30 lines
758 B
JSON
30 lines
758 B
JSON
{
|
|
"architectures": [
|
|
"BaichuanForCausalLM"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_baichuan.BaichuanConfig",
|
|
"AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
|
|
},
|
|
"tokenizer_class": "BaichuanTokenizer",
|
|
"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,
|
|
"_from_model_config": true,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.29.2",
|
|
"use_cache": true,
|
|
"vocab_size": 125696
|
|
}
|