{
  "architectures": [
    "MobilintQwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "proxy_qwen2.MobilintQwen2Config",
    "AutoModelForCausalLM": "proxy_qwen2.MobilintQwen2ForCausalLM"
  },
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 16384,
  "max_window_layers": 70,
  "model_type": "mobilint-qwen2",
  "mxq_path": "Qwen2.5-3B-Instruct-W4V8.mxq",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "target_cores": [
    "0:0"
  ],
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "npu_prefill_chunk_size": {
    "global4": 512,
    "global8": 1024,
    "single": 512
  },
  "max_batch_size": 1
}