OpenGVLab

/

InternVL-Chat-V1-5-AWQ

like 10

The lmdeploy official docker is also failing to start this model "ModuleNotFoundError: No module named 'timm'"

Try to install a timm?

Like this:

pip install timm==0.9.12

I did try that, I got new errors.

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.                                                                                                                    
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
  File "/opt/py38/bin/lmdeploy", line 11, in <module>
    load_entry_point('lmdeploy', 'console_scripts', 'lmdeploy')()
  File "/opt/lmdeploy/lmdeploy/cli/entrypoint.py", line 37, in run
    args.run(args)
  File "/opt/lmdeploy/lmdeploy/cli/serve.py", line 303, in api_server
    run_api_server(args.model_path,
  File "/opt/lmdeploy/lmdeploy/serve/openai/api_server.py", line 1191, in serve
    VariableInterface.async_engine = pipeline_class(
  File "/opt/lmdeploy/lmdeploy/serve/vl_async_engine.py", line 21, in __init__
    super().__init__(model_path, **kwargs)
  File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 206, in __init__
    self._build_turbomind(model_path=model_path,
  File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 253, in _build_turbomind
    self.engine = tm.TurboMind.from_pretrained(
  File "/opt/lmdeploy/lmdeploy/turbomind/turbomind.py", line 387, in from_pretrained
    return cls(model_path=pretrained_model_name_or_path,
  File "/opt/lmdeploy/lmdeploy/turbomind/turbomind.py", line 161, in __init__
    self.model_comm = self._from_hf(model_source=model_source,
  File "/opt/lmdeploy/lmdeploy/turbomind/turbomind.py", line 270, in _from_hf
    output_model = OUTPUT_MODELS.get(output_format)(
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/target_model/fp.py", line 26, in __init__
    super().__init__(input_model, cfg, to_file, out_dir)
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/target_model/base.py", line 156, in __init__
    self.cfg = self.get_config(cfg)
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/target_model/fp.py", line 38, in get_config
    w1, _, _ = bin.ffn(i)
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/source_model/internlm2.py", line 69, in ffn
    return self._ffn(i, 'weight')
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/source_model/internlm2.py", line 62, in _ffn
    tensor = self.params[
KeyError: 'language_model.model.layers.0.feed_forward.w1.weight'

I would still also prefer to run it directly without lmdeploy if possible, thanks!

I did try that, I got new errors.

Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.                                                                                                                    
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
  File "/opt/py38/bin/lmdeploy", line 11, in <module>
    load_entry_point('lmdeploy', 'console_scripts', 'lmdeploy')()
  File "/opt/lmdeploy/lmdeploy/cli/entrypoint.py", line 37, in run
    args.run(args)
  File "/opt/lmdeploy/lmdeploy/cli/serve.py", line 303, in api_server
    run_api_server(args.model_path,
  File "/opt/lmdeploy/lmdeploy/serve/openai/api_server.py", line 1191, in serve
    VariableInterface.async_engine = pipeline_class(
  File "/opt/lmdeploy/lmdeploy/serve/vl_async_engine.py", line 21, in __init__
    super().__init__(model_path, **kwargs)
  File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 206, in __init__
    self._build_turbomind(model_path=model_path,
  File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 253, in _build_turbomind
    self.engine = tm.TurboMind.from_pretrained(
  File "/opt/lmdeploy/lmdeploy/turbomind/turbomind.py", line 387, in from_pretrained
    return cls(model_path=pretrained_model_name_or_path,
  File "/opt/lmdeploy/lmdeploy/turbomind/turbomind.py", line 161, in __init__
    self.model_comm = self._from_hf(model_source=model_source,
  File "/opt/lmdeploy/lmdeploy/turbomind/turbomind.py", line 270, in _from_hf
    output_model = OUTPUT_MODELS.get(output_format)(
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/target_model/fp.py", line 26, in __init__
    super().__init__(input_model, cfg, to_file, out_dir)
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/target_model/base.py", line 156, in __init__
    self.cfg = self.get_config(cfg)
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/target_model/fp.py", line 38, in get_config
    w1, _, _ = bin.ffn(i)
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/source_model/internlm2.py", line 69, in ffn
    return self._ffn(i, 'weight')
  File "/opt/lmdeploy/lmdeploy/turbomind/deploy/source_model/internlm2.py", line 62, in _ffn
    tensor = self.params[
KeyError: 'language_model.model.layers.0.feed_forward.w1.weight'

Can you provide more details including test code and environment configuration?

I would still also prefer to run it directly without lmdeploy if possible, thanks!

Our awq model is generated by lmdeploy. If you want to use autoawq integrated by transformers, you need to make sure that the autoawq library supports our model.