ImagineIt/Alpha-basic

1{2  "_name_or_path": "NousResearch/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": 128001,10  "hidden_act": "silu",11  "hidden_size": 4096,12  "initializer_range": 0.02,13  "intermediate_size": 14336,14  "max_position_embeddings": 20000,15  "model_type": "llama",16  "num_attention_heads": 32,17  "num_hidden_layers": 32,18  "num_key_value_heads": 8,19  "pad_token_id": 128255,20  "pretraining_tp": 1,21  "rms_norm_eps": 1e-05,22  "rope_scaling": {23    "factor": 2.44140625,24    "type": "linear"25  },26  "rope_theta": 500000.0,27  "tie_word_embeddings": false,28  "torch_dtype": "bfloat16",29  "transformers_version": "4.40.2",30  "unsloth_version": "2024.5",31  "use_cache": true,32  "vocab_size": 12825633}34