captionbert-8192-v2 / amoe /moe /config.json
AbstractPhil's picture
final: 2 anchors + dispatch + card
9154293 verified
Raw
History Blame Contribute Delete
1.66 kB
{
"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
}