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
| { | |
| "baseline": { | |
| "STS-B": { | |
| "spearman": 0.574721280584061, | |
| "self_cos": 0.13962045311927795, | |
| "erank": 36.611595622425114 | |
| }, | |
| "SICK-R": { | |
| "spearman": 0.652602297708298, | |
| "self_cos": 0.32337328791618347, | |
| "erank": 39.12520123844512 | |
| } | |
| }, | |
| "history": [ | |
| { | |
| "step": 500, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7159579493702058, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.7435196218188278 | |
| }, | |
| { | |
| "step": 1000, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.725601245272485, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.755576808863059 | |
| }, | |
| { | |
| "step": 1500, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7151407457911756, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.7578871303476999 | |
| }, | |
| { | |
| "step": 2000, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7154519898827421, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.7573430151835525 | |
| }, | |
| { | |
| "step": 2500, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7104465658474052, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.7582781951617588 | |
| }, | |
| { | |
| "step": 3000, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7083951957883847, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.7590069820334998 | |
| }, | |
| { | |
| "step": 3500, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7083951980791002, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.761045872510455 | |
| }, | |
| { | |
| "step": 4000, | |
| "STS-B_OFF": 0.574721280584061, | |
| "STS-B_ON": 0.7078438640997194, | |
| "SICK-R_OFF": 0.652602297708298, | |
| "SICK-R_ON": 0.7611122380587768 | |
| } | |
| ], | |
| "step": 4000, | |
| "config": { | |
| "run_name": "captionbert-v2-sts-anchor", | |
| "trunk_repo": "AbstractPhil/captionbert-8192-v2", | |
| "trunk_ckpt": "checkpoints/best_model.pt", | |
| "tokenizer": "google-bert/bert-base-uncased", | |
| "d_model": 512, | |
| "n_heads": 8, | |
| "n_layers": 12, | |
| "d_ff": 2048, | |
| "max_len": 8192, | |
| "output_dim": 768, | |
| "pooling": "mean", | |
| "sites": "all", | |
| "n_slots": 16, | |
| "K": 64, | |
| "D": 4, | |
| "tau": 0.1, | |
| "hidden": 178, | |
| "gate_init": -3.0, | |
| "data_repo": "sentence-transformers/all-nli", | |
| "data_config": "triplet", | |
| "n_train": 200000, | |
| "max_tokens": 64, | |
| "batch_size": 256, | |
| "temperature": 0.05, | |
| "use_hard_negatives": true, | |
| "steps": 4000, | |
| "lr": 0.001, | |
| "warmup": 200, | |
| "grad_clip": 1.0, | |
| "seed": 0, | |
| "log_every": 100, | |
| "eval_every": 500, | |
| "out_dir": "/content/amoe_sts", | |
| "hf_repo": "AbstractPhil/captionbert-8192-v2", | |
| "hf_path": "amoe/sts", | |
| "hf_private": false, | |
| "hf_push": true | |
| } | |
| } |