28 lines
723 B
JSON
28 lines
723 B
JSON
|
|
{
|
||
|
|
"_name_or_path": "/mntcephfs/data/med/zhanghongbo/MOSS/ckpts/ppo_all_new_huatuo_Ziya_230K_it1_16/latest_tfmr",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 13824,
|
||
|
|
"layer_norm_eps": 1e-05,
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 40,
|
||
|
|
"num_hidden_layers": 40,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rotary_emb_base": 10000,
|
||
|
|
"rotary_pct": 1,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float16",
|
||
|
|
"transformers_version": "4.29.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_parallel_residual": false,
|
||
|
|
"vocab_size": 39424
|
||
|
|
}
|