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 | |
| } | |
| }, | |
| "rows": { | |
| "OFF": { | |
| "STS-B": { | |
| "spearman": 0.574721280584061, | |
| "self_cos": 0.13962045311927795, | |
| "erank": 36.611595622425114 | |
| }, | |
| "SICK-R": { | |
| "spearman": 0.652602297708298, | |
| "self_cos": 0.32337328791618347, | |
| "erank": 39.12520123844512 | |
| } | |
| }, | |
| "equiv-only": { | |
| "STS-B": { | |
| "spearman": 0.731078083351727, | |
| "self_cos": 0.1255255937576294, | |
| "erank": 50.663957003073875 | |
| }, | |
| "SICK-R": { | |
| "spearman": 0.7325251878585886, | |
| "self_cos": 0.17530100047588348, | |
| "erank": 34.694745020767634 | |
| } | |
| }, | |
| "simplify-only": { | |
| "STS-B": { | |
| "spearman": 0.6031180553522926, | |
| "self_cos": 0.12380383908748627, | |
| "erank": 43.472962330224135 | |
| }, | |
| "SICK-R": { | |
| "spearman": 0.6609382896862828, | |
| "self_cos": 0.3064461648464203, | |
| "erank": 39.3687757862779 | |
| } | |
| }, | |
| "MOE": { | |
| "STS-B": { | |
| "spearman": 0.7524264373550089, | |
| "self_cos": 0.12201106548309326, | |
| "erank": 54.394680890714454 | |
| }, | |
| "SICK-R": { | |
| "spearman": 0.7380408425545968, | |
| "self_cos": 0.16639426350593567, | |
| "erank": 34.39546446727023 | |
| } | |
| } | |
| }, | |
| "telemetry_before": { | |
| "equiv": 0.3097170293331146, | |
| "simplify": 0.3800048828125 | |
| }, | |
| "telemetry_after": { | |
| "equiv": 0.6454874873161316, | |
| "simplify": 0.2226928472518921 | |
| }, | |
| "alarms": [], | |
| "anchors": [ | |
| "equiv.anchor.pt", | |
| "simplify.anchor.pt" | |
| ], | |
| "config": { | |
| "run_name": "captionbert-v2-moe", | |
| "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", | |
| "experts": [ | |
| [ | |
| "equiv", | |
| [ | |
| [ | |
| "sentence-transformers/all-nli", | |
| "triplet", | |
| "anchor", | |
| "positive", | |
| "negative", | |
| 200000 | |
| ] | |
| ] | |
| ], | |
| [ | |
| "simplify", | |
| [ | |
| [ | |
| "sentence-transformers/simple-wiki", | |
| "pair", | |
| "text", | |
| "simplified", | |
| null, | |
| 0 | |
| ], | |
| [ | |
| "sentence-transformers/altlex", | |
| "pair", | |
| "text", | |
| "simplified", | |
| null, | |
| 0 | |
| ], | |
| [ | |
| "sentence-transformers/sentence-compression", | |
| "pair", | |
| "text", | |
| "simplified", | |
| null, | |
| 0 | |
| ] | |
| ] | |
| ] | |
| ], | |
| "dedup_jaccard": 0.95, | |
| "n_slots": 16, | |
| "K": 64, | |
| "D": 4, | |
| "tau": 0.1, | |
| "hidden": 178, | |
| "gate_init": -3.0, | |
| "anchor_steps": 1500, | |
| "anchor_lr": 0.001, | |
| "batch_size": 256, | |
| "temperature": 0.05, | |
| "max_tokens": 64, | |
| "align_steps": 800, | |
| "align_lr": 0.001, | |
| "align_emb": 64, | |
| "align_tau": 0.1, | |
| "check_every": 200, | |
| "usage_ppl_floor": 1.5, | |
| "usage_min": 0.02, | |
| "max_strikes": 3, | |
| "seed": 0, | |
| "log_every": 100, | |
| "eval_every": 500, | |
| "out_dir": "/content/amoe_moe", | |
| "hf_repo": "AbstractPhil/captionbert-8192-v2", | |
| "hf_path": "amoe/moe", | |
| "hf_private": false, | |
| "hf_push": true | |
| } | |
| } |