[BUG] 简洁阐述问题 /怎么加载ChatGLM-6B微调出来的模型

[LGghost]

问题描述 /怎么加载ChatGLM-6B微调出来的模型

你好，我现在通过ChatGLM-6B的chatglm-6b模型在加上自己的数据微调出了一个adgen-chatglm-6b-pt-45，我现在想吧这个也使用到[Langchain-Chatchat上来，请问我需要这么修改

[dosubot[bot]]

你好，@LGghost！我是 Dosu，一个友好的机器人，随时准备帮助你解决问题、回答问题，甚至成为一个贡献者。我在这里提供帮助，同时等待人类维护者的回应。现在，我将开始查看你的问题，并很快给你一个完整的答复。

[LGghost]

好的，请问我该这么把ChatGLM-6B的chatglm-6b模型在这个上面使用

[LGghost]

自己微调的数据

[dosubot[bot]]

To use your fine-tuned adgen-chatglm-6b-pt-45 model with Langchain-Chatchat, follow these steps:

1. Update Model Configuration: Add your model to configs/model_config.py under LLM_MODELS and specify its path or identifier in MODEL_PATH like so:

LLM_MODELS = ["chatglm3-6b", "zhipu-api", "openai-api", "adgen-chatglm-6b-pt-45"]
MODEL_PATH = {
    "llm_model": {
        "adgen-chatglm-6b-pt-45": "path_or_identifier_for_adgen-chatglm-6b-pt-45",
    },
}

Replace "path_or_identifier_for_adgen-chatglm-6b-pt-45" with the actual path or identifier of your model.

2. Manage Models via Endpoints: Use the provided endpoints (/llm_model/list_config_models, /llm_model/change, /llm_model/get_model_config) to manage and switch to your model. Ensure it's listed and properly configured before making chat requests.

3. Integration and Testing: After switching to your model, test the chat functionality to ensure it works as expected. Adjust configurations as needed based on the test outcomes.

4. Deployment: Once satisfied with the testing, proceed to deploy your changes, making sure all model dependencies are correctly set up.

This guide assumes familiarity with Langchain-Chatchat's structure and model management. For detailed implementation, refer to the Langchain-Chatchat repository.

Details

Sources

• 在线embedding的使用
• 微调模型的导入
• 使用模型chatglm3-6b,如何在langchain-chatchat交互中调用到chatglm3-6b自定义的function，请提供实例
• 使用模型chatglm3-6b,如何在langchain-chatchat交互中调用到chatglm3-6b自定义的function，请提供实例
• 使用模型chatglm3-6b,如何在langchain-chatchat交互中调用到chatglm3-6b自定义的工具（function calling），请提供实例
• V0.2.4以上版本如何加载ptunig-v2的微调模型？
• [FEATURE] 如何接入CustomLLM？
• [询问帖] 我该如何在该项目使用ChatGLM-LoRA呢
• server/api.py
• README_en.md
• configs/model_config.py.example
• server/llm_api.py
• tests/test_online_api.py
• server/agent/custom_agent/ChatGLM3Agent.py
• knowledge_base/samples/content/test_files/langchain-ChatGLM_closed.jsonl
• knowledge_base/samples/content/test_files/langchain-ChatGLM_open.jsonl

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.

To continue the conversation, mention @dosu.

[zRzRzRzRzRzRzR]

查看wiki