Tanuki-8B-dpo-v1.0 / config.json
kanhatakeyama's picture
Duplicate from team-hatakeyama-phase2/Tanuki-8B-dpo-v1.0
42b7238 verified
raw
history blame contribute delete
770 Bytes
{
"_name_or_path": "/storage5/personal/shioya/sft_model/sftlab-experiments/8B/pass4_exp001-0809_exp_01-zero1",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"use_cache": true,
"vocab_size": 65024
}