Open jtoy opened 8 months ago
I think the whole point of this project is to allow local LLM via ollama to be run easily.
You can use an LLM Gateway for such usecases. Mine should work for that use case also: https://github.com/adrianliechti/llama
Enchanted Settings:
LLM Platform Config:
config.yaml
providers:
- type: groq
token: ${GROQ_API_TOKEN}
models:
llama3-70b-instruct:
id: llama3-70b-8192
mixtral-8x7b-instruct:
id: mixtral-8x7b-32768
I dont think it makes sense to support tons of other models, but since groq is 10x faster and has free api keys to mixtral at 30 reqs a minute, I think worth it :) https://groq.com/