blockblockblock/TableLLM-13b-bpw3.7

1{2    "_name_or_path": "/data2/wangyuanchun/models/base_ckpt/llama2/CodeLlama-13b-Instruct-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": 5120,12    "initializer_range": 0.02,13    "intermediate_size": 13824,14    "max_position_embeddings": 16384,15    "model_type": "llama",16    "num_attention_heads": 40,17    "num_hidden_layers": 40,18    "num_key_value_heads": 40,19    "pad_token_id": 0,20    "pretraining_tp": 1,21    "rms_norm_eps": 1e-05,22    "rope_scaling": null,23    "rope_theta": 1000000,24    "tie_word_embeddings": false,25    "torch_dtype": "bfloat16",26    "transformers_version": "4.37.0",27    "use_cache": true,28    "vocab_size": 32016,29    "quantization_config": {30        "quant_method": "exl2",31        "version": "0.0.16",32        "bits": 3.7,33        "head_bits": 6,34        "calibration": {35            "rows": 100,36            "length": 2048,37            "dataset": "(default)"38        }39    }40}