ccly1996
ccly1996
hello，excuse me, could you display your requirements details?thank you
emmm, I am deploying this code, but wrong happened when i install requirements, can you help me?The author may write something wrong in requirements, so i need requirements list.😂
thanks,i install these requirements ,but something wrong.
the wrong is from torchvision, when i import torchvision.models.i think this wrong from the version of torchvision, but the author did not note that.
> what's your LLM_MODEL in .env, and can you show your curl example to access your Qwen llm service? this is example  LLM_MODEL in .env is proxyllm
> check your `PROXY_SERVER_URL` in .env, and you can debug what base_url in dbgpt/model/proxy/llms/chatgpt.py . i use the same PROXY_SERVER_URL in between .env and curl,but also appear the openai.APIConnectionError: Connection...
we test the effect of cogvlm2 is perfect
> 您好，执行“bash ./scripts/test_inference_quantized.sh 0 ./tests/test_prompt.txt”， 请问这个怎么处理呢 File "/opt/conda/envs/python38/lib/python3.8/site-packages/codegeex-1.0-py3.8.egg/codegeex/kernels/**init**.py", line 15, in **init** raise RuntimeError("File `%s` not found in `%s`" % (filename, RESOURCE_PACKAGE_NAME)) RuntimeError: File `quantization.fatbin` not found in `codegeex.kernels` 我也是这个问题，请问你解决了吗
> > 解决了就好哈哈 我也碰到这个问题了，重装了也不行 
Can codexgraph support locally deployed models?