zaydzuhri's picture
Training in progress, step 2500
0094a2a verified
raw
history blame contribute delete
591 Bytes
{
"attn_mode": "chunk",
"bos_token_id": 1,
"clamp_min": null,
"eos_token_id": 2,
"expand_k": 1,
"expand_v": 1,
"fuse_cross_entropy": true,
"fuse_norm": true,
"hidden_act": "swish",
"hidden_ratio": 4,
"hidden_size": 256,
"initializer_range": 0.02,
"intermediate_size": null,
"max_position_embeddings": 2048,
"model_type": "gsa",
"num_slots": 16,
"num_heads": 4,
"num_hidden_layers": 10,
"norm_eps": 1e-06,
"tie_word_embeddings": true,
"transformers_version": "4.38.2",
"use_cache": true,
"use_gk": true,
"use_gv": false,
"vocab_size": 32000
}