35 lines
1003 B
JSON
35 lines
1003 B
JSON
{
|
|
"_name_or_path": "/data/zhangzheng/model/Meta-Llama-3-8B-Instruct",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"auto_map": {
|
|
"AutoConfig":"configuration_llama.LlamaConfig",
|
|
"AutoModel": "modeling_llama.LlamaForCausalLM",
|
|
"AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM",
|
|
"AutoModelForSequenceClassification":"modeling_llama.LlamaForSequenceClassification"
|
|
},
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 128000,
|
|
"eos_token_id": 128001,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 8192,
|
|
"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": "float16",
|
|
"transformers_version": "4.39.0",
|
|
"use_cache": true,
|
|
"vocab_size": 128256
|
|
}
|