24 lines
619 B
JSON
24 lines
619 B
JSON
{
|
|
"_name_or_path": "/juice5/scr5/nlp/crfm/human-feedback/models/selfinstruct/sft_v6_52k_llama_7b_regen_v7_3ep",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 11008,
|
|
"max_position_embeddings": 2048,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"pad_token_id": 0,
|
|
"rms_norm_eps": 1e-06,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.28.0.dev0",
|
|
"use_cache": true,
|
|
"vocab_size": 32001
|
|
}
|