schauppi comments

Results 11 comments of


                                            schauppi

Which version is ready for Mac with M1 Apple Silicon Chip?

@Jiahui-Bai´s solution worked for me - THX!

stopping_strings not working for me

Do not work for me either. Edit: NVM: Wrong formatting. With the stable-vicuna-13B-GPT model the following works for me: 'stopping_strings': ["\n###"],

Suddenly 403 Forbidden

Same issue here... 403 Forbidden

QLora Support

> Hello, > > Wondering if you got any insights on what would be the inference performance of bitsandbytes 4bit compared to 8bit. Will it be any better? In my...

[web search] An error occurred with the web search "Invalid inference output: Expected Array<{generated_text: string}>. Use the 'request' method with the same parameters to do a custom call with no type checking."

> It seems to fix the problem, if you omit the `/generate_stream` in the url in the definition of the model in the .env file. This means that the configuration...

Failed to find service port for display

Same issue on Mac M1. open3d 0.11.2 and python 3.8.13.

Need ability to send multiple files in one go

> Yes, I agree that the ability to send multiple files at once will be awesome and it's in the TODO list. Basically, we need some bookkeeping in addition. In...

[BUG] Arguments validation failed: 2 validation errors for DelegateWorkToolSchema

I have the same problem using 4o-mini.

first tests for dropdown

@afourney

BatchedInferencePipeline degrades transcription quality heavily

same here