bayling-13b-diff / config.json
Vily1998
first commit
d196152
{
"_name_or_path": "/data/zhangshaolei/FastChat/checkpoints/imt.llama_13B.data=en-zh-de-fr.wmt_dev+IMT.v8+personal+gpt4_alpaca_zhen+sharegpt+pe.393739",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"end_token_id": 2,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"vocab_size": 32000
}