Tom Himanen

@genieai-info: max_tokens sets the length of output, right? Is there any setting that defines how long piece of previous conversation is included? In longer conversations GPT often gets derailed and...

I'm also interested. Haven't found any myself. I already replaced Github Co-Pilot's AI-powered code completion with Starcoder LLM (huggingface-vscode). But would love to use Genie AI powered by Starcoder LLM...

I'm also interested in setting a finetuned Whisper model from Huggin Face ([Finnish-NLP/whisper-large-v2-finnish](https://huggingface.co/Finnish-NLP/whisper-large-v2-finnish)). If someone figures out how to do it, please let us know!

Just as an update, I talked with NixOS guys and the optimal NixOS way to do this would be building the server on NixOS and providing that endpoint to the...

Thanks @McPatate! I managed to create a working derivation and at the moment I'm using llm-ls with llm-vscode on VSCodium running on NixOS. I have never submitted a derivation to...

> > Which python version are you using? I just tried pipx on 3.12 and I had no issues installing. > > python 3.12 failed for me as well, same...

@tanadech789 You might wanna try this version of Deepseek R1: https://ollama.com/tom_himanen/deepseek-r1-roo-cline-tools:32b There are different model sizes available. If you have enough VRAM, it should work. Especially large tasks require lots...

I was wondering the same. It would definitely make sense to be able to define OPENAI_API_KEY in config.yaml like this: ``` OPENAI_API_KEY: "ignore" ``` The OpenAI compatible model configuration is...

Also I am facing this same error when using local Devstral as model and local full-size Deepseek as expert model. RA.Aid seemed to be able to do programming but those...