{
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "model_type": "qwen2",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}

Traceback (most recent call last):
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/model.py", line 28, in initialize
    return self.python_model.initialize(config)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/model_wrapper/standard_model.py", line 28, in initialize
    self.generator = Generator(
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/generator.py", line 41, in __init__
    self.generator_backend = get_generator_backend(model_config)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/__init__.py", line 17, in get_generator_backend
    return generator_cls(model_config)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_torch.py", line 16, in __init__
    super().__init__(model_config)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/text_generator/adapter/generator_backend.py", line 17, in __init__
    self.model_wrapper = get_model_wrapper(model_config, backend_type)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/__init__.py", line 16, in get_model_wrapper
    return wrapper_cls(**model_config)
  File "/usr/local/python3.10.2/lib/python3.10/site-packages/mindie_llm/modeling/model_wrapper/atb/atb_model_wrapper.py", line 36, in __init__
    self.model_runner.load_weights()
  File "/usr/local/Ascend/llm_model/atb_llm/runner/model_runner.py", line 84, in load_weights
    self.model = self.model_cls(self.config, weights)
  File "/usr/local/Ascend/llm_model/atb_llm/models/qwen2/flash_causal_qwen2.py", line 27, in __init__
    self.lm_head = load_column_multi(
  File "/usr/local/Ascend/llm_model/atb_llm/utils/layers/__init__.py", line 38, in load_column_multi
    weight = weights.get_multi_weights_col(prefixes, quantize=quantize, dim=0, gqa_size=head_size)
  File "/usr/local/Ascend/llm_model/atb_llm/utils/weights.py", line 515, in get_multi_weights_col
    w = [self.get_sharded(f"{p}.weight", dim=0, gqa_size=gqa_size) for p in prefixes]
  File "/usr/local/Ascend/llm_model/atb_llm/utils/weights.py", line 515, in <listcomp>
    w = [self.get_sharded(f"{p}.weight", dim=0, gqa_size=gqa_size) for p in prefixes]
  File "/usr/local/Ascend/llm_model/atb_llm/utils/weights.py", line 203, in get_sharded
    slice_ = self._get_slice(tensor_name)
  File "/usr/local/Ascend/llm_model/atb_llm/utils/weights.py", line 561, in _get_slice
    filename, tensor_name = self.get_filename(tensor_name)
  File "/usr/local/Ascend/llm_model/atb_llm/utils/weights.py", line 80, in get_filename
    raise AssertionError(f"weight {tensor_name} does not exist")
AssertionError: weight lm_head.weight does not exist