config.json

{
    "architectures": [
        "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoModel": "modeling_qwen.Qwen2Model",
        "AutoModelForCausalLM": "modeling_qwen.Qwen2ForCausalLM",
        "AutoModelForSequenceClassification": "modeling_qwen.Qwen2ForSequenceClassification"
    },
    "bos_token_id": 151643,
    "eos_token_id": 151643,
    "hidden_act": "silu",
    "hidden_size": 1536,
    "initializer_range": 0.02,
    "intermediate_size": 8960,
    "is_causal": false,
    "max_position_embeddings": 131072,
    "max_window_layers": 21,
    "model_type": "qwen2",
    "num_attention_heads": 12,
    "num_hidden_layers": 28,
    "num_key_value_heads": 2,
    "quantization": {
        "group_size": 64,
        "bits": 6,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 6,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "sliding_window": 131072,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "transformers_version": "4.41.2",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151646
}