{
  "_name_or_path": "/models/Qwen2-0.5B-Instruct",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 896,
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 14,
  "num_hidden_layers": 24,
  "num_key_value_heads": 2,
  "quantization_config": {
    "autoround_version": "0.2.1.dev",
    "bits": 4,
    "damp_percent": 0.01,
    "desc_act": false,
    "enable_minmax_tuning": true,
    "enable_quanted_input": true,
    "group_size": 32,
    "is_marlin_format": false,
    "iters": 1000,
    "lr": 0.001,
    "minmax_lr": 0.002,
    "model_file_base_name": "model",
    "model_name_or_path": null,
    "quant_method": "gptq",
    "scale_dtype": "float16",
    "static_groups": false,
    "sym": true,
    "true_sequential": false
  },
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}