明君非

使用部署服务，但是在访问OPENAI过程中遇到如下问题。

1

**例行检查** **问题描述** ``` openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid value for 'content': expected a string, got null. (request id: 20231206054444375592893PDWPRFyf)", 'type': 'invalid_request_error', 'param': 'messages.[1].content', 'code': None}} ``` 代码，这个码是官方案例代码。...

正常启动，过程发现报错，如下，应该是这个文件不存在。cache_file_popup_url

3

AssertionError Traceback (most recent call last): File "/Users/luxi.lm/opt/miniconda3/envs/Etuning/lib/python3.8/site-packages/gradio/routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "/Users/luxi.lm/opt/miniconda3/envs/Etuning/lib/python3.8/site-packages/gradio/blocks.py", line 1435, in process_api result = await self.call_function( File "/Users/luxi.lm/opt/miniconda3/envs/Etuning/lib/python3.8/site-packages/gradio/blocks.py", line 1121,...

v100部署出现如下问题。挺奇怪，cutlassF: no kernel found to launch!

2

03/19 21:17:01 llm_wrapper.py:msg:55 Caught an exception: RuntimeError: cutlassF: no kernel found to launch! Traceback (most recent call last): File "/home/admin/workspace/aop_lab/app_source/llm_wrapper.py", line 43, in msg response, usage = await self.call(messages_, **kwargs)...

请问作者是否意愿实现qlora.

1

请问作者是否意愿实现qlora。

Can you choose which GPU to use. like tf inference device_map="cuda:0"

8

As the title suggests