Florian Euler comments

Repositories
Issues
Comments

Results 5 comments of


                                            Florian Euler

Document how to use specific LLMs

I use oobabooga with the openai compatible api. And currently trying OpenCodeInterpreter-DS-33B (exl2) as model first. I'm not aware which non-openai/claude model works best yet... config.toml: WORKSPACE_DIR="./workspace" LLM_API_KEY="sk-111111111111111111111111111111111111111111111111" LLM_BASE_URL="http://127.0.0.1:5000" LLM_EMBEDDING_MODEL="local"...

[Bug] Llama 3.1 Support

> I was able to create a chat template myself and got it working. Can you maybe share it ?

Stuck in a loop using ollama/llama2

Try using another model. I'm currently using "OpenCodeInterpreter-DS-33B" and it worked (more or less). Other options could be "CodeFuse-DeepSeek-33b" or "Phind-CodeLlama-34B-v2" See: https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard

LLM_MODEL not updated

I have the same issue.

Added support for NVIDIA GeForce RTX 4090

Can someone please merge this ?