Mac设备问题解决

[lijiaxing1997]

我在mac m4 pro上使用 weclone-cli make-dataset 出现以下错误 聊天记录是在windows上导出来的。

Traceback (most recent call last):
  File "/opt/homebrew/anaconda3/envs/weclone/bin/weclone-cli", line 8, in <module>
    sys.exit(cli())
  File "/opt/homebrew/anaconda3/envs/weclone/lib/python3.10/site-packages/click/core.py", line 1442, in __call__
    return self.main(*args, **kwargs)
  File "/opt/homebrew/anaconda3/envs/weclone/lib/python3.10/site-packages/click/core.py", line 1363, in main
    rv = self.invoke(ctx)
  File "/opt/homebrew/anaconda3/envs/weclone/lib/python3.10/site-packages/click/core.py", line 1830, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/opt/homebrew/anaconda3/envs/weclone/lib/python3.10/site-packages/click/core.py", line 1226, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/opt/homebrew/anaconda3/envs/weclone/lib/python3.10/site-packages/click/core.py", line 794, in invoke
    return callback(*args, **kwargs)
  File "/Users/macbookpro/AI/WeClone/weclone/cli.py", line 26, in wrapper
    return func(*args, **kwargs)
  File "/Users/macbookpro/AI/WeClone/weclone/cli.py", line 47, in qa_generator
    processor.main()
  File "/Users/macbookpro/AI/WeClone/weclone/data/qa_generator.py", line 98, in main
    self.clean_strategy.judge(qa_res)
  File "/Users/macbookpro/AI/WeClone/weclone/data/clean/strategies.py", line 46, in judge
    outputs = infer(
  File "/Users/macbookpro/AI/WeClone/weclone/core/inference/vllm_infer.py", line 61, in infer
    raise ValueError("Pipeline parallel size should be smaller than the number of gpus.")
ValueError: Pipeline parallel size should be smaller than the number of gpus.

[aku12138]

我也是，解决了吗？

[xming521]

• vllm还不支持mac，配置里的enable_clean设为false，不清洗数据集
• fp16 关掉

[stopium]

windows也遇到了这个问题。

1. enable_clean = false
2. fp16=false
3. cuda.py 注释掉了 import vllm._C

[hotstar-xia]

如果用google colab会不会好跑一些