{
    "architectures": [
        "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": [
        128001,
        128008,
        128009
    ],
    "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,
    "pad_token_id": 128004,
    "pretraining_tp": 1,
    "quantization": {
        "group_size": 128,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.3.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.5.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.6.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.9.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.10.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.12.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.13.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.15.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.24.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.28.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.29.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.32.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.33.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.34.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.35.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.36.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.37.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.39.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.42.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.43.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.45.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.46.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.46.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.47.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.48.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.49.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.50.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.50.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.51.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.53.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.54.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.54.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.55.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.55.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.55.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.57.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.58.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.59.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.61.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.62.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.63.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.64.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.66.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.67.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.69.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.70.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.72.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.73.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.74.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.76.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.76.mlp.gate_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.79.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.79.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        }
    },
    "quantization_config": {
        "group_size": 128,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.3.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.5.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.6.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.9.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.10.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.12.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.13.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.15.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.24.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.28.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.29.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.32.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.33.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.34.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.35.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.36.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.37.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.39.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.42.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.43.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.45.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.46.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.46.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.47.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.48.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.49.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.50.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.50.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.51.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.53.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.54.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.54.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.55.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.55.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.55.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.57.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.58.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.59.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.61.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.62.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.63.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.64.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.66.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.67.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.69.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.70.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.72.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.73.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.74.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.76.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.76.mlp.gate_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.79.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.79.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        }
    },
    "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": "4.44.2",
    "unsloth_version": "2024.9",
    "use_cache": true,
    "vocab_size": 128256
}