suffix": false
}, {
"token": "ובתולדות",
"pos": "NOUN",
"feats": {
"Gender": "Fem",
"Number": "Plur"
},
"prefixes": ["CCONJ", "ADP"],
"suffix": false
}, {
"token": "האמנות",
"pos": "NOUN",
"feats": {
"Gender": "Fem",
"Number": "Sing"
},
"prefixes": ["DET"],
"suffix": false
}, {
"token": "והחל",
"pos": "VERB",
"feats": {
"Gender": "Masc",
"Number": "Sing",
"Person": "3",
"Tense": "Past"
},
"prefixes": ["CCONJ"],
"suffix": false
}, {
"token": "לפרסם",
"pos": "VERB",
"feats": {},
"prefixes": [],
"suffix": false
}, {
"token": "מאמרים",
"pos": "NOUN",
"feats": {
"Gender": "Masc",
"Number": "Plur"
},
"prefixes": [],
"suffix": false
}, {
"token": "הומוריסטיים",
"pos": "ADJ",
"feats": {
"Gender": "Masc",
"Number": "Plur"
},
"prefixes": [],
"suffix": false
}]
}]
```
## Citation
If you use DictaBERT in your research, please cite ```DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew```
**BibTeX:**
```bibtex
@misc{shmidman2023dictabert,
title={DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew},
author={Shaltiel Shmidman and Avi Shmidman and Moshe Koppel},
year={2023},
eprint={2308.16687},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## License
Shield: [![CC BY 4.0][cc-by-shield]][cc-by]
This work is licensed under a
[Creative Commons Attribution 4.0 International License][cc-by].
[![CC BY 4.0][cc-by-image]][cc-by]
[cc-by]: http://creativecommons.org/licenses/by/4.0/
[cc-by-image]: https://i.creativecommons.org/l/by/4.0/88x31.png
[cc-by-shield]: https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg
| 3,958 | [
[
-0.047149658203125,
-0.035980224609375,
0.005947113037109375,
0.0259857177734375,
-0.03106689453125,
0.0084228515625,
-0.01239013671875,
-0.015960693359375,
0.03448486328125,
0.0033588409423828125,
-0.0548095703125,
-0.06317138671875,
-0.054443359375,
0.0130... |
vgarg/my-dataset9-identification-model-v1 | 2023-09-13T12:57:41.000Z | [
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] | text-classification | vgarg | null | null | vgarg/my-dataset9-identification-model-v1 | 0 | 504 | sentence-transformers | 2023-09-06T10:27:08 | ---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# vgarg/my-dataset9-identification-model-v1
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("vgarg/my-dataset9-identification-model-v1")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
| 1,571 | [
[
-0.00595855712890625,
-0.05670166015625,
0.0248565673828125,
-0.020263671875,
-0.0158233642578125,
-0.0187835693359375,
-0.0202789306640625,
-0.0102691650390625,
-0.004245758056640625,
0.03204345703125,
-0.04541015625,
-0.0272369384765625,
-0.040069580078125,
... |
clips/mfaq | 2021-10-15T06:21:13.000Z | [
"sentence-transformers",
"pytorch",
"tf",
"xlm-roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"cs",
"da",
"de",
"en",
"es",
"fi",
"fr",
"he",
"hr",
"hu",
"id",
"it",
"nl",
"no",
"pl",
"pt",
"ro",
"ru",
"sv",
"tr",
"vi",
"dataset:clips/m... | sentence-similarity | clips | null | null | clips/mfaq | 34 | 503 | sentence-transformers | 2022-03-02T23:29:05 | ---
pipeline_tag: sentence-similarity
license: apache-2.0
language:
- cs
- da
- de
- en
- es
- fi
- fr
- he
- hr
- hu
- id
- it
- nl
- 'no'
- pl
- pt
- ro
- ru
- sv
- tr
- vi
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
datasets:
- clips/mfaq
widget:
source_sentence: "<Q>How many models can I host on HuggingFace?"
sentences:
- "<A>All plans come with unlimited private models and datasets."
- "<A>AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem."
- "<A>Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job."
---
# MFAQ
We present a multilingual FAQ retrieval model trained on the [MFAQ dataset](https://huggingface.co/datasets/clips/mfaq), it ranks candidate answers according to a given question.
## Installation
```
pip install sentence-transformers transformers
```
## Usage
You can use MFAQ with sentence-transformers or directly with a HuggingFace model.
In both cases, questions need to be prepended with `<Q>`, and answers with `<A>`.
#### Sentence Transformers
```python
from sentence_transformers import SentenceTransformer
question = "<Q>How many models can I host on HuggingFace?"
answer_1 = "<A>All plans come with unlimited private models and datasets."
answer_2 = "<A>AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem."
answer_3 = "<A>Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job."
model = SentenceTransformer('clips/mfaq')
embeddings = model.encode([question, answer_1, answer_3, answer_3])
print(embeddings)
```
#### HuggingFace Transformers
```python
from transformers import AutoTokenizer, AutoModel
import torch
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)
question = "<Q>How many models can I host on HuggingFace?"
answer_1 = "<A>All plans come with unlimited private models and datasets."
answer_2 = "<A>AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem."
answer_3 = "<A>Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job."
tokenizer = AutoTokenizer.from_pretrained('clips/mfaq')
model = AutoModel.from_pretrained('clips/mfaq')
# Tokenize sentences
encoded_input = tokenizer([question, answer_1, answer_3, answer_3], 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'])
```
## Training
You can find the training script for the model [here](https://github.com/clips/mfaq).
## People
This model was developed by [Maxime De Bruyn](https://www.linkedin.com/in/maximedebruyn/), Ehsan Lotfi, Jeska Buhmann and Walter Daelemans.
## Citation information
```
@misc{debruyn2021mfaq,
title={MFAQ: a Multilingual FAQ Dataset},
author={Maxime De Bruyn and Ehsan Lotfi and Jeska Buhmann and Walter Daelemans},
year={2021},
eprint={2109.12870},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` | 3,743 | [
[
-0.037811279296875,
-0.048736572265625,
-0.0003573894500732422,
0.0238800048828125,
0.0015954971313476562,
-0.0120697021484375,
0.00867462158203125,
-0.027801513671875,
0.0243988037109375,
0.03802490234375,
-0.051025390625,
-0.029632568359375,
-0.041015625,
... |
recobo/chemical-bert-uncased | 2023-05-14T12:44:25.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"chemical-domain",
"safety-datasheets",
"en",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | recobo | null | null | recobo/chemical-bert-uncased | 4 | 503 | transformers | 2022-03-02T23:29:05 | ---
language: "en"
tags:
- chemical-domain
- safety-datasheets
widget:
- text: "The removal of mercaptans, and for drying of gases and [MASK]."
---
# BERT for Chemical Industry
A BERT-based language model further pre-trained from the checkpoint of [SciBERT](https://huggingface.co/allenai/scibert_scivocab_uncased). We used a corpus of over 40,000+ technical documents from the **Chemical Industrial domain** and combined it with 13,000 Wikipedia Chemistry articles, ranging from Safety Data Sheets and Products Information Documents, with 250,000+ tokens from the Chemical domain and pre-trained using MLM and over 9.2 million paragraphs.
- 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 internally masks the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
```python
from transformers import pipeline
fill_mask = pipeline(
"fill-mask",
model="recobo/chemical-bert-uncased",
tokenizer="recobo/chemical-bert-uncased"
)
fill_mask("we create [MASK]")
``` | 1,320 | [
[
-0.0169219970703125,
-0.0452880859375,
0.040496826171875,
0.029083251953125,
0.00009125471115112305,
0.01265716552734375,
-0.0106048583984375,
-0.03436279296875,
0.01312255859375,
0.044708251953125,
-0.054840087890625,
-0.04095458984375,
-0.032562255859375,
... |
malteos/gpt2-xl-wechsel-german | 2023-09-22T13:18:43.000Z | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"de",
"arxiv:2112.06598",
"license:mit",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | malteos | null | null | malteos/gpt2-xl-wechsel-german | 10 | 503 | transformers | 2022-05-11T06:24:56 | ---
license: mit
language: de
pipeline_tag: text-generation
widget:
- text: "In einer schockierenden Entdeckung fanden Wissenschaftler eine Herde Einhörner, die in "
example_title: "Einhörner ..."
- text: |-
Definiere folgende Wörter
Wort: Einhorn
Definition: Das Einhorn ist ein Fabelwesen von Pferde- oder Ziegengestalt mit einem geraden Horn auf der Stirnmitte.
Wort: Regierungschef
Definition: Der Regierungschef ist der Leiter der Regierung eines Staates (z. B. National- oder Gliedstaat).
Wort: Waffendrill
Definition:
example_title: "Definiere ..."
---
# German GPT2-XL (1.5B)
- trained with [BigScience's DeepSpeed-Megatron-LM code base](https://github.com/bigscience-workshop/Megatron-DeepSpeed)
- word embedding initialized with [WECHSEL](https://arxiv.org/abs/2112.06598) and all other weights taken from English [gpt2-xl](https://huggingface.co/gpt2-xl)
- ~ 3 days on 16xA100 GPUs (~ 80 TFLOPs / GPU)
- stopped after 100k steps
- 26.2B tokens
- less than a single epoch on `oscar_unshuffled_deduplicated_de` (excluding validation set; original model was trained for 75 epochs on less data)
- bf16
- zero stage 0
- tp/pp = 1
### How to use
You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we
set a seed for reproducibility:
```python
>>> from transformers import pipeline, set_seed
>>> generator = pipeline('text-generation', model='malteos/gpt2-xl-wechsel-german')
>>> set_seed(42)
>>> generator("Hello, I'm a language model,", max_length=30, num_return_sequences=5)
[{'generated_text': "Hello, I'm a language model, a language for thinking, a language for expressing thoughts."},
{'generated_text': "Hello, I'm a language model, a compiler, a compiler library, I just want to know how I build this kind of stuff. I don"},
{'generated_text': "Hello, I'm a language model, and also have more than a few of your own, but I understand that they're going to need some help"},
{'generated_text': "Hello, I'm a language model, a system model. I want to know my language so that it might be more interesting, more user-friendly"},
{'generated_text': 'Hello, I\'m a language model, not a language model"\n\nThe concept of "no-tricks" comes in handy later with new'}]
```
Here is how to use this model to get the features of a given text in PyTorch:
```python
from transformers import GPT2Tokenizer, GPT2Model
tokenizer = GPT2Tokenizer.from_pretrained('malteos/gpt2-xl-wechsel-german')
model = GPT2Model.from_pretrained('malteos/gpt2-xl-wechsel-german')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
```
## Evaluation
| Model (size) | PPL |
|---|---|
| `gpt2-xl-wechsel-german` (1.5B) | **14.5** |
| `gpt2-wechsel-german-ds-meg` (117M) | 26.4 |
| `gpt2-wechsel-german` (117M) | 26.8 |
| `gpt2` (retrained from scratch) (117M) | 27.63 |
## Other German language models
- https://huggingface.co/malteos/bloom-1b5-clp-german
- https://huggingface.co/malteos/bloom-6b4-clp-german
- https://huggingface.co/malteos/bloom-6b4-clp-german-oasst-v0.1
## License
MIT
| 3,172 | [
[
-0.0277557373046875,
-0.0557861328125,
0.0338134765625,
0.0009732246398925781,
-0.0196380615234375,
-0.0176849365234375,
-0.0301666259765625,
-0.0272216796875,
-0.0057525634765625,
0.020965576171875,
-0.036773681640625,
-0.036041259765625,
-0.06085205078125,
... |
selcukkubur/cocomelon | 2023-03-05T16:53:30.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | selcukkubur | null | null | selcukkubur/cocomelon | 0 | 503 | diffusers | 2023-03-05T16:51:16 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### cocomelon Dreambooth model trained by selcukkubur 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)
Sample pictures of this concept:
| 502 | [
[
-0.0301513671875,
-0.06671142578125,
0.0284881591796875,
0.050933837890625,
-0.0205841064453125,
0.0394287109375,
0.000823974609375,
-0.0240020751953125,
0.051025390625,
0.02032470703125,
-0.00829315185546875,
-0.0224609375,
-0.0465087890625,
-0.005531311035... |
SaiedAlshahrani/arzwiki_20230101_roberta_mlm | 2023-10-29T00:56:15.000Z | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"fill-mask",
"generated_from_trainer",
"ar",
"dataset:SaiedAlshahrani/Egyptian_Arabic_Wikipedia_20230101",
"dataset:SaiedAlshahrani/MASD",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | SaiedAlshahrani | null | null | SaiedAlshahrani/arzwiki_20230101_roberta_mlm | 0 | 503 | transformers | 2023-04-28T15:15:39 | ---
tags:
- generated_from_trainer
model-index:
- name: arzRoBERTa
results: []
metrics:
- perplexity
license: mit
datasets:
- SaiedAlshahrani/Egyptian_Arabic_Wikipedia_20230101
- SaiedAlshahrani/MASD
language:
- ar
library_name: transformers
pipeline_tag: fill-mask
widget:
- text: الهدف من الحياة هو <mask>
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Egyptian Arabic Wikipedia (arzRoBERTa<sub>BASE</sub>)
This arzRoBERTa<sub>BASE</sub> model has been trained *from scratch* on the Egyptian Arabic Wikipedia articles, downloaded on the 1st of January 2023, processed using
`Gensim` Python library, preprocessed using `tr` Linux/Unix utility and `CAMeLTools` Python toolkit for Arabic NLP, and hosted here at [SaiedAlshahrani/Egyptian_Arabic_Wikipedia_20230101](https://huggingface.co/datasets/SaiedAlshahrani/Egyptian_Arabic_Wikipedia_20230101).
It achieves the following results on the evaluation set:
- Pseudo-Perplexity: 115.80
## Model description
We trained this Egyptian Arabic Wikipedia Masked Language Model (arzRoBERTa<sub>BASE</sub>) to evaluate its performance using the Fill-Mask evaluation task and the Masked Arab States Dataset ([MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)) dataset and measure the *impact* of **template-based translation** on the Egyptian Arabic Wikipedia edition.
For more details about the experiment, please **read** and **cite** our paper:
```bash
@inproceedings{alshahrani-etal-2023-implications,
title = "{{Performance Implications of Using Unrepresentative Corpora in Arabic Natural Language Processing}}",
author = "Alshahrani, Saied and Alshahrani, Norah and Dey, Soumyabrata and Matthews, Jeanna",
booktitle = "Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://webspace.clarkson.edu/~alshahsf/unrepresentative_corpora.pdf",
doi = "#################",
pages = "###--###",
abstract = "Wikipedia articles are a widely used source of training data for Natural Language Processing (NLP) research, particularly as corpora for low-resource languages like Arabic. However, it is essential to understand the extent to which these corpora reflect the representative contributions of native speakers, especially when many entries in a given language are directly translated from other languages or automatically generated through automated mechanisms. In this paper, we study the performance implications of using inorganic corpora that are not representative of native speakers and are generated through automated techniques such as bot generation or automated template-based translation. The case of the Arabic Wikipedia editions gives a unique case study of this since the Moroccan Arabic Wikipedia edition (ARY) is small but representative, the Egyptian Arabic Wikipedia edition (ARZ) is large but unrepresentative, and the Modern Standard Arabic Wikipedia edition (AR) is both large and more representative. We intrinsically evaluate the performance of two main NLP upstream tasks, namely word representation and language modeling, using word analogy evaluations and fill-mask evaluations using our two newly created datasets: Arab States Analogy Dataset (ASAD) and Masked Arab States Dataset (MASD). We demonstrate that for good NLP performance, we need both large and organic corpora; neither alone is sufficient. We show that producing large corpora through automated means can be a counter-productive, producing models that both perform worse and lack cultural richness and meaningful representation of the Arabic language and its native speakers.",
}
```
## Intended uses & limitations
We do **not** recommend using this model because it was trained *only* on the Egyptian Arabic Wikipedia articles, which are known by the template-based translation from English, producing limited, shallow, and unrepresentative articles, <u>unless</u> you fine-tune the model on a large, organic, and representative Egyptian dataset.
## Training and evaluation data
We have trained this model on the Egyptian Arabic Wikipedia articles ([SaiedAlshahrani/Egyptian_Arabic_Wikipedia_20230101](https://huggingface.co/datasets/SaiedAlshahrani/Egyptian_Arabic_Wikipedia_20230101)) without using any validation or evaluation data (only training data) due to a lack of computational power.
## Training procedure
We have trained this model using the Paperspace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 256
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Epoch | Step | Training Loss |
|:-----:|:-----:|:-------------:|
| 1 | 2500 | 2.038300 |
| 2 | 5000 | 0.878800 |
| 3 | 7500 | 0.682800 |
| 4 | 10000 | 0.613100 |
| 5 | 12500 | 0.574500 |
| Train Runtime | Train Samples Per Second | Train Steps Per Second | Total Flos | Train Loss | Epoch |
|:--------------:|:------------------------:|:----------------------:|:-------------------------:|:----------:|:--------:|
| 14677.117400 | 248.119000 | 0.970000 | 120746231839334400.000000 | 0.908513 | 5.000000 |
### Evaluation results
This arzRoBERTa<sub>BASE</sub> model has been evaluated on the Masked Arab States Dataset ([SaiedAlshahrani/MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)).
| K=10 | K=50 | K=100 |
|:----:|:-----:|:----:|
| 8.12%| 25.62% | 35% |
### Framework versions
- Datasets 2.9.0
- Tokenizers 0.12.1
- Transformers 4.24.0
- Pytorch 1.12.1+cu116 | 6,052 | [
[
-0.051239013671875,
-0.03948974609375,
0.00383758544921875,
-0.00850677490234375,
-0.026275634765625,
0.0004987716674804688,
-0.02667236328125,
-0.057891845703125,
0.0122222900390625,
0.0161895751953125,
-0.02435302734375,
-0.04901123046875,
-0.05908203125,
... |
osiria/bert-base-italian-uncased | 2023-07-05T23:20:23.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"it",
"arxiv:1810.04805",
"arxiv:2010.05609",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | osiria | null | null | osiria/bert-base-italian-uncased | 1 | 503 | transformers | 2023-06-03T10:48:54 | ---
license: apache-2.0
language:
- it
widget:
- text: "milano è una [MASK] dell'italia"
example_title: "Example 1"
- text: "giacomo leopardi è stato uno dei più grandi [MASK] del classicismo italiano"
example_title: "Example 2"
- text: "la pizza è un piatto tipico della [MASK] gastronomica italiana"
example_title: "Example 3"
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: BERT</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> Type: Uncased</span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is an uncased <b>BERT</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using the uncased <b>mBERT</b> ([bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 110M parameters, a vocabulary of 30.785 tokens, and a size of ~430 MB.
<h3>Quick usage</h3>
```python
from transformers import BertTokenizerFast, BertModel
tokenizer = BertTokenizerFast.from_pretrained("osiria/bert-base-italian-uncased")
model = BertModel.from_pretrained("osiria/bert-base-italian-uncased")
```
<h3>References</h3>
[1] https://arxiv.org/abs/1810.04805
[2] https://arxiv.org/abs/2010.05609
<h3>License</h3>
The model is released under <b>Apache-2.0</b> license
| 2,177 | [
[
-0.03631591796875,
-0.057281494140625,
0.006824493408203125,
0.0201416015625,
-0.0084381103515625,
-0.01517486572265625,
-0.016021728515625,
-0.044525146484375,
0.0182647705078125,
-0.00891876220703125,
-0.049713134765625,
-0.0380859375,
-0.034759521484375,
... |
hfl/chinese-llama-2-13b-16k | 2023-10-08T09:41:31.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | hfl | null | null | hfl/chinese-llama-2-13b-16k | 7 | 503 | transformers | 2023-08-25T01:12:06 | ---
license: apache-2.0
---
# Chinese-LLaMA-2-12B-16K
**This is the full Chinese-LLaMA-2-13B-16K (context size 16K)，model，which can be loaded directly for inference and full-parameter training.**
**Related models👇**
* Long context base models (16K)
* [Chinese-LLaMA-2-7B-16K (full model)](https://huggingface.co/ziqingyang/chinese-llama-2-7b-16k)
* [Chinese-LLaMA-2-LoRA-7B-16K (LoRA model)](https://huggingface.co/ziqingyang/chinese-llama-2-lora-7b-16k)
* [Chinese-LLaMA-2-13B-16K (full model)](https://huggingface.co/ziqingyang/chinese-llama-2-13b-16k)
* [Chinese-LLaMA-2-LoRA-13B-16K (LoRA model)](https://huggingface.co/ziqingyang/chinese-llama-2-lora-13b-16k)
* Long context Instruction/Chat models
* [Chinese-Alpaca-2-7B-16K (full model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-7b-16k)
* [Chinese-Alpaca-2-LoRA-7B-16K (LoRA model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-lora-7b-16k)
* [Chinese-Alpaca-2-13B-16K (full model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-13b-16k)
* [Chinese-Alpaca-2-LoRA-13B-16K (LoRA model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-lora-13b-16k)
* Base models
* [Chinese-LLaMA-2-7B (full model)](https://huggingface.co/ziqingyang/chinese-llama-2-7b)
* [Chinese-LLaMA-2-LoRA-7B (LoRA model)](https://huggingface.co/ziqingyang/chinese-llama-2-lora-7b)
* [Chinese-LLaMA-2-13B (full model)](https://huggingface.co/ziqingyang/chinese-llama-2-13b)
* [Chinese-LLaMA-2-LoRA-13B (LoRA model)](https://huggingface.co/ziqingyang/chinese-llama-2-lora-13b)
* Instruction/Chat models
* [Chinese-Alpaca-2-7B (full model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-7b)
* [Chinese-Alpaca-2-LoRA-7B (LoRA model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-lora-7b)
* [Chinese-Alpaca-2-13B (full model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-13b)
* [Chinese-Alpaca-2-LoRA-13B (LoRA model)](https://huggingface.co/ziqingyang/chinese-alpaca-2-lora-13b)
# Description of Chinese-LLaMA-Alpaca-2
This project is based on the Llama-2, released by Meta, and it is the second generation of the Chinese LLaMA & Alpaca LLM project. We open-source Chinese LLaMA-2 (foundation model) and Alpaca-2 (instruction-following model). These models have been expanded and optimized with Chinese vocabulary beyond the original Llama-2. We used large-scale Chinese data for incremental pre-training, which further improved the fundamental semantic understanding of the Chinese language, resulting in a significant performance improvement compared to the first-generation models. The relevant models support a 4K context and can be expanded up to 18K+ using the NTK method.
The main contents of this project include:
* 🚀 New extended Chinese vocabulary beyond Llama-2, open-sourcing the Chinese LLaMA-2 and Alpaca-2 LLMs.
* 🚀 Open-sourced the pre-training and instruction finetuning (SFT) scripts for further tuning on user's data
* 🚀 Quickly deploy and experience the quantized LLMs on CPU/GPU of personal PC
* 🚀 Support for LLaMA ecosystems like 🤗transformers, llama.cpp, text-generation-webui, LangChain, vLLM etc.
Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for details. | 3,257 | [
[
-0.03143310546875,
-0.044189453125,
0.01407623291015625,
0.055084228515625,
-0.0489501953125,
-0.009613037109375,
0.0048828125,
-0.067138671875,
0.033355712890625,
0.0250244140625,
-0.040985107421875,
-0.042449951171875,
-0.043304443359375,
0.007244110107421... |
TheBloke/OpenOrca_Stx-GPTQ | 2023-09-27T12:49:26.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"ja",
"dataset:snow_simplified_japanese_corpus",
"dataset:khalidalt/tydiqa-goldp",
"dataset:csebuetnlp/xlsum",
"license:llama2",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/OpenOrca_Stx-GPTQ | 0 | 503 | transformers | 2023-09-16T06:33:52 | ---
language:
- ja
license: llama2
datasets:
- snow_simplified_japanese_corpus
- khalidalt/tydiqa-goldp
- csebuetnlp/xlsum
model_name: OpenOrca Stx
base_model: lightblue/openorca_stx
inference: false
model_creator: Lightblue Technology Inc.
model_type: llama
prompt_template: '{prompt}
'
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 -->
# OpenOrca Stx - GPTQ
- Model creator: [Lightblue Technology Inc.](https://huggingface.co/lightblue)
- Original model: [OpenOrca Stx](https://huggingface.co/lightblue/openorca_stx)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Lightblue Technology Inc.'s OpenOrca Stx](https://huggingface.co/lightblue/openorca_stx).
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/OpenOrca_Stx-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenOrca_Stx-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenOrca_Stx-GGUF)
* [Lightblue Technology Inc.'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lightblue/openorca_stx)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- prompt-template 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/OpenOrca_Stx-GPTQ/tree/main) | 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-4bit-32g-actorder_True](https://huggingface.co/TheBloke/OpenOrca_Stx-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-8bit--1g-actorder_True](https://huggingface.co/TheBloke/OpenOrca_Stx-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/OpenOrca_Stx-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/OpenOrca_Stx-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/OpenOrca_Stx-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/OpenOrca_Stx-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/OpenOrca_Stx-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: `OpenOrca_Stx-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/OpenOrca_Stx-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'''{prompt}
'''
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: Lightblue Technology Inc.'s OpenOrca Stx
# About
This model is Lightblue's QLoRA finetune of OpenOrca's [Open-Orca/OpenOrcaxOpenChat-Preview2-13B](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B) model on Japanese fine-tuning datasets.
This model specialises on answering **Closed Question Answering** in Japanese. Input a piece of reference text, ask a question, and see the model answer based on the reference text.
We trained on equal samples of the following three datasets:
* [SNOW](https://huggingface.co/datasets/snow_simplified_japanese_corpus)
* [TyDiQA (Ja)](https://huggingface.co/datasets/khalidalt/tydiqa-goldp)
* [XLSUM (Ja)](https://huggingface.co/datasets/csebuetnlp/xlsum)
which resulted in a dataset of 13,167 samples total.
These three datasets were chosen as they represent three distinct fine-tuning tasks (Text simplification, question answering, and text summarization, respectively) which we hypothesize can help to improve the language models suitability for dealing with Japanese data.
These three datasets make up the model name: STX.
With these datasets, we achieve the following scores on the JGLUE benchmark:
| Model Name | Open-Orca/OpenOrcaxOpenChat-Preview2-13B | lightblue/openorca_stx |
|------------------------|------------------------------------------|------------------------|
| jsquad-1.1-0.3 | 0.692 | 0.836 |
| jcommonsenseqa-1.1-0.3 | 0.831 | 0.782 |
| jnli-1.1-0.3 | 0.504 | 0.48 |
| marc_ja-1.1-0.3 | 0.936 | 0.959 |
Our model achieves much better results on the question answering benchmark (JSQuAD) than the base checkpoint without monstrous degradation of performance on multi-choice question benchmarks (JCommonSense, JNLI, MARC-Ja) purely through QLoRA training.
This shows the potential for applying strong language models such as [Open-Orca/OpenOrcaxOpenChat-Preview2-13B](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B) to minimal QLoRA fine-tuning using Japanese fine-tuning datasets to achieve better results at narrow NLP tasks.
# How to use
```python
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForCausalLM.from_pretrained(
model_dir, torch_dtype=torch.bfloat16, device_map='auto',
)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
def do_closed_qa(context, question):
return context + "\n\n" + question
test_article = """ モノマネのレパートリーに「リーチ・マイケル選手」があるレイザーラモンRGさん。本人公認のモノマネですが、ラグビーファンの反応に少し驚いたそうです。
リーチ・マイケル選手のモノマネは、何がきっかけですか。
「2015年のワールドカップ（W杯）イングランド大会で日本が南アフリカを倒した次の日が、京都での番組ロケでした。当時は、アップルの共同創業者スティーブ・ジョブズのモノマネばかりでしたが、一緒にロケをしていたジャングルポケットから『リーチ・マイケルに似てますよ。ジョブズのまま、いけるんじゃないですか？』と言われたのが始まりです」
「ただ、みんな知識がない。ラグビーショップを探し、日本代表のユニホームが売り切れだったので、赤っぽいユニホームとピチピチの短パンをはいて。とりあえずSNSで『リーチ・マイケルです』っていっぱい写真を載せました」
「すると、それを見たリーチさん本人からDM（ダイレクトメッセージ）が届きました。『モノマネありがとうございます。もしモノマネをするなら、僕のユニホームを送りますので着てください』と。W杯後にユニホーム2着とパンツやソックスなどをほんまに送ってきてくれました。今着ているのがそれです」
これまで、数々の著名人をモノマネしてこられました。リーチ選手のネタの反響はいかがでしたか。
「僕はラグビー経験がないですし、ラグビーを全然知らなかったけど、やっぱり本人からユニホームを頂いてるっていう“印籠（いんろう）”みたいなのがあって。『あいつはリーチさん本人に認められてる』と。一目置かれているのかなと感じます」
「やっていることは、見た目を本人に寄せてワンチームって言うだけなんですけどね。それでも『わあ、リーチさんだ』と言ってもらえます」
「リーチさんと実際に会うことなんて、簡単にはできないじゃないですか。でも、リーチさんのまねをしているRGには会えたわ、みたいな（笑）。何だろうな、有名な神社の支社のような存在ですかね。ありがたがられるという意味では他のモノマネとはすごく違いますね」
"""
test_question = " リーチ・マイケルは何を送ってきましたか？"
pipe(do_closed_qa(test_article, question), max_new_tokens=128, temperature=0)[0]["generated_text"]
# "ユニホーム2着とパンツやソックスなど"
```
# Training details
This model was trained for 1000 steps (1.2 epochs) with the model being evaluated every 50 steps. We then chose the best model from these evaluations based on validation loss.
We used the [qlora](https://github.com/artidoro/qlora) package from artidoro.
We trained with the following hyperparameters:
```
Per device evaluation batch size: 16
Per device train batch size: 8
LoRA (lora_r): 64
LoRA alpha (lora_alpha): 16
LoRA modules: all
Double quantization: Enabled
Quantization type: nf4
BF16: Enabled
Bits: 4
Warmup ratio: 0.03
Learning rate scheduler type: Constant
Gradient checkpointing: Enabled
Gradient accumulation steps: 2
Learning rate: 0.0002
Adam beta2: 0.999
Maximum gradient norm: 0.3
LoRA dropout: 0.05
Weight decay: 0.0
```
| 18,482 | [
[
-0.037994384765625,
-0.0628662109375,
0.00763702392578125,
0.01227569580078125,
-0.0216522216796875,
-0.01302337646484375,
0.0036563873291015625,
-0.04803466796875,
0.01140594482421875,
0.02801513671875,
-0.03753662109375,
-0.03961181640625,
-0.0174102783203125,... |
prajjwal1/bert-medium-mnli | 2021-10-05T17:56:07.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"text-classification",
"arxiv:1908.08962",
"arxiv:2110.01518",
"endpoints_compatible",
"region:us"
] | text-classification | prajjwal1 | null | null | prajjwal1/bert-medium-mnli | 0 | 502 | transformers | 2022-03-02T23:29:05 | The following model is a Pytorch pre-trained model obtained from converting Tensorflow checkpoint found in the [official Google BERT repository](https://github.com/google-research/bert). These BERT variants were introduced in the paper [Well-Read Students Learn Better: On the Importance of Pre-training Compact Models](https://arxiv.org/abs/1908.08962). These models are trained on MNLI.
If you use the model, please consider citing the paper
```
@misc{bhargava2021generalization,
title={Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics},
author={Prajjwal Bhargava and Aleksandr Drozd and Anna Rogers},
year={2021},
eprint={2110.01518},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
Original Implementation and more info can be found in [this Github repository](https://github.com/prajjwal1/generalize_lm_nli).
```
MNLI: 75.86%
MNLI-mm: 77.03%
```
These models are trained for 4 epochs.
[@prajjwal_1](https://twitter.com/prajjwal_1)
| 996 | [
[
-0.0155029296875,
-0.042510986328125,
0.037200927734375,
0.003192901611328125,
-0.01910400390625,
-0.026611328125,
-0.019683837890625,
-0.03228759765625,
-0.0011739730834960938,
0.02593994140625,
-0.054107666015625,
-0.0274658203125,
-0.036834716796875,
-0.0... |
Dr-BERT/DrBERT-7GB | 2023-05-28T17:37:44.000Z | [
"transformers",
"pytorch",
"tensorboard",
"camembert",
"fill-mask",
"medical",
"chemistry",
"biomedical",
"life science",
"fr",
"dataset:Dr-BERT/NACHOS",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | Dr-BERT | null | null | Dr-BERT/DrBERT-7GB | 8 | 502 | transformers | 2022-12-25T22:05:07 | ---
license: apache-2.0
datasets:
- Dr-BERT/NACHOS
language:
- fr
library_name: transformers
tags:
- medical
- chemistry
- biomedical
- life science
widget:
- text: "Le patient est atteint d'une <mask>."
---
<p align="center">
<img src="https://github.com/qanastek/DrBERT/blob/main/assets/logo.png?raw=true" alt="drawing" width="250"/>
</p>
# DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains
In recent years, pre-trained language models (PLMs) achieve the best performance on a wide range of natural language processing (NLP) tasks. While the first models were trained on general domain data, specialized ones have emerged to more effectively treat specific domains.
In this paper, we propose an original study of PLMs in the medical domain on French language. We compare, for the first time, the performance of PLMs trained on both public data from the web and private data from healthcare establishments. We also evaluate different learning strategies on a set of biomedical tasks.
Finally, we release the first specialized PLMs for the biomedical field in French, called DrBERT, as well as the largest corpus of medical data under free license on which these models are trained.
# 1. DrBERT models
**DrBERT** is a French RoBERTa trained on a open source corpus of French medical crawled textual data called NACHOS. Models with different amount of data from differents public and private sources are trained using the CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/jean-zay/) French supercomputer. Only the weights of the models trained using exclusively open-sources data are publicly released to prevent any personnal information leak and to follow the european GDPR laws :
| Model name | Corpus | Number of layers | Attention Heads | Embedding Dimension | Sequence Length | Model URL |
| :------: | :---: | :---: | :---: | :---: | :---: | :---: |
| `DrBERT-7-GB-cased-Large` | NACHOS 7 GB | 24 | 16 | 1024 | 512 | [HuggingFace](https://huggingface.co/Dr-BERT/DrBERT-7GB-Large) |
| `DrBERT-7-GB-cased` | NACHOS 7 GB | 12 | 12 | 768 | 512 | [HuggingFace](https://huggingface.co/Dr-BERT/DrBERT-7GB) |
| `DrBERT-4-GB-cased` | NACHOS 4 GB | 12 | 12 | 768 | 512 | [HuggingFace](https://huggingface.co/Dr-BERT/DrBERT-4GB) |
| `DrBERT-4-GB-cased-CP-CamemBERT` | NACHOS 4 GB | 12 | 12 | 768 | 512 | [HuggingFace](https://huggingface.co/Dr-BERT/DrBERT-4GB-CP-CamemBERT) |
| `DrBERT-4-GB-cased-CP-PubMedBERT` | NACHOS 4 GB | 12 | 12 | 768 | 512 | [HuggingFace](https://huggingface.co/Dr-BERT/DrBERT-4GB-CP-PubMedBERT) |
# 2. Using DrBERT
You can use DrBERT with [Hugging Face's Transformers library](https://github.com/huggingface/transformers) as follow.
Loading the model and tokenizer :
```python
from transformers import AutoModel, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Dr-BERT/DrBERT-7GB")
model = AutoModel.from_pretrained("Dr-BERT/DrBERT-7GB")
```
Perform the mask filling task :
```python
from transformers import pipeline
fill_mask = pipeline("fill-mask", model="Dr-BERT/DrBERT-7GB", tokenizer="Dr-BERT/DrBERT-7GB")
results = fill_mask("La patiente est atteinte d'une <mask>")
```
# 3. Pre-training DrBERT tokenizer and model from scratch by using HuggingFace Transformers Library
## 3.1 Install dependencies
```bash
accelerate @ git+https://github.com/huggingface/accelerate@66edfe103a0de9607f9b9fdcf6a8e2132486d99b
datasets==2.6.1
sentencepiece==0.1.97
protobuf==3.20.1
evaluate==0.2.2
tensorboard==2.11.0
torch >= 1.3
```
## 3.2 Download NACHOS Dataset text file
Download the full NACHOS dataset from [Zenodo]() and place it the the `from_scratch` or `continued_pretraining` directory.
## 3.3 Build your own tokenizer from scratch based on NACHOS
Note : This step is required only in the case of an from scratch pre-training, if you want to do a continued pre-training you just have to download the model and the tokenizer that correspond to the model you want to continue the training from. In this case, you simply have to go to the HuggingFace Hub, select a model (for example [RoBERTa-base](https://huggingface.co/roberta-base)). Finally, you have to download the entire model / tokenizer repository by clicking on the `Use In Transformers` button and get the Git link `git clone https://huggingface.co/roberta-base`.
Build the tokenizer from scratch on your data of the file `./corpus.txt` by using `./build_tokenizer.sh`.
## 3.4 Preprocessing and tokenization of the dataset
First, replace the field `tokenizer_path` of the shell script to match the path of your tokenizer directory downloaded before using HuggingFace Git or the one you have build.
Run `./preprocessing_dataset.sh` to generate the tokenized dataset by using the givent tokenizer.
## 3.5 Model training
First, change the number of GPUs `--ntasks=128` you are needing to match your computational capabilities in the shell script called `run_training.sh`. In our case, we used 128 V100 32 GB GPUs from 32 nodes of 4 GPUs (`--ntasks-per-node=4` and `--gres=gpu:4`) during 20 hours (`--time=20:00:00`).
If you are using Jean Zay, you also need to change the `-A` flag to match one of your `@gpu` profile capable of running the job. You also need to move **ALL** of your datasets, tokenizer, script and outputs on the `$SCRATCH` disk space to preserve others users of suffuring of IO issues.
### 3.5.1 Pre-training from scratch
Once the SLURM parameters updated, you have to change name of the model architecture in the flag `--model_type="camembert"` and to update the `--config_overrides=` according to the specifications of the architecture you are trying to train. In our case, RoBERTa had a `514` sequence length, a vocabulary of `32005` (32K tokens of the tokenizer and 5 of the model architecture) tokens, the identifier of the beginning-of-sentence token (BOS) and end-of-sentence token (EOS) are respectivly `5` and `6`. Change the
Then, go to `./from_scratch/` directory.
Run `sbatch ./run_training.sh` to send the training job in the SLURM queue.
### 3.5.2 continue pre-training
Once the SLURM parameters updated, you have to change path of the model / tokenizer you want to start from `--model_name_or_path=` / `--tokenizer_name=` to the path of the model downloaded from HuggingFace's Git in the section 3.3.
Then, go to `./continued_pretraining/` directory.
Run `sbatch ./run_training.sh` to send the training job in the SLURM queue.
# 4. Fine-tuning on a downstream task
You just need to change the name of the model to `Dr-BERT/DrBERT-7GB` in any of the examples given by HuggingFace's team [here](https://huggingface.co/docs/transformers/tasks/sequence_classification).
# Citation BibTeX
```bibtex
@inproceedings{labrak2023drbert,
title = {{DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains}},
author = {Labrak, Yanis and Bazoge, Adrien and Dufour, Richard and Rouvier, Mickael and Morin, Emmanuel and Daille, Béatrice and Gourraud, Pierre-Antoine},
booktitle = {Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), Long Paper},
month = july,
year = 2023,
address = {Toronto, Canada},
publisher = {Association for Computational Linguistics}
}
```
| 7,307 | [
[
-0.033294677734375,
-0.043426513671875,
0.0218353271484375,
0.0173492431640625,
-0.0160064697265625,
0.0103607177734375,
-0.01020050048828125,
-0.0265655517578125,
0.035247802734375,
0.0321044921875,
-0.046234130859375,
-0.032867431640625,
-0.06927490234375,
... |
ltg/norbert3-large | 2023-07-03T16:07:58.000Z | [
"transformers",
"pytorch",
"fill-mask",
"BERT",
"NorBERT",
"Norwegian",
"encoder",
"custom_code",
"no",
"nb",
"nn",
"license:cc-by-4.0",
"autotrain_compatible",
"has_space",
"region:us"
] | fill-mask | ltg | null | null | ltg/norbert3-large | 2 | 502 | transformers | 2023-03-02T20:27:09 | ---
language:
- 'no'
- nb
- nn
inference: false
tags:
- BERT
- NorBERT
- Norwegian
- encoder
license: cc-by-4.0
---
# NorBERT 3 large
<img src="https://huggingface.co/ltg/norbert3-base/resolve/main/norbert.png" width=12.5%>
The official release of a new generation of NorBERT language models described in paper [**NorBench — A Benchmark for Norwegian Language Models**](https://aclanthology.org/2023.nodalida-1.61/). Plese read the paper to learn more details about the model.
## Other sizes:
- [NorBERT 3 xs (15M)](https://huggingface.co/ltg/norbert3-xs)
- [NorBERT 3 small (40M)](https://huggingface.co/ltg/norbert3-small)
- [NorBERT 3 base (123M)](https://huggingface.co/ltg/norbert3-base)
- [NorBERT 3 large (323M)](https://huggingface.co/ltg/norbert3-large)
## Generative NorT5 siblings:
- [NorT5 xs (32M)](https://huggingface.co/ltg/nort5-xs)
- [NorT5 small (88M)](https://huggingface.co/ltg/nort5-small)
- [NorT5 base (228M)](https://huggingface.co/ltg/nort5-base)
- [NorT5 large (808M)](https://huggingface.co/ltg/nort5-large)
## Example usage
This model currently needs a custom wrapper from `modeling_norbert.py`, you should therefore load the model with `trust_remote_code=True`.
```python
import torch
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("ltg/norbert3-large")
model = AutoModelForMaskedLM.from_pretrained("ltg/norbert3-large", trust_remote_code=True)
mask_id = tokenizer.convert_tokens_to_ids("[MASK]")
input_text = tokenizer("Nå ønsker de seg en[MASK] bolig.", return_tensors="pt")
output_p = model(**input_text)
output_text = torch.where(input_text.input_ids == mask_id, output_p.logits.argmax(-1), input_text.input_ids)
# should output: '[CLS] Nå ønsker de seg en ny bolig.[SEP]'
print(tokenizer.decode(output_text[0].tolist()))
```
The following classes are currently implemented: `AutoModel`, `AutoModelMaskedLM`, `AutoModelForSequenceClassification`, `AutoModelForTokenClassification`, `AutoModelForQuestionAnswering` and `AutoModeltForMultipleChoice`.
## Cite us
```bibtex
@inproceedings{samuel-etal-2023-norbench,
title = "{N}or{B}ench {--} A Benchmark for {N}orwegian Language Models",
author = "Samuel, David and
Kutuzov, Andrey and
Touileb, Samia and
Velldal, Erik and
{\O}vrelid, Lilja and
R{\o}nningstad, Egil and
Sigdel, Elina and
Palatkina, Anna",
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.61",
pages = "618--633",
abstract = "We present NorBench: a streamlined suite of NLP tasks and probes for evaluating Norwegian language models (LMs) on standardized data splits and evaluation metrics. We also introduce a range of new Norwegian language models (both encoder and encoder-decoder based). Finally, we compare and analyze their performance, along with other existing LMs, across the different benchmark tests of NorBench.",
}
``` | 3,146 | [
[
-0.024871826171875,
-0.041534423828125,
0.0021209716796875,
0.0174560546875,
-0.0234222412109375,
-0.0126190185546875,
-0.012115478515625,
-0.040740966796875,
0.01355743408203125,
0.0374755859375,
-0.0304107666015625,
-0.060333251953125,
-0.03680419921875,
0... |
TheBloke/LLaMa-7B-GPTQ | 2023-09-20T08:28:32.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:other",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/LLaMa-7B-GPTQ | 3 | 502 | transformers | 2023-07-15T18:15:35 | ---
base_model: https://ai.meta.com/blog/large-language-model-llama-meta-ai
inference: false
license: other
model_creator: Meta
model_name: LLaMA 7B
model_type: llama
prompt_template: '{prompt}
'
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 -->
# LLaMA 7B - GPTQ
- Model creator: [Meta](https://huggingface.co/none)
- Original model: [LLaMA 7B](https://ai.meta.com/blog/large-language-model-llama-meta-ai)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Meta's LLaMA 7b](https://ai.meta.com/blog/large-language-model-llama-meta-ai).
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/LLaMA-7b-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/LLaMA-7b-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/LLaMA-7b-GGUF)
* [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/huggyllama/llama-7b)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- prompt-template 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/LLaMA-7b-GPTQ/tree/main) | 4 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.90 GB | Yes | 4-bit, without Act Order and group size 128g. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/LLaMA-7b-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 4.28 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/LLaMA-7b-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 4.02 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/LLaMA-7b-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 3.90 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/LLaMA-7b-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_False](https://huggingface.co/TheBloke/LLaMA-7b-GPTQ/tree/gptq-8bit-128g-actorder_False) | 8 | 128 | No | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and without Act Order to improve AutoGPTQ speed. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/LLaMA-7b-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.16 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-64g-actorder_True](https://huggingface.co/TheBloke/LLaMA-7b-GPTQ/tree/gptq-8bit-64g-actorder_True) | 8 | 64 | Yes | 0.01 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 2048 | 7.31 GB | No | 8-bit, with group size 64g and Act Order for even higher inference quality. Poor AutoGPTQ CUDA speed. |
<!-- 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/LLaMA-7b-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/LLaMA-7b-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/LLaMA-7b-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/LLaMA-7b-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: `LLaMA-7b-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/LLaMA-7b-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'''{prompt}
'''
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: Meta's LLaMA 7b
This contains the weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file).
You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.
| 15,335 | [
[
-0.039794921875,
-0.056671142578125,
0.007686614990234375,
0.0196685791015625,
-0.0211944580078125,
-0.00809478759765625,
-0.00012814998626708984,
-0.04254150390625,
0.0198974609375,
0.025848388671875,
-0.04486083984375,
-0.0384521484375,
-0.02960205078125,
... |
dandelin/vilt-b32-finetuned-coco | 2022-01-23T09:45:24.000Z | [
"transformers",
"pytorch",
"vilt",
"arxiv:2102.03334",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | dandelin | null | null | dandelin/vilt-b32-finetuned-coco | 0 | 501 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
---
# Vision-and-Language Transformer (ViLT), fine-tuned on COCO
Vision-and-Language Transformer (ViLT) model fine-tuned on [COCO](https://cocodataset.org/#home). It was introduced in the paper [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://arxiv.org/abs/2102.03334) by Kim et al. and first released in [this repository](https://github.com/dandelin/ViLT).
Disclaimer: The team releasing ViLT did not write a model card for this model so this model card has been written by the Hugging Face team.
## Intended uses & limitations
You can use the model for image and text retrieval.
### How to use
Here is how to use the model in PyTorch:
```
from transformers import ViltProcessor, ViltForImageAndTextRetrieval
import requests
from PIL import Image
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
texts = ["An image of two cats chilling on a couch", "A football player scoring a goal"]
processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-coco")
model = ViltForImageAndTextRetrieval.from_pretrained("dandelin/vilt-b32-finetuned-coco")
# prepare inputs
encoding = processor(image, text, return_tensors="pt")
# forward pass
scores = dict()
for text in texts:
encoding = processor(image, text, return_tensors="pt")
outputs = model(**encoding)
scores[text] = outputs.logits[0, :].item()
```
## Training data
(to do)
## Training procedure
### Preprocessing
(to do)
### Pretraining
(to do)
## Evaluation results
(to do)
### BibTeX entry and citation info
```bibtex
@misc{kim2021vilt,
title={ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision},
author={Wonjae Kim and Bokyung Son and Ildoo Kim},
year={2021},
eprint={2102.03334},
archivePrefix={arXiv},
primaryClass={stat.ML}
}
``` | 1,928 | [
[
-0.04058837890625,
-0.057220458984375,
-0.0038166046142578125,
0.023040771484375,
-0.032684326171875,
-0.0029926300048828125,
-0.028350830078125,
-0.03533935546875,
0.00872802734375,
0.0305023193359375,
-0.035186767578125,
-0.033294677734375,
-0.055328369140625,... |
ken11/albert-base-japanese-v1 | 2021-12-21T18:04:30.000Z | [
"transformers",
"pytorch",
"tf",
"albert",
"fill-mask",
"japanese",
"ja",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | ken11 | null | null | ken11/albert-base-japanese-v1 | 0 | 501 | transformers | 2022-03-02T23:29:05 | ---
tags:
- fill-mask
- japanese
- albert
language:
- ja
license: mit
widget:
- text: "2022年の[MASK]概要"
---
## albert-base-japanese-v1
日本語事前学習済みALBERTモデルです
## How to use
### ファインチューニング
このモデルはPreTrainedモデルです
基本的には各種タスク用にファインチューニングして使用されることを想定しています
### Fill-Mask
このモデルではTokenizerにSentencepieceを利用しています
そのままでは`[MASK]`トークンのあとに[余計なトークンが混入する問題](https://ken11.jp/blog/sentencepiece-tokenizer-bug)があるので、利用する際には以下のようにする必要があります
#### for PyTorch
```py
from transformers import (
AlbertForMaskedLM, AlbertTokenizerFast
)
import torch
tokenizer = AlbertTokenizerFast.from_pretrained("ken11/albert-base-japanese-v1")
model = AlbertForMaskedLM.from_pretrained("ken11/albert-base-japanese-v1")
text = "大学で[MASK]の研究をしています"
tokenized_text = tokenizer.tokenize(text)
del tokenized_text[tokenized_text.index(tokenizer.mask_token) + 1]
input_ids = [tokenizer.cls_token_id]
input_ids.extend(tokenizer.convert_tokens_to_ids(tokenized_text))
input_ids.append(tokenizer.sep_token_id)
inputs = {"input_ids": [input_ids], "token_type_ids": [[0]*len(input_ids)], "attention_mask": [[1]*len(input_ids)]}
batch = {k: torch.tensor(v, dtype=torch.int64) for k, v in inputs.items()}
output = model(**batch)[0]
_, result = output[0, input_ids.index(tokenizer.mask_token_id)].topk(5)
print(tokenizer.convert_ids_to_tokens(result.tolist()))
# ['英語', '心理学', '数学', '医学', '日本語']
```
#### for TensorFlow
```py
from transformers import (
TFAlbertForMaskedLM, AlbertTokenizerFast
)
import tensorflow as tf
tokenizer = AlbertTokenizerFast.from_pretrained("ken11/albert-base-japanese-v1")
model = TFAlbertForMaskedLM.from_pretrained("ken11/albert-base-japanese-v1")
text = "大学で[MASK]の研究をしています"
tokenized_text = tokenizer.tokenize(text)
del tokenized_text[tokenized_text.index(tokenizer.mask_token) + 1]
input_ids = [tokenizer.cls_token_id]
input_ids.extend(tokenizer.convert_tokens_to_ids(tokenized_text))
input_ids.append(tokenizer.sep_token_id)
inputs = {"input_ids": [input_ids], "token_type_ids": [[0]*len(input_ids)], "attention_mask": [[1]*len(input_ids)]}
batch = {k: tf.convert_to_tensor(v, dtype=tf.int32) for k, v in inputs.items()}
output = model(**batch)[0]
result = tf.math.top_k(output[0, input_ids.index(tokenizer.mask_token_id)], k=5)
print(tokenizer.convert_ids_to_tokens(result.indices.numpy()))
# ['英語', '心理学', '数学', '医学', '日本語']
```
## Training Data
学習には
- [日本語Wikipediaの全文](https://ja.wikipedia.org/wiki/Wikipedia:%E3%83%87%E3%83%BC%E3%82%BF%E3%83%99%E3%83%BC%E3%82%B9%E3%83%80%E3%82%A6%E3%83%B3%E3%83%AD%E3%83%BC%E3%83%89)
- [livedoorニュースコーパス](https://www.rondhuit.com/download.html#ldcc)
を利用しています
## Tokenizer
トークナイザーは[Sentencepiece](https://github.com/google/sentencepiece)を利用しています
こちらも学習データは同様です
## Licenese
[The MIT license](https://opensource.org/licenses/MIT)
| 2,788 | [
[
-0.0232696533203125,
-0.049896240234375,
0.01593017578125,
0.0145416259765625,
-0.02593994140625,
0.00665283203125,
-0.02838134765625,
0.0011882781982421875,
0.0184326171875,
0.01290130615234375,
-0.03857421875,
-0.05194091796875,
-0.055328369140625,
0.00943... |
stanfordnlp/stanza-de | 2023-10-02T23:32:24.000Z | [
"stanza",
"token-classification",
"de",
"license:apache-2.0",
"region:us",
"has_space"
] | token-classification | stanfordnlp | null | null | stanfordnlp/stanza-de | 3 | 501 | stanza | 2022-03-02T23:29:05 | ---
tags:
- stanza
- token-classification
library_name: stanza
language: de
license: apache-2.0
---
# Stanza model for German (de)
Stanza is a collection of accurate and efficient tools for the linguistic analysis of many human languages. Starting from raw text to syntactic analysis and entity recognition, Stanza brings state-of-the-art NLP models to languages of your choosing.
Find more about it in [our website](https://stanfordnlp.github.io/stanza) and our [GitHub repository](https://github.com/stanfordnlp/stanza).
This card and repo were automatically prepared with `hugging_stanza.py` in the `stanfordnlp/huggingface-models` repo
Last updated 2023-10-02 23:31:53.680
| 679 | [
[
-0.03924560546875,
-0.06927490234375,
0.027435302734375,
0.0266265869140625,
-0.023773193359375,
-0.01248931884765625,
-0.008575439453125,
-0.03497314453125,
0.0102386474609375,
0.0250701904296875,
-0.04693603515625,
-0.0443115234375,
-0.0390625,
-0.00280380... |
Lykon/absolute-realism-1.0 | 2023-08-27T16:05:59.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"art",
"artistic",
"absolute-realism",
"en",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | Lykon | null | null | Lykon/absolute-realism-1.0 | 1 | 501 | diffusers | 2023-08-27T16:05:58 | ---
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- art
- artistic
- diffusers
- absolute-realism
duplicated_from: lykon-absolute-realism/absolute-reality-1.0
---
# Absolute reality 1.0
`lykon-absolute-realism/absolute-reality-1.0` is a Stable Diffusion model that has been fine-tuned on [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5).
Please consider supporting me:
- on [Patreon](https://www.patreon.com/Lykon275)
- or [buy me a coffee](https://snipfeed.co/lykon)
## Diffusers
For more general information on how to run text-to-image models with 🧨 Diffusers, see [the docs](https://huggingface.co/docs/diffusers/using-diffusers/conditional_image_generation).
1. Installation
```
pip install diffusers transformers accelerate
```
2. Run
```py
from diffusers import AutoPipelineForText2Image, DEISMultistepScheduler
import torch
pipe = AutoPipelineForText2Image.from_pretrained('lykon-absolute-realism/absolute-reality-1.0', torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DEISMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")
prompt = "portrait photo of muscular bearded guy in a worn mech suit, light bokeh, intricate, steel metal, elegant, sharp focus, soft lighting, vibrant colors"
generator = torch.manual_seed(33)
image = pipe(prompt, generator=generator, num_inference_steps=25).images[0]
image.save("./image.png")
```
| 1,509 | [
[
-0.02716064453125,
-0.052764892578125,
0.036834716796875,
0.028533935546875,
-0.030059814453125,
-0.00643157958984375,
0.0009822845458984375,
-0.026092529296875,
0.020538330078125,
0.02813720703125,
-0.052093505859375,
-0.03265380859375,
-0.048675537109375,
... |
stablediffusionapi/juggernaut-xl | 2023-09-07T02:26:23.000Z | [
"diffusers",
"stablediffusionapi.com",
"stable-diffusion-api",
"text-to-image",
"ultra-realistic",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | stablediffusionapi | null | null | stablediffusionapi/juggernaut-xl | 1 | 501 | diffusers | 2023-09-07T02:21:46 | ---
license: creativeml-openrail-m
tags:
- stablediffusionapi.com
- stable-diffusion-api
- text-to-image
- ultra-realistic
pinned: true
---
# Juggernaut XL (SDXL model) 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"
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)
Model link: [View model](https://stablediffusionapi.com/models/juggernaut-xl)
Credits: [View credits](https://civitai.com/?query=Juggernaut%20XL%20%28SDXL%20model%29)
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",
"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** | 2,490 | [
[
-0.035247802734375,
-0.047027587890625,
0.034210205078125,
0.0144500732421875,
-0.034698486328125,
0.01873779296875,
0.0273590087890625,
-0.02508544921875,
0.03802490234375,
0.052459716796875,
-0.06683349609375,
-0.060028076171875,
-0.0311279296875,
0.000527... |
dltjdgh0928/lsh_finetune_v0.11 | 2023-10-31T09:37:21.000Z | [
"transformers",
"pytorch",
"mistral",
"text-generation",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | dltjdgh0928 | null | null | dltjdgh0928/lsh_finetune_v0.11 | 0 | 501 | transformers | 2023-10-31T09:29:43 | ---
license: apache-2.0
---
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test
mistral_finetune_test | 291 | [
[
-0.0150909423828125,
-0.0227203369140625,
0.0316162109375,
0.060302734375,
-0.0088348388671875,
-0.0287628173828125,
0.01442718505859375,
0.01372528076171875,
0.0013189315795898438,
0.031463623046875,
-0.020660400390625,
-0.0148773193359375,
-0.031341552734375,
... |
timm/vit_base_patch16_clip_224.laion2b_ft_in1k | 2023-05-06T00:01:30.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"dataset:laion-2b",
"arxiv:2212.07143",
"arxiv:2210.08402",
"arxiv:2010.11929",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/vit_base_patch16_clip_224.laion2b_ft_in1k | 0 | 500 | timm | 2022-11-08T23:16:23 | ---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
datasets:
- imagenet-1k
- laion-2b
---
# Model card for vit_base_patch16_clip_224.laion2b_ft_in1k
A Vision Transformer (ViT) image classification model. Pretrained on LAION-2B image-text pairs using OpenCLIP. Fine-tuned on ImageNet-1k in `timm`. See recipes in [Reproducible scaling laws](https://arxiv.org/abs/2212.07143).
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 86.6
- GMACs: 16.9
- Activations (M): 16.5
- Image size: 224 x 224
- **Papers:**
- OpenCLIP: https://github.com/mlfoundations/open_clip
- Reproducible scaling laws for contrastive language-image learning: https://arxiv.org/abs/2212.07143
- LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:**
- LAION-2B
## 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_base_patch16_clip_224.laion2b_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(
'vit_base_patch16_clip_224.laion2b_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, 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
@software{ilharco_gabriel_2021_5143773,
author = {Ilharco, Gabriel and
Wortsman, Mitchell and
Wightman, Ross and
Gordon, Cade and
Carlini, Nicholas and
Taori, Rohan and
Dave, Achal and
Shankar, Vaishaal and
Namkoong, Hongseok and
Miller, John and
Hajishirzi, Hannaneh and
Farhadi, Ali and
Schmidt, Ludwig},
title = {OpenCLIP},
month = jul,
year = 2021,
note = {If you use this software, please cite it as below.},
publisher = {Zenodo},
version = {0.1},
doi = {10.5281/zenodo.5143773},
url = {https://doi.org/10.5281/zenodo.5143773}
}
```
```bibtex
@article{cherti2022reproducible,
title={Reproducible scaling laws for contrastive language-image learning},
author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia},
journal={arXiv preprint arXiv:2212.07143},
year={2022}
}
```
```bibtex
@inproceedings{schuhmann2022laionb,
title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
author={Christoph Schuhmann and
Romain Beaumont and
Richard Vencu and
Cade W Gordon and
Ross Wightman and
Mehdi Cherti and
Theo Coombes and
Aarush Katta and
Clayton Mullis and
Mitchell Wortsman and
Patrick Schramowski and
Srivatsa R Kundurthy and
Katherine Crowson and
Ludwig Schmidt and
Robert Kaczmarczyk and
Jenia Jitsev},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2022},
url={https://openreview.net/forum?id=M3Y74vmsMcY}
}
```
```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}}
}
```
| 5,690 | [
[
-0.02899169921875,
-0.0288238525390625,
0.00994110107421875,
0.00982666015625,
-0.0272369384765625,
-0.033416748046875,
-0.033355712890625,
-0.030242919921875,
0.008392333984375,
0.02716064453125,
-0.030242919921875,
-0.0430908203125,
-0.051177978515625,
-0.... |
Lianglab/PharmBERT-cased | 2023-06-23T18:44:04.000Z | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | Lianglab | null | null | Lianglab/PharmBERT-cased | 1 | 500 | transformers | 2023-05-10T21:28:07 | ## PharmBERT cased
A domain-specific BERT model for drug labels
Please refer to the PharmBERT paper for the model description:
https://doi.org/10.1093/bib/bbad226
For pre-training and fine-tuning codes, please refer to the PharmBERT Github:
https://github.com/TahaAslani/PharmBERT
## Citation
Please cite as:
```
@article{PharmBERT,
author = {ValizadehAslani, Taha and Shi, Yiwen and Ren, Ping and Wang, Jing and Zhang, Yi and Hu, Meng and Zhao, Liang and Liang, Hualou},
title = "{PharmBERT: a domain-specific BERT model for drug labels}",
journal = {Briefings in Bioinformatics},
year = {2023},
month = {06},
issn = {1477-4054},
doi = {10.1093/bib/bbad226},
url = {https://doi.org/10.1093/bib/bbad226},
note = {bbad226},
eprint = {https://academic.oup.com/bib/advance-article-pdf/doi/10.1093/bib/bbad226/50603440/bbad226.pdf},
}
``` | 877 | [
[
-0.006191253662109375,
-0.036712646484375,
0.02996826171875,
0.0182647705078125,
-0.01947021484375,
-0.005992889404296875,
-0.002849578857421875,
-0.00627899169921875,
0.0170440673828125,
0.047332763671875,
-0.042572021484375,
-0.0645751953125,
-0.0506591796875,... |
digiplay/bluePencil_v09b | 2023-06-20T21:14:37.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | digiplay | null | null | digiplay/bluePencil_v09b | 2 | 500 | diffusers | 2023-06-20T09:49:45 | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/79083?modelVersionId=89814
Original Author's DEMO image:
| 366 | [
[
-0.0276641845703125,
-0.0096893310546875,
0.035919189453125,
0.00952911376953125,
-0.0245819091796875,
-0.0191802978515625,
0.016357421875,
0.00208282470703125,
0.046417236328125,
0.048431396484375,
-0.048248291015625,
-0.01554107666015625,
-0.003734588623046875... |
TheBloke/CodeLlama-7B-GPTQ | 2023-09-27T12:46:09.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"llama-2",
"custom_code",
"code",
"arxiv:2308.12950",
"license:llama2",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/CodeLlama-7B-GPTQ | 11 | 500 | transformers | 2023-08-24T23:39:33 | ---
language:
- code
license: llama2
tags:
- llama-2
model_name: CodeLlama 7B
base_model: codellama/CodeLlama-7b-hf
inference: false
model_creator: Meta
model_type: llama
pipeline_tag: text-generation
prompt_template: '{prompt}
'
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 -->
# CodeLlama 7B - GPTQ
- Model creator: [Meta](https://huggingface.co/meta-llama)
- Original model: [CodeLlama 7B](https://huggingface.co/codellama/CodeLlama-7b-hf)
<!-- description start -->
## Description
This repo contains GPTQ model files for [Meta's CodeLlama 7B](https://huggingface.co/codellama/CodeLlama-7b-hf).
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/CodeLlama-7B-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-7B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-7B-GGUF)
* [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-7b-hf)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: None
```
{prompt}
```
<!-- prompt-template 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/CodeLlama-7B-GPTQ/tree/main) | 4 | 128 | No | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 3.90 GB | Yes | 4-bit, without Act Order and group size 128g. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-7B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 4.28 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/CodeLlama-7B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 4.02 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/CodeLlama-7B-GPTQ/tree/gptq-4bit-128g-actorder_True) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 3.90 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/CodeLlama-7B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 7.01 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/CodeLlama-7B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) | 8192 | 7.16 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/CodeLlama-7B-GPTQ:main`
- With Git, you can clone a branch with:
```
git clone --single-branch --branch main https://huggingface.co/TheBloke/CodeLlama-7B-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/CodeLlama-7B-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/CodeLlama-7B-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: `CodeLlama-7B-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/CodeLlama-7B-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=True,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
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: Meta's CodeLlama 7B
# **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 7B 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.
- [ ] Instructions / chat.
- [ ] Python specialist.
```python
from transformers import AutoTokenizer
import transformers
import torch
model = "codellama/CodeLlama-7b-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 model of 7B parameters.**
**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 it's [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-user-guide](https://ai.meta.com/llama/responsible-user-guide).
| 21,017 | [
[
-0.0377197265625,
-0.060791015625,
0.01129913330078125,
0.01007080078125,
-0.0258026123046875,
-0.0078277587890625,
0.0018663406372070312,
-0.037200927734375,
0.0160369873046875,
0.02972412109375,
-0.0438232421875,
-0.04571533203125,
-0.02471923828125,
-0.00... |
bloomberg/KBIR | 2023-02-21T18:04:20.000Z | [
"transformers",
"pytorch",
"roberta",
"license:apache-2.0",
"endpoints_compatible",
"has_space",
"region:us"
] | null | bloomberg | null | null | bloomberg/KBIR | 8 | 499 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
---
# Keyphrase Boundary Infilling with Replacement (KBIR)
The KBIR model as described in "Learning Rich Representations of Keyphrases from Text" from Findings of NAACL 2022 (https://aclanthology.org/2022.findings-naacl.67.pdf) builds on top of the RoBERTa architecture by adding an Infilling head and a Replacement Classification head that is used during pre-training. However, these heads are not used during the downstream evaluation of the model and we only leverage the pre-trained embeddings. Discarding the heads thereby allows us to be compatible with all AutoModel classes that RoBERTa supports.
We provide examples on how to perform downstream evaluation on some of the tasks reported in the paper.
## Downstream Evaluation
### Keyphrase Extraction
```
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("bloomberg/KBIR")
model = AutoModelForTokenClassification.from_pretrained("bloomberg/KBIR")
from datasets import load_dataset
dataset = load_dataset("midas/semeval2017_ke_tagged")
```
Reported Results:
| Model | Inspec | SE10 | SE17 |
|-----------------------|--------|-------|-------|
| RoBERTa+BiLSTM-CRF | 59.5 | 27.8 | 50.8 |
| RoBERTa+TG-CRF | 60.4 | 29.7 | 52.1 |
| SciBERT+Hypernet-CRF | 62.1 | 36.7 | 54.4 |
| RoBERTa+Hypernet-CRF | 62.3 | 34.8 | 53.3 |
| RoBERTa-extended-CRF* | 62.09 | 40.61 | 52.32 |
| KBI-CRF* | 62.61 | 40.81 | 59.7 |
| KBIR-CRF* | 62.72 | 40.15 | 62.56 |
### Named Entity Recognition
```
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("bloomberg/KBIR")
model = AutoModelForTokenClassification.from_pretrained("bloomberg/KBIR")
from datasets import load_dataset
dataset = load_dataset("conll2003")
```
Reported Results:
| Model | F1 |
|---------------------------------|-------|
| LSTM-CRF (Lample et al., 2016) | 91.0 |
| ELMo (Peters et al., 2018) | 92.2 |
| BERT (Devlin et al., 2018) | 92.8 |
| (Akbik et al., 2019) | 93.1 |
| (Baevski et al., 2019) | 93.5 |
| LUKE (Yamada et al., 2020) | 94.3 |
| LUKE w/o entity attention | 94.1 |
| RoBERTa (Yamada et al., 2020) | 92.4 |
| RoBERTa-extended* | 92.54 |
| KBI* | 92.73 |
| KBIR* | 92.97 |
### Question Answering
```
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("bloomberg/KBIR")
model = AutoModelForQuestionAnswering.from_pretrained("bloomberg/KBIR")
from datasets import load_dataset
dataset = load_dataset("squad")
```
Reported Results:
| Model | EM | F1 |
|------------------------|-------|-------|
| BERT | 84.2 | 91.1 |
| XLNet | 89.0 | 94.5 |
| ALBERT | 89.3 | 94.8 |
| LUKE | 89.8 | 95.0 |
| LUKE w/o entity attention | 89.2 | 94.7 |
| RoBERTa | 88.9 | 94.6 |
| RoBERTa-extended* | 88.88 | 94.55 |
| KBI* | 88.97 | 94.7 |
| KBIR* | 89.04 | 94.75 |
## Any other classification task
As mentioned above since KBIR is built on top of the RoBERTa architecture, it is compatible with any AutoModel setting that RoBERTa is also compatible with.
We encourage you to try fine-tuning KBIR on different datasets and report the downstream results.
## Citation
Please cite this work using the following BibTeX entry:
```
@inproceedings{kulkarni-etal-2022-learning,
title = "Learning Rich Representation of Keyphrases from Text",
author = "Kulkarni, Mayank and
Mahata, Debanjan and
Arora, Ravneet and
Bhowmik, Rajarshi",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.67",
doi = "10.18653/v1/2022.findings-naacl.67",
pages = "891--906",
abstract = "In this work, we explore how to train task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 8.16 points in F1) over SOTA, when the LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases related to the input text in the CatSeq format, instead of the denoised original input. This also led to gains in performance (upto 4.33 points in F1@M) over SOTA for keyphrase generation. Additionally, we also fine-tune the pre-trained language models on named entity recognition (NER), question answering (QA), relation extraction (RE), abstractive summarization and achieve comparable performance with that of the SOTA, showing that learning rich representation of keyphrases is indeed beneficial for many other fundamental NLP tasks.",
}
```
## Contact
For any questions contact dmahata@bloomberg.net
| 5,550 | [
[
-0.0207977294921875,
-0.037628173828125,
0.023040771484375,
0.01329803466796875,
-0.0299835205078125,
0.0222625732421875,
-0.021026611328125,
-0.0216522216796875,
0.0096282958984375,
0.0311126708984375,
-0.02734375,
-0.043853759765625,
-0.063720703125,
0.004... |
google/roberta2roberta_L-24_wikisplit | 2023-01-24T16:43:24.000Z | [
"transformers",
"pytorch",
"encoder-decoder",
"text2text-generation",
"en",
"arxiv:1907.12461",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | text2text-generation | google | null | null | google/roberta2roberta_L-24_wikisplit | 7 | 499 | transformers | 2022-03-02T23:29:05 | ---
language: en
license: apache-2.0
---
# Roberta2Roberta_L-24_wikisplit EncoderDecoder model
The model was introduced in
[this paper](https://arxiv.org/abs/1907.12461) by Sascha Rothe, Shashi Narayan, Aliaksei Severyn and first released in [this repository](https://tfhub.dev/google/bertseq2seq/roberta24_cnndm/1).
The model is an encoder-decoder model that was initialized on the `roberta-large` checkpoints for both the encoder
and decoder and fine-tuned on sentence splitting on the [WikiSplit](https://github.com/google-research-datasets/wiki-split) dataset.
Disclaimer: The model card has been written by the Hugging Face team.
## How to use
You can use this model for sentence splitting, *e.g.*
**IMPORTANT**: The model was not trained on the `"` (double quotation mark) character -> so the before tokenizing the text,
it is advised to replace all `"` (double quotation marks) with two single `'` (single quotation mark).
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_wikisplit")
model = AutoModelForSeq2SeqLM.from_pretrained("google/roberta2roberta_L-24_wikisplit")
long_sentence = """Due to the hurricane, Lobsterfest has been canceled, making Bob very happy about it and he decides to open Bob 's Burgers for customers who were planning on going to Lobsterfest."""
input_ids = tokenizer(tokenizer.bos_token + long_sentence + tokenizer.eos_token, return_tensors="pt").input_ids
output_ids = model.generate(input_ids)[0]
print(tokenizer.decode(output_ids, skip_special_tokens=True))
# should output
# Due to the hurricane, Lobsterfest has been canceled, making Bob very happy about it. He decides to open Bob's Burgers for customers who were planning on going to Lobsterfest.
```
| 1,802 | [
[
-0.032562255859375,
-0.0635986328125,
0.0160980224609375,
0.0087890625,
-0.0289306640625,
-0.0191802978515625,
-0.0184783935546875,
-0.0185699462890625,
0.02203369140625,
0.0241546630859375,
-0.052398681640625,
-0.019989013671875,
-0.054840087890625,
0.03341... |
lucascheist/zerfito | 2023-04-14T23:31:42.000Z | [
"diffusers",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | lucascheist | null | null | lucascheist/zerfito | 0 | 499 | diffusers | 2023-04-14T23:26:22 | ---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### zerfito Dreambooth model trained by lucascheist 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)
Sample pictures of this concept:
| 500 | [
[
-0.036651611328125,
-0.05694580078125,
0.04718017578125,
0.01861572265625,
-0.0179901123046875,
0.024505615234375,
0.01377105712890625,
-0.032806396484375,
0.056732177734375,
0.0046539306640625,
-0.0242462158203125,
-0.01439666748046875,
-0.032989501953125,
... |
shehan97/mobilevitv2-1.0-voc-deeplabv3 | 2023-05-02T13:31:27.000Z | [
"transformers",
"pytorch",
"mobilevitv2",
"vision",
"image-segmentation",
"arxiv:2206.02680",
"arxiv:1706.05587",
"license:other",
"endpoints_compatible",
"region:us"
] | image-segmentation | shehan97 | null | null | shehan97/mobilevitv2-1.0-voc-deeplabv3 | 0 | 499 | transformers | 2023-05-02T09:36:36 | ---
license: other
library_name: transformers
tags:
- vision
- image-segmentation
---
# MobileViTv2 + DeepLabv3 (shehan97/mobilevitv2-1.0-voc-deeplabv3)
<!-- Provide a quick summary of what the model is/does. -->
MobileViTv2 model pre-trained on PASCAL VOC at resolution 512x512.
It was introduced in [Separable Self-attention for Mobile Vision Transformers](https://arxiv.org/abs/2206.02680) by Sachin Mehta and Mohammad Rastegari, and first released in [this](https://github.com/apple/ml-cvnets) repository. The license used is [Apple sample code license](https://github.com/apple/ml-cvnets/blob/main/LICENSE).
Disclaimer: The team releasing MobileViT did not write a model card for this model so this model card has been written by the Hugging Face team.
### Model Description
<!-- Provide a longer summary of what this model is. -->
MobileViTv2 is constructed by replacing the multi-headed self-attention in MobileViT with separable self-attention.
The model in this repo adds a [DeepLabV3](https://arxiv.org/abs/1706.05587) head to the MobileViT backbone for semantic segmentation.
### Intended uses & limitations
You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?search=mobilevitv2) to look for fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model:
```python
from transformers import MobileViTv2FeatureExtractor, MobileViTv2ForSemanticSegmentation
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 = MobileViTv2FeatureExtractor.from_pretrained("shehan97/mobilevitv2-1.0-voc-deeplabv3")
model = MobileViTv2ForSemanticSegmentation.from_pretrained("shehan97/mobilevitv2-1.0-voc-deeplabv3")
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
predicted_mask = logits.argmax(1).squeeze(0)
```
Currently, both the feature extractor and model support PyTorch.
## Training data
The MobileViT + DeepLabV3 model was pretrained on [ImageNet-1k](https://huggingface.co/datasets/imagenet-1k), a dataset consisting of 1 million images and 1,000 classes, and then fine-tuned on the [PASCAL VOC2012](http://host.robots.ox.ac.uk/pascal/VOC/) dataset.
### BibTeX entry and citation info
```bibtex
@inproceedings{vision-transformer,
title = {Separable Self-attention for Mobile Vision Transformers},
author = {Sachin Mehta and Mohammad Rastegari},
year = {2022},
URL = {https://arxiv.org/abs/2206.02680}
}
```
| 2,597 | [
[
-0.045867919921875,
-0.0162200927734375,
0.002498626708984375,
0.0195465087890625,
-0.03143310546875,
-0.0267333984375,
0.0164642333984375,
-0.03375244140625,
0.00977325439453125,
0.0301666259765625,
-0.0455322265625,
-0.0256805419921875,
-0.0443115234375,
-... |
seara/rubert-tiny2-ru-go-emotions | 2023-08-25T19:25:01.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"text-classification",
"sentiment-analysis",
"multi-label-classification",
"sentiment analysis",
"rubert",
"sentiment",
"tiny",
"russian",
"multilabel",
"classification",
"emotion-classification",
"emotion-recognition",
"emotion",
"... | text-classification | seara | null | null | seara/rubert-tiny2-ru-go-emotions | 4 | 499 | transformers | 2023-05-02T16:52:52 | ---
license: mit
language:
- ru
metrics:
- f1
- roc_auc
- precision
- recall
pipeline_tag: text-classification
tags:
- sentiment-analysis
- multi-label-classification
- sentiment analysis
- rubert
- sentiment
- bert
- tiny
- russian
- multilabel
- classification
- emotion-classification
- emotion-recognition
- emotion
datasets:
- seara/ru_go_emotions
---
This is [RuBERT-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) model fine-tuned for __emotion classification__ of short __Russian__ texts.
The task is a __multi-label classification__ with the following labels:
```yaml
0: admiration
1: amusement
2: anger
3: annoyance
4: approval
5: caring
6: confusion
7: curiosity
8: desire
9: disappointment
10: disapproval
11: disgust
12: embarrassment
13: excitement
14: fear
15: gratitude
16: grief
17: joy
18: love
19: nervousness
20: optimism
21: pride
22: realization
23: relief
24: remorse
25: sadness
26: surprise
27: neutral
```
Label to Russian label:
```yaml
admiration: восхищение
amusement: веселье
anger: злость
annoyance: раздражение
approval: одобрение
caring: забота
confusion: непонимание
curiosity: любопытство
desire: желание
disappointment: разочарование
disapproval: неодобрение
disgust: отвращение
embarrassment: смущение
excitement: возбуждение
fear: страх
gratitude: признательность
grief: горе
joy: радость
love: любовь
nervousness: нервозность
optimism: оптимизм
pride: гордость
realization: осознание
relief: облегчение
remorse: раскаяние
sadness: грусть
surprise: удивление
neutral: нейтральность
```
## Usage
```python
from transformers import pipeline
model = pipeline(model="seara/rubert-tiny2-ru-go-emotions")
model("Привет, ты мне нравишься!")
# [{'label': 'love', 'score': 0.5955629944801331}]
```
## Dataset
This model was trained on translated GoEmotions dataset called [ru_go_emotions](https://huggingface.co/datasets/seara/ru_go_emotions).
An overview of the training data can be found on [Hugging Face card](https://huggingface.co/datasets/seara/ru_go_emotions) and on
[Github repository](https://github.com/searayeah/ru-goemotions).
## Training
Training were done in this [project](https://github.com/searayeah/bert-russian-sentiment-emotion) with this parameters:
```yaml
tokenizer.max_length: null
batch_size: 64
optimizer: adam
lr: 0.00001
weight_decay: 0
num_epochs: 31
```
## Eval results (on test split)
| |precision|recall|f1-score|auc-roc|support|
|--------------|---------|------|--------|-------|-------|
|admiration |0.68 |0.61 |0.64 |0.92 |504 |
|amusement |0.8 |0.84 |0.82 |0.96 |264 |
|anger |0.55 |0.33 |0.42 |0.9 |198 |
|annoyance |0.56 |0.03 |0.06 |0.81 |320 |
|approval |0.6 |0.18 |0.28 |0.78 |351 |
|caring |0.5 |0.04 |0.07 |0.84 |135 |
|confusion |0.77 |0.07 |0.12 |0.9 |153 |
|curiosity |0.51 |0.34 |0.41 |0.92 |284 |
|desire |0.71 |0.18 |0.29 |0.88 |83 |
|disappointment|0.0 |0.0 |0.0 |0.76 |151 |
|disapproval |0.48 |0.1 |0.17 |0.85 |267 |
|disgust |0.94 |0.12 |0.22 |0.9 |123 |
|embarrassment |0.0 |0.0 |0.0 |0.84 |37 |
|excitement |0.81 |0.2 |0.33 |0.88 |103 |
|fear |0.73 |0.42 |0.54 |0.92 |78 |
|gratitude |0.95 |0.89 |0.92 |0.99 |352 |
|grief |0.0 |0.0 |0.0 |0.76 |6 |
|joy |0.66 |0.52 |0.58 |0.93 |161 |
|love |0.8 |0.79 |0.79 |0.97 |238 |
|nervousness |0.0 |0.0 |0.0 |0.81 |23 |
|optimism |0.67 |0.41 |0.51 |0.89 |186 |
|pride |0.0 |0.0 |0.0 |0.89 |16 |
|realization |0.0 |0.0 |0.0 |0.7 |145 |
|relief |0.0 |0.0 |0.0 |0.84 |11 |
|remorse |0.59 |0.71 |0.65 |0.99 |56 |
|sadness |0.77 |0.37 |0.5 |0.89 |156 |
|surprise |0.59 |0.35 |0.44 |0.88 |141 |
|neutral |0.64 |0.58 |0.61 |0.81 |1787 |
|micro avg |0.68 |0.43 |0.53 |0.93 |6329 |
|macro avg |0.51 |0.29 |0.33 |0.87 |6329 |
|weighted avg |0.62 |0.43 |0.48 |0.86 |6329 |
| 4,316 | [
[
-0.0264892578125,
-0.03765869140625,
0.00858306884765625,
0.0243988037109375,
-0.0399169921875,
-0.004482269287109375,
-0.0160980224609375,
-0.0222625732421875,
0.03387451171875,
0.007373809814453125,
-0.039703369140625,
-0.04510498046875,
-0.058929443359375,
... |
filipealmeida/Mistral-7B-Instruct-v0.1-sharded | 2023-09-28T01:08:41.000Z | [
"transformers",
"pytorch",
"llama",
"text-generation",
"finetuned",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | filipealmeida | null | null | filipealmeida/Mistral-7B-Instruct-v0.1-sharded | 1 | 499 | transformers | 2023-09-28T00:59:50 | ---
license: apache-2.0
pipeline_tag: text-generation
tags:
- finetuned
---
# Sharded version of Mistral-7B-Instruct-v0.1
This is the sharded version of Mistral-7B-Instruct-v0.1 so you can use it when you have limited CPU memory
# Model Card for Mistral-7B-Instruct-v0.1
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets.
For full details of this model please read our [release blog post](https://mistral.ai/news/announcing-mistral-7b/)
## Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[\INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
encodeds = tokenizer(text, return_tensors="pt", add_special_tokens=False)
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Model Architecture
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
## The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed. | 2,359 | [
[
-0.0218048095703125,
-0.06866455078125,
0.01678466796875,
0.0263671875,
-0.003643035888671875,
-0.0283050537109375,
-0.00438690185546875,
-0.00910186767578125,
-0.00244140625,
0.047943115234375,
-0.038421630859375,
-0.03564453125,
-0.038604736328125,
-0.0050... |
flobbit/div0-tank-sdxl-lora | 2023-10-07T03:13:04.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"en",
"license:apache-2.0",
"has_space",
"region:us"
] | text-to-image | flobbit | null | null | flobbit/div0-tank-sdxl-lora | 2 | 499 | diffusers | 2023-10-07T02:17:06 | ---
license: apache-2.0
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
widget:
- text: a (miniature) vtnktnk tank being used as a flower pot, dslr, 8k, beautiful, hyper realistic (cfg = 7.5, seed = 158618480)
inference: true
language:
- en
---
# div0-tank-sdxl-lora
LoRA for SDXL 1.0 Base for for generating images of the widely recognized Div0 tank... known as Div0 because $/quality results in a divide by zero error. People have generally given up on the tank, and are trying to find new uses for it. Hipsters generally avoid being seen in such a non-trendy ride. Common uses are demonstrated in the sample images. Can you discover more? The LoRA is in a `safetensors` format for use in diffusers or in UIs such as A1111.
## How to use
In A1111, specify the LoRA in the prompt along with a weight \<lora:vtnktnk_SDXL_v1_32-000015:1\>, then use the trigger keyword. Further example images with A1111 prompts at (https://civitai.com/models/157883/div0-xl-tank-model)
Example diffusers prompt which you can run in the inference to the right: 'a (miniature) vtnktnk tank being used as a flower pot, dslr, 8k, beautiful, hyper realistic (cfg = 7.5, seed = 158618480)'
## Recommended Weight:
1.0 (lowering the LoRA weight in A1111 may remove the cover text and leave an artistic cover)
## Trigger:
vtnktnk
## Helper:
In general you can generate a wide variety of tanks, characters, and scenes.
## Notes:
The LoRA seems to work well with other base SDXL models.
## Methodology:
This model was trained on only images at 1024x1024. No regularization images were used. 15 epochs with 5880 overall steps.
| 1,832 | [
[
-0.040435791015625,
-0.0390625,
0.041412353515625,
0.0308074951171875,
-0.040283203125,
-0.0140228271484375,
0.0391845703125,
0.004421234130859375,
0.0245361328125,
0.033599853515625,
-0.046173095703125,
-0.033233642578125,
-0.04052734375,
-0.004722595214843... |
publichealthsurveillance/PHS-BERT | 2022-07-29T03:39:46.000Z | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"arxiv:2204.04521",
"autotrain_compatible",
"endpoints_compatible",
"has_space",
"region:us"
] | fill-mask | publichealthsurveillance | null | null | publichealthsurveillance/PHS-BERT | 5 | 498 | transformers | 2022-04-12T05:35:31 | # PHS-BERT
We present and release [PHS-BERT](https://arxiv.org/abs/2204.04521), a transformer-based pretrained language model (PLM), to identify tasks related to public health surveillance (PHS) on social media. Compared with existing PLMs that are mainly evaluated on limited tasks, PHS-BERT achieved state-of-the-art performance on 25 tested datasets, showing that our PLM is robust and generalizable in common PHS tasks.
## Usage
Load the model via [Huggingface's Transformers library](https://github.com/huggingface/transformers]):
```
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("publichealthsurveillance/PHS-BERT")
model = AutoModel.from_pretrained("publichealthsurveillance/PHS-BERT")
```
## Training Procedure
### Pretraining
We followed the standard pretraining protocols of BERT and initialized PHS-BERT with weights from BERT during the training phase instead of training from scratch and used the uncased version of the BERT model.
PHS-BERT is trained on a corpus of health-related tweets that were crawled via the Twitter API. Focusing on the tasks related to PHS, keywords used to collect pretraining corpus are set to disease, symptom, vaccine, and mental health-related words in English. Retweet tags were deleted from the raw corpus, and URLs and usernames were replaced with HTTP-URL and @USER, respectively. All emoticons were replaced with their associated meanings.
Each sequence of BERT LM inputs is converted to 50,265 vocabulary tokens. Twitter posts are restricted to 200 characters, and during the training and evaluation phase, we used a batch size of 8. Distributed training was performed on a TPU v3-8.
### Fine-tuning
We used the embedding of the special token [CLS] of the last hidden layer as the final feature of the input text. We adopted the multilayer perceptron (MLP) with the hyperbolic tangent activation function and used Adam optimizer. The models are trained with a one cycle policy at a maximum learning rate of 2e-05 with momentum cycled between 0.85 and 0.95.
## Societal Impact
We train and release a PLM to accelerate the automatic identification of tasks related to PHS on social media. Our work aims to develop a new computational method for screening users in need of early intervention and is not intended to use in clinical settings or as a diagnostic tool.
## BibTex entry and citation info
For more details, refer to the paper [Benchmarking for Public Health Surveillance tasks on Social Media with a Domain-Specific Pretrained Language Model](https://arxiv.org/abs/2204.04521).
```
@inproceedings{naseem-etal-2022-benchmarking,
title = "Benchmarking for Public Health Surveillance tasks on Social Media with a Domain-Specific Pretrained Language Model",
author = "Naseem, Usman and
Lee, Byoung Chan and
Khushi, Matloob and
Kim, Jinman and
Dunn, Adam",
booktitle = "Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nlppower-1.3",
doi = "10.18653/v1/2022.nlppower-1.3",
pages = "22--31",
abstract = "A user-generated text on social media enables health workers to keep track of information, identify possible outbreaks, forecast disease trends, monitor emergency cases, and ascertain disease awareness and response to official health correspondence. This exchange of health information on social media has been regarded as an attempt to enhance public health surveillance (PHS). Despite its potential, the technology is still in its early stages and is not ready for widespread application. Advancements in pretrained language models (PLMs) have facilitated the development of several domain-specific PLMs and a variety of downstream applications. However, there are no PLMs for social media tasks involving PHS. We present and release PHS-BERT, a transformer-based PLM, to identify tasks related to public health surveillance on social media. We compared and benchmarked the performance of PHS-BERT on 25 datasets from different social medial platforms related to 7 different PHS tasks. Compared with existing PLMs that are mainly evaluated on limited tasks, PHS-BERT achieved state-of-the-art performance on all 25 tested datasets, showing that our PLM is robust and generalizable in the common PHS tasks. By making PHS-BERT available, we aim to facilitate the community to reduce the computational cost and introduce new baselines for future works across various PHS-related tasks.",
}
```
| 4,660 | [
[
-0.007442474365234375,
-0.0443115234375,
0.037139892578125,
0.02850341796875,
-0.03814697265625,
0.00719451904296875,
-0.0206298828125,
-0.0176239013671875,
0.03570556640625,
0.02569580078125,
-0.0406494140625,
-0.057098388671875,
-0.07080078125,
0.001056671... |
microsoft/xclip-base-patch16-16-frames | 2022-09-08T11:07:19.000Z | [
"transformers",
"pytorch",
"xclip",
"feature-extraction",
"vision",
"video-classification",
"en",
"arxiv:2208.02816",
"license:mit",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | feature-extraction | microsoft | null | null | microsoft/xclip-base-patch16-16-frames | 0 | 498 | transformers | 2022-09-07T15:01:41 | ---
language: en
license: mit
tags:
- vision
- video-classification
model-index:
- name: nielsr/xclip-base-patch16-16-frames
results:
- task:
type: video-classification
dataset:
name: Kinetics 400
type: kinetics-400
metrics:
- type: top-1 accuracy
value: 84.7
- type: top-5 accuracy
value: 96.8
---
# X-CLIP (base-sized model)
X-CLIP model (base-sized, patch resolution of 16) trained fully-supervised on [Kinetics-400](https://www.deepmind.com/open-source/kinetics). It was introduced in the paper [Expanding Language-Image Pretrained Models for General Video Recognition](https://arxiv.org/abs/2208.02816) by Ni et al. and first released in [this repository](https://github.com/microsoft/VideoX/tree/master/X-CLIP).
This model was trained using 16 frames per video, at a resolution of 224x224.
Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
X-CLIP is a minimal extension of [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
This allows the model to be used for tasks like zero-shot, few-shot or fully supervised video classification and video-text retrieval.
## Intended uses & limitations
You can use the raw model for determining how well text goes with a given video. See the [model hub](https://huggingface.co/models?search=microsoft/xclip) to look for
fine-tuned versions on a task that interests you.
### How to use
For code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/xclip.html#).
## Training data
This model was trained on [Kinetics-400](https://www.deepmind.com/open-source/kinetics).
### Preprocessing
The exact details of preprocessing during training can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L247).
The exact details of preprocessing during validation can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L285).
During validation, one resizes the shorter edge of each frame, after which center cropping is performed to a fixed-size resolution (like 224x224). Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
## Evaluation results
This model achieves a top-1 accuracy of 84.7% and a top-5 accuracy of 96.8%.
| 2,739 | [
[
-0.045989990234375,
-0.034912109375,
0.025543212890625,
0.0041656494140625,
-0.024200439453125,
0.004016876220703125,
-0.0179443359375,
-0.01514434814453125,
0.025421142578125,
0.02484130859375,
-0.0670166015625,
-0.046875,
-0.060455322265625,
-0.01687622070... |
BirdL/PhotorealV0.5 | 2023-02-03T22:23:15.000Z | [
"diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"has_space",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | BirdL | null | null | BirdL/PhotorealV0.5 | 0 | 498 | diffusers | 2022-12-20T19:33:16 | ---
license: creativeml-openrail-m
tags:
- text-to-image
---
# Unstable Diffusion PhotorealV0.5 converted to Diffusers Format!
You will most likely need to disable the safety checker. | 187 | [
[
-0.02044677734375,
-0.047607421875,
0.0125732421875,
0.03021240234375,
-0.0506591796875,
-0.005802154541015625,
0.03094482421875,
-0.00939178466796875,
-0.01239776611328125,
0.02984619140625,
-0.0215911865234375,
-0.002437591552734375,
-0.0579833984375,
-0.0... |
Lucetepolis/MareAcernis | 2023-03-05T07:20:02.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | Lucetepolis | null | null | Lucetepolis/MareAcernis | 25 | 498 | diffusers | 2023-03-05T06:24:42 | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
# MareNoctis, MareAcernis
OctaFuzz - <a href="https://huggingface.co/Lucetepolis/OctaFuzz">Download</a><br/>
Orion-Mix - <a href="https://civitai.com/models/14712/orion-mix">Download</a><br/>
WinterMoonMix - <a href="https://civitai.com/models/12433/wintermoonmix">Download</a><br/>
Gyokai / ononoimoko (魚介 / おののいもこ) Art Style LoRA - <a href="https://civitai.com/models/11794/gyokai-ononoimoko-art-style-lora">Download</a><br/>
Maplestory style - <a href="https://civitai.com/models/14313/maplestory-style">Download</a><br/>
Vanripperart style - LORA - <a href="https://civitai.com/models/12325/vanripperart-style-lora">Download</a><br/>
Yoneyama Mai Style LoRA - <a href="https://civitai.com/models/11701/yoneyama-mai-style-lora">Download</a><br/>
EasyNegative and pastelmix-lora seem to work well with the models.
EasyNegative - <a href="https://huggingface.co/datasets/gsdf/EasyNegative">Download</a><br/>
pastelmix-lora - <a href="https://huggingface.co/andite/pastel-mix">Download</a>
# Formula
```
MBW
model_0 : orionmix.safetensors
model_1 : wintermoon.safetensors
model_Out : ow.safetensors
base_alpha : 0.5
weight : 0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5
MBW
model_0 : octafuzz.safetensors
model_1 : ow.safetensors
model_Out : MareNoctis.safetensors
base_alpha : 0.5
weight : 0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5,0.5
SuperMerger LoRA Merge
model_0 : MareNoctis.safetensors
model_Out : MareAcernis.safetensors
LoRa : gyokai:0.3, maplestory:0.3, vanripper:0.3, yoneyama:0.3
```
# Samples
All of the images use following negatives/settings. EXIF preserved.
```
Negative prompt: (worst quality, low quality:1.4), EasyNegative, bad anatomy, bad hands, error, missing fingers, extra digit, fewer digits
Steps: 28, Sampler: DPM++ 2M Karras, CFG scale: 7, Size: 768x512, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires upscale: 1.5, Hires steps: 14, Hires upscaler: Latent (nearest-exact)
```
# MareNoctis
# MareAcernis
| 4,180 | [
[
-0.0491943359375,
-0.026092529296875,
0.0232086181640625,
0.032562255859375,
-0.027862548828125,
-0.0216064453125,
0.010009765625,
-0.05328369140625,
0.08221435546875,
0.028350830078125,
-0.05267333984375,
-0.0567626953125,
-0.03277587890625,
0.0162353515625... |
badmatr11x/distilroberta-base-offensive-hateful-speech-text-multiclassification | 2023-03-22T06:24:41.000Z | [
"transformers",
"pytorch",
"roberta",
"text-classification",
"code",
"en",
"dataset:badmatr11x/hate-offensive-speech",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-classification | badmatr11x | null | null | badmatr11x/distilroberta-base-offensive-hateful-speech-text-multiclassification | 0 | 498 | transformers | 2023-03-16T20:52:22 | ---
license: mit
datasets:
- badmatr11x/hate-offensive-speech
language:
- en
pipeline_tag: text-classification
tags:
- code
---
This is pre-trained model for offensive and hateful speech multiclassification.
Model is fine-tuned on distilroberta-base model from the huggingface repository.
This model is pre-trained on my original datasets. Reported accuracy of this model is **94.50%**.
You can find all the datasets on this [repository](https://huggingface.co/datasets/badmatr11x/hate-offensive-speech).
Find out my Space on this model [here](https://huggingface.co/spaces/badmatr11x/offensive-hateful-speech-multiclassification).
You can find training notebook on my github profile [@purveshpatel511](https://github.com/purveshpatel511/offensive-hateful-text-multiclassification/blob/master/text-multiclassification.ipynb).
Report any bugs or issue [here](https://github.com/purveshpatel511/offensive-hateful-text-multiclassification/issues).
Checkout my GitHub Profile [@purveshpatel511](https://github.com/purveshpatel511). | 1,032 | [
[
-0.0226898193359375,
-0.06268310546875,
-0.0011081695556640625,
0.01360321044921875,
-0.0071563720703125,
0.011688232421875,
-0.018768310546875,
-0.0239410400390625,
0.0244903564453125,
0.0188446044921875,
-0.0445556640625,
-0.043701171875,
-0.0670166015625,
... |
osiria/bert-base-italian-cased | 2023-09-29T18:07:17.000Z | [
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"it",
"arxiv:1810.04805",
"arxiv:2010.05609",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | osiria | null | null | osiria/bert-base-italian-cased | 0 | 498 | transformers | 2023-05-29T17:52:45 | ---
license: apache-2.0
language:
- it
widget:
- text: "Milano è una [MASK] dell'Italia"
example_title: "Example 1"
- text: "Giacomo Leopardi è stato uno dei più grandi [MASK] del classicismo italiano"
example_title: "Example 2"
- text: "La pizza è un piatto tipico della [MASK] gastronomica italiana"
example_title: "Example 3"
---
--------------------------------------------------------------------------------------------------
<body>
<span class="vertical-text" style="background-color:lightgreen;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:orange;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:lightblue;border-radius: 3px;padding: 3px;"> Model: BERT</span>
<br>
<span class="vertical-text" style="background-color:tomato;border-radius: 3px;padding: 3px;"> Lang: IT</span>
<br>
<span class="vertical-text" style="background-color:lightgrey;border-radius: 3px;padding: 3px;"> </span>
<br>
<span class="vertical-text" style="background-color:#CF9FFF;border-radius: 3px;padding: 3px;"> </span>
</body>
--------------------------------------------------------------------------------------------------
<h3>Model description</h3>
This is a <b>BERT</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using <b>mBERT</b> ([bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased)) as a starting point and focusing it on the Italian language by modifying the embedding layer
(as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
The resulting model has 110M parameters, a vocabulary of 30.785 tokens, and a size of ~430 MB.
<h3>Quick usage</h3>
```python
from transformers import BertTokenizerFast, BertModel
tokenizer = BertTokenizerFast.from_pretrained("osiria/bert-base-italian-cased")
model = BertModel.from_pretrained("osiria/bert-base-italian-cased")
```
<h3>References</h3>
[1] https://arxiv.org/abs/1810.04805
[2] https://arxiv.org/abs/2010.05609
<h3>License</h3>
The model is released under <b>Apache-2.0</b> license
| 2,135 | [
[
-0.0379638671875,
-0.05902099609375,
0.007537841796875,
0.0202178955078125,
-0.006748199462890625,
-0.016143798828125,
-0.01383209228515625,
-0.0423583984375,
0.0189056396484375,
-0.00920867919921875,
-0.05230712890625,
-0.03912353515625,
-0.0340576171875,
-... |
SaiedAlshahrani/arwiki_20230101_roberta_mlm_bots | 2023-10-29T00:55:40.000Z | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"fill-mask",
"generated_from_trainer",
"ar",
"dataset:SaiedAlshahrani/Arabic_Wikipedia_20230101_bots",
"dataset:SaiedAlshahrani/MASD",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | SaiedAlshahrani | null | null | SaiedAlshahrani/arwiki_20230101_roberta_mlm_bots | 0 | 497 | transformers | 2023-04-28T22:06:39 | ---
tags:
- generated_from_trainer
model-index:
- name: arRoBERTa
results: []
metrics:
- perplexity
license: mit
datasets:
- SaiedAlshahrani/Arabic_Wikipedia_20230101_bots
- SaiedAlshahrani/MASD
language:
- ar
library_name: transformers
pipeline_tag: fill-mask
widget:
- text: الهدف من الحياة هو <mask>
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Arabic Wikipedia (arRoBERTa<sub>BASE</sub>)
This arRoBERTa<sub>BASE</sub> model has been trained *from scratch* on the Arabic Wikipedia articles, downloaded on the 1st of January 2023, processed using
`Gensim` Python library, preprocessed using `tr` Linux/Unix utility and `CAMeLTools` Python toolkit for Arabic NLP, and hosted here at [SaiedAlshahrani/Arabic_Wikipedia_20230101_bots](https://huggingface.co/datasets/SaiedAlshahrani/Arabic_Wikipedia_20230101_bots).
It achieves the following results on the evaluation set:
- Pseudo-Perplexity: 23.70
## Model description
We trained this Arabic Wikipedia Masked Language Model (arRoBERTa<sub>BASE</sub>) to evaluate its performance using the Fill-Mask evaluation task and the Masked Arab States Dataset ([MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)) dataset and measure the *impact* of **template-based translation** on the Egyptian Arabic Wikipedia edition.
For more details about the experiment, please **read** and **cite** our paper:
```bash
@inproceedings{alshahrani-etal-2023-implications,
title = "{{Performance Implications of Using Unrepresentative Corpora in Arabic Natural Language Processing}}",
author = "Alshahrani, Saied and Alshahrani, Norah and Dey, Soumyabrata and Matthews, Jeanna",
booktitle = "Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://webspace.clarkson.edu/~alshahsf/unrepresentative_corpora.pdf",
doi = "#################",
pages = "###--###",
abstract = "Wikipedia articles are a widely used source of training data for Natural Language Processing (NLP) research, particularly as corpora for low-resource languages like Arabic. However, it is essential to understand the extent to which these corpora reflect the representative contributions of native speakers, especially when many entries in a given language are directly translated from other languages or automatically generated through automated mechanisms. In this paper, we study the performance implications of using inorganic corpora that are not representative of native speakers and are generated through automated techniques such as bot generation or automated template-based translation. The case of the Arabic Wikipedia editions gives a unique case study of this since the Moroccan Arabic Wikipedia edition (ARY) is small but representative, the Egyptian Arabic Wikipedia edition (ARZ) is large but unrepresentative, and the Modern Standard Arabic Wikipedia edition (AR) is both large and more representative. We intrinsically evaluate the performance of two main NLP upstream tasks, namely word representation and language modeling, using word analogy evaluations and fill-mask evaluations using our two newly created datasets: Arab States Analogy Dataset (ASAD) and Masked Arab States Dataset (MASD). We demonstrate that for good NLP performance, we need both large and organic corpora; neither alone is sufficient. We show that producing large corpora through automated means can be a counter-productive, producing models that both perform worse and lack cultural richness and meaningful representation of the Arabic language and its native speakers.",
}
```
## Intended uses & limitations
We do **not** recommend using this model because it was trained *only* on the Arabic Wikipedia articles, <u>unless</u> you fine-tune the model on a large, organic, and representative Arabic dataset.
## Training and evaluation data
We have trained this model on the Arabic Wikipedia articles ([SaiedAlshahrani/Arabic_Wikipedia_20230101_bots](https://huggingface.co/datasets/SaiedAlshahrani/Arabic_Wikipedia_20230101_bots)) without using any validation or evaluation data (only training data) due to a lack of computational power.
## Training procedure
We have trained this model using the Paperspace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 256
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Epoch | Step | Training Loss |
|:-----:|:-----:|:-------------:|
| 1 | 3000 | 5.681200 |
| 2 | 6000 | 3.777100 |
| 3 | 9000 | 3.246300 |
| 4 | 12000 | 3.012100 |
| 5 | 15000 | 2.888400 |
| Train Runtime | Train Samples Per Second | Train Steps Per Second | Total Flos | Train Loss | Epoch |
|:--------------:|:------------------------:|:----------------------:|:-------------------------:|:----------:|:--------:|
| 17048.756800 | 248.355000 | 0.970000 | 140390797515571200.000000 | 3.639375 | 5.000000 |
### Evaluation results
This arRoBERTa<sub>BASE</sub> model has been evaluated on the Masked Arab States Dataset ([SaiedAlshahrani/MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)).
| K=10 | K=50 | K=100 |
|:----:|:-----:|:----:|
| 43.12%| 45% | 50.62% |
### Framework versions
- Datasets 2.9.0
- Tokenizers 0.12.1
- Transformers 4.24.0
- Pytorch 1.12.1+cu116 | 5,857 | [
[
-0.051483154296875,
-0.04315185546875,
0.005451202392578125,
-0.00896453857421875,
-0.0242919921875,
0.00402069091796875,
-0.02606201171875,
-0.053466796875,
0.00817108154296875,
0.016998291015625,
-0.027374267578125,
-0.048370361328125,
-0.059326171875,
0.0... |
MMG/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac | 2023-07-26T09:39:16.000Z | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bert",
"question-answering",
"generated_from_trainer",
"es",
"dataset:sqac",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | question-answering | MMG | null | null | MMG/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac | 2 | 496 | transformers | 2022-03-02T23:29:04 | ---
tags:
- generated_from_trainer
datasets:
- sqac
model-index:
- name: bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac-v2
results: []
language:
- es
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-spanish-wwm-cased-finetuned-spa-squad2-es-finetuned-sqac-v2
This model is a fine-tuned version of [mrm8488/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es](https://huggingface.co/mrm8488/bert-base-spanish-wwm-cased-finetuned-spa-squad2-es) on the sqac dataset.
It achieves the following results on the evaluation set:
- {'exact_match': 65.02145922746782, 'f1': 81.6651482773275}
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.9417 | 1.0 | 1277 | 0.7903 |
| 0.5002 | 2.0 | 2554 | 0.8459 |
| 0.2895 | 3.0 | 3831 | 0.9482 |
### Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3
| 1,603 | [
[
-0.039154052734375,
-0.04522705078125,
0.00949859619140625,
0.0267333984375,
-0.0202484130859375,
-0.0250091552734375,
-0.01540374755859375,
-0.0262451171875,
0.008941650390625,
0.0226287841796875,
-0.06365966796875,
-0.0447998046875,
-0.046112060546875,
-0.... |
facebook/incoder-6B | 2023-01-24T17:06:34.000Z | [
"transformers",
"pytorch",
"xglm",
"text-generation",
"code",
"python",
"javascript",
"arxiv:2204.05999",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"has_space",
"region:us"
] | text-generation | facebook | null | null | facebook/incoder-6B | 65 | 496 | transformers | 2022-04-06T03:17:49 | ---
license: "cc-by-nc-4.0"
tags:
- code
- python
- javascript
---
# InCoder 6B
A 6B parameter decoder-only Transformer model trained on code using a causal-masked objective, which allows inserting/infilling code as well as standard left-to-right generation.
The model was trained on public open-source repositories with a permissive, non-copyleft, license (Apache 2.0, MIT, BSD-2 or BSD-3) from GitHub and GitLab, as well as StackOverflow. Repositories primarily contained Python and JavaScript, but also include code from 28 languages, as well as StackOverflow.
For more information, see our:
- [Demo](https://huggingface.co/spaces/facebook/incoder-demo)
- [Project site](https://sites.google.com/view/incoder-code-models)
- [Examples](https://sites.google.com/view/incoder-code-models/home/examples)
- [Paper](https://arxiv.org/abs/2204.05999)
A smaller, 1B, parameter model is also available at [facebook/incoder-1B](https://huggingface.co/facebook/incoder-1B).
## Requirements
`pytorch`, `tokenizers`, and `transformers`. Our model requires HF's tokenizers >= 0.12.1, due to changes in the pretokenizer.
```
pip install torch
pip install "tokenizers>=0.12.1"
pip install transformers
```
## Usage
### Model
See [https://github.com/dpfried/incoder](https://github.com/dpfried/incoder) for example code.
This 6B model comes in two versions: with weights in full-precision (float32, stored on branch `main`) and weights in half-precision (float16, stored on branch `float16`). The versions can be loaded as follows:
*Full-precision* (float32): This should be used if you are fine-tuning the model (note: this will take a lot of GPU memory, probably multiple GPUs, and we have not tried training the model in `transformers` --- it was trained in Fairseq). Load with:
`model = AutoModelForCausalLM.from_pretrained("facebook/incoder-6B")`
*Half-precision* (float16): This can be used if you are only doing inference (i.e. generating from the model). It will use less GPU memory, and less RAM when loading the model. With this version it should be able to perform inference on a 16 GB GPU (with a batch size of 1, to sequence lengths of at least 256). Load with:
`model = AutoModelForCausalLM.from_pretrained("facebook/incoder-6B", revision="float16", torch_dtype=torch.float16, low_cpu_mem_usage=True)`
### Tokenizer
`tokenizer = AutoTokenizer.from_pretrained("facebook/incoder-6B")`
Note: the incoder-1B and incoder-6B tokenizers are identical, so 'facebook/incoder-1B' could also be used.
When calling `tokenizer.decode`, it's important to pass `clean_up_tokenization_spaces=False` to avoid removing spaces after punctuation:
`tokenizer.decode(tokenizer.encode("from ."), clean_up_tokenization_spaces=False)`
(Note: encoding prepends the `<|endoftext|>` token, as this marks the start of a document to our model. This token can be removed from the decoded output by passing `skip_special_tokens=True` to `tokenizer.decode`.)
## License
CC-BY-NC 4.0
## Credits
The model was developed by Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer and Mike Lewis.
Thanks to Lucile Saulnier, Leandro von Werra, Nicolas Patry, Suraj Patil, Omar Sanseviero, and others at HuggingFace for help with the model release, and to Naman Goyal and Stephen Roller for the code our demo was based on! | 3,377 | [
[
-0.01910400390625,
-0.046173095703125,
0.01001739501953125,
0.024688720703125,
-0.0157928466796875,
-0.02471923828125,
-0.0018243789672851562,
-0.04278564453125,
0.00455474853515625,
0.03564453125,
-0.061767578125,
-0.036590576171875,
-0.040985107421875,
0.0... |
timm/seresnext50_32x4d.gluon_in1k | 2023-04-05T19:33:48.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:1611.05431",
"arxiv:1512.03385",
"arxiv:1709.01507",
"arxiv:1812.01187",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/seresnext50_32x4d.gluon_in1k | 0 | 496 | timm | 2023-04-05T19:33:18 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
---
# Model card for seresnext50_32x4d.gluon_in1k
A SE-ResNeXt-B image classification model with Squeeze-and-Excitation channel attention.
This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample
* grouped 3x3 bottleneck convolutions
* Squeeze-and-Excitation channel attention
Trained on ImageNet-1k in Apache Gluon using Bag-of-Tricks based recipes.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 27.6
- GMACs: 4.3
- Activations (M): 14.4
- Image size: 224 x 224
- **Papers:**
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
- Squeeze-and-Excitation Networks: https://arxiv.org/abs/1709.01507
- Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
- **Original:** https://cv.gluon.ai/model_zoo/classification.html
## 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('seresnext50_32x4d.gluon_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(
'seresnext50_32x4d.gluon_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, 1024, 14, 14])
# torch.Size([1, 2048, 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(
'seresnext50_32x4d.gluon_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).
|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 |
|[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 |
|[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 |
|[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 |
|[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 |
|[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 |
|[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 |
|[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 |
|[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 |
|[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 |
|[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 |
|[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 |
|[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 |
|[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 |
|[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 |
|[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 |
|[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 |
|[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 |
|[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 |
|[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 |
|[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 |
|[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 |
|[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 |
|[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 |
|[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 |
|[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 |
|[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 |
|[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 |
|[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 |
|[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 |
|[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 |
|[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 |
|[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 |
|[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 |
|[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 |
|[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 |
|[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 |
|[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 |
|[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 |
|[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 |
|[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 |
|[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 |
|[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 |
|[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 |
|[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 |
|[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 |
|[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 |
|[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 |
|[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 |
|[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 |
|[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 |
|[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 |
|[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 |
|[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 |
|[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 |
|[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 |
|[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 |
|[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 |
|[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 |
|[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 |
|[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 |
|[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 |
|[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 |
|[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 |
|[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 |
|[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 |
|[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 |
|[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 |
|[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 |
|[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 |
|[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 |
|[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 |
|[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 |
|[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 |
|[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 |
|[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 |
|[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 |
|[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 |
|[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 |
|[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 |
|[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 |
|[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 |
|[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 |
|[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 |
|[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 |
|[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 |
|[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 |
|[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 |
|[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 |
|[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 |
|[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 |
|[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 |
|[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 |
|[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 |
|[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 |
|[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 |
|[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 |
|[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 |
|[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 |
|[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 |
|[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 |
|[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 |
|[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 |
|[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 |
|[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 |
|[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 |
|[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 |
|[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 |
|[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 |
|[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 |
|[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 |
|[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 |
|[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 |
|[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 |
|[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 |
|[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 |
|[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 |
|[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 |
|[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 |
|[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 |
|[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 |
|[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 |
|[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 |
|[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 |
|[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 |
|[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 |
|[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 |
|[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 |
|[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 |
|[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 |
|[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 |
|[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 |
|[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 |
|[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 |
|[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 |
|[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 |
|[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 |
|[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 |
|[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 |
## Citation
```bibtex
@article{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
```bibtex
@article{He2015,
author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
title = {Deep Residual Learning for Image Recognition},
journal = {arXiv preprint arXiv:1512.03385},
year = {2015}
}
```
```bibtex
@inproceedings{hu2018senet,
title={Squeeze-and-Excitation Networks},
author={Jie Hu and Li Shen and Gang Sun},
journal={IEEE Conference on Computer Vision and Pattern Recognition},
year={2018}
}
```
```bibtex
@article{He2018BagOT,
title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
pages={558-567}
}
```
```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}}
}
```
| 39,176 | [
[
-0.064453125,
-0.0189666748046875,
0.004791259765625,
0.027557373046875,
-0.03167724609375,
-0.0086669921875,
-0.01009368896484375,
-0.0341796875,
0.08380126953125,
0.0186004638671875,
-0.046295166015625,
-0.038787841796875,
-0.047607421875,
-0.0023441314697... |
retrieva-jp/t5-small-short | 2023-05-10T00:55:39.000Z | [
"transformers",
"pytorch",
"t5",
"text2text-generation",
"ja",
"arxiv:2002.05202",
"license:cc-by-sa-4.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | retrieva-jp | null | null | retrieva-jp/t5-small-short | 1 | 496 | transformers | 2023-04-25T04:37:20 | ---
license: cc-by-sa-4.0
language:
- ja
---
# Model card for model ID
This is a T5 v1.1 model, pre-trained on a Japanese corpus.
## Model details
T5 is a Transformer-based Encoder-Decoder model, now in v1.1, with the following improvements over the original T5.
- GEGLU activation in feed-forward hidden layer, rather than ReLU - see https://arxiv.org/abs/2002.05202 .
- Dropout was turned off in pre-training (quality win). Dropout should be re-enabled during fine-tuning.
- no parameter sharing between embedding and classifier layer
- "xl" and "xxl" replace "3B" and "11B". The model shapes are a bit different - larger d_model and smaller num_heads and d_ff.
This model is based on T5 v1.1. It was pre-trained on a Japanese corpus. For the Japanese corpus, Japanese Wikipedia and mC4/ja were used.
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** Retrieva, Inc.
- **Model type:** T5 v1.1
- **Language(s) (NLP):** Japanese
- **License:** CC-BY-SA 4.0 Although commercial use is permitted, we kindly request that you contact us beforehand.
## Training Details
We use T5X (https://github.com/google-research/t5x) for the training of this model, and it has been converted to the Huggingface transformer format.
## Training Data
The training data used is
- The Japanese part of the multilingual C4(mC4/ja).
- Japanese Wikipedia(20220920).
#### Preprocessing
The following filtering is done
- Remove documents that do not use a single hiragana character. This removes English-only documents and documents in Chinese.
- Whitelist-style filtering using the top level domain of URL to remove affiliate sites.
#### Training Hyperparameters
- dropout rate: 0.0
- batch size: 256
- fp32
- input length: 512
- output length: 114
- Otherwise, the default value of T5X (https://github.com/google-research/t5x/blob/main/t5x/examples/t5/t5_1_1/small.gin) is followed, including the following.
- optimizer: Adafactor
- base_learning_rate: 1.0
- warmup steps: 10000
#### Speeds, Sizes, Times
We trained 589824 steps.
## Technical Specifications
### Model Architecture and Objective
Model architecture.
- T5 v1.1(https://github.com/google-research/text-to-text-transfer-transformer/blob/main/released_checkpoints.md#t511)
- Size: Small(~77 million parameters)
### Compute Infrastructure
Google Cloud TPU v4-8.
#### Software
- T5X(https://github.com/google-research/t5x).
## More Information
https://note.com/retrieva/n/n7b4186dc5ada (in Japanese)
## Model Card Authors
Jiro Nishitoba
## Model Card Contact
pr@retrieva.jp
| 2,595 | [
[
-0.02960205078125,
-0.0323486328125,
0.0247344970703125,
-0.0009183883666992188,
-0.029632568359375,
0.0022335052490234375,
-0.007343292236328125,
-0.038818359375,
0.0037250518798828125,
0.0273590087890625,
-0.058441162109375,
-0.07122802734375,
-0.0530090332031... |
ggrn/e5-small-v2 | 2023-06-21T03:30:34.000Z | [
"sentence-transformers",
"pytorch",
"bert",
"mteb",
"feature-extraction",
"en",
"arxiv:2212.03533",
"arxiv:2104.08663",
"arxiv:2210.07316",
"license:mit",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | feature-extraction | ggrn | null | null | ggrn/e5-small-v2 | 7 | 496 | sentence-transformers | 2023-06-21T02:39:56 | ---
language:
- en
license: mit
library_name: sentence-transformers
pipeline_tag: feature-extraction
tags:
- mteb
model-index:
- name: e5-small-v2
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy
value: 77.59701492537313
- type: ap
value: 41.67064885731708
- type: f1
value: 71.86465946398573
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy
value: 91.265875
- type: ap
value: 87.67633085349644
- type: f1
value: 91.24297521425744
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy
value: 45.882000000000005
- type: f1
value: 45.08058870381236
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 20.697
- type: map_at_10
value: 33.975
- type: map_at_100
value: 35.223
- type: map_at_1000
value: 35.260000000000005
- type: map_at_3
value: 29.776999999999997
- type: map_at_5
value: 32.035000000000004
- type: mrr_at_1
value: 20.982
- type: mrr_at_10
value: 34.094
- type: mrr_at_100
value: 35.343
- type: mrr_at_1000
value: 35.38
- type: mrr_at_3
value: 29.884
- type: mrr_at_5
value: 32.141999999999996
- type: ndcg_at_1
value: 20.697
- type: ndcg_at_10
value: 41.668
- type: ndcg_at_100
value: 47.397
- type: ndcg_at_1000
value: 48.305
- type: ndcg_at_3
value: 32.928000000000004
- type: ndcg_at_5
value: 36.998999999999995
- type: precision_at_1
value: 20.697
- type: precision_at_10
value: 6.636
- type: precision_at_100
value: 0.924
- type: precision_at_1000
value: 0.099
- type: precision_at_3
value: 14.035
- type: precision_at_5
value: 10.398
- type: recall_at_1
value: 20.697
- type: recall_at_10
value: 66.35799999999999
- type: recall_at_100
value: 92.39
- type: recall_at_1000
value: 99.36
- type: recall_at_3
value: 42.105
- type: recall_at_5
value: 51.991
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure
value: 42.1169517447068
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure
value: 34.79553720107097
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map
value: 58.10811337308168
- type: mrr
value: 71.56410763751482
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson
value: 78.46834918248696
- type: cos_sim_spearman
value: 79.4289182755206
- type: euclidean_pearson
value: 76.26662973727008
- type: euclidean_spearman
value: 78.11744260952536
- type: manhattan_pearson
value: 76.08175262609434
- type: manhattan_spearman
value: 78.29395265552289
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy
value: 81.63636363636364
- type: f1
value: 81.55779952376953
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure
value: 35.88541137137571
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure
value: 30.05205685274407
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 30.293999999999997
- type: map_at_10
value: 39.876
- type: map_at_100
value: 41.315000000000005
- type: map_at_1000
value: 41.451
- type: map_at_3
value: 37.194
- type: map_at_5
value: 38.728
- type: mrr_at_1
value: 37.053000000000004
- type: mrr_at_10
value: 45.281
- type: mrr_at_100
value: 46.188
- type: mrr_at_1000
value: 46.245999999999995
- type: mrr_at_3
value: 43.228
- type: mrr_at_5
value: 44.366
- type: ndcg_at_1
value: 37.053000000000004
- type: ndcg_at_10
value: 45.086
- type: ndcg_at_100
value: 50.756
- type: ndcg_at_1000
value: 53.123
- type: ndcg_at_3
value: 41.416
- type: ndcg_at_5
value: 43.098
- type: precision_at_1
value: 37.053000000000004
- type: precision_at_10
value: 8.34
- type: precision_at_100
value: 1.346
- type: precision_at_1000
value: 0.186
- type: precision_at_3
value: 19.647000000000002
- type: precision_at_5
value: 13.877
- type: recall_at_1
value: 30.293999999999997
- type: recall_at_10
value: 54.309
- type: recall_at_100
value: 78.59
- type: recall_at_1000
value: 93.82300000000001
- type: recall_at_3
value: 43.168
- type: recall_at_5
value: 48.192
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 28.738000000000003
- type: map_at_10
value: 36.925999999999995
- type: map_at_100
value: 38.017
- type: map_at_1000
value: 38.144
- type: map_at_3
value: 34.446
- type: map_at_5
value: 35.704
- type: mrr_at_1
value: 35.478
- type: mrr_at_10
value: 42.786
- type: mrr_at_100
value: 43.458999999999996
- type: mrr_at_1000
value: 43.507
- type: mrr_at_3
value: 40.648
- type: mrr_at_5
value: 41.804
- type: ndcg_at_1
value: 35.478
- type: ndcg_at_10
value: 42.044
- type: ndcg_at_100
value: 46.249
- type: ndcg_at_1000
value: 48.44
- type: ndcg_at_3
value: 38.314
- type: ndcg_at_5
value: 39.798
- type: precision_at_1
value: 35.478
- type: precision_at_10
value: 7.764
- type: precision_at_100
value: 1.253
- type: precision_at_1000
value: 0.174
- type: precision_at_3
value: 18.047
- type: precision_at_5
value: 12.637
- type: recall_at_1
value: 28.738000000000003
- type: recall_at_10
value: 50.659
- type: recall_at_100
value: 68.76299999999999
- type: recall_at_1000
value: 82.811
- type: recall_at_3
value: 39.536
- type: recall_at_5
value: 43.763999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 38.565
- type: map_at_10
value: 50.168
- type: map_at_100
value: 51.11
- type: map_at_1000
value: 51.173
- type: map_at_3
value: 47.044000000000004
- type: map_at_5
value: 48.838
- type: mrr_at_1
value: 44.201
- type: mrr_at_10
value: 53.596999999999994
- type: mrr_at_100
value: 54.211
- type: mrr_at_1000
value: 54.247
- type: mrr_at_3
value: 51.202000000000005
- type: mrr_at_5
value: 52.608999999999995
- type: ndcg_at_1
value: 44.201
- type: ndcg_at_10
value: 55.694
- type: ndcg_at_100
value: 59.518
- type: ndcg_at_1000
value: 60.907
- type: ndcg_at_3
value: 50.395999999999994
- type: ndcg_at_5
value: 53.022999999999996
- type: precision_at_1
value: 44.201
- type: precision_at_10
value: 8.84
- type: precision_at_100
value: 1.162
- type: precision_at_1000
value: 0.133
- type: precision_at_3
value: 22.153
- type: precision_at_5
value: 15.260000000000002
- type: recall_at_1
value: 38.565
- type: recall_at_10
value: 68.65
- type: recall_at_100
value: 85.37400000000001
- type: recall_at_1000
value: 95.37400000000001
- type: recall_at_3
value: 54.645999999999994
- type: recall_at_5
value: 60.958
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.945
- type: map_at_10
value: 30.641000000000002
- type: map_at_100
value: 31.599
- type: map_at_1000
value: 31.691000000000003
- type: map_at_3
value: 28.405
- type: map_at_5
value: 29.704000000000004
- type: mrr_at_1
value: 25.537
- type: mrr_at_10
value: 32.22
- type: mrr_at_100
value: 33.138
- type: mrr_at_1000
value: 33.214
- type: mrr_at_3
value: 30.151
- type: mrr_at_5
value: 31.298
- type: ndcg_at_1
value: 25.537
- type: ndcg_at_10
value: 34.638000000000005
- type: ndcg_at_100
value: 39.486
- type: ndcg_at_1000
value: 41.936
- type: ndcg_at_3
value: 30.333
- type: ndcg_at_5
value: 32.482
- type: precision_at_1
value: 25.537
- type: precision_at_10
value: 5.153
- type: precision_at_100
value: 0.7929999999999999
- type: precision_at_1000
value: 0.104
- type: precision_at_3
value: 12.429
- type: precision_at_5
value: 8.723
- type: recall_at_1
value: 23.945
- type: recall_at_10
value: 45.412
- type: recall_at_100
value: 67.836
- type: recall_at_1000
value: 86.467
- type: recall_at_3
value: 34.031
- type: recall_at_5
value: 39.039
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 14.419
- type: map_at_10
value: 20.858999999999998
- type: map_at_100
value: 22.067999999999998
- type: map_at_1000
value: 22.192
- type: map_at_3
value: 18.673000000000002
- type: map_at_5
value: 19.968
- type: mrr_at_1
value: 17.785999999999998
- type: mrr_at_10
value: 24.878
- type: mrr_at_100
value: 26.021
- type: mrr_at_1000
value: 26.095000000000002
- type: mrr_at_3
value: 22.616
- type: mrr_at_5
value: 23.785
- type: ndcg_at_1
value: 17.785999999999998
- type: ndcg_at_10
value: 25.153
- type: ndcg_at_100
value: 31.05
- type: ndcg_at_1000
value: 34.052
- type: ndcg_at_3
value: 21.117
- type: ndcg_at_5
value: 23.048
- type: precision_at_1
value: 17.785999999999998
- type: precision_at_10
value: 4.590000000000001
- type: precision_at_100
value: 0.864
- type: precision_at_1000
value: 0.125
- type: precision_at_3
value: 9.908999999999999
- type: precision_at_5
value: 7.313
- type: recall_at_1
value: 14.419
- type: recall_at_10
value: 34.477999999999994
- type: recall_at_100
value: 60.02499999999999
- type: recall_at_1000
value: 81.646
- type: recall_at_3
value: 23.515
- type: recall_at_5
value: 28.266999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 26.268
- type: map_at_10
value: 35.114000000000004
- type: map_at_100
value: 36.212
- type: map_at_1000
value: 36.333
- type: map_at_3
value: 32.436
- type: map_at_5
value: 33.992
- type: mrr_at_1
value: 31.761
- type: mrr_at_10
value: 40.355999999999995
- type: mrr_at_100
value: 41.125
- type: mrr_at_1000
value: 41.186
- type: mrr_at_3
value: 37.937
- type: mrr_at_5
value: 39.463
- type: ndcg_at_1
value: 31.761
- type: ndcg_at_10
value: 40.422000000000004
- type: ndcg_at_100
value: 45.458999999999996
- type: ndcg_at_1000
value: 47.951
- type: ndcg_at_3
value: 35.972
- type: ndcg_at_5
value: 38.272
- type: precision_at_1
value: 31.761
- type: precision_at_10
value: 7.103
- type: precision_at_100
value: 1.133
- type: precision_at_1000
value: 0.152
- type: precision_at_3
value: 16.779
- type: precision_at_5
value: 11.877
- type: recall_at_1
value: 26.268
- type: recall_at_10
value: 51.053000000000004
- type: recall_at_100
value: 72.702
- type: recall_at_1000
value: 89.521
- type: recall_at_3
value: 38.619
- type: recall_at_5
value: 44.671
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 25.230999999999998
- type: map_at_10
value: 34.227000000000004
- type: map_at_100
value: 35.370000000000005
- type: map_at_1000
value: 35.488
- type: map_at_3
value: 31.496000000000002
- type: map_at_5
value: 33.034
- type: mrr_at_1
value: 30.822
- type: mrr_at_10
value: 39.045
- type: mrr_at_100
value: 39.809
- type: mrr_at_1000
value: 39.873
- type: mrr_at_3
value: 36.663000000000004
- type: mrr_at_5
value: 37.964
- type: ndcg_at_1
value: 30.822
- type: ndcg_at_10
value: 39.472
- type: ndcg_at_100
value: 44.574999999999996
- type: ndcg_at_1000
value: 47.162
- type: ndcg_at_3
value: 34.929
- type: ndcg_at_5
value: 37.002
- type: precision_at_1
value: 30.822
- type: precision_at_10
value: 7.055
- type: precision_at_100
value: 1.124
- type: precision_at_1000
value: 0.152
- type: precision_at_3
value: 16.591
- type: precision_at_5
value: 11.667
- type: recall_at_1
value: 25.230999999999998
- type: recall_at_10
value: 50.42100000000001
- type: recall_at_100
value: 72.685
- type: recall_at_1000
value: 90.469
- type: recall_at_3
value: 37.503
- type: recall_at_5
value: 43.123
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 24.604166666666664
- type: map_at_10
value: 32.427166666666665
- type: map_at_100
value: 33.51474999999999
- type: map_at_1000
value: 33.6345
- type: map_at_3
value: 30.02366666666667
- type: map_at_5
value: 31.382333333333328
- type: mrr_at_1
value: 29.001166666666666
- type: mrr_at_10
value: 36.3315
- type: mrr_at_100
value: 37.16683333333333
- type: mrr_at_1000
value: 37.23341666666668
- type: mrr_at_3
value: 34.19916666666667
- type: mrr_at_5
value: 35.40458333333334
- type: ndcg_at_1
value: 29.001166666666666
- type: ndcg_at_10
value: 37.06883333333334
- type: ndcg_at_100
value: 41.95816666666666
- type: ndcg_at_1000
value: 44.501583333333336
- type: ndcg_at_3
value: 32.973499999999994
- type: ndcg_at_5
value: 34.90833333333334
- type: precision_at_1
value: 29.001166666666666
- type: precision_at_10
value: 6.336
- type: precision_at_100
value: 1.0282499999999999
- type: precision_at_1000
value: 0.14391666666666664
- type: precision_at_3
value: 14.932499999999996
- type: precision_at_5
value: 10.50825
- type: recall_at_1
value: 24.604166666666664
- type: recall_at_10
value: 46.9525
- type: recall_at_100
value: 68.67816666666667
- type: recall_at_1000
value: 86.59783333333334
- type: recall_at_3
value: 35.49783333333333
- type: recall_at_5
value: 40.52525000000001
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.559
- type: map_at_10
value: 29.023
- type: map_at_100
value: 29.818
- type: map_at_1000
value: 29.909000000000002
- type: map_at_3
value: 27.037
- type: map_at_5
value: 28.225
- type: mrr_at_1
value: 26.994
- type: mrr_at_10
value: 31.962000000000003
- type: mrr_at_100
value: 32.726
- type: mrr_at_1000
value: 32.800000000000004
- type: mrr_at_3
value: 30.266
- type: mrr_at_5
value: 31.208999999999996
- type: ndcg_at_1
value: 26.994
- type: ndcg_at_10
value: 32.53
- type: ndcg_at_100
value: 36.758
- type: ndcg_at_1000
value: 39.362
- type: ndcg_at_3
value: 28.985
- type: ndcg_at_5
value: 30.757
- type: precision_at_1
value: 26.994
- type: precision_at_10
value: 4.968999999999999
- type: precision_at_100
value: 0.759
- type: precision_at_1000
value: 0.106
- type: precision_at_3
value: 12.219
- type: precision_at_5
value: 8.527999999999999
- type: recall_at_1
value: 23.559
- type: recall_at_10
value: 40.585
- type: recall_at_100
value: 60.306000000000004
- type: recall_at_1000
value: 80.11
- type: recall_at_3
value: 30.794
- type: recall_at_5
value: 35.186
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 16.384999999999998
- type: map_at_10
value: 22.142
- type: map_at_100
value: 23.057
- type: map_at_1000
value: 23.177
- type: map_at_3
value: 20.29
- type: map_at_5
value: 21.332
- type: mrr_at_1
value: 19.89
- type: mrr_at_10
value: 25.771
- type: mrr_at_100
value: 26.599
- type: mrr_at_1000
value: 26.680999999999997
- type: mrr_at_3
value: 23.962
- type: mrr_at_5
value: 24.934
- type: ndcg_at_1
value: 19.89
- type: ndcg_at_10
value: 25.97
- type: ndcg_at_100
value: 30.605
- type: ndcg_at_1000
value: 33.619
- type: ndcg_at_3
value: 22.704
- type: ndcg_at_5
value: 24.199
- type: precision_at_1
value: 19.89
- type: precision_at_10
value: 4.553
- type: precision_at_100
value: 0.8049999999999999
- type: precision_at_1000
value: 0.122
- type: precision_at_3
value: 10.541
- type: precision_at_5
value: 7.46
- type: recall_at_1
value: 16.384999999999998
- type: recall_at_10
value: 34.001
- type: recall_at_100
value: 55.17100000000001
- type: recall_at_1000
value: 77.125
- type: recall_at_3
value: 24.618000000000002
- type: recall_at_5
value: 28.695999999999998
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.726
- type: map_at_10
value: 31.227
- type: map_at_100
value: 32.311
- type: map_at_1000
value: 32.419
- type: map_at_3
value: 28.765
- type: map_at_5
value: 30.229
- type: mrr_at_1
value: 27.705000000000002
- type: mrr_at_10
value: 35.085
- type: mrr_at_100
value: 35.931000000000004
- type: mrr_at_1000
value: 36
- type: mrr_at_3
value: 32.603
- type: mrr_at_5
value: 34.117999999999995
- type: ndcg_at_1
value: 27.705000000000002
- type: ndcg_at_10
value: 35.968
- type: ndcg_at_100
value: 41.197
- type: ndcg_at_1000
value: 43.76
- type: ndcg_at_3
value: 31.304
- type: ndcg_at_5
value: 33.661
- type: precision_at_1
value: 27.705000000000002
- type: precision_at_10
value: 5.942
- type: precision_at_100
value: 0.964
- type: precision_at_1000
value: 0.13
- type: precision_at_3
value: 13.868
- type: precision_at_5
value: 9.944
- type: recall_at_1
value: 23.726
- type: recall_at_10
value: 46.786
- type: recall_at_100
value: 70.072
- type: recall_at_1000
value: 88.2
- type: recall_at_3
value: 33.981
- type: recall_at_5
value: 39.893
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWebmastersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 23.344
- type: map_at_10
value: 31.636999999999997
- type: map_at_100
value: 33.065
- type: map_at_1000
value: 33.300000000000004
- type: map_at_3
value: 29.351
- type: map_at_5
value: 30.432
- type: mrr_at_1
value: 27.866000000000003
- type: mrr_at_10
value: 35.587
- type: mrr_at_100
value: 36.52
- type: mrr_at_1000
value: 36.597
- type: mrr_at_3
value: 33.696
- type: mrr_at_5
value: 34.713
- type: ndcg_at_1
value: 27.866000000000003
- type: ndcg_at_10
value: 36.61
- type: ndcg_at_100
value: 41.88
- type: ndcg_at_1000
value: 45.105000000000004
- type: ndcg_at_3
value: 33.038000000000004
- type: ndcg_at_5
value: 34.331
- type: precision_at_1
value: 27.866000000000003
- type: precision_at_10
value: 6.917
- type: precision_at_100
value: 1.3599999999999999
- type: precision_at_1000
value: 0.233
- type: precision_at_3
value: 15.547
- type: precision_at_5
value: 10.791
- type: recall_at_1
value: 23.344
- type: recall_at_10
value: 45.782000000000004
- type: recall_at_100
value: 69.503
- type: recall_at_1000
value: 90.742
- type: recall_at_3
value: 35.160000000000004
- type: recall_at_5
value: 39.058
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackWordpressRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 20.776
- type: map_at_10
value: 27.285999999999998
- type: map_at_100
value: 28.235
- type: map_at_1000
value: 28.337
- type: map_at_3
value: 25.147000000000002
- type: map_at_5
value: 26.401999999999997
- type: mrr_at_1
value: 22.921
- type: mrr_at_10
value: 29.409999999999997
- type: mrr_at_100
value: 30.275000000000002
- type: mrr_at_1000
value: 30.354999999999997
- type: mrr_at_3
value: 27.418
- type: mrr_at_5
value: 28.592000000000002
- type: ndcg_at_1
value: 22.921
- type: ndcg_at_10
value: 31.239
- type: ndcg_at_100
value: 35.965
- type: ndcg_at_1000
value: 38.602
- type: ndcg_at_3
value: 27.174
- type: ndcg_at_5
value: 29.229
- type: precision_at_1
value: 22.921
- type: precision_at_10
value: 4.806
- type: precision_at_100
value: 0.776
- type: precision_at_1000
value: 0.11
- type: precision_at_3
value: 11.459999999999999
- type: precision_at_5
value: 8.022
- type: recall_at_1
value: 20.776
- type: recall_at_10
value: 41.294
- type: recall_at_100
value: 63.111
- type: recall_at_1000
value: 82.88600000000001
- type: recall_at_3
value: 30.403000000000002
- type: recall_at_5
value: 35.455999999999996
- task:
type: Retrieval
dataset:
type: climate-fever
name: MTEB ClimateFEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 9.376
- type: map_at_10
value: 15.926000000000002
- type: map_at_100
value: 17.585
- type: map_at_1000
value: 17.776
- type: map_at_3
value: 13.014000000000001
- type: map_at_5
value: 14.417
- type: mrr_at_1
value: 20.195
- type: mrr_at_10
value: 29.95
- type: mrr_at_100
value: 31.052000000000003
- type: mrr_at_1000
value: 31.108000000000004
- type: mrr_at_3
value: 26.667
- type: mrr_at_5
value: 28.458
- type: ndcg_at_1
value: 20.195
- type: ndcg_at_10
value: 22.871
- type: ndcg_at_100
value: 29.921999999999997
- type: ndcg_at_1000
value: 33.672999999999995
- type: ndcg_at_3
value: 17.782999999999998
- type: ndcg_at_5
value: 19.544
- type: precision_at_1
value: 20.195
- type: precision_at_10
value: 7.394
- type: precision_at_100
value: 1.493
- type: precision_at_1000
value: 0.218
- type: precision_at_3
value: 13.073
- type: precision_at_5
value: 10.436
- type: recall_at_1
value: 9.376
- type: recall_at_10
value: 28.544999999999998
- type: recall_at_100
value: 53.147999999999996
- type: recall_at_1000
value: 74.62
- type: recall_at_3
value: 16.464000000000002
- type: recall_at_5
value: 21.004
- task:
type: Retrieval
dataset:
type: dbpedia-entity
name: MTEB DBPedia
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 8.415000000000001
- type: map_at_10
value: 18.738
- type: map_at_100
value: 27.291999999999998
- type: map_at_1000
value: 28.992
- type: map_at_3
value: 13.196
- type: map_at_5
value: 15.539
- type: mrr_at_1
value: 66.5
- type: mrr_at_10
value: 74.518
- type: mrr_at_100
value: 74.86
- type: mrr_at_1000
value: 74.87
- type: mrr_at_3
value: 72.375
- type: mrr_at_5
value: 73.86200000000001
- type: ndcg_at_1
value: 54.37499999999999
- type: ndcg_at_10
value: 41.317
- type: ndcg_at_100
value: 45.845
- type: ndcg_at_1000
value: 52.92
- type: ndcg_at_3
value: 44.983000000000004
- type: ndcg_at_5
value: 42.989
- type: precision_at_1
value: 66.5
- type: precision_at_10
value: 33.6
- type: precision_at_100
value: 10.972999999999999
- type: precision_at_1000
value: 2.214
- type: precision_at_3
value: 48.583
- type: precision_at_5
value: 42.15
- type: recall_at_1
value: 8.415000000000001
- type: recall_at_10
value: 24.953
- type: recall_at_100
value: 52.48199999999999
- type: recall_at_1000
value: 75.093
- type: recall_at_3
value: 14.341000000000001
- type: recall_at_5
value: 18.468
- task:
type: Classification
dataset:
type: mteb/emotion
name: MTEB EmotionClassification
config: default
split: test
revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37
metrics:
- type: accuracy
value: 47.06499999999999
- type: f1
value: 41.439327599975385
- task:
type: Retrieval
dataset:
type: fever
name: MTEB FEVER
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 66.02
- type: map_at_10
value: 76.68599999999999
- type: map_at_100
value: 76.959
- type: map_at_1000
value: 76.972
- type: map_at_3
value: 75.024
- type: map_at_5
value: 76.153
- type: mrr_at_1
value: 71.197
- type: mrr_at_10
value: 81.105
- type: mrr_at_100
value: 81.232
- type: mrr_at_1000
value: 81.233
- type: mrr_at_3
value: 79.758
- type: mrr_at_5
value: 80.69
- type: ndcg_at_1
value: 71.197
- type: ndcg_at_10
value: 81.644
- type: ndcg_at_100
value: 82.645
- type: ndcg_at_1000
value: 82.879
- type: ndcg_at_3
value: 78.792
- type: ndcg_at_5
value: 80.528
- type: precision_at_1
value: 71.197
- type: precision_at_10
value: 10.206999999999999
- type: precision_at_100
value: 1.093
- type: precision_at_1000
value: 0.11299999999999999
- type: precision_at_3
value: 30.868000000000002
- type: precision_at_5
value: 19.559
- type: recall_at_1
value: 66.02
- type: recall_at_10
value: 92.50699999999999
- type: recall_at_100
value: 96.497
- type: recall_at_1000
value: 97.956
- type: recall_at_3
value: 84.866
- type: recall_at_5
value: 89.16199999999999
- task:
type: Retrieval
dataset:
type: fiqa
name: MTEB FiQA2018
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 17.948
- type: map_at_10
value: 29.833
- type: map_at_100
value: 31.487
- type: map_at_1000
value: 31.674000000000003
- type: map_at_3
value: 26.029999999999998
- type: map_at_5
value: 28.038999999999998
- type: mrr_at_1
value: 34.721999999999994
- type: mrr_at_10
value: 44.214999999999996
- type: mrr_at_100
value: 44.994
- type: mrr_at_1000
value: 45.051
- type: mrr_at_3
value: 41.667
- type: mrr_at_5
value: 43.032
- type: ndcg_at_1
value: 34.721999999999994
- type: ndcg_at_10
value: 37.434
- type: ndcg_at_100
value: 43.702000000000005
- type: ndcg_at_1000
value: 46.993
- type: ndcg_at_3
value: 33.56
- type: ndcg_at_5
value: 34.687
- type: precision_at_1
value: 34.721999999999994
- type: precision_at_10
value: 10.401
- type: precision_at_100
value: 1.7049999999999998
- type: precision_at_1000
value: 0.22799999999999998
- type: precision_at_3
value: 22.531000000000002
- type: precision_at_5
value: 16.42
- type: recall_at_1
value: 17.948
- type: recall_at_10
value: 45.062999999999995
- type: recall_at_100
value: 68.191
- type: recall_at_1000
value: 87.954
- type: recall_at_3
value: 31.112000000000002
- type: recall_at_5
value: 36.823
- task:
type: Retrieval
dataset:
type: hotpotqa
name: MTEB HotpotQA
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 36.644
- type: map_at_10
value: 57.658
- type: map_at_100
value: 58.562000000000005
- type: map_at_1000
value: 58.62500000000001
- type: map_at_3
value: 54.022999999999996
- type: map_at_5
value: 56.293000000000006
- type: mrr_at_1
value: 73.288
- type: mrr_at_10
value: 80.51700000000001
- type: mrr_at_100
value: 80.72
- type: mrr_at_1000
value: 80.728
- type: mrr_at_3
value: 79.33200000000001
- type: mrr_at_5
value: 80.085
- type: ndcg_at_1
value: 73.288
- type: ndcg_at_10
value: 66.61
- type: ndcg_at_100
value: 69.723
- type: ndcg_at_1000
value: 70.96000000000001
- type: ndcg_at_3
value: 61.358999999999995
- type: ndcg_at_5
value: 64.277
- type: precision_at_1
value: 73.288
- type: precision_at_10
value: 14.17
- type: precision_at_100
value: 1.659
- type: precision_at_1000
value: 0.182
- type: precision_at_3
value: 39.487
- type: precision_at_5
value: 25.999
- type: recall_at_1
value: 36.644
- type: recall_at_10
value: 70.851
- type: recall_at_100
value: 82.94399999999999
- type: recall_at_1000
value: 91.134
- type: recall_at_3
value: 59.230000000000004
- type: recall_at_5
value: 64.997
- task:
type: Classification
dataset:
type: mteb/imdb
name: MTEB ImdbClassification
config: default
split: test
revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7
metrics:
- type: accuracy
value: 86.00280000000001
- type: ap
value: 80.46302061021223
- type: f1
value: 85.9592921596419
- task:
type: Retrieval
dataset:
type: msmarco
name: MTEB MSMARCO
config: default
split: dev
revision: None
metrics:
- type: map_at_1
value: 22.541
- type: map_at_10
value: 34.625
- type: map_at_100
value: 35.785
- type: map_at_1000
value: 35.831
- type: map_at_3
value: 30.823
- type: map_at_5
value: 32.967999999999996
- type: mrr_at_1
value: 23.180999999999997
- type: mrr_at_10
value: 35.207
- type: mrr_at_100
value: 36.315
- type: mrr_at_1000
value: 36.355
- type: mrr_at_3
value: 31.483
- type: mrr_at_5
value: 33.589999999999996
- type: ndcg_at_1
value: 23.195
- type: ndcg_at_10
value: 41.461
- type: ndcg_at_100
value: 47.032000000000004
- type: ndcg_at_1000
value: 48.199999999999996
- type: ndcg_at_3
value: 33.702
- type: ndcg_at_5
value: 37.522
- type: precision_at_1
value: 23.195
- type: precision_at_10
value: 6.526999999999999
- type: precision_at_100
value: 0.932
- type: precision_at_1000
value: 0.10300000000000001
- type: precision_at_3
value: 14.308000000000002
- type: precision_at_5
value: 10.507
- type: recall_at_1
value: 22.541
- type: recall_at_10
value: 62.524
- type: recall_at_100
value: 88.228
- type: recall_at_1000
value: 97.243
- type: recall_at_3
value: 41.38
- type: recall_at_5
value: 50.55
- task:
type: Classification
dataset:
type: mteb/mtop_domain
name: MTEB MTOPDomainClassification (en)
config: en
split: test
revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf
metrics:
- type: accuracy
value: 92.69949840401279
- type: f1
value: 92.54141471311786
- task:
type: Classification
dataset:
type: mteb/mtop_intent
name: MTEB MTOPIntentClassification (en)
config: en
split: test
revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba
metrics:
- type: accuracy
value: 72.56041951664386
- type: f1
value: 55.88499977508287
- task:
type: Classification
dataset:
type: mteb/amazon_massive_intent
name: MTEB MassiveIntentClassification (en)
config: en
split: test
revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7
metrics:
- type: accuracy
value: 71.62071284465365
- type: f1
value: 69.36717546572152
- task:
type: Classification
dataset:
type: mteb/amazon_massive_scenario
name: MTEB MassiveScenarioClassification (en)
config: en
split: test
revision: 7d571f92784cd94a019292a1f45445077d0ef634
metrics:
- type: accuracy
value: 76.35843981170142
- type: f1
value: 76.15496453538884
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-p2p
name: MTEB MedrxivClusteringP2P
config: default
split: test
revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73
metrics:
- type: v_measure
value: 31.33664956793118
- task:
type: Clustering
dataset:
type: mteb/medrxiv-clustering-s2s
name: MTEB MedrxivClusteringS2S
config: default
split: test
revision: 35191c8c0dca72d8ff3efcd72aa802307d469663
metrics:
- type: v_measure
value: 27.883839621715524
- task:
type: Reranking
dataset:
type: mteb/mind_small
name: MTEB MindSmallReranking
config: default
split: test
revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69
metrics:
- type: map
value: 30.096874986740758
- type: mrr
value: 30.97300481932132
- task:
type: Retrieval
dataset:
type: nfcorpus
name: MTEB NFCorpus
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 5.4
- type: map_at_10
value: 11.852
- type: map_at_100
value: 14.758
- type: map_at_1000
value: 16.134
- type: map_at_3
value: 8.558
- type: map_at_5
value: 10.087
- type: mrr_at_1
value: 44.272
- type: mrr_at_10
value: 52.05800000000001
- type: mrr_at_100
value: 52.689
- type: mrr_at_1000
value: 52.742999999999995
- type: mrr_at_3
value: 50.205999999999996
- type: mrr_at_5
value: 51.367
- type: ndcg_at_1
value: 42.57
- type: ndcg_at_10
value: 32.449
- type: ndcg_at_100
value: 29.596
- type: ndcg_at_1000
value: 38.351
- type: ndcg_at_3
value: 37.044
- type: ndcg_at_5
value: 35.275
- type: precision_at_1
value: 44.272
- type: precision_at_10
value: 23.87
- type: precision_at_100
value: 7.625
- type: precision_at_1000
value: 2.045
- type: precision_at_3
value: 34.365
- type: precision_at_5
value: 30.341
- type: recall_at_1
value: 5.4
- type: recall_at_10
value: 15.943999999999999
- type: recall_at_100
value: 29.805
- type: recall_at_1000
value: 61.695
- type: recall_at_3
value: 9.539
- type: recall_at_5
value: 12.127
- task:
type: Retrieval
dataset:
type: nq
name: MTEB NQ
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 36.047000000000004
- type: map_at_10
value: 51.6
- type: map_at_100
value: 52.449999999999996
- type: map_at_1000
value: 52.476
- type: map_at_3
value: 47.452
- type: map_at_5
value: 49.964
- type: mrr_at_1
value: 40.382
- type: mrr_at_10
value: 54.273
- type: mrr_at_100
value: 54.859
- type: mrr_at_1000
value: 54.876000000000005
- type: mrr_at_3
value: 51.014
- type: mrr_at_5
value: 52.983999999999995
- type: ndcg_at_1
value: 40.353
- type: ndcg_at_10
value: 59.11300000000001
- type: ndcg_at_100
value: 62.604000000000006
- type: ndcg_at_1000
value: 63.187000000000005
- type: ndcg_at_3
value: 51.513
- type: ndcg_at_5
value: 55.576
- type: precision_at_1
value: 40.353
- type: precision_at_10
value: 9.418
- type: precision_at_100
value: 1.1440000000000001
- type: precision_at_1000
value: 0.12
- type: precision_at_3
value: 23.078000000000003
- type: precision_at_5
value: 16.250999999999998
- type: recall_at_1
value: 36.047000000000004
- type: recall_at_10
value: 79.22200000000001
- type: recall_at_100
value: 94.23
- type: recall_at_1000
value: 98.51100000000001
- type: recall_at_3
value: 59.678
- type: recall_at_5
value: 68.967
- task:
type: Retrieval
dataset:
type: quora
name: MTEB QuoraRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 68.232
- type: map_at_10
value: 81.674
- type: map_at_100
value: 82.338
- type: map_at_1000
value: 82.36099999999999
- type: map_at_3
value: 78.833
- type: map_at_5
value: 80.58
- type: mrr_at_1
value: 78.64
- type: mrr_at_10
value: 85.164
- type: mrr_at_100
value: 85.317
- type: mrr_at_1000
value: 85.319
- type: mrr_at_3
value: 84.127
- type: mrr_at_5
value: 84.789
- type: ndcg_at_1
value: 78.63
- type: ndcg_at_10
value: 85.711
- type: ndcg_at_100
value: 87.238
- type: ndcg_at_1000
value: 87.444
- type: ndcg_at_3
value: 82.788
- type: ndcg_at_5
value: 84.313
- type: precision_at_1
value: 78.63
- type: precision_at_10
value: 12.977
- type: precision_at_100
value: 1.503
- type: precision_at_1000
value: 0.156
- type: precision_at_3
value: 36.113
- type: precision_at_5
value: 23.71
- type: recall_at_1
value: 68.232
- type: recall_at_10
value: 93.30199999999999
- type: recall_at_100
value: 98.799
- type: recall_at_1000
value: 99.885
- type: recall_at_3
value: 84.827
- type: recall_at_5
value: 89.188
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering
name: MTEB RedditClustering
config: default
split: test
revision: 24640382cdbf8abc73003fb0fa6d111a705499eb
metrics:
- type: v_measure
value: 45.71879170816294
- task:
type: Clustering
dataset:
type: mteb/reddit-clustering-p2p
name: MTEB RedditClusteringP2P
config: default
split: test
revision: 282350215ef01743dc01b456c7f5241fa8937f16
metrics:
- type: v_measure
value: 59.65866311751794
- task:
type: Retrieval
dataset:
type: scidocs
name: MTEB SCIDOCS
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 4.218
- type: map_at_10
value: 10.337
- type: map_at_100
value: 12.131
- type: map_at_1000
value: 12.411
- type: map_at_3
value: 7.4270000000000005
- type: map_at_5
value: 8.913
- type: mrr_at_1
value: 20.8
- type: mrr_at_10
value: 30.868000000000002
- type: mrr_at_100
value: 31.903
- type: mrr_at_1000
value: 31.972
- type: mrr_at_3
value: 27.367
- type: mrr_at_5
value: 29.372
- type: ndcg_at_1
value: 20.8
- type: ndcg_at_10
value: 17.765
- type: ndcg_at_100
value: 24.914
- type: ndcg_at_1000
value: 30.206
- type: ndcg_at_3
value: 16.64
- type: ndcg_at_5
value: 14.712
- type: precision_at_1
value: 20.8
- type: precision_at_10
value: 9.24
- type: precision_at_100
value: 1.9560000000000002
- type: precision_at_1000
value: 0.32299999999999995
- type: precision_at_3
value: 15.467
- type: precision_at_5
value: 12.94
- type: recall_at_1
value: 4.218
- type: recall_at_10
value: 18.752
- type: recall_at_100
value: 39.7
- type: recall_at_1000
value: 65.57300000000001
- type: recall_at_3
value: 9.428
- type: recall_at_5
value: 13.133000000000001
- task:
type: STS
dataset:
type: mteb/sickr-sts
name: MTEB SICK-R
config: default
split: test
revision: a6ea5a8cab320b040a23452cc28066d9beae2cee
metrics:
- type: cos_sim_pearson
value: 83.04338850207233
- type: cos_sim_spearman
value: 78.5054651430423
- type: euclidean_pearson
value: 80.30739451228612
- type: euclidean_spearman
value: 78.48377464299097
- type: manhattan_pearson
value: 80.40795049052781
- type: manhattan_spearman
value: 78.49506205443114
- task:
type: STS
dataset:
type: mteb/sts12-sts
name: MTEB STS12
config: default
split: test
revision: a0d554a64d88156834ff5ae9920b964011b16384
metrics:
- type: cos_sim_pearson
value: 84.11596224442962
- type: cos_sim_spearman
value: 76.20997388935461
- type: euclidean_pearson
value: 80.56858451349109
- type: euclidean_spearman
value: 75.92659183871186
- type: manhattan_pearson
value: 80.60246102203844
- type: manhattan_spearman
value: 76.03018971432664
- task:
type: STS
dataset:
type: mteb/sts13-sts
name: MTEB STS13
config: default
split: test
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
metrics:
- type: cos_sim_pearson
value: 81.34691640755737
- type: cos_sim_spearman
value: 82.4018369631579
- type: euclidean_pearson
value: 81.87673092245366
- type: euclidean_spearman
value: 82.3671489960678
- type: manhattan_pearson
value: 81.88222387719948
- type: manhattan_spearman
value: 82.3816590344736
- task:
type: STS
dataset:
type: mteb/sts14-sts
name: MTEB STS14
config: default
split: test
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
metrics:
- type: cos_sim_pearson
value: 81.2836092579524
- type: cos_sim_spearman
value: 78.99982781772064
- type: euclidean_pearson
value: 80.5184271010527
- type: euclidean_spearman
value: 78.89777392101904
- type: manhattan_pearson
value: 80.53585705018664
- type: manhattan_spearman
value: 78.92898405472994
- task:
type: STS
dataset:
type: mteb/sts15-sts
name: MTEB STS15
config: default
split: test
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
metrics:
- type: cos_sim_pearson
value: 86.7349907750784
- type: cos_sim_spearman
value: 87.7611234446225
- type: euclidean_pearson
value: 86.98759326731624
- type: euclidean_spearman
value: 87.58321319424618
- type: manhattan_pearson
value: 87.03483090370842
- type: manhattan_spearman
value: 87.63278333060288
- task:
type: STS
dataset:
type: mteb/sts16-sts
name: MTEB STS16
config: default
split: test
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
metrics:
- type: cos_sim_pearson
value: 81.75873694924825
- type: cos_sim_spearman
value: 83.80237999094724
- type: euclidean_pearson
value: 83.55023725861537
- type: euclidean_spearman
value: 84.12744338577744
- type: manhattan_pearson
value: 83.58816983036232
- type: manhattan_spearman
value: 84.18520748676501
- 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: 87.21630882940174
- type: cos_sim_spearman
value: 87.72382883437031
- type: euclidean_pearson
value: 88.69933350930333
- type: euclidean_spearman
value: 88.24660814383081
- type: manhattan_pearson
value: 88.77331018833499
- type: manhattan_spearman
value: 88.26109989380632
- 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: 61.11854063060489
- type: cos_sim_spearman
value: 63.14678634195072
- type: euclidean_pearson
value: 61.679090067000864
- type: euclidean_spearman
value: 62.28876589509653
- type: manhattan_pearson
value: 62.082324165511004
- type: manhattan_spearman
value: 62.56030932816679
- task:
type: STS
dataset:
type: mteb/stsbenchmark-sts
name: MTEB STSBenchmark
config: default
split: test
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
metrics:
- type: cos_sim_pearson
value: 84.00319882832645
- type: cos_sim_spearman
value: 85.94529772647257
- type: euclidean_pearson
value: 85.6661390122756
- type: euclidean_spearman
value: 85.97747815545827
- type: manhattan_pearson
value: 85.58422770541893
- type: manhattan_spearman
value: 85.9237139181532
- task:
type: Reranking
dataset:
type: mteb/scidocs-reranking
name: MTEB SciDocsRR
config: default
split: test
revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab
metrics:
- type: map
value: 79.16198731863916
- type: mrr
value: 94.25202702163487
- task:
type: Retrieval
dataset:
type: scifact
name: MTEB SciFact
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 54.761
- type: map_at_10
value: 64.396
- type: map_at_100
value: 65.07
- type: map_at_1000
value: 65.09899999999999
- type: map_at_3
value: 61.846000000000004
- type: map_at_5
value: 63.284
- type: mrr_at_1
value: 57.667
- type: mrr_at_10
value: 65.83099999999999
- type: mrr_at_100
value: 66.36800000000001
- type: mrr_at_1000
value: 66.39399999999999
- type: mrr_at_3
value: 64.056
- type: mrr_at_5
value: 65.206
- type: ndcg_at_1
value: 57.667
- type: ndcg_at_10
value: 68.854
- type: ndcg_at_100
value: 71.59100000000001
- type: ndcg_at_1000
value: 72.383
- type: ndcg_at_3
value: 64.671
- type: ndcg_at_5
value: 66.796
- type: precision_at_1
value: 57.667
- type: precision_at_10
value: 9.167
- type: precision_at_100
value: 1.053
- type: precision_at_1000
value: 0.11199999999999999
- type: precision_at_3
value: 25.444
- type: precision_at_5
value: 16.667
- type: recall_at_1
value: 54.761
- type: recall_at_10
value: 80.9
- type: recall_at_100
value: 92.767
- type: recall_at_1000
value: 99
- type: recall_at_3
value: 69.672
- type: recall_at_5
value: 75.083
- task:
type: PairClassification
dataset:
type: mteb/sprintduplicatequestions-pairclassification
name: MTEB SprintDuplicateQuestions
config: default
split: test
revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46
metrics:
- type: cos_sim_accuracy
value: 99.8079207920792
- type: cos_sim_ap
value: 94.88470927617445
- type: cos_sim_f1
value: 90.08179959100204
- type: cos_sim_precision
value: 92.15481171548117
- type: cos_sim_recall
value: 88.1
- type: dot_accuracy
value: 99.58613861386138
- type: dot_ap
value: 82.94822578881316
- type: dot_f1
value: 77.33333333333333
- type: dot_precision
value: 79.36842105263158
- type: dot_recall
value: 75.4
- type: euclidean_accuracy
value: 99.8069306930693
- type: euclidean_ap
value: 94.81367858031837
- type: euclidean_f1
value: 90.01009081735621
- type: euclidean_precision
value: 90.83503054989816
- type: euclidean_recall
value: 89.2
- type: manhattan_accuracy
value: 99.81188118811882
- type: manhattan_ap
value: 94.91405337220161
- type: manhattan_f1
value: 90.2763561924258
- type: manhattan_precision
value: 92.45283018867924
- type: manhattan_recall
value: 88.2
- type: max_accuracy
value: 99.81188118811882
- type: max_ap
value: 94.91405337220161
- type: max_f1
value: 90.2763561924258
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering
name: MTEB StackExchangeClustering
config: default
split: test
revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259
metrics:
- type: v_measure
value: 58.511599500053094
- task:
type: Clustering
dataset:
type: mteb/stackexchange-clustering-p2p
name: MTEB StackExchangeClusteringP2P
config: default
split: test
revision: 815ca46b2622cec33ccafc3735d572c266efdb44
metrics:
- type: v_measure
value: 31.984728147814707
- task:
type: Reranking
dataset:
type: mteb/stackoverflowdupquestions-reranking
name: MTEB StackOverflowDupQuestions
config: default
split: test
revision: e185fbe320c72810689fc5848eb6114e1ef5ec69
metrics:
- type: map
value: 49.93428193939015
- type: mrr
value: 50.916557911043206
- task:
type: Summarization
dataset:
type: mteb/summeval
name: MTEB SummEval
config: default
split: test
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
metrics:
- type: cos_sim_pearson
value: 31.562500894537145
- type: cos_sim_spearman
value: 31.162587976726307
- type: dot_pearson
value: 22.633662187735762
- type: dot_spearman
value: 22.723000282378962
- task:
type: Retrieval
dataset:
type: trec-covid
name: MTEB TRECCOVID
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 0.219
- type: map_at_10
value: 1.871
- type: map_at_100
value: 10.487
- type: map_at_1000
value: 25.122
- type: map_at_3
value: 0.657
- type: map_at_5
value: 1.0699999999999998
- type: mrr_at_1
value: 84
- type: mrr_at_10
value: 89.567
- type: mrr_at_100
value: 89.748
- type: mrr_at_1000
value: 89.748
- type: mrr_at_3
value: 88.667
- type: mrr_at_5
value: 89.567
- type: ndcg_at_1
value: 80
- type: ndcg_at_10
value: 74.533
- type: ndcg_at_100
value: 55.839000000000006
- type: ndcg_at_1000
value: 49.748
- type: ndcg_at_3
value: 79.53099999999999
- type: ndcg_at_5
value: 78.245
- type: precision_at_1
value: 84
- type: precision_at_10
value: 78.4
- type: precision_at_100
value: 56.99999999999999
- type: precision_at_1000
value: 21.98
- type: precision_at_3
value: 85.333
- type: precision_at_5
value: 84.8
- type: recall_at_1
value: 0.219
- type: recall_at_10
value: 2.02
- type: recall_at_100
value: 13.555
- type: recall_at_1000
value: 46.739999999999995
- type: recall_at_3
value: 0.685
- type: recall_at_5
value: 1.13
- task:
type: Retrieval
dataset:
type: webis-touche2020
name: MTEB Touche2020
config: default
split: test
revision: None
metrics:
- type: map_at_1
value: 3.5029999999999997
- type: map_at_10
value: 11.042
- type: map_at_100
value: 16.326999999999998
- type: map_at_1000
value: 17.836
- type: map_at_3
value: 6.174
- type: map_at_5
value: 7.979
- type: mrr_at_1
value: 42.857
- type: mrr_at_10
value: 52.617000000000004
- type: mrr_at_100
value: 53.351000000000006
- type: mrr_at_1000
value: 53.351000000000006
- type: mrr_at_3
value: 46.939
- type: mrr_at_5
value: 50.714000000000006
- type: ndcg_at_1
value: 38.775999999999996
- type: ndcg_at_10
value: 27.125
- type: ndcg_at_100
value: 35.845
- type: ndcg_at_1000
value: 47.377
- type: ndcg_at_3
value: 29.633
- type: ndcg_at_5
value: 28.378999999999998
- type: precision_at_1
value: 42.857
- type: precision_at_10
value: 24.082
- type: precision_at_100
value: 6.877999999999999
- type: precision_at_1000
value: 1.463
- type: precision_at_3
value: 29.932
- type: precision_at_5
value: 28.571
- type: recall_at_1
value: 3.5029999999999997
- type: recall_at_10
value: 17.068
- type: recall_at_100
value: 43.361
- type: recall_at_1000
value: 78.835
- type: recall_at_3
value: 6.821000000000001
- type: recall_at_5
value: 10.357
- task:
type: Classification
dataset:
type: mteb/toxic_conversations_50k
name: MTEB ToxicConversationsClassification
config: default
split: test
revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c
metrics:
- type: accuracy
value: 71.0954
- type: ap
value: 14.216844153511959
- type: f1
value: 54.63687418565117
- task:
type: Classification
dataset:
type: mteb/tweet_sentiment_extraction
name: MTEB TweetSentimentExtractionClassification
config: default
split: test
revision: d604517c81ca91fe16a244d1248fc021f9ecee7a
metrics:
- type: accuracy
value: 61.46293152235427
- type: f1
value: 61.744177921638645
- task:
type: Clustering
dataset:
type: mteb/twentynewsgroups-clustering
name: MTEB TwentyNewsgroupsClustering
config: default
split: test
revision: 6125ec4e24fa026cec8a478383ee943acfbd5449
metrics:
- type: v_measure
value: 41.12708617788644
- task:
type: PairClassification
dataset:
type: mteb/twittersemeval2015-pairclassification
name: MTEB TwitterSemEval2015
config: default
split: test
revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1
metrics:
- type: cos_sim_accuracy
value: 85.75430649102938
- type: cos_sim_ap
value: 73.34252536948081
- type: cos_sim_f1
value: 67.53758935173774
- type: cos_sim_precision
value: 63.3672525439408
- type: cos_sim_recall
value: 72.29551451187335
- type: dot_accuracy
value: 81.71305954580676
- type: dot_ap
value: 59.5532209082386
- type: dot_f1
value: 56.18466898954705
- type: dot_precision
value: 47.830923248053395
- type: dot_recall
value: 68.07387862796834
- type: euclidean_accuracy
value: 85.81987244441795
- type: euclidean_ap
value: 73.34325409809446
- type: euclidean_f1
value: 67.83451360417443
- type: euclidean_precision
value: 64.09955388588871
- type: euclidean_recall
value: 72.0316622691293
- type: manhattan_accuracy
value: 85.68277999642368
- type: manhattan_ap
value: 73.1535450121903
- type: manhattan_f1
value: 67.928237896289
- type: manhattan_precision
value: 63.56945722171113
- type: manhattan_recall
value: 72.9287598944591
- type: max_accuracy
value: 85.81987244441795
- type: max_ap
value: 73.34325409809446
- type: max_f1
value: 67.928237896289
- task:
type: PairClassification
dataset:
type: mteb/twitterurlcorpus-pairclassification
name: MTEB TwitterURLCorpus
config: default
split: test
revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf
metrics:
- type: cos_sim_accuracy
value: 88.90441262079403
- type: cos_sim_ap
value: 85.79331880741438
- type: cos_sim_f1
value: 78.31563529842548
- type: cos_sim_precision
value: 74.6683424102779
- type: cos_sim_recall
value: 82.33754234678165
- type: dot_accuracy
value: 84.89928978926534
- type: dot_ap
value: 75.25819218316
- type: dot_f1
value: 69.88730119720536
- type: dot_precision
value: 64.23362374959665
- type: dot_recall
value: 76.63227594702803
- type: euclidean_accuracy
value: 89.01695967710637
- type: euclidean_ap
value: 85.98986606038852
- type: euclidean_f1
value: 78.5277880014722
- type: euclidean_precision
value: 75.22211253701876
- type: euclidean_recall
value: 82.13735756082538
- type: manhattan_accuracy
value: 88.99561454573679
- type: manhattan_ap
value: 85.92262421793953
- type: manhattan_f1
value: 78.38866094740769
- type: manhattan_precision
value: 76.02373028505282
- type: manhattan_recall
value: 80.9054511857099
- type: max_accuracy
value: 89.01695967710637
- type: max_ap
value: 85.98986606038852
- type: max_f1
value: 78.5277880014722
---
# E5-small-v2
[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 384.
## 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: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
'query: summit define',
"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: Definition of summit for English Language Learners. : 1 the highest point of a mountain : the top of a mountain. : 2 the highest level. : 3 a meeting or series of meetings between the leaders of two or more governments."]
tokenizer = AutoTokenizer.from_pretrained('ggrn/e5-small-v2')
model = AutoModel.from_pretrained('ggrn/e5-small-v2')
# 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'])
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())
```
## Training Details
Please refer to our paper at [https://arxiv.org/pdf/2212.03533.pdf](https://arxiv.org/pdf/2212.03533.pdf).
## 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).
## 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
This model only works for English texts. Long texts will be truncated to at most 512 tokens.
## Sentence Transformers
Below is an example for usage with sentence_transformers. `pip install sentence_transformers~=2.2.2`
This is community contributed, and results may vary up to numerical precision.
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('ggrn/e5-small-v2')
embeddings = model.encode(input_texts, normalize_embeddings=True)
``` | 65,988 | [
[
-0.018157958984375,
-0.04547119140625,
0.02264404296875,
0.00963592529296875,
-0.030548095703125,
-0.03619384765625,
-0.01154327392578125,
-0.02850341796875,
0.006988525390625,
0.00904083251953125,
-0.03515625,
-0.050262451171875,
-0.068603515625,
0.01777648... |
ra100/sdxl-lora-lower-decks-aesthetic | 2023-11-07T00:43:36.000Z | [
"diffusers",
"tensorboard",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"has_space",
"region:us"
] | text-to-image | ra100 | null | null | ra100/sdxl-lora-lower-decks-aesthetic | 1 | 496 | diffusers | 2023-08-14T12:21:02 |
---
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-xl-base-1.0
dataset: None
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - ra100/sdxl-lora-lower-decks-aesthetic
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the None dataset.
Tokens to use:
- `sttld aesthetic` - Star Trek Lower Decks style
- `blue and gray sttldunf uniform` - to see uniform
Images below generated with prompt:
> a female in a blue and gray sttldunf uniform standing in woods next to a lake, sttldjrlt, sttld aesthetic
You can find some example images in the following.
LoRA for the text encoder was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
| 945 | [
[
-0.016754150390625,
-0.053802490234375,
0.01580810546875,
0.00846099853515625,
-0.05340576171875,
0.00140380859375,
0.006649017333984375,
-0.020111083984375,
0.058349609375,
0.06317138671875,
-0.05621337890625,
-0.058197021484375,
-0.0501708984375,
-0.010475... |
SaiedAlshahrani/arwiki_20230101_roberta_mlm_nobots | 2023-10-29T01:26:43.000Z | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"fill-mask",
"generated_from_trainer",
"ar",
"dataset:SaiedAlshahrani/Arabic_Wikipedia_20230101_nobots",
"dataset:SaiedAlshahrani/MASD",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | SaiedAlshahrani | null | null | SaiedAlshahrani/arwiki_20230101_roberta_mlm_nobots | 0 | 496 | transformers | 2023-08-27T09:32:55 | ---
tags:
- generated_from_trainer
model-index:
- name: arRoBERTa
results: []
metrics:
- perplexity
license: mit
datasets:
- SaiedAlshahrani/Arabic_Wikipedia_20230101_nobots
- SaiedAlshahrani/MASD
language:
- ar
library_name: transformers
pipeline_tag: fill-mask
widget:
- text: الهدف من الحياة هو <mask>
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Arabic Wikipedia (arRoBERTa<sub>BASE</sub>)
This arRoBERTa<sub>BASE</sub> model has been trained *from scratch* on the Arabic Wikipedia articles (**after removing the bot-generated articles**), downloaded on the 1st of January 2023, processed using
`Gensim` Python library, preprocessed using `tr` Linux/Unix utility and `CAMeLTools` Python toolkit for Arabic NLP, and hosted here at [SaiedAlshahrani/Arabic\_Wikipedia\_20230101\_nobots](https://huggingface.co/datasets/SaiedAlshahrani/Arabic_Wikipedia_20230101_nobots).
It achieves the following results on the evaluation set:
- Pseudo-Perplexity: 20.41
## Model description
We trained this Arabic Wikipedia Masked Language Model (arRoBERTa<sub>BASE</sub>) to evaluate its performance using the Fill-Mask evaluation task and the Masked Arab States Dataset ([MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)) dataset and measure the *impact* of **bot-based generation** on the Arabic Wikipedia edition.
For more details about the experiment, please **read** and **cite** our paper:
```bash
@inproceedings{alshahrani-etal-2023-implications,
title = "{{Performance Implications of Using Unrepresentative Corpora in Arabic Natural Language Processing}}",
author = "Alshahrani, Saied and Alshahrani, Norah and Dey, Soumyabrata and Matthews, Jeanna",
booktitle = "Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://webspace.clarkson.edu/~alshahsf/unrepresentative_corpora.pdf",
doi = "#################",
pages = "###--###",
abstract = "Wikipedia articles are a widely used source of training data for Natural Language Processing (NLP) research, particularly as corpora for low-resource languages like Arabic. However, it is essential to understand the extent to which these corpora reflect the representative contributions of native speakers, especially when many entries in a given language are directly translated from other languages or automatically generated through automated mechanisms. In this paper, we study the performance implications of using inorganic corpora that are not representative of native speakers and are generated through automated techniques such as bot generation or automated template-based translation. The case of the Arabic Wikipedia editions gives a unique case study of this since the Moroccan Arabic Wikipedia edition (ARY) is small but representative, the Egyptian Arabic Wikipedia edition (ARZ) is large but unrepresentative, and the Modern Standard Arabic Wikipedia edition (AR) is both large and more representative. We intrinsically evaluate the performance of two main NLP upstream tasks, namely word representation and language modeling, using word analogy evaluations and fill-mask evaluations using our two newly created datasets: Arab States Analogy Dataset (ASAD) and Masked Arab States Dataset (MASD). We demonstrate that for good NLP performance, we need both large and organic corpora; neither alone is sufficient. We show that producing large corpora through automated means can be a counter-productive, producing models that both perform worse and lack cultural richness and meaningful representation of the Arabic language and its native speakers.",
}
```
## Intended uses & limitations
We do **not** recommend using this model because it was trained *only* on the Arabic Wikipedia articles (**after removing the bot-generated articles**), <u>unless</u> you fine-tune the model on a large, organic, and representative Arabic dataset.
## Training and evaluation data
We have trained this model on the Arabic Wikipedia articles without bot-generated articles ([SaiedAlshahrani/Arabic\_Wikipedia\_20230101\_nobots](https://huggingface.co/datasets/SaiedAlshahrani/Arabic_Wikipedia_20230101_nobots)) without using any validation or evaluation data (only training data) due to a lack of computational power.
## Training procedure
We have trained this model using the Paperspace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 256
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Epoch | Step | Training Loss |
|:-----:|:-----:|:-------------:|
| 1 | 3000 | 5.681200 |
| 2 | 6000 | 3.777100 |
| 3 | 9000 | 3.246300 |
| 4 | 12000 | 3.012100 |
| 5 | 15000 | 2.888400 |
| Train Runtime | Train Samples Per Second | Train Steps Per Second | Total Flos | Train Loss | Epoch |
|:--------------:|:------------------------:|:----------------------:|:-------------------------:|:----------:|:--------:|
| 17048.756800 | 248.355000 | 0.970000 | 140390797515571200.000000 | 3.639375 | 5.000000 |
### Evaluation results
This arRoBERTa<sub>BASE</sub> model has been evaluated on the Masked Arab States Dataset ([SaiedAlshahrani/MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)).
| K=10 | K=50 | K=100 |
|:----:|:-----:|:----:|
| 45.62%| 51.25% | 53.12% |
### Framework versions
- Datasets 2.9.0
- Tokenizers 0.12.1
- Transformers 4.24.0
- Pytorch 1.12.1+cu116 | 5,986 | [
[
-0.05224609375,
-0.0457763671875,
0.006542205810546875,
-0.01070404052734375,
-0.022247314453125,
0.0052337646484375,
-0.0241546630859375,
-0.05267333984375,
0.00885009765625,
0.019256591796875,
-0.0290679931640625,
-0.049102783203125,
-0.056854248046875,
0.... |
TheBloke/openchat_3.5-GPTQ | 2023-11-02T21:40:18.000Z | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"arxiv:2309.11235",
"arxiv:2303.08774",
"arxiv:2212.10560",
"license:apache-2.0",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/openchat_3.5-GPTQ | 7 | 496 | transformers | 2023-11-02T20:04:23 | ---
base_model: openchat/openchat_3.5
inference: false
license: apache-2.0
model_creator: OpenChat
model_name: OpenChat 3.5 7B
model_type: mistral
prompt_template: 'GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
'
quantized_by: TheBloke
---
<!-- markdownlint-disable MD041 -->
<!-- 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 -->
# OpenChat 3.5 7B - GPTQ
- Model creator: [OpenChat](https://huggingface.co/openchat)
- Original model: [OpenChat 3.5 7B](https://huggingface.co/openchat/openchat_3.5)
<!-- description start -->
## Description
This repo contains GPTQ model files for [OpenChat's OpenChat 3.5 7B](https://huggingface.co/openchat/openchat_3.5).
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.
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/openchat_3.5-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/openchat_3.5-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/openchat_3.5-GGUF)
* [OpenChat's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openchat/openchat_3.5)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: OpenChat
```
GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
```
<!-- prompt-template end -->
<!-- README_GPTQ.md-compatible clients start -->
## Known compatible clients / servers
These GPTQ models are known to work in the following inference servers/webuis.
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
- [KoboldAI United](https://github.com/henk717/koboldai)
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
This may not be a complete list; if you know of others, please let me know!
<!-- README_GPTQ.md-compatible clients 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.
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
<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 calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration 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 and Mistral models in 4-bit.
</details>
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/openchat_3.5-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/openchat_3.5-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/openchat_3.5-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.95 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/openchat_3.5-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 5.00 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/openchat_3.5-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.97 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/openchat_3.5-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 4.30 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
<!-- README_GPTQ.md-provided-files end -->
<!-- README_GPTQ.md-download-from-branches start -->
## How to download, including from branches
### In text-generation-webui
To download from the `main` branch, enter `TheBloke/openchat_3.5-GPTQ` in the "Download model" box.
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/openchat_3.5-GPTQ:gptq-4bit-32g-actorder_True`
### From the command line
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
To download the `main` branch to a folder called `openchat_3.5-GPTQ`:
```shell
mkdir openchat_3.5-GPTQ
huggingface-cli download TheBloke/openchat_3.5-GPTQ --local-dir openchat_3.5-GPTQ --local-dir-use-symlinks False
```
To download from a different branch, add the `--revision` parameter:
```shell
mkdir openchat_3.5-GPTQ
huggingface-cli download TheBloke/openchat_3.5-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir openchat_3.5-GPTQ --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage</summary>
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
mkdir openchat_3.5-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/openchat_3.5-GPTQ --local-dir openchat_3.5-GPTQ --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
### With `git` (**not** recommended)
To clone a specific branch with `git`, use a command like this:
```shell
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/openchat_3.5-GPTQ
```
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
<!-- 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/openchat_3.5-GPTQ`.
- To download from a specific branch, enter for example `TheBloke/openchat_3.5-GPTQ:gptq-4bit-32g-actorder_True`
- 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: `openchat_3.5-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-tgi start -->
## Serving this model from Text Generation Inference (TGI)
It's recommended to use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/openchat_3.5-GPTQ --port 3000 --quantize gptq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
prompt = "Tell me about AI"
prompt_template=f'''GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_GPTQ.md-use-from-tgi end -->
<!-- README_GPTQ.md-use-from-python start -->
## How to use this GPTQ model from Python code
### Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
```shell
pip3 install transformers optimum
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
git checkout v0.4.2
pip3 install .
```
### You can then use the following code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/openchat_3.5-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4bit-32g-actorder_True"
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'''GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
'''
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 Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama and Mistral models in 4-bit. Please see the Provided Files table above for per-file compatibility.
For a list of clients/servers, please see "Known compatible clients / servers", above.
<!-- 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**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: OpenChat's OpenChat 3.5 7B
# OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
<div align="center">
<img src="https://raw.githubusercontent.com/imoneoi/openchat/master/assets/logo_new.png" style="width: 65%">
</div>
<p align="center">
<a href="https://openchat.team">Online Demo</a> •
<a href="https://discord.gg/pQjnXvNKHY">Discord</a> •
<a href="https://huggingface.co/openchat">Huggingface</a> •
<a href="https://arxiv.org/pdf/2309.11235.pdf">Paper</a>
</p>
**🔥 The first 7B model Achieves Comparable Results with ChatGPT (March)! 🔥**
**🤖 #1 Open-source model on MT-bench scoring 7.81, outperforming 70B models 🤖**
<div align="center">
<img src="https://raw.githubusercontent.com/imoneoi/openchat/master/assets/openchat.png" style="width: 50%">
</div>
OpenChat is an innovative library of open-source language models, fine-tuned with [C-RLFT](https://arxiv.org/pdf/2309.11235.pdf) - a strategy inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model. Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.
[](https://zenodo.org/badge/latestdoi/645397533)
## Usage
To use this model, we highly recommend installing the OpenChat package by following the [installation guide](#installation) and using the OpenChat OpenAI-compatible API server by running the serving command from the table below. The server is optimized for high-throughput deployment using [vLLM](https://github.com/vllm-project/vllm) and can run on a consumer GPU with 24GB RAM. To enable tensor parallelism, append `--tensor-parallel-size N` to the serving command.
Once started, the server listens at `localhost:18888` for requests and is compatible with the [OpenAI ChatCompletion API specifications](https://platform.openai.com/docs/api-reference/chat). Please refer to the example request below for reference. Additionally, you can use the [OpenChat Web UI](#web-ui) for a user-friendly experience.
If you want to deploy the server as an online service, you can use `--api-keys sk-KEY1 sk-KEY2 ...` to specify allowed API keys and `--disable-log-requests --disable-log-stats --log-file openchat.log` for logging only to a file. For security purposes, we recommend using an [HTTPS gateway](https://fastapi.tiangolo.com/es/deployment/concepts/#security-https) in front of the server.
<details>
<summary>Example request (click to expand)</summary>
```bash
curl http://localhost:18888/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openchat_3.5",
"messages": [{"role": "user", "content": "You are a large language model named OpenChat. Write a poem to describe yourself"}]
}'
```
Coding Mode
```bash
curl http://localhost:18888/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "openchat_3.5",
"condition": "Code",
"messages": [{"role": "user", "content": "Write an aesthetic TODO app using HTML5 and JS, in a single file. You should use round corners and gradients to make it more aesthetic."}]
}'
```
</details>
| Model | Size | Context | Weights | Serving |
|--------------|------|---------|-------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------|
| OpenChat 3.5 | 7B | 8192 | [Huggingface](https://huggingface.co/openchat/openchat_3.5) | `python -m ochat.serving.openai_api_server --model openchat/openchat_3.5 --engine-use-ray --worker-use-ray` |
For inference with Huggingface Transformers (slow and not recommended), follow the conversation template provided below.
<details>
<summary>Conversation templates (click to expand)</summary>
```python
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat_3.5")
# Single-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Multi-turn
tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids
assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747]
# Coding Mode
tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids
assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747]
```
</details>
## <a id="benchmarks"></a> Benchmarks
| Model | # Params | Average | MT-Bench | AGIEval | BBH MC | TruthfulQA | MMLU | HumanEval | BBH CoT | GSM8K |
|--------------------|----------|----------|--------------|----------|----------|---------------|--------------|-----------------|-------------|--------------|
| OpenChat-3.5 | **7B** | **61.6** | 7.81 | **47.4** | **47.6** | **59.1** | 64.3 | **55.5** | 63.5 | **77.3** |
| ChatGPT (March)* | ? | 61.5 | **7.94** | 47.1 | **47.6** | 57.7 | **67.3** | 48.1 | **70.1** | 74.9 |
| Mistral | 7B | - | 6.84 | 38.0 | 39.0 | - | 60.1 | 30.5 | - | 52.2 |
| Open-source SOTA** | 13B-70B | 61.4 | 7.71 | 41.7 | 49.7 | 62.3 | 63.7 | 73.2 | 41.4 | 82.3 |
| | | | WizardLM 70B | Orca 13B | Orca 13B | Platypus2 70B | WizardLM 70B | WizardCoder 34B | Flan-T5 11B | MetaMath 70B |
*: ChatGPT (March) results are from [GPT-4 Technical Report](https://arxiv.org/abs/2303.08774), [Chain-of-Thought Hub](https://github.com/FranxYao/chain-of-thought-hub), and our evaluation. Please note that ChatGPT is not a fixed baseline and evolves rapidly over time.
**: Open-source SOTA results are taken from reported results in instruction-tuned model papers and official repositories.
***: All zero-shot benchmarks follow the same setting as in the AGIEval paper and Orca paper. CoT tasks use the same configuration as Chain-of-Thought Hub, HumanEval is evaluated with EvalPlus, and MT-bench is run using FastChat. To reproduce our results, follow the instructions in [our repository](https://github.com/imoneoi/openchat/#benchmarks).
## Limitations
**Foundation Model Limitations**
Despite its advanced capabilities, OpenChat is still bound by the limitations inherent in its foundation models. These limitations may impact the model's performance in areas such as:
- Complex reasoning
- Mathematical and arithmetic tasks
- Programming and coding challenges
**Hallucination of Non-existent Information**
OpenChat may sometimes generate information that does not exist or is not accurate, also known as "hallucination". Users should be aware of this possibility and verify any critical information obtained from the model.
**Safety**
OpenChat may sometimes generate harmful, hate speech, biased responses, or answer unsafe questions. It's crucial to apply additional AI safety measures in use cases that require safe and moderated responses.
## License
Our OpenChat 3.5 code and models are distributed under the Apache License 2.0.
## Citation
```
@article{wang2023openchat,
title={OpenChat: Advancing Open-source Language Models with Mixed-Quality Data},
author={Wang, Guan and Cheng, Sijie and Zhan, Xianyuan and Li, Xiangang and Song, Sen and Liu, Yang},
journal={arXiv preprint arXiv:2309.11235},
year={2023}
}
```
## Acknowledgements
We extend our heartfelt gratitude to Alignment Lab AI, Nous Research, and Pygmalion AI for their substantial contributions to data collection and model training.
Special thanks go to Changling Liu from GPT Desk Pte. Ltd., Qiying Yu at Tsinghua University, Baochang Ma, and Hao Wan from 01.AI company for their generous provision of resources. We are also deeply grateful to Jianxiong Li and Peng Li at Tsinghua University for their insightful discussions.
Furthermore, we appreciate the developers behind the following projects for their significant contributions to our research: [Mistral](https://mistral.ai/), [Chain-of-Thought Hub](https://github.com/FranxYao/chain-of-thought-hub), [Llama 2](https://ai.meta.com/llama/), [Self-Instruct](https://arxiv.org/abs/2212.10560), [FastChat (Vicuna)](https://github.com/lm-sys/FastChat), [Alpaca](https://github.com/tatsu-lab/stanford_alpaca.git), and [StarCoder](https://github.com/bigcode-project/starcoder). Their work has been instrumental in driving our research forward.
| 27,964 | [
[
-0.041259765625,
-0.06878662109375,
0.01119232177734375,
0.025726318359375,
-0.01461029052734375,
-0.016326904296875,
-0.005199432373046875,
-0.038604736328125,
0.01436614990234375,
0.02703857421875,
-0.043182373046875,
-0.03692626953125,
-0.01442718505859375,
... |
vasista22/whisper-kannada-medium | 2023-04-24T20:23:05.000Z | [
"transformers",
"pytorch",
"jax",
"whisper",
"automatic-speech-recognition",
"whisper-event",
"kn",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"has_space",
"region:us"
] | automatic-speech-recognition | vasista22 | null | null | vasista22/whisper-kannada-medium | 0 | 495 | transformers | 2022-12-19T17:14:53 | ---
language:
- kn
license: apache-2.0
tags:
- whisper-event
metrics:
- wer
model-index:
- name: Whisper Kannada Medium - Vasista Sai Lodagala
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: google/fleurs
type: google/fleurs
config: kn_in
split: test
metrics:
- type: wer
value: 7.65
name: WER
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Kannada Medium
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Kannada data available from multiple publicly available ASR corpuses.
It has been fine-tuned as a part of the Whisper fine-tuning sprint.
**NOTE:** The code used to train this model is available for re-use in the [whisper-finetune](https://github.com/vasistalodagala/whisper-finetune) repository.
## Usage
In order to evaluate this model on an entire dataset, the evaluation codes available in the [whisper-finetune](https://github.com/vasistalodagala/whisper-finetune) repository can be used.
The same repository also provides the scripts for faster inference using whisper-jax.
In order to infer a single audio file using this model, the following code snippet can be used:
```python
>>> import torch
>>> from transformers import pipeline
>>> # path to the audio file to be transcribed
>>> audio = "/path/to/audio.format"
>>> device = "cuda:0" if torch.cuda.is_available() else "cpu"
>>> transcribe = pipeline(task="automatic-speech-recognition", model="vasista22/whisper-kannada-medium", chunk_length_s=30, device=device)
>>> transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="kn", task="transcribe")
>>> print('Transcription: ', transcribe(audio)["text"])
```
For faster inference of whisper models, the [whisper-jax](https://github.com/sanchit-gandhi/whisper-jax) library can be used. Please follow the necessary installation steps as mentioned [here](https://github.com/vasistalodagala/whisper-finetune#faster-evaluation-with-whisper-jax), before using the following code snippet:
```python
>>> import jax.numpy as jnp
>>> from whisper_jax import FlaxWhisperForConditionalGeneration, FlaxWhisperPipline
>>> # path to the audio file to be transcribed
>>> audio = "/path/to/audio.format"
>>> transcribe = FlaxWhisperPipline("vasista22/whisper-kannada-medium", batch_size=16)
>>> transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="kn", task="transcribe")
>>> print('Transcription: ', transcribe(audio)["text"])
```
## Training and evaluation data
Training Data:
- [IISc-MILE Kannada ASR Corpus](https://www.openslr.org/126/)
- [ULCA ASR Corpus](https://github.com/Open-Speech-EkStep/ULCA-asr-dataset-corpus#kannada-labelled-total-duration-is-60891-hours)
- [Shrutilipi ASR Corpus](https://ai4bharat.org/shrutilipi)
- [Google/Fleurs Train+Dev set](https://huggingface.co/datasets/google/fleurs)
Evaluation Data:
- [Google/Fleurs Test Set](https://huggingface.co/datasets/google/fleurs)
- [IISc-MILE Test Set](https://www.openslr.org/126/)
- [OpenSLR](https://www.openslr.org/79/)
## Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 24
- eval_batch_size: 48
- seed: 22
- optimizer: adamw_bnb_8bit
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- training_steps: 13752 (terminated upon convergence. Initially set to 51570 steps)
- mixed_precision_training: True
## Acknowledgement
This work was done at [Speech Lab, IIT Madras](https://asr.iitm.ac.in/).
The compute resources for this work were funded by "Bhashini: National Language translation Mission" project of the Ministry of Electronics and Information Technology (MeitY), Government of India.
| 4,022 | [
[
-0.01284027099609375,
-0.049591064453125,
0.008087158203125,
0.040863037109375,
-0.024444580078125,
-0.0099639892578125,
-0.034423828125,
-0.0300750732421875,
0.0033512115478515625,
0.0214691162109375,
-0.037750244140625,
-0.0330810546875,
-0.04656982421875,
... |
KETI-AIR/ke-t5-small | 2023-09-18T01:23:33.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"t5",
"text2text-generation",
"en",
"ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | KETI-AIR | null | null | KETI-AIR/ke-t5-small | 1 | 494 | transformers | 2022-03-02T23:29:04 | ---
license: apache-2.0
language: [en, ko]
tags:
- t5
eos_token: "</s>"
widget:
- text: 아버지가 방에 들어가신다.</s>
---
# ke-t5 base
Pretrained T5 Model on Korean and English. See [Github](https://github.com/AIRC-KETI/ke-t5) and [Paper](https://aclanthology.org/2021.findings-emnlp.33/) [Korean paper](https://koreascience.kr/article/CFKO202130060717834.pdf) for more details.
## How to use
```python
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("KETI-AIR/ke-t5-small")
tokenizer = AutoTokenizer.from_pretrained("KETI-AIR/ke-t5-small")
```
## BibTeX entry and citation info
```bibtex
@inproceedings{kim-etal-2021-model-cross,
title = "A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems",
author = "Kim, San and
Jang, Jin Yea and
Jung, Minyoung and
Shin, Saim",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.33",
doi = "10.18653/v1/2021.findings-emnlp.33",
pages = "352--365",
abstract = "Research on open-domain dialogue systems that allow free topics is challenging in the field of natural language processing (NLP). The performance of the dialogue system has been improved recently by the method utilizing dialogue-related knowledge; however, non-English dialogue systems suffer from reproducing the performance of English dialogue systems because securing knowledge in the same language with the dialogue system is relatively difficult. Through experiments with a Korean dialogue system, this paper proves that the performance of a non-English dialogue system can be improved by utilizing English knowledge, highlighting the system uses cross-lingual knowledge. For the experiments, we 1) constructed a Korean version of the Wizard of Wikipedia dataset, 2) built Korean-English T5 (KE-T5), a language model pre-trained with Korean and English corpus, and 3) developed a knowledge-grounded Korean dialogue model based on KE-T5. We observed the performance improvement in the open-domain Korean dialogue model even only English knowledge was given. The experimental results showed that the knowledge inherent in cross-lingual language models can be helpful for generating responses in open dialogue systems.",
}
``` | 2,488 | [
[
-0.0303802490234375,
-0.04498291015625,
0.0175323486328125,
0.012451171875,
-0.0111236572265625,
0.00855255126953125,
-0.029022216796875,
-0.03118896484375,
0.01003265380859375,
0.0181427001953125,
-0.033233642578125,
-0.044769287109375,
-0.035247802734375,
... |
GlobalSymbols/Mulberry-AAC-Profession | 2023-07-19T16:03:12.000Z | [
"diffusers",
"tensorboard",
"text-to-image",
"license:creativeml-openrail-m",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | GlobalSymbols | null | null | GlobalSymbols/Mulberry-AAC-Profession | 1 | 494 | diffusers | 2023-07-11T12:52:33 | ---
license: creativeml-openrail-m
tags:
- text-to-image
widget:
- text: mulberry
---
### Mulberry AAC Profession Dreambooth model trained by Chaohai with [Hugging Face Dreambooth Training Space](https://huggingface.co/spaces/multimodalart/dreambooth-training) with the v1-5 base model
You 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). Don't forget to use the concept prompts!
mulberry (use that on your prompt) e.g. Astronaut in mulberry style | 584 | [
[
-0.0278167724609375,
-0.040130615234375,
0.024810791015625,
0.028594970703125,
-0.0140380859375,
0.029693603515625,
0.040130615234375,
-0.03643798828125,
0.0579833984375,
0.021148681640625,
-0.040985107421875,
-0.0171051025390625,
-0.0297088623046875,
-0.024... |
SaiedAlshahrani/arywiki_20230101_roberta_mlm_nobots | 2023-10-29T01:16:53.000Z | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"fill-mask",
"generated_from_trainer",
"ar",
"dataset:SaiedAlshahrani/Moroccan_Arabic_Wikipedia_20230101_nobots",
"dataset:SaiedAlshahrani/MASD",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | SaiedAlshahrani | null | null | SaiedAlshahrani/arywiki_20230101_roberta_mlm_nobots | 0 | 494 | transformers | 2023-08-26T19:10:36 | ---
tags:
- generated_from_trainer
model-index:
- name: aryRoBERTa
results: []
metrics:
- perplexity
license: mit
datasets:
- SaiedAlshahrani/Moroccan_Arabic_Wikipedia_20230101_nobots
- SaiedAlshahrani/MASD
language:
- ar
library_name: transformers
pipeline_tag: fill-mask
widget:
- text: الهدف من الحياة هو <mask>
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Moroccan Arabic Wikipedia (aryRoBERTa<sub>BASE</sub>)
This aryRoBERTa<sub>BASE</sub> model has been trained *from scratch* on the Moroccan Arabic Wikipedia articles (**after removing the bot-generated articles**), downloaded on the 1st of January 2023, processed using
`Gensim` Python library, preprocessed using `tr` Linux/Unix utility and `CAMeLTools` Python toolkit for Arabic NLP, and hosted here at [SaiedAlshahrani/Moroccan\_Arabic\_Wikipedia\_20230101\_nobots](https://huggingface.co/datasets/SaiedAlshahrani/Moroccan_Arabic_Wikipedia_20230101_nobots).
It achieves the following results on the evaluation set:
- Pseudo-Perplexity: 5,686.44
## Model description
We trained this Moroccan Arabic Wikipedia Masked Language Model (aryRoBERTa<sub>BASE</sub>) to evaluate its performance using the Fill-Mask evaluation task and the Masked Arab States Dataset ([MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)) dataset and measure the *impact* of **bot-based generation** on the Moroccan Arabic Wikipedia edition.
For more details about the experiment, please **read** and **cite** our paper:
```bash
@inproceedings{alshahrani-etal-2023-implications,
title = "{{Performance Implications of Using Unrepresentative Corpora in Arabic Natural Language Processing}}",
author = "Alshahrani, Saied and Alshahrani, Norah and Dey, Soumyabrata and Matthews, Jeanna",
booktitle = "Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://webspace.clarkson.edu/~alshahsf/unrepresentative_corpora.pdf",
doi = "#################",
pages = "###--###",
abstract = "Wikipedia articles are a widely used source of training data for Natural Language Processing (NLP) research, particularly as corpora for low-resource languages like Arabic. However, it is essential to understand the extent to which these corpora reflect the representative contributions of native speakers, especially when many entries in a given language are directly translated from other languages or automatically generated through automated mechanisms. In this paper, we study the performance implications of using inorganic corpora that are not representative of native speakers and are generated through automated techniques such as bot generation or automated template-based translation. The case of the Arabic Wikipedia editions gives a unique case study of this since the Moroccan Arabic Wikipedia edition (ARY) is small but representative, the Egyptian Arabic Wikipedia edition (ARZ) is large but unrepresentative, and the Modern Standard Arabic Wikipedia edition (AR) is both large and more representative. We intrinsically evaluate the performance of two main NLP upstream tasks, namely word representation and language modeling, using word analogy evaluations and fill-mask evaluations using our two newly created datasets: Arab States Analogy Dataset (ASAD) and Masked Arab States Dataset (MASD). We demonstrate that for good NLP performance, we need both large and organic corpora; neither alone is sufficient. We show that producing large corpora through automated means can be a counter-productive, producing models that both perform worse and lack cultural richness and meaningful representation of the Arabic language and its native speakers.",
}
```
## Intended uses & limitations
We do **not** recommend using this model because it was trained *only* on the Moroccan Arabic Wikipedia articles (**after removing the bot-generated articles**), <u>unless</u> you fine-tune the model on a large, organic, and representative Moroccan Arabic dataset.
## Training and evaluation data
We have trained this model on the Moroccan Arabic Wikipedia articles without bot-generated articles ([SaiedAlshahrani/Moroccan\_Arabic\_Wikipedia\_20230101\_nobots](https://huggingface.co/datasets/SaiedAlshahrani/Moroccan_Arabic_Wikipedia_20230101_nobots)) without using any validation or evaluation data (only training data) due to a lack of computational power.
## Training procedure
We have trained this model using the Paperspace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 128
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Epoch | Step | Training Loss |
|:-----:|:-----:|:-------------:|
| 1 | 35 | 9.561500 |
| 2 | 70 | 7.946000 |
| 3 | 105 | 7.420400 |
| 4 | 140 | 7.197800 |
| 5 | 175 | 7.174400 |
| Train Runtime | Train Samples Per Second | Train Steps Per Second | Total Flos | Train Loss | Epoch |
|:--------------:|:------------------------:|:----------------------:|:-------------------------:|:----------:|:--------:|
| 192.684800 | 121.260000 | 0.960000 | 774708261150720.000000 | 7.812142 | 5.000000 |
### Evaluation results
This aryRoBERTa<sub>BASE</sub> model has been evaluated on the Masked Arab States Dataset ([SaiedAlshahrani/MASD](https://huggingface.co/datasets/SaiedAlshahrani/MASD)).
| K=10 | K=50 | K=100 |
|:----:|:-----:|:----:|
| 0.00%| 0.00% | 0.62% |
### Framework versions
- Datasets 2.9.0
- Tokenizers 0.12.1
- Transformers 4.24.0
- Pytorch 1.12.1+cu116 | 6,103 | [
[
-0.0513916015625,
-0.04547119140625,
0.0026760101318359375,
-0.0037403106689453125,
-0.02081298828125,
0.00485992431640625,
-0.0259552001953125,
-0.054840087890625,
0.0108642578125,
0.0208587646484375,
-0.02935791015625,
-0.047332763671875,
-0.051361083984375,
... |
TheBloke/Athena-v4-AWQ | 2023-10-08T22:30:37.000Z | [
"transformers",
"safetensors",
"llama",
"text-generation",
"license:cc-by-nc-4.0",
"text-generation-inference",
"region:us"
] | text-generation | TheBloke | null | null | TheBloke/Athena-v4-AWQ | 2 | 494 | transformers | 2023-10-08T22:10:16 | ---
base_model: IkariDev/Athena-v4
inference: false
license: cc-by-nc-4.0
model_creator: IkariDev + Undi95
model_name: Athena v4
model_type: llama
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
### Instruction:
{prompt}
### 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 -->
# Athena v4 - AWQ
- Model creator: [IkariDev + Undi95](https://huggingface.co/IkariDev)
- Original model: [Athena v4](https://huggingface.co/IkariDev/Athena-v4)
<!-- description start -->
## Description
This repo contains AWQ model files for [IkariDev + Undi95's Athena v4](https://huggingface.co/IkariDev/Athena-v4).
### About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.
It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.
As of September 25th 2023, preliminary Llama-only AWQ support has also been added to [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference).
Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
<!-- description end -->
<!-- repositories-available start -->
## Repositories available
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Athena-v4-AWQ)
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Athena-v4-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Athena-v4-GGUF)
* [IkariDev + Undi95's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/IkariDev/Athena-v4)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- licensing start -->
## Licensing
The creator of the source model has listed its license as `cc-by-nc-4.0`, 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: [IkariDev + Undi95's Athena v4](https://huggingface.co/IkariDev/Athena-v4).
<!-- licensing end -->
<!-- README_AWQ.md-provided-files start -->
## Provided files, and AWQ parameters
For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
Models are released as sharded safetensors files.
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
| ------ | ---- | -- | ----------- | ------- | ---- |
| [main](https://huggingface.co/TheBloke/Athena-v4-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 7.25 GB
<!-- README_AWQ.md-provided-files end -->
<!-- README_AWQ.md-use-from-vllm start -->
## Serving this model from vLLM
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
Note: at the time of writing, vLLM has not yet done a new release with AWQ support.
If you try the vLLM examples below and get an error about `quantization` being unrecognised, or other AWQ-related issues, please install vLLM from Github source.
- When using vLLM as a server, pass the `--quantization awq` parameter, for example:
```shell
python3 python -m vllm.entrypoints.api_server --model TheBloke/Athena-v4-AWQ --quantization awq --dtype half
```
When using vLLM from Python code, pass the `quantization=awq` parameter, for example:
```python
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="TheBloke/Athena-v4-AWQ", quantization="awq", dtype="half")
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```
<!-- README_AWQ.md-use-from-vllm start -->
<!-- README_AWQ.md-use-from-tgi start -->
## Serving this model from Text Generation Inference (TGI)
Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
Example Docker parameters:
```shell
--model-id TheBloke/Athena-v4-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
```
Example Python code for interfacing with TGI (requires huggingface-hub 0.17.0 or later):
```shell
pip3 install huggingface-hub
```
```python
from huggingface_hub import InferenceClient
endpoint_url = "https://your-endpoint-url-here"
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:
'''
client = InferenceClient(endpoint_url)
response = client.text_generation(prompt,
max_new_tokens=128,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1)
print(f"Model output: {response}")
```
<!-- README_AWQ.md-use-from-tgi end -->
<!-- README_AWQ.md-use-from-python start -->
## How to use this AWQ model from Python code
### Install the necessary packages
Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later
```shell
pip3 install autoawq
```
If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
```shell
pip3 uninstall -y autoawq
git clone https://github.com/casper-hansen/AutoAWQ
cd AutoAWQ
pip3 install .
```
### You can then try the following example code
```python
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer
model_name_or_path = "TheBloke/Athena-v4-AWQ"
# Load model
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
trust_remote_code=False, safetensors=True)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
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:")
tokens = tokenizer(
prompt_template,
return_tensors='pt'
).input_ids.cuda()
# Generate output
generation_output = model.generate(
tokens,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
max_new_tokens=512
)
print("Output: ", tokenizer.decode(generation_output[0]))
"""
# Inference should be possible with transformers pipeline as well in future
# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
from transformers import 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_AWQ.md-use-from-python end -->
<!-- README_AWQ.md-compatibility start -->
## Compatibility
The files provided are tested to work with:
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
- [vLLM](https://github.com/vllm-project/vllm)
- [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
TGI merged AWQ support on September 25th, 2023: [TGI PR #1054](https://github.com/huggingface/text-generation-inference/pull/1054). Use the `:latest` Docker container until the next TGI release is made.
<!-- README_AWQ.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**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
# Original model card: IkariDev + Undi95's Athena v4
Experimental Athena v4 model. Use Alpaca format. Suitable for RP, ERP and general stuff.
I should state here that this is a HIGHLY experimental model!
<!-- description start -->
## Description
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
This repo contains fp16 files of Athena-V4.
<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v3-GGUF)-->
<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v3-GPTQ)-->
<!-- [exl2 - by AzureBlack](https://huggingface.co/AzureBlack/Athena-v2-6.0bit-exl2) -->
<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v3-AWQ)-->
[fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)
[GGUF - by IkariDev](https://huggingface.co/IkariDev/Athena-v4-GGUF)
<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v3-GGUF)-->
## Ratings:
Note: I have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here!
If you want your rating to be here, send me a message over on DC and ill put up a screenshot of it here. DC name is "ikaridev".
<!-- description end -->
<!-- description start -->
## Models+loras used and recipe
- Athena-v3
- Xwin-LM/Xwin-LM-13B-V0.1
- Undi95/PsyMedRP-v1-13B
- cgato/Thespis-13b-v0.2
- jondurbin/airoboros-l2-13b-3.0
```
Athena-v4-tmp1 = [ Athena-v3(0.85)+Xwin-LM/Xwin-LM-13B-V0.1(0.15) ]
Athena-v4-tmp2 = [ Undi95/PsyMedRP-v1-13B(0.55)+cgato/Thespis-13b-v0.2(0.45) ]
Athena-v4-tmp3 = Athena-v4-tmp1(0.55) + Athena-v4-tmp2(0.35)
Athena-v4 = Athena-v4-tmp3 + jondurbin/airoboros-l2-13b-3.0(0.1)
```
<!-- description end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
Thanks to [Undi95](https://huggingface.co/Undi95) for providing the machine for Athena v2 and Athena v3, and giving me infos about how things work. Going forward i will use a merging server provided by a friend.
| 15,733 | [
[
-0.040802001953125,
-0.0543212890625,
0.03839111328125,
0.00673675537109375,
-0.0306854248046875,
-0.0152130126953125,
0.01534271240234375,
-0.050323486328125,
0.001422882080078125,
0.0338134765625,
-0.05413818359375,
-0.0408935546875,
-0.026153564453125,
-0... |
Norod78/hebrew-bad_wiki-gpt_neo-tiny | 2023-04-23T16:38:52.000Z | [
"transformers",
"pytorch",
"coreml",
"safetensors",
"gpt_neo",
"text-generation",
"he",
"arxiv:1910.09700",
"arxiv:2105.09680",
"license:mit",
"endpoints_compatible",
"region:us"
] | text-generation | Norod78 | null | null | Norod78/hebrew-bad_wiki-gpt_neo-tiny | 0 | 493 | transformers | 2022-03-02T23:29:04 | ---
language: he
thumbnail: https://avatars1.githubusercontent.com/u/3617152?norod.jpg
widget:
- text: "מתמטיקה:"
- text: "עליית המכונות"
- text: "ויקיפדיה העברית"
- text: "האירוויזיון הוא"
- text: "דוד בן-גוריון היה"
license: mit
---
# hebrew-bad_wiki-gpt_neo-tiny
## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Risks, Limitations and Biases](#risks-limitations-and-biases)
- [Training](#training)
- [Evaluation](#evaluation)
- [Environmental Impact](#environmental-impact)
- [How to Get Started With the Model](#how-to-get-started-with-the-model)
## Model Details
**Model Description:**
The model developer notes that the model is
> Hebrew nonsense generation model which produces really bad wiki-abstract text.
- **Developed by:** [Doron Adler](https://github.com/Norod)
- **Model Type:** Text Generation
- **Language(s):** Hebrew
- **License:** MIT
- **Resources for more information:**
- [GitHub Repo](https://github.com/Norod/hebrew-gpt_neo)
- [HuggingFace Space](https://huggingface.co/spaces/Norod78/Hebrew-GPT-Neo-Small)
## Uses
#### Direct Use
This model can be used for text generation.
#### Misuse and Out-of-scope Use
## Risks, Limitations and Biases
**CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes.**
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)).
## Training
#### Training Data
[Hebrew Wikipedia Dump](https://dumps.wikimedia.org/hewiki/latest/) (hewiki abstract) from May 2020
#### Training Procedure
This model was fined tuned upon [hebrew-gpt_neo-tiny](https://huggingface.co/Norod78/hebrew-gpt_neo-tiny) which was previously trained using [EleutherAI's gpt-neo](https://github.com/EleutherAI/gpt-neo).
Fine-tuning on the wiki-absract text was done using [@minimaxir](https://twitter.com/minimaxir)'s [aitextgen](https://github.com/minimaxir/aitextgen).
## Evaluation
#### Configs
Model configs for the hebrew-gpt_neo-tiny is available on the [hebrew-gpt_neo model github](https://github.com/Norod/hebrew-gpt_neo/tree/main/hebrew-gpt_neo-tiny/configs)
* **Activation Function:** gelu
* **Number_Head:** 12
* **Number_Vocab:** 50257
* **Train batch size:** 250
* **Eval batch size:** 64
* **Predict batch size:** 1
## 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). We present the hardware type based on the [associated paper](https://arxiv.org/pdf/2105.09680.pdf).
- **Hardware Type:** [More information needed]
- **Hours used:** Unknown
- **Cloud Provider:** GCP tpu-v8s
- **Compute Region:** europe-west4
- **Carbon Emitted:** [More information needed]
## How to Get Started With the Model
A Google Colab Notebook is also available [here](https://colab.research.google.com/github/Norod/hebrew-gpt_neo/blob/main/hebrew-gpt_neo-tiny/Norod78_hebrew_gpt_neo_tiny_Colab.ipynb)
```
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Norod78/hebrew-bad_wiki-gpt_neo-tiny")
model = AutoModelForCausalLM.from_pretrained("Norod78/hebrew-bad_wiki-gpt_neo-tiny")
```
| 3,493 | [
[
-0.022674560546875,
-0.052398681640625,
0.0194549560546875,
-0.006511688232421875,
-0.032470703125,
-0.0245513916015625,
-0.01409912109375,
-0.040679931640625,
0.0083160400390625,
0.01873779296875,
-0.047027587890625,
-0.041656494140625,
-0.041839599609375,
... |
aubmindlab/bert-large-arabertv02-twitter | 2023-04-26T15:36:18.000Z | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bert",
"fill-mask",
"ar",
"dataset:wikipedia",
"dataset:Osian",
"dataset:1.5B-Arabic-Corpus",
"dataset:oscar-arabic-unshuffled",
"dataset:Assafir(private)",
"dataset:Twitter(private)",
"arxiv:2003.00104",
"autotrain_compatible",
... | fill-mask | aubmindlab | null | null | aubmindlab/bert-large-arabertv02-twitter | 2 | 493 | transformers | 2022-03-02T23:29:05 | ---
language: ar
datasets:
- wikipedia
- Osian
- 1.5B-Arabic-Corpus
- oscar-arabic-unshuffled
- Assafir(private)
- Twitter(private)
widget:
- text: " عاصمة لبنان هي [MASK] ."
---
<img src="https://raw.githubusercontent.com/aub-mind/arabert/master/arabert_logo.png" width="100" align="center"/>
# AraBERTv0.2-Twitter
AraBERTv0.2-Twitter-base/large are two new models for Arabic dialects and tweets, trained by continuing the pre-training using the MLM task on ~60M Arabic tweets (filtered from a collection on 100M).
The two new models have had emojies added to their vocabulary in addition to common words that weren't at first present. The pre-training was done with a max sentence length of 64 only for 1 epoch.
**AraBERT** is an Arabic pretrained language model based on [Google's BERT architechture](https://github.com/google-research/bert). AraBERT uses the same BERT-Base config. More details are available in the [AraBERT Paper](https://arxiv.org/abs/2003.00104) and in the [AraBERT Meetup](https://github.com/WissamAntoun/pydata_khobar_meetup)
## Other Models
Model | HuggingFace Model Name | Size (MB/Params)| Pre-Segmentation | DataSet (Sentences/Size/nWords) |
---|:---:|:---:|:---:|:---:
AraBERTv0.2-base | [bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) | 543MB / 136M | No | 200M / 77GB / 8.6B |
AraBERTv0.2-large| [bert-large-arabertv02](https://huggingface.co/aubmindlab/bert-large-arabertv02) | 1.38G / 371M | No | 200M / 77GB / 8.6B |
AraBERTv2-base| [bert-base-arabertv2](https://huggingface.co/aubmindlab/bert-base-arabertv2) | 543MB / 136M | Yes | 200M / 77GB / 8.6B |
AraBERTv2-large| [bert-large-arabertv2](https://huggingface.co/aubmindlab/bert-large-arabertv2) | 1.38G / 371M | Yes | 200M / 77GB / 8.6B |
AraBERTv0.1-base| [bert-base-arabertv01](https://huggingface.co/aubmindlab/bert-base-arabertv01) | 543MB / 136M | No | 77M / 23GB / 2.7B |
AraBERTv1-base| [bert-base-arabert](https://huggingface.co/aubmindlab/bert-base-arabert) | 543MB / 136M | Yes | 77M / 23GB / 2.7B |
AraBERTv0.2-Twitter-base| [bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) | 543MB / 136M | No | Same as v02 + 60M Multi-Dialect Tweets|
AraBERTv0.2-Twitter-large| [bert-large-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-large-arabertv02-twitter) | 1.38G / 371M | No | Same as v02 + 60M Multi-Dialect Tweets|
# Preprocessing
**The model is trained on a sequence length of 64, using max length beyond 64 might result in degraded performance**
It is recommended to apply our preprocessing function before training/testing on any dataset.
The preprocessor will keep and space out emojis when used with a "twitter" model.
```python
from arabert.preprocess import ArabertPreprocessor
from transformers import AutoTokenizer, AutoModelForMaskedLM
model_name="aubmindlab/bert-base-arabertv02-twitter"
arabert_prep = ArabertPreprocessor(model_name=model_name)
text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
arabert_prep.preprocess(text)
tokenizer = AutoTokenizer.from_pretrained("aubmindlab/bert-base-arabertv02-twitter")
model = AutoModelForMaskedLM.from_pretrained("aubmindlab/bert-base-arabertv02-twitter")
```
# If you used this model please cite us as :
Google Scholar has our Bibtex wrong (missing name), use this instead
```
@inproceedings{antoun2020arabert,
title={AraBERT: Transformer-based Model for Arabic Language Understanding},
author={Antoun, Wissam and Baly, Fady and Hajj, Hazem},
booktitle={LREC 2020 Workshop Language Resources and Evaluation Conference 11--16 May 2020},
pages={9}
}
```
# Acknowledgments
Thanks to TensorFlow Research Cloud (TFRC) for the free access to Cloud TPUs, couldn't have done it without this program, and to the [AUB MIND Lab](https://sites.aub.edu.lb/mindlab/) Members for the continuous support. Also thanks to [Yakshof](https://www.yakshof.com/#/) and Assafir for data and storage access. Another thanks for Habib Rahal (https://www.behance.net/rahalhabib), for putting a face to AraBERT.
# Contacts
**Wissam Antoun**: [Linkedin](https://www.linkedin.com/in/wissam-antoun-622142b4/) | [Twitter](https://twitter.com/wissam_antoun) | [Github](https://github.com/WissamAntoun) | <wfa07@mail.aub.edu> | <wissam.antoun@gmail.com>
**Fady Baly**: [Linkedin](https://www.linkedin.com/in/fadybaly/) | [Twitter](https://twitter.com/fadybaly) | [Github](https://github.com/fadybaly) | <fgb06@mail.aub.edu> | <baly.fady@gmail.com>
| 4,517 | [
[
-0.04705810546875,
-0.051025390625,
0.01560211181640625,
0.007503509521484375,
-0.0216827392578125,
0.0150909423828125,
-0.03106689453125,
-0.0394287109375,
0.032562255859375,
0.0144500732421875,
-0.0452880859375,
-0.045989990234375,
-0.061859130859375,
0.00... |
bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16 | 2021-09-24T07:46:55.000Z | [
"transformers",
"pytorch",
"jax",
"bert",
"bluebert",
"en",
"dataset:PubMed",
"license:cc0-1.0",
"endpoints_compatible",
"region:us"
] | null | bionlp | null | null | bionlp/bluebert_pubmed_uncased_L-24_H-1024_A-16 | 0 | 493 | transformers | 2022-03-02T23:29:05 | ---
language:
- en
tags:
- bert
- bluebert
license: cc0-1.0
datasets:
- PubMed
---
# BlueBert-Base, Uncased, PubMed
## Model description
A BERT model pre-trained on PubMed abstracts.
## Intended uses & limitations
#### How to use
Please see https://github.com/ncbi-nlp/bluebert
## Training data
We provide [preprocessed PubMed texts](https://ftp.ncbi.nlm.nih.gov/pub/lu/Suppl/NCBI-BERT/pubmed_uncased_sentence_nltk.txt.tar.gz) that were used to pre-train the BlueBERT models.
The corpus contains ~4000M words extracted from the [PubMed ASCII code version](https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/BioC-PubMed/).
Pre-trained model: https://huggingface.co/bert-large-uncased
## Training procedure
* lowercasing the text
* removing speical chars `\x00`-`\x7F`
* tokenizing the text using the [NLTK Treebank tokenizer](https://www.nltk.org/_modules/nltk/tokenize/treebank.html)
Below is a code snippet for more details.
```python
value = value.lower()
value = re.sub(r'[\r\n]+', ' ', value)
value = re.sub(r'[^\x00-\x7F]+', ' ', value)
tokenized = TreebankWordTokenizer().tokenize(value)
sentence = ' '.join(tokenized)
sentence = re.sub(r"\s's\b", "'s", sentence)
```
### BibTeX entry and citation info
```bibtex
@InProceedings{peng2019transfer,
author = {Yifan Peng and Shankai Yan and Zhiyong Lu},
title = {Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets},
booktitle = {Proceedings of the 2019 Workshop on Biomedical Natural Language Processing (BioNLP 2019)},
year = {2019},
pages = {58--65},
}
```
### Acknowledgments
This work was supported by the Intramural Research Programs of the National Institutes of Health, National Library of
Medicine and Clinical Center. This work was supported by the National Library of Medicine of the National Institutes of Health under award number 4R00LM013001-01.
We are also grateful to the authors of BERT and ELMo to make the data and codes publicly available.
We would like to thank Dr Sun Kim for processing the PubMed texts.
### Disclaimer
This tool shows the results of research conducted in the Computational Biology Branch, NCBI. The information produced
on this website is not intended for direct diagnostic use or medical decision-making without review and oversight
by a clinical professional. Individuals should not change their health behavior solely on the basis of information
produced on this website. NIH does not independently verify the validity or utility of the information produced
by this tool. If you have questions about the information produced on this website, please see a health care
professional. More information about NCBI's disclaimer policy is available.
| 2,762 | [
[
0.004436492919921875,
-0.04278564453125,
0.034088134765625,
0.0298309326171875,
-0.03179931640625,
0.0015840530395507812,
-0.030670166015625,
-0.055206298828125,
0.0231475830078125,
0.0203399658203125,
-0.0245361328125,
-0.0572509765625,
-0.042633056640625,
... |
marefa-nlp/marefa-mt-en-ar | 2021-09-22T08:59:51.000Z | [
"transformers",
"pytorch",
"marian",
"text2text-generation",
"translation",
"Arabic Abjad Characters",
"Arabic",
"en",
"ar",
"dataset:marefa-mt",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | marefa-nlp | null | null | marefa-nlp/marefa-mt-en-ar | 3 | 492 | transformers | 2022-03-02T23:29:05 | ---
language:
- en
- ar
tags:
- translation
- Arabic Abjad Characters
- Arabic
license: apache-2.0
datasets:
- marefa-mt
---
# Marefa-Mt-En-Ar
# نموذج المعرفة للترجمة الآلية من الإنجليزية للعربية
## Model description
This is a model for translating English to Arabic. The special about this model that is take into considration the
using of additional Arabic characters like `پ` or `گ`.
## عن النموذج
هذا النموذج للترجمة الآلية من اللغة الإنجليزية إلى اللغة العربية, هو أول نماذج الترجمة الآلية التي تصدر تحت رعاية
[موسوعة المعرفة](https://www.marefa.org)
يتميز هذا النموذج عن غيره من النماذج بدعمه لحروف الأبجدية العربية الإضافية لتمييز الصوتيات الخاصة في اللغة الإنجليزية مثل `پ` , `گ`.
يمكنك زيارة
[هذه الصفحة](https://www.marefa.org/%D8%A7%D9%84%D9%85%D8%B9%D8%B1%D9%81%D8%A9:%D8%AF%D9%84%D9%8A%D9%84_%D8%A7%D9%84%D8%A3%D8%B3%D9%84%D9%88%D8%A8#.D8.AD.D8.B1.D9.88.D9.81_.D8.A5.D8.B6.D8.A7.D9.81.D9.8A.D8.A9_.D9.84.D9.84.D9.86.D8.B7.D9.82_.D8.A7.D9.84.D8.B3.D9.84.D9.8A.D9.85)
لمعرفة أكثر عن أسلوب إستخدام هذه الحروف الأبجدية العربية
### How to use كيفية الإستخدام
Install transformers and sentencepiece (python >= 3.6)
`$ pip3 install transformers==4.3.0 sentencepiece==0.1.95 nltk==3.5 protobuf==3.15.3 torch==1.7.1`
> If you are using `Google Colab`, please restart your runtime after installing the packages.
-----------
```python
from transformers import MarianTokenizer, MarianMTModel
mname = "marefa-nlp/marefa-mt-en-ar"
tokenizer = MarianTokenizer.from_pretrained(mname)
model = MarianMTModel.from_pretrained(mname)
# English Sample Text
input = "President Putin went to the presidential palace in the capital, Kiev"
translated_tokens = model.generate(**tokenizer.prepare_seq2seq_batch([input], return_tensors="pt"))
translated_text = [tokenizer.decode(t, skip_special_tokens=True) for t in translated_tokens]
# translated Arabic Text
print(translated_text)
# ذهب الرئيس پوتن إلى القصر الرئاسي في العاصمة كييڤ
``` | 1,987 | [
[
-0.02069091796875,
-0.0576171875,
0.0294342041015625,
0.034637451171875,
-0.047119140625,
-0.0069122314453125,
0.00421905517578125,
-0.01375579833984375,
0.0304718017578125,
0.034698486328125,
-0.0369873046875,
-0.05218505859375,
-0.07171630859375,
0.0277709... |
google/vit-large-patch32-224-in21k | 2022-01-28T10:21:30.000Z | [
"transformers",
"pytorch",
"tf",
"jax",
"vit",
"feature-extraction",
"vision",
"dataset:imagenet-21k",
"arxiv:2010.11929",
"arxiv:2006.03677",
"license:apache-2.0",
"has_space",
"region:us"
] | feature-extraction | google | null | null | google/vit-large-patch32-224-in21k | 0 | 491 | transformers | 2022-03-02T23:29:05 | ---
license: apache-2.0
tags:
- vision
datasets:
- imagenet-21k
inference: false
---
# Vision Transformer (large-sized model)
Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224. It was introduced in the paper [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/abs/2010.11929) by Dosovitskiy et al. and first released in [this repository](https://github.com/google-research/vision_transformer). However, the weights were converted from the [timm repository](https://github.com/rwightman/pytorch-image-models) by Ross Wightman, who already converted the weights from JAX to PyTorch. Credits go to him.
Disclaimer: The team releasing ViT did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels.
Images are presented to the model as a sequence of fixed-size patches (resolution 32x32), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.
Note that this model does not provide any fine-tuned heads, as these were zero'd by Google researchers. However, the model does include the pre-trained pooler, which can be used for downstream tasks (such as image classification).
By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.
## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=google/vit) to look for
fine-tuned versions on a task that interests you.
### How to use
Here is how to use this model:
```python
from transformers import ViTFeatureExtractor, ViTModel
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 = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
model = ViTModel.from_pretrained('google/vit-base-patch16-224-in21k')
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_state = outputs.last_hidden_state
```
Currently, both the feature extractor and model support PyTorch. Tensorflow and JAX/FLAX are coming soon, and the API of ViTFeatureExtractor might change.
## Training data
The ViT model was pretrained on [ImageNet-21k](http://www.image-net.org/), a dataset consisting of 14 million images and 21k classes.
## Training procedure
### Preprocessing
The exact details of preprocessing of images during training/validation can be found [here](https://github.com/google-research/vision_transformer/blob/master/vit_jax/input_pipeline.py).
Images are resized/rescaled to the same resolution (224x224) and normalized across the RGB channels with mean (0.5, 0.5, 0.5) and standard deviation (0.5, 0.5, 0.5).
### Pretraining
The model was trained on TPUv3 hardware (8 cores). All model variants are trained with a batch size of 4096 and learning rate warmup of 10k steps. For ImageNet, the authors found it beneficial to additionally apply gradient clipping at global norm 1. Pre-training resolution is 224.
## Evaluation results
For evaluation results on several image classification benchmarks, we refer to tables 2 and 5 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution (384x384). Of course, increasing the model size will result in better performance.
### BibTeX entry and citation info
```bibtex
@misc{wu2020visual,
title={Visual Transformers: Token-based Image Representation and Processing for Computer Vision},
author={Bichen Wu and Chenfeng Xu and Xiaoliang Dai and Alvin Wan and Peizhao Zhang and Zhicheng Yan and Masayoshi Tomizuka and Joseph Gonzalez and Kurt Keutzer and Peter Vajda},
year={2020},
eprint={2006.03677},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
```bibtex
@inproceedings{deng2009imagenet,
title={Imagenet: A large-scale hierarchical image database},
author={Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Li, Kai and Fei-Fei, Li},
booktitle={2009 IEEE conference on computer vision and pattern recognition},
pages={248--255},
year={2009},
organization={Ieee}
}
``` | 4,996 | [
[
-0.04388427734375,
-0.018463134765625,
0.008331298828125,
-0.006755828857421875,
-0.0325927734375,
-0.01195526123046875,
-0.00495147705078125,
-0.044097900390625,
0.01148223876953125,
0.03424072265625,
-0.02130126953125,
-0.019012451171875,
-0.058837890625,
... |
cross-attention/asymmetric-autoencoder-kl-x-2 | 2023-07-19T17:54:38.000Z | [
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"arxiv:2306.04632",
"diffusers:AsymmetricAutoencoderKL",
"region:us"
] | null | cross-attention | null | null | cross-attention/asymmetric-autoencoder-kl-x-2 | 1 | 491 | diffusers | 2023-07-07T14:33:17 | ---
tags:
- stable-diffusion
- stable-diffusion-diffusers
inference: false
library_name: diffusers
---
# Asymmetric Autoencoder KL
[Designing a Better Asymmetric VQGAN for StableDiffusion](https://arxiv.org/abs/2306.04632)
## Abstract
*StableDiffusion is a revolutionary text-to-image generator that is causing a stir in the world of image generation and editing. Unlike traditional methods that learn a diffusion model in pixel space, StableDiffusion learns a diffusion model in the latent space via a VQGAN, ensuring both efficiency and quality. It not only supports image generation tasks, but also enables image editing for real images, such as image inpainting and local editing. However, we have observed that the vanilla VQGAN used in StableDiffusion leads to significant information loss, causing distortion artifacts even in non-edited image regions. To this end, we propose a new asymmetric VQGAN with two simple designs. Firstly, in addition to the input from the encoder, the decoder contains a conditional branch that incorporates information from task-specific priors, such as the unmasked image region in inpainting. Secondly, the decoder is much heavier than the encoder, allowing for more detailed recovery while only slightly increasing the total inference cost. The training cost of our asymmetric VQGAN is cheap, and we only need to retrain a new asymmetric decoder while keeping the vanilla VQGAN encoder and StableDiffusion unchanged. Our asymmetric VQGAN can be widely used in StableDiffusion-based inpainting and local editing methods. Extensive experiments demonstrate that it can significantly improve the inpainting and editing performance, while maintaining the original text-to-image capability. The code is available at https://github.com/buxiangzhiren/Asymmetric_VQGAN/tree/main*
## Scales
* https://huggingface.co/cross-attention/asymmetric-autoencoder-kl-x-1-5
* https://huggingface.co/cross-attention/asymmetric-autoencoder-kl-x-2
## Diffusers
```python
from io import BytesIO
from PIL import Image
import requests
from diffusers import AsymmetricAutoencoderKL, StableDiffusionInpaintPipeline
def download_image(url: str) -> Image.Image:
response = requests.get(url)
return Image.open(BytesIO(response.content)).convert("RGB")
prompt = "a photo of a person"
img_url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/repaint/celeba_hq_256.png"
mask_url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/repaint/mask_256.png"
image = download_image(img_url).resize((256, 256))
mask_image = download_image(mask_url).resize((256, 256))
pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting")
pipe.vae = AsymmetricAutoencoderKL.from_pretrained("cross-attention/asymmetric-autoencoder-kl-x-2")
pipe.to("cuda")
image = pipe(prompt=prompt, image=image, mask_image=mask_image).images[0]
image.save("image.jpeg")
```
### Visual
_Visualization of VAE perfomance on 512x512 image with runwayml/stable-diffusion-inpainting_
<p align="center">
<br>original image, masked image, mask
<br><b>runwayml/stable-diffusion-inpainting original VAE</b>
<br><b>stabilityai/sd-vae-ft-mse VAE</b>
<br><b>Asymmetric Autoencoder KL x1.5 VAE</b>
<br><b>Asymmetric Autoencoder KL x2 VAE</b>
</p>
<p align="center">
<img src=https://huggingface.co/cross-attention/asymmetric-autoencoder-kl-x-2/resolve/main/compare.jpeg width="50%"/>
</p> | 3,481 | [
[
-0.032958984375,
-0.0245361328125,
0.008575439453125,
0.0270538330078125,
-0.030120849609375,
-0.00021016597747802734,
-0.00815582275390625,
-0.0236968994140625,
0.0275421142578125,
0.0279083251953125,
-0.04217529296875,
-0.02490234375,
-0.053009033203125,
0... |
SiberiaSoft/SiberianFredT5-instructor | 2023-09-18T13:06:55.000Z | [
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"ru",
"dataset:SiberiaSoft/SiberianInstructions-small",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text2text-generation | SiberiaSoft | null | null | SiberiaSoft/SiberianFredT5-instructor | 8 | 491 | transformers | 2023-09-14T04:06:13 | ---
license: mit
language:
- ru
datasets:
- SiberiaSoft/SiberianInstructions-small
---
Модель обучена на миксе инструкционных датасетов, способна отвечать на вопросы, и выполнять несложные инструкции
Из обучающей выборки были исключены арифметические задачи, поэтому считать модель не умеет
Для запуска можно использовать следующий код:
```python:
import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
from transformers import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("SiberiaSoft/SiberianFredT5-instructor")
model = AutoModelForSeq2SeqLM.from_pretrained("SiberiaSoft/SiberianFredT5-instructor")
model.eval()
def generate(prompt):
data = tokenizer('<SC6>' + prompt + '\nОтвет: <extra_id_0>', return_tensors="pt")
data = {k: v.to(model.device) for k, v in data.items()}
output_ids = model.generate(
**data, do_sample=True, temperature=0.2, max_new_tokens=512, top_p=0.95, top_k=5, repetition_penalty=1.03, no_repeat_ngram_size=2
)[0]
out = tokenizer.decode(output_ids.tolist())
out = out.replace("<s>","").replace("</s>","")
return out
while 1:
print(generate(input("Введите промпт и фразу: ")))
print("====================")
```
<b>Можно просто задавать ей разные вопросы:</b><br>
<i>Что такое циновка?<br>
Как сделать десерт из клубники?</i>
<b>Промпт, который выделяет из фразы ключевые слова и сразу ставит их в нормальную форму:</b><br>
<i>Выдели ключевые слова: Мы праздновали день рождения друга и подарили ему подарок</i>
<b>Промпт для выделения главной мысли в предложении (суммаризация предложения):</b><br>
<i>Выдели главные мысли в предложении: Чтение книг важно не только для развития нашего интеллекта, но и для расширения кругозора и понимания различных культур и мировоззрений.</i>
<b>Промпт для определения тематики предложения:</b><br>
<i>Определи тематику: В наше время все больше и больше людей занимаются йогой.</i>
<b>Промпты для придумывания вопросов:</b><br>
<i>Придумай вопросы на тему Политика<br>
Придумай 5 вопросов к собеседнику на тему детство<br>
Придумай другие варианты вопроса: Кем ты работаешь?<br>
Придумай вопросы к этому тексту: "К особым префектурам можно отнести Токио, Киото, Осаку и Хоккайдо. В период Эдо (1603—1867), сёгунат установил 9 городских районов, которыми управляли чиновники из центра (奉行支配地), и 302 районных города, которыми управляли городские чиновники (郡代支配地). С наступлением эпохи Мэйдзи 9 городских центров были превращены в округа фу, а 302 районных города — в префектуры кэн. В 1871 г., после административной реформы, в Японии было установлено 3 городских префектур фу — Токио, Киото и Осака. В 1943 г. городская префектура Токио была переименована в столицу то (хотя закона о столице утверждено не было).",<br></i>
<b>Промпт для предсказания последствий действия:</b><br>
<i>Что произойдет дальше: Я выиграл в лотерею</i>
<b>Промпт для объяснения чего-то простыми словами:</b><br>
<i>Объясни ребенку тему виды отдыха.</i>
<b>Промпт для решения проблем:</b><br>
<i>Реши проблему: Борьба с низкой самооценкой.</i>
<b>Промпт для раскрытия анафоры по предыдущей фразе</b><br>
<i>Раскрой анафору последней фразы в диалоге: "футбол ты любишь?" , "нет",</i>
<b>Промпт для ответа на вопрос по тексту:</b><br>
<i>Текст:\nПервые благотворительные фонды возникли в начале XX в. в США, благодаря усилиям известного промышленника и филантропа Джона Рокфеллера. Именно Дж. Рокфеллер выдвинул идею поставить благотворительность на регулярную основу, предложив создать трест благотворительности [6]. Первой организацией такого типа стал Совет по всеобщему образованию (1902 г.), позднее вошедший в состав фонда Рокфеллера. Примеру Рокфеллера последовали и другие крупные предприниматели США: Эндрю Карнеги, Билл Гейтс и другие.\n\nИсходя из текста выше, 'где возникли благотворительные фонды'\n</i>
<b>Промпт для продолжения диалога с контекстом:</b><br>
<i>Я парень, программист. Увлекаюсь эзотерикой и конспирологией. Пишу фантастику. Люблю природу. Недавно, у меня был следующий диалог:\nТы: Ты знаешь, фантастика меня всегда привлекала. Что-нибудь интересное можешь порекомендовать?\nЯ: Если тебе нравится научная фантастика, то обязательно прочитай Война миров Герберта Уэллса. Очень увлекательная история о захвате Земли инопланетными существами.\nТы: А ты не считаешь, что на самом деле существует возможность контакта с другими цивилизациями во Вселенной?\nЯ: Мы точно не знаем, что на самом деле находится в космосе и какие существа могут обитать где-то далеко от нашей планеты. Многие теории конспирологов и эзотериков говорят о существовании инопланетян и их влиянии на нашу жизнь.\nТы: А есть ли у тебя какие-то любимые книги или фильмы в жанре фантастики?\nЯ:</i>
Кроме вышеназванных промптов, в обучающей выборке было множество других, поэтому вы может просто придумать свой промпт, главное, не забывайте - модель не предназначена для арифметических действий и генерации программного кода | 4,932 | [
[
-0.049835205078125,
-0.045623779296875,
0.0216064453125,
0.007633209228515625,
-0.031524658203125,
0.0033435821533203125,
0.00539398193359375,
-0.02191162109375,
0.045501708984375,
0.01493072509765625,
-0.038665771484375,
-0.0333251953125,
-0.038787841796875,
... |
raphgonda/FilipinoShopping | 2023-10-26T10:08:15.000Z | [
"transformers",
"tf",
"roberta",
"text-classification",
"endpoints_compatible",
"region:us"
] | text-classification | raphgonda | null | null | raphgonda/FilipinoShopping | 0 | 491 | transformers | 2023-10-19T10:02:19 | ---
Language:
- Filipino, English, and Taglish
Results:
- Loss: 0.2594
- Accuracy: 0.7
- Recall: 0.7
- F1 Score: 0.7412
Training hyperparameters:
- learning_rate: 0.00001
- train_batch_size: 32
- eval_batch_size: 32
- optimizer: Adam
- num_epochs: 10
Datasets:
- Shopee Online Reviews
---
<b>Filipino Language Sentiment Classifier - Online Shopping Domain</b>
The model is based on 400,000 Shopee online reviews written in Taglish and Filipino (Tagalog) language.
It is a sentiment classifier that can predict the probability that the text is either positive, negative, or neutral. | 605 | [
[
-0.03363037109375,
-0.0235595703125,
-0.00835418701171875,
0.060211181640625,
-0.03118896484375,
0.01245880126953125,
0.006465911865234375,
-0.049560546875,
0.02154541015625,
0.0262908935546875,
-0.0306549072265625,
-0.0306854248046875,
-0.016021728515625,
0... |
tlphams/gollm-12.8b-instruct-v2.1 | 2023-11-03T04:19:22.000Z | [
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"text-generation-inference",
"region:us"
] | text-generation | tlphams | null | null | tlphams/gollm-12.8b-instruct-v2.1 | 0 | 491 | transformers | 2023-11-01T04:17:11 | ---
license: apache-2.0
base_model: EleutherAI/polyglot-ko-12.8b
tags:
- generated_from_trainer
model-index:
- name: gollm-12.8b-instruct-v2.1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gollm-12.8b-instruct-v2.1
This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a custom mixed dataset
## Model description
- No-context template
```
아래는 작업을 설명하는 질문어와 추가 컨텍스트를 제공하는 맥락이 함께 제공됩니다. 요청을 적절히 완료하는 답변을 작성하세요.
### 질문:
{instruction}
### 답변:
```
- With context template
```
아래는 작업을 설명하는 질문어와 추가 컨텍스트를 제공하는 맥락이 함께 제공됩니다. 요청을 적절히 완료하는 답변을 작성하세요.
### 맥락:
{input}
### 질문:
{instruction}
### 답변:
```
## Intended uses & limitations
More information needed
## Training and evaluation data
- self-introduction (20 samples)
- Combined KoAlpaca v1.0 and 1.1- no-context samples only (53k samples)
+ KoAlpaca v1.0
+ KoAlpaca v1.1
- KoCoT (2k samples)
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- stop_at_epoch: 4
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3 | 1,575 | [
[
-0.035430908203125,
-0.057220458984375,
0.01036834716796875,
0.005260467529296875,
-0.0465087890625,
-0.020538330078125,
-0.00569915771484375,
-0.038055419921875,
0.0316162109375,
0.0255126953125,
-0.040863037109375,
-0.041595458984375,
-0.04840087890625,
-0... |
johngiorgi/declutr-sci-base | 2022-08-10T00:35:23.000Z | [
"sentence-transformers",
"pytorch",
"jax",
"bert",
"feature-extraction",
"sentence-similarity",
"en",
"dataset:s2orc",
"arxiv:2006.03659",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | sentence-similarity | johngiorgi | null | null | johngiorgi/declutr-sci-base | 6 | 490 | sentence-transformers | 2022-03-02T23:29:05 | ---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
language: en
license: apache-2.0
datasets:
- s2orc
---
# DeCLUTR-sci-base
## Model description
This is the [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) model, with extended pretraining on over 2 million scientific papers from [S2ORC](https://github.com/allenai/s2orc/) using the self-supervised training strategy presented in [DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations](https://arxiv.org/abs/2006.03659).
## Intended uses & limitations
The model is intended to be used as a sentence encoder, similar to [Google's Universal Sentence Encoder](https://tfhub.dev/google/universal-sentence-encoder/4) or [Sentence Transformers](https://github.com/UKPLab/sentence-transformers). It is particularly suitable for scientific text.
#### How to use
Please see [our repo](https://github.com/JohnGiorgi/DeCLUTR) for full details. A simple example is shown below.
##### With [SentenceTransformers](https://www.sbert.net/)
```python
from scipy.spatial.distance import cosine
from sentence_transformers import SentenceTransformer
# Load the model
model = SentenceTransformer("johngiorgi/declutr-sci-base")
# Prepare some text to embed
text = [
"Oncogenic KRAS mutations are common in cancer.",
"Notably, c-Raf has recently been found essential for development of K-Ras-driven NSCLCs.",
]
# Embed the text
embeddings = model.encode(texts)
# Compute a semantic similarity via the cosine distance
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])
```
##### With 🤗 Transformers
```python
import torch
from scipy.spatial.distance import cosine
from transformers import AutoModel, AutoTokenizer
# Load the model
tokenizer = AutoTokenizer.from_pretrained("johngiorgi/declutr-sci-base")
model = AutoModel.from_pretrained("johngiorgi/declutr-sci-base")
# Prepare some text to embed
text = [
"Oncogenic KRAS mutations are common in cancer.",
"Notably, c-Raf has recently been found essential for development of K-Ras-driven NSCLCs.",
]
inputs = tokenizer(text, padding=True, truncation=True, return_tensors="pt")
# Embed the text
with torch.no_grad():
sequence_output = model(**inputs)[0]
# Mean pool the token-level embeddings to get sentence-level embeddings
embeddings = torch.sum(
sequence_output * inputs["attention_mask"].unsqueeze(-1), dim=1
) / torch.clamp(torch.sum(inputs["attention_mask"], dim=1, keepdims=True), min=1e-9)
# Compute a semantic similarity via the cosine distance
semantic_sim = 1 - cosine(embeddings[0], embeddings[1])
```
### BibTeX entry and citation info
```bibtex
@inproceedings{giorgi-etal-2021-declutr,
title = {{D}e{CLUTR}: Deep Contrastive Learning for Unsupervised Textual Representations},
author = {Giorgi, John and Nitski, Osvald and Wang, Bo and Bader, Gary},
year = 2021,
month = aug,
booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
publisher = {Association for Computational Linguistics},
address = {Online},
pages = {879--895},
doi = {10.18653/v1/2021.acl-long.72},
url = {https://aclanthology.org/2021.acl-long.72}
}
``` | 3,443 | [
[
-0.00974273681640625,
-0.039337158203125,
0.039306640625,
0.00981903076171875,
-0.0259857177734375,
-0.006458282470703125,
-0.0220794677734375,
-0.021209716796875,
0.0226593017578125,
0.029022216796875,
-0.044830322265625,
-0.057159423828125,
-0.04949951171875,
... |
timm/deit3_large_patch16_224.fb_in1k | 2023-03-28T01:12:10.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"dataset:imagenet-1k",
"arxiv:2204.07118",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/deit3_large_patch16_224.fb_in1k | 0 | 490 | timm | 2023-03-28T01:08:11 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
datasets:
- imagenet-1k
---
# Model card for deit3_large_patch16_224.fb_in1k
A DeiT-III image classification model. Trained on ImageNet-1k by paper authors.
## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
- Params (M): 304.4
- GMACs: 61.6
- Activations (M): 63.5
- Image size: 224 x 224
- **Papers:**
- DeiT III: Revenge of the ViT: https://arxiv.org/abs/2204.07118
- **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('deit3_large_patch16_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(
'deit3_large_patch16_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, 197, 1024) 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{Touvron2022DeiTIR,
title={DeiT III: Revenge of the ViT},
author={Hugo Touvron and Matthieu Cord and Herve Jegou},
journal={arXiv preprint arXiv:2204.07118},
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}}
}
```
| 2,945 | [
[
-0.0313720703125,
-0.037353515625,
0.00923919677734375,
0.01473236083984375,
-0.0272216796875,
-0.02349853515625,
-0.003177642822265625,
-0.030029296875,
0.0167236328125,
0.02471923828125,
-0.0390625,
-0.05670166015625,
-0.046966552734375,
-0.005237579345703... |
timm/cspresnext50.ra_in1k | 2023-04-12T20:40:16.000Z | [
"timm",
"pytorch",
"safetensors",
"image-classification",
"arxiv:2110.00476",
"arxiv:1911.11929",
"arxiv:1611.05431",
"license:apache-2.0",
"region:us"
] | image-classification | timm | null | null | timm/cspresnext50.ra_in1k | 0 | 490 | timm | 2023-04-12T20:39:56 | ---
tags:
- image-classification
- timm
library_tag: timm
license: apache-2.0
---
# Model card for cspresnext50.ra_in1k
A CSP-ResNeXt (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): 20.6
- GMACs: 4.0
- Activations (M): 15.9
- Image size: 256 x 256
- **Papers:**
- CSPNet: A New Backbone that can Enhance Learning Capability of CNN: https://arxiv.org/abs/1911.11929
- Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
- 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('cspresnext50.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(
'cspresnext50.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, 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(
'cspresnext50.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, 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{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{Xie2016,
title={Aggregated Residual Transformations for Deep Neural Networks},
author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
journal={arXiv preprint arXiv:1611.05431},
year={2016}
}
```
```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}}
}
```
| 5,093 | [
[
-0.034576416015625,
-0.0207672119140625,
-0.005283355712890625,
0.006694793701171875,
-0.01678466796875,
-0.01398468017578125,
-0.02642822265625,
-0.0267181396484375,
0.0164337158203125,
0.0299224853515625,
-0.034759521484375,
-0.046112060546875,
-0.053314208984... |
skyprolk/iPhone-Wallpaper-Style | 2023-11-06T07:59:56.000Z | [
"diffusers",
"art",
"text-to-image",
"stable-diffusion",
"lora",
"style",
"iphone-wallpaper",
"en",
"dataset:skyprolk/iPhone-Wallpapers",
"license:gpl-3.0",
"region:us"
] | text-to-image | skyprolk | null | null | skyprolk/iPhone-Wallpaper-Style | 0 | 490 | diffusers | 2023-09-29T17:37:30 | ---
license: gpl-3.0
datasets:
- skyprolk/iPhone-Wallpapers
tags:
- art
- text-to-image
- stable-diffusion
- lora
- diffusers
- style
- iphone-wallpaper
language:
- en
pipeline_tag: text-to-image
base_model: runwayml/stable-diffusion-v1-5
---
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model is designed for applying stylish filters and aesthetic enhancements to your images. It can transform your photos to have a style reminiscent of iPhone wallpapers, giving your images a unique and eye-catching appearance.
- **Developed by:** SKY PRODUCTION
- **Shared by:** KNOIT
- **Model type:** STABLE DIFFUSION
- **Finetuned from model:** LORA
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
Dataset used to train : https://huggingface.co/datasets/skyprolk/iPhone-Wallpapers
## Disclaimer
- This model is for artistic and aesthetic purposes and may not be suitable for all images or use cases.
- The performance of the style transfer may vary depending on the input image and the desired style.
- Use this model responsibly and respect copyright and licensing agreements when applying styles to images.
## Feedback and Contributions
The model's author, SKY PRODUCTION, welcomes feedback and contributions to improve the model.
# Have Fun Styling Your Images!
We hope you enjoy using the iPhone-Wallpaper-Style model to add a unique touch to your images. If you have any questions or need further assistance, please don't hesitate to reach out to the model's author or the community. | 1,745 | [
[
-0.037078857421875,
-0.049224853515625,
0.0087890625,
0.0211181640625,
-0.0282745361328125,
-0.01432037353515625,
0.017333984375,
-0.0379638671875,
0.041351318359375,
0.05810546875,
-0.056427001953125,
-0.0589599609375,
-0.038299560546875,
-0.03759765625,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.