mosesdaudu/LLama-1B-BaseModel-4bit

1{2  "_name_or_path": "/home/moses/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B/snapshots/1460c22666392e470910ce3d44ffeb2ab7dbd4df",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": 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  "quantization_config": {21    "bits": 4,22    "group_size": 128,23    "modules_to_not_convert": null,24    "quant_method": "awq",25    "version": "gemm",26    "zero_point": true27  },28  "rms_norm_eps": 1e-05,29  "rope_scaling": null,30  "rope_theta": 500000.0,31  "tie_word_embeddings": false,32  "torch_dtype": "float16",33  "transformers_version": "4.38.2",34  "use_cache": true,35  "vocab_size": 12825636}37