config.json

{
    "architectures": [
        "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "initializer_range": 0.02,
    "intermediate_size": 27648,
    "max_position_embeddings": 32768,
    "max_window_layers": 64,
    "model_type": "qwen2",
    "num_attention_heads": 40,
    "num_hidden_layers": 64,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "sliding_window": 131072,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.43.1",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 152064,
    "quantization_config": {
        "quant_method": "exl2",
        "version": "0.2.4",
        "bits": 7.0,
        "head_bits": 6,
        "calibration": {
            "rows": 115,
            "length": 2048,
            "dataset": "(default)"
        }
    }
}