Tom Dörr

icon indicating a website link https://meta.stackoverflow.com/users/6105651/tom-d%c3%b6rr?tab=profile icon indicating an email [email protected]

Results 187 comments of Tom Dörr

Failed to parse JSON response: {"detail":"Not Found"}

Doesn't happen when I switch the model to `astronomer/Llama-3-8B-Instruct-GPTQ-8-Bit` ``` python3 -m vllm.entrypoints.openai.api_server --model astronomer/Llama-3-8B-Instruct-GPTQ-8-Bit --quantization gptq --tensor-parallel-size 1 --port 38242 --gpu-memory-utilization 0.8 --dtype float16 ```

Failed to parse JSON response: {"detail":"Not Found"}

Now I'm getting a `BadRequestError` again. Maybe the vllm server just blocked me because I was senden that many bad request errors earlier. ``` Creating basic bootstrap: 1/9 2%|▊ |...

Failed to parse JSON response: {"detail":"Not Found"}

Getting the same "Not found" error again, but only after the MIPRO bootstraping phase.

TypeError: cannot pickle 'module' object - teleprompter.compile

Similar issue: https://github.com/stanfordnlp/dspy/issues/1011

Can not run tecoGAN-master folder on my anaconda navigator

You could use my docker setup to avoid installation issues: https://github.com/tom-doerr/TecoGAN

Allow OPTIONS Method on Http Server and add Cors headers.

Could you send the server log? I think I got that error when it didn't finish loading the model.

[NO ISSUE] Guidance fork is alive and well.

Do you mean running the code in this repo failed?

[NO ISSUE] Guidance fork is alive and well.

@lopugit It worked for you, right?

feat: update docs and allow specifying temperature

There seem to be merge conflicts

feat: update docs and allow specifying temperature

Thank you, that should improve usefulness a lot