AI4DS/Llama3_70B_NL2SQL

1{2  "_name_or_path": "meta-llama/Meta-Llama-3-70B-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": 8192,12  "initializer_range": 0.02,13  "intermediate_size": 28672,14  "max_position_embeddings": 8192,15  "model_type": "llama",16  "num_attention_heads": 64,17  "num_hidden_layers": 80,18  "num_key_value_heads": 8,19  "pretraining_tp": 1,20  "quantization_config": {21    "_load_in_4bit": true,22    "_load_in_8bit": false,23    "bnb_4bit_compute_dtype": "bfloat16",24    "bnb_4bit_quant_storage": "uint8",25    "bnb_4bit_quant_type": "nf4",26    "bnb_4bit_use_double_quant": true,27    "llm_int8_enable_fp32_cpu_offload": false,28    "llm_int8_has_fp16_weight": false,29    "llm_int8_skip_modules": null,30    "llm_int8_threshold": 6.0,31    "load_in_4bit": true,32    "load_in_8bit": false,33    "quant_method": "bitsandbytes"34  },35  "rms_norm_eps": 1e-05,36  "rope_scaling": null,37  "rope_theta": 500000.0,38  "tie_word_embeddings": false,39  "torch_dtype": "bfloat16",40  "transformers_version": "4.40.1",41  "use_cache": true,42  "vocab_size": 12825643}44