config.json

{
  "_name_or_path": "/data5/models/Llama-3.1-Nemotron-70B-Instruct-HF",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 28672,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 64,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "amp": true,
    "autoround_version": "0.4.2.dev",
    "batch_size": 8,
    "bits": 4,
    "data_type": "int",
    "dataset": "NeelNanda/pile-10k",
    "enable_minmax_tuning": true,
    "enable_norm_bias_tuning": false,
    "enable_quanted_input": true,
    "gradient_accumulate_steps": 1,
    "group_size": 128,
    "iters": 200,
    "low_gpu_mem_usage": false,
    "lr": 0.005,
    "minmax_lr": 0.005,
    "nsamples": 128,
    "quant_method": "auto-round",
    "scale_dtype": "torch.float16",
    "seqlen": 2048,
    "sym": true,
    "to_quant_block_names": [
      [
        "model.layers.0",
        "model.layers.1",
        "model.layers.2",
        "model.layers.3",
        "model.layers.4",
        "model.layers.5",
        "model.layers.6",
        "model.layers.7",
        "model.layers.8",
        "model.layers.9",
        "model.layers.10",
        "model.layers.11",
        "model.layers.12",
        "model.layers.13",
        "model.layers.14",
        "model.layers.15",
        "model.layers.16",
        "model.layers.17",
        "model.layers.18",
        "model.layers.19",
        "model.layers.20",
        "model.layers.21",
        "model.layers.22",
        "model.layers.23",
        "model.layers.24",
        "model.layers.25",
        "model.layers.26",
        "model.layers.27",
        "model.layers.28",
        "model.layers.29",
        "model.layers.30",
        "model.layers.31",
        "model.layers.32",
        "model.layers.33",
        "model.layers.34",
        "model.layers.35",
        "model.layers.36",
        "model.layers.37",
        "model.layers.38",
        "model.layers.39",
        "model.layers.40",
        "model.layers.41",
        "model.layers.42",
        "model.layers.43",
        "model.layers.44",
        "model.layers.45",
        "model.layers.46",
        "model.layers.47",
        "model.layers.48",
        "model.layers.49",
        "model.layers.50",
        "model.layers.51",
        "model.layers.52",
        "model.layers.53",
        "model.layers.54",
        "model.layers.55",
        "model.layers.56",
        "model.layers.57",
        "model.layers.58",
        "model.layers.59",
        "model.layers.60",
        "model.layers.61",
        "model.layers.62",
        "model.layers.63",
        "model.layers.64",
        "model.layers.65",
        "model.layers.66",
        "model.layers.67",
        "model.layers.68",
        "model.layers.69",
        "model.layers.70",
        "model.layers.71",
        "model.layers.72",
        "model.layers.73",
        "model.layers.74",
        "model.layers.75",
        "model.layers.76",
        "model.layers.77",
        "model.layers.78",
        "model.layers.79"
      ]
    ]
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "vocab_size": 128256
}