usagent100/modelv3

1{2  "_name_or_path": "openlm-research/open_llama_7b",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "bos_token_id": 1,7  "eos_token_id": 2,8  "hidden_act": "silu",9  "hidden_size": 4096,10  "initializer_range": 0.02,11  "intermediate_size": 11008,12  "max_position_embeddings": 2048,13  "model_type": "llama",14  "num_attention_heads": 32,15  "num_hidden_layers": 32,16  "pad_token_id": 0,17  "rms_norm_eps": 1e-06,18  "tie_word_embeddings": false,19  "torch_dtype": "bfloat16",20  "transformers_version": "4.30.0.dev0",21  "use_cache": true,22  "vocab_size": 3200023}24