{
    "architectures": [
        "LlamaForCausalLM"
    ],
    "bos_token_id": 0,
    "eos_token_id": [
        1,
        130073
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1536,
    "initializer_range": 0.02,
    "intermediate_size": 4608,
    "max_position_embeddings": 131072,
    "model_type": "llama",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "num_key_value_heads": 2,
    "pad_token_id": 1,
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.embed_tokens": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.gate_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.1.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.1.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.1.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.2.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.2.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.3.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.3.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.5.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.5.self_attn.o_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.6.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.6.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.self_attn.v_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.self_attn.v_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.9.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.9.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.10.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.10.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.12.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.12.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.13.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.13.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.15.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.15.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.16.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.16.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.17.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.17.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.17.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.18.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.18.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.19.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.19.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.20.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.20.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.20.self_attn.o_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.21.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.21.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.22.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.22.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.mlp.gate_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "lm_head": {
            "bits": 8,
            "group_size": 64
        }
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.embed_tokens": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.gate_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.0.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.1.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.1.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.1.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.1.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.2.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.2.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.2.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.3.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.3.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.3.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.4.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.4.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.5.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.5.self_attn.o_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.5.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.6.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.6.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.6.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.self_attn.v_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.7.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.7.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.self_attn.v_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.8.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.8.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.9.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.9.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.9.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.10.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.10.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.10.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.11.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.11.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.12.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.12.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.12.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.13.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.13.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.13.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.14.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.14.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.15.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.15.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.15.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.16.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.16.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.16.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.17.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.17.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.17.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.17.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.18.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.18.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.18.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.19.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.19.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.19.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.20.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.20.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.20.self_attn.o_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.20.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.21.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.21.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.21.mlp.up_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.self_attn.q_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.self_attn.k_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.22.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.22.mlp.gate_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.mlp.down_proj": {
            "bits": 4,
            "group_size": 64
        },
        "model.layers.22.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.q_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.k_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.v_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.self_attn.o_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.mlp.gate_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.mlp.down_proj": {
            "bits": 8,
            "group_size": 64
        },
        "model.layers.23.mlp.up_proj": {
            "bits": 8,
            "group_size": 64
        },
        "lm_head": {
            "bits": 8,
            "group_size": 64
        }
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 5000000,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "5.6.2",
    "use_cache": true,
    "vocab_size": 130560
}