Cao Zhi Hui comments

Results 10 comments of


                                            Cao Zhi Hui

Trace: InternalServerErrorException: InvalidBrowserConnection

this is ws://localhost:8080 , Do we have to start this ourselves

可以加QQ联系吗 229555644

老板在不在

I use Apple mlx lora tainer to fine-tune qwen3 8b. It will always output {{{{{{{{{{{{{{{{{{{ It seems that it does not match the end character.

https://github.com/QwenLM/Qwen3/issues/198

I use Apple mlx lora tainer to fine-tune qwen3 8b. It will always output {{{{{{{{{{{{{{{{{{{ It seems that it does not match the end character.

why , So I have a chat dataset. How should I write it? How should I make a chat dataset?

I use Apple mlx lora tainer to fine-tune qwen3 8b. It will always output {{{{{{{{{{{{{{{{{{{ It seems that it does not match the end character.

thank you

I use Apple mlx lora tainer to fine-tune qwen3 8b. It will always output {{{{{{{{{{{{{{{{{{{ It seems that it does not match the end character.

i use ' mlx_lm.lora --model /Users/caozhihui/ai_model/Qwen/Qwen3-8B --train --data ./data' try it again and see if there is no problem

I use Apple mlx lora tainer to fine-tune qwen3 8b. It will always output {{{{{{{{{{{{{{{{{{{ It seems that it does not match the end character.

![Image](https://github.com/user-attachments/assets/fd30ca5c-7f35-46bc-a959-82fbac23ecd8) I used mlx_lm.lora command to fine-tune , and then imported the fused model into transformerLab , and it output what I wanted, but when I asked the same question...

I use Apple mlx lora tainer to fine-tune qwen3 8b. It will always output {{{{{{{{{{{{{{{{{{{ It seems that it does not match the end character.

https://github.com/ml-explore/mlx-lm Is this added?

[BUG]I use mlx_lm.lora --model /Users/caozhihui/ai_model/Qwen/Qwen3-8B --train --data ./data to fine-tune. After fine-tuning, the model will directly reply <|endoftext|> after multiple rounds of inquiries.

![Image](https://github.com/user-attachments/assets/ce41c4f8-a11d-41fc-8974-70b400891484)