[BUG] 简洁阐述[BUG] 当使用LLaMA-Factory 使用.bin格式训练合并之后的模型，然后使用langchain-chatchat，加载训练的模型出现TypeError: PeftConfig.__init__() got an unexpected keyword argument '_name_or_path'问题 / Concise description of the issue

[caijx168]

[BUG] 简洁阐述[BUG] 当使用LLaMA-Factory 使用.bin格式训练合并之后的模型，然后使用langchain-chatchat，加载训练的模型出现TypeError: PeftConfig.init() got an unexpected keyword argument '_name_or_path'问题 / Concise description of the issue

[dosubot]

To address the TypeError: PeftConfig.__init__() got an unexpected keyword argument '_name_or_path' error when loading a model with langchain-chatchat, follow these steps:

1. Verify Library Versions: Ensure the library version for loading the model matches the model's requirements. Incompatibilities often lead to such errors.

2. Inspect Model Loading Code: Check the code for loading the model to ensure the arguments passed match the expected parameters of PeftConfig.

3. Consult Documentation: Review the documentation for the model loading library to understand the correct way to load models and the expected arguments.

4. Update or Adjust Library Code: If using a custom or outdated library, update to the latest version or adjust the code to meet the model's loading requirements.

5. Community Support: If unresolved, seek advice from community forums or channels related to langchain-chatchat or the model loading library for specific guidance.

Sources

• lora训练合并后的模型无法像上个版本一样使用
• knowledge_base/samples/content/test_files/langchain-ChatGLM_open.jsonl
• configs/model_config.py.example
• configs/init.py
• requirements.txt

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[TC10127]

不能直接把config.json文件名字改成adapter_config.json