Feature Extraction
Transformers
TensorBoard
Safetensors
English
captionbert_v2
sentence-similarity
consensus-distillation
geometric-deep-learning
amoe
custom_code
Instructions to use AbstractPhil/captionbert-8192-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AbstractPhil/captionbert-8192-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="AbstractPhil/captionbert-8192-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AbstractPhil/captionbert-8192-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bert": { | |
| "in_sample": { | |
| "cos": 1.0, | |
| "r1": 0.9965000152587891, | |
| "n": 24000, | |
| "chance": 0.0005 | |
| }, | |
| "out_of_sample": { | |
| "cos": 1.0, | |
| "r1": 0.9909999966621399, | |
| "n": 8000, | |
| "chance": 0.0005 | |
| } | |
| }, | |
| "modern": { | |
| "in_sample": { | |
| "cos": 0.38715124130249023, | |
| "r1": 0.9649999737739563, | |
| "n": 24000, | |
| "chance": 0.0005 | |
| }, | |
| "out_of_sample": { | |
| "cos": 0.3266415596008301, | |
| "r1": 0.9164999723434448, | |
| "n": 8000, | |
| "chance": 0.0005 | |
| } | |
| }, | |
| "roberta": { | |
| "in_sample": { | |
| "cos": 0.4255034923553467, | |
| "r1": 0.9810000061988831, | |
| "n": 24000, | |
| "chance": 0.0005 | |
| }, | |
| "out_of_sample": { | |
| "cos": 0.37222719192504883, | |
| "r1": 0.9480000138282776, | |
| "n": 8000, | |
| "chance": 0.0005 | |
| } | |
| }, | |
| "albert": { | |
| "in_sample": { | |
| "cos": 0.3922822177410126, | |
| "r1": 0.9785000085830688, | |
| "n": 24000, | |
| "chance": 0.0005 | |
| }, | |
| "out_of_sample": { | |
| "cos": 0.3313330411911011, | |
| "r1": 0.9384999871253967, | |
| "n": 8000, | |
| "chance": 0.0005 | |
| } | |
| }, | |
| "distil": { | |
| "in_sample": { | |
| "cos": 0.6433802247047424, | |
| "r1": 0.9955000281333923, | |
| "n": 24000, | |
| "chance": 0.0005 | |
| }, | |
| "out_of_sample": { | |
| "cos": 0.6245564818382263, | |
| "r1": 0.9810000061988831, | |
| "n": 8000, | |
| "chance": 0.0005 | |
| } | |
| } | |
| } |