SFT-baichuan-v4-5000 / config.json
Jianyuan's picture
Upload BaichuanForCausalLM
e65e0cd
raw
history blame contribute delete
897 Bytes
{
"_from_model_config": true,
"_name_or_path": "baichuan-inc/Baichuan2-7B-Chat",
"architectures": [
"BaichuanForCausalLM"
],
"auto_map": {
"AutoConfig": "baichuan-inc/Baichuan2-7B-Chat--configuration_baichuan.BaichuanConfig",
"AutoModelForCausalLM": "baichuan-inc/Baichuan2-7B-Chat--modeling_baichuan.BaichuanForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_max_length": 4096,
"model_type": "baichuan",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"tokenizer_class": "BaichuanTokenizer",
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 125696,
"z_loss_weight": 0
}