{
    "architectures": [
        "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 8192,
    "initializer_range": 0.02,
    "intermediate_size": 29568,
    "max_position_embeddings": 32768,
    "max_window_layers": 70,
    "model_type": "qwen2",
    "num_attention_heads": 64,
    "num_hidden_layers": 80,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "sliding_window": 131072,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.43.1",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 152064,
    "quantize": "w8a8",
    "quantization_config": {
        "group_size": 0,
        "kv_quant_type": null,
        "fa_quant_type": null,
        "w_bit": 8,
        "a_bit": 8,
        "dev_type": "npu",
        "fraction": 0.01,
        "act_method": 1,
        "co_sparse": false,
        "anti_method": "",
        "disable_level": "L0",
        "do_smooth": false,
        "use_sigma": false,
        "sigma_factor": 3.0,
        "is_lowbit": false,
        "mm_tensor": false,
        "w_sym": true,
        "open_outlier": true,
        "is_dynamic": false
    }
}