OpenGVLab

/

InternVL3_5-8B

like 81

Follow

OpenGVLab 1.66k

I encountered this error when load the 8B model with lmdeploy v0.9.2.post1.

  File "utils/internvl_utils.py", line 60, in batch_generate_with_lmd
    _cached_lmdeploy_pipeline = pipeline(
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/api.py", line 83, in pipeline
    return pipeline_class(model_path,
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/serve/vl_async_engine.py", line 32, in __init__
    super().__init__(model_path, backend=backend, backend_config=backend_config, **kwargs)
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/serve/async_engine.py", line 284, in __init__
    self._build_turbomind(model_path=model_path, backend_config=backend_config, **kwargs)
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/serve/async_engine.py", line 338, in _build_turbomind
    self.engine = tm.TurboMind.from_pretrained(model_path,
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 386, in from_pretrained
    return cls(model_path=pretrained_model_name_or_path,
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 159, in __init__
    self._load_weights(model_source)
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/turbomind/turbomind.py", line 178, in _load_weights
    self._tm_model.export()
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/turbomind/deploy/target_model/base.py", line 210, in export
    for i, reader in self.input_model.readers():
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/turbomind/deploy/source_model/llama.py", line 113, in readers
    reader = self.Reader(param, {}, False, self.model_config, policy=self.policy)
  File ".env/miniconda3/envs/lmdeploy/lib/python3.10/site-packages/lmdeploy/turbomind/deploy/source_model/internvl.py", line 64, in __init__
    raise ValueError(f'Miss "text_config" in model config: {model_cfg}')
ValueError: Miss "text_config" in model config: None

            from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig, GenerationConfig
            backend_config = TurbomindEngineConfig(
                session_len=16384, tp=tp, dp=dp
            )
            chat_template_config = ChatTemplateConfig(
                model_name='internvl2_5'
            )
            _cached_lmdeploy_pipeline = pipeline(
                model_path,
                backend_config=backend_config,
                chat_template_config=chat_template_config,
            )

The same code works pretty well for Internvl3.5 38B model, but cannot load 8B model.

Is there any missing config files or something?