{
    "add_cross_attention": false,
    "architectures": [
        "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "chunk_size_feed_forward": 0,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": [
        151643,
        151645
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 65536,
    "min_length": 0,
    "model_type": "qwen3",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 151643,
    "pruned_heads": {},
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.0.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.0.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.1.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.1.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.1.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.2.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.2.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.2.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.3.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.3.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.3.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.4.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.4.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.4.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.5.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.5.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.5.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.6.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.6.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.6.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.7.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.7.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.7.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.8.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.8.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.8.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.9.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.9.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.9.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.10.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.10.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.10.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.11.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.11.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.11.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.12.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.12.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.12.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.13.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.13.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.13.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.14.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.14.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.14.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.15.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.15.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.15.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.16.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.16.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.16.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.17.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.17.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.17.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.18.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.18.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.18.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.19.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.19.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.19.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.20.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.20.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.20.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.21.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.21.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.21.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.22.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.22.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.22.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.23.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.23.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.23.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.24.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.24.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.24.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.25.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.25.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.25.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.26.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.26.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.26.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.27.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.27.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.27.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        }
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.0.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.0.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.0.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.1.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.1.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.1.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.2.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.2.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.2.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.3.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.3.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.3.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.4.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.4.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.4.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.5.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.5.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.5.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.6.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.6.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.6.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.7.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.7.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.7.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.8.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.8.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.8.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.9.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.9.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.9.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.10.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.10.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.10.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.11.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.11.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.11.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.12.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.12.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.12.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.13.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.13.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.13.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.14.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.14.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.14.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.15.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.15.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.15.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.16.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.16.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.16.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.17.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.17.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.17.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.18.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.18.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.18.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.19.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.19.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.19.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.20.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.20.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.20.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.21.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.21.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.21.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.22.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.22.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.22.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.23.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.23.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.23.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.24.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.24.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.24.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.25.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.25.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.25.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.26.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.26.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.26.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.27.self_attn.q_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.self_attn.k_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.self_attn.v_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.self_attn.o_proj": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.mlp.gate_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.27.mlp.down_proj": {
            "group_size": 64,
            "bits": 4
        },
        "model.layers.27.mlp.up_proj": {
            "group_size": 64,
            "bits": 4
        }
    },
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
        "interleaved": true,
        "mrope_interleaved": true,
        "mrope_section": [
            24,
            20,
            20
        ],
        "rope_type": "default",
        "type": "default"
    },
    "rope_theta": 1000000,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 151936
}