zxjyes

Results 11 comments of zxjyes

I also have this problem: Max retries exceeded with url: /v1/chat/completions I use python3.8 and python 3.9.

我把图片的路径该到了本地,如下所示 ![image](https://github.com/user-attachments/assets/354c06ae-8352-42ab-ad77-336253b70b60) 但是gradio的网页中也不显示图片,我自己写的一个gradio ![image](https://github.com/user-attachments/assets/c8c1ded6-8666-4250-bf4d-8c8b9590aca2)

我也遇到这个问题,按照版本安装的 ![Image](https://github.com/user-attachments/assets/bc733f39-0cc4-4b0d-830c-ffb231accd77) ![Image](https://github.com/user-attachments/assets/b9f65123-7b85-42dc-bf44-6945bc219eec) ![Image](https://github.com/user-attachments/assets/47684e16-3355-4cee-a588-83ed1da39584) ![Image](https://github.com/user-attachments/assets/a74814b8-ee6c-4e5d-95d8-81e5f9ebc21c)

> llama-3.1-8B-instruct有同样的问题 我本地微调llama3-8b也这样

> easy to handle, \bert_score\score.py this file,change the line 95 , ` if num_layers is None: num_layers = model2layers[model_type]` to ` if num_layers is None: # 如果 model_type 是路径,则截取最后一个/后的字符串 if...

I try the other embedding models,it is solved. I really want to know the principles for choosing embedding models.

> I try the other embedding models,it is solved. I really want to know the principles for choosing embedding models. Today I tried to use nomic-embed-text:latest as an embedding model...

I've tried other files and I've noticed that some files will upload and some won't, is there a requirement for the file?

> It would appear that if that specific model is not working that the result object is incorrect. Are you able to embed text via Ollama's API directly - it...