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
File size: 2,387 Bytes
12f2835 ffc8b95 12f2835 ffc8b95 12f2835 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | {
"config": {
"run_name": "captionbert-8192-v2",
"sources": [
{
"repo": "AbstractPhil/conceptual-captions-12m-webdataset-berts",
"n_chunks": 66,
"chunk_rows": 500000,
"missing": {
"modern": []
}
}
],
"experts": [
"bert",
"modern",
"roberta",
"albert",
"distil"
],
"ref_expert": "bert",
"ref_hf_name": "google-bert/bert-base-uncased",
"require_all_experts": true,
"caption_field": "(flat)",
"caption_field_candidates": [
"caption_llava",
"caption",
"caption_llava_short"
],
"work_dir": "/content/cbv2",
"keep_expert_shards": false,
"disk_floor_gb": 25.0,
"ram_resident": true,
"preflight": true,
"hf_repo": "AbstractPhil/captionbert-8192-v2",
"targets_repo": "AbstractPhil/captionbert-8192-v2-consensus",
"push_targets": true,
"hf_push": true,
"push_every_min": 30.0,
"keep_local_ckpts": 3,
"parity_chunk": 0,
"parity_n": 64,
"parity_min_cos": 0.999,
"fit_chunks": [
0,
11,
22,
33,
44,
55
],
"fit_rows_per_chunk": 4000,
"holdout_chunks": [
60,
61
],
"fit_seed": 0,
"d_model": 512,
"n_heads": 8,
"n_layers": 12,
"d_ff": 2048,
"max_len": 8192,
"output_dim": 768,
"dropout": 0.1,
"pooling": "mean",
"max_tokens": 256,
"length_bucketing": true,
"bucket_window": 64,
"grad_checkpointing": true,
"vram_probe": true,
"epochs": 4,
"batch_size": 2048,
"lr": 0.0006,
"min_lr": 1e-06,
"warmup_steps": 2000,
"grad_clip": 1.0,
"seed": 42,
"amp": true,
"num_workers": 0,
"log_every": 50,
"eval_every": 1000,
"ckpt_every_min": 20.0,
"nce_weight": 1.0,
"mse_weight": 1.0,
"nce_temperature": 0.07,
"cv_weight": 0.0,
"cv_target": 0.084,
"run_stage0": true,
"run_stage1": true,
"run_stage2": true,
"run_stage3": true,
"resume": true
},
"final": {
"mimicry_r1": 0.9975000023841858,
"cos_to_target": 0.8409875631332397,
"self_cos": 0.003099770750850439,
"erank": 102.90254876814863,
"cv": 0.09320895820921411,
"n": 5120,
"frame_r1_after_rotation": 0.9984999895095825,
"frame_cos_after_rotation": 0.8356035351753235,
"frame_n_heldout": 2000
}
} |