config.json

{
    "_name_or_path": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": 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,
    "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": "bfloat16",
    "transformers_version": "4.45.1",
    "use_cache": false,
    "vocab_size": 128256,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.2.3",
        "bits": 3.0,
        "head_bits": 6,
        "calibration": {
            "rows": 115,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}