Ziya-LLaMA-13B-v1 / config.json
Ray0323's picture
Upload 2 files
4a3eac9
raw
history blame
626 Bytes
{
"_name_or_path": "/cognitive_comp/wanghao/models/llama_sft/llama_13b_v2_s2_6600_rlhf_0515_kl_RM13BB0510_step49_hf/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"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": "4.29.0.dev0",
"use_cache": true,
"vocab_size": 39424
}