samaxr/codellma-7b

1{2  "_name_or_path": "codellama/CodeLlama-7b-hf",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "hidden_act": "silu",11  "hidden_size": 4096,12  "initializer_range": 0.02,13  "intermediate_size": 11008,14  "max_position_embeddings": 16384,15  "model_type": "llama",16  "num_attention_heads": 32,17  "num_hidden_layers": 32,18  "num_key_value_heads": 32,19  "pretraining_tp": 1,20  "quantization_config": {21    "_load_in_4bit": true,22    "_load_in_8bit": false,23    "bnb_4bit_compute_dtype": "float32",24    "bnb_4bit_quant_type": "fp4",25    "bnb_4bit_use_double_quant": false,26    "llm_int8_enable_fp32_cpu_offload": false,27    "llm_int8_has_fp16_weight": false,28    "llm_int8_skip_modules": null,29    "llm_int8_threshold": 6.0,30    "load_in_4bit": true,31    "load_in_8bit": false,32    "quant_method": "bitsandbytes"33  },34  "rms_norm_eps": 1e-05,35  "rope_scaling": null,36  "rope_theta": 1000000,37  "tie_word_embeddings": false,38  "torch_dtype": "float16",39  "transformers_version": "4.39.0.dev0",40  "use_cache": true,41  "vocab_size": 3201642}43