BIDALAB/Tutorial-Model

1{2  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 128000,9  "eos_token_id": 128009,10  "hidden_act": "silu",11  "hidden_size": 4096,12  "initializer_range": 0.02,13  "intermediate_size": 14336,14  "max_position_embeddings": 8192,15  "model_type": "llama",16  "num_attention_heads": 32,17  "num_hidden_layers": 32,18  "num_key_value_heads": 8,19  "pretraining_tp": 1,20  "rms_norm_eps": 1e-05,21  "rope_scaling": null,22  "rope_theta": 500000.0,23  "tie_word_embeddings": false,24  "torch_dtype": "float16",25  "transformers_version": "4.39.0",26  "use_cache": true,27  "vocab_size": 12825628}29