{
    "architectures": [
        "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151643,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 27648,
    "max_position_embeddings": 131072,
    "max_window_layers": 64,
    "model_type": "qwen2",
    "num_attention_heads": 40,
    "num_hidden_layers": 64,
    "num_key_value_heads": 8,
    "quantization_config": {
        "config_groups": {
            "group_0": {
                "input_activations": {
                    "dynamic": false,
                    "num_bits": 8,
                    "strategy": "tensor",
                    "type": "float"
                },
                "output_activations": null,
                "targets": [
                    "Linear"
                ],
                "weights": {
                    "dynamic": false,
                    "num_bits": 8,
                    "strategy": "tensor",
                    "type": "float"
                }
            }
        },
        "format": "naive-quantized",
        "kv_cache_scheme": null,
        "quant_method": "compressed-tensors",
        "quantization_status": "compressed",
        "ignored_layers": [
            "lm_head",
            "model.embed_tokens"
        ]
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": 131072,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.51.3",
    "use_cache": false,
    "use_sliding_window": false,
    "vocab_size": 152064
}