model
#1
by
rakmik
- opened
Please specify a llm model and a embading model so they can give the best answer, or maybe from anyone who has tried it.
Please specify a llm model and a embading model so they can give the best answer, or maybe from anyone who has tried it.
- Update: I’ve switched the LLM to
google_gemma-3-1b-it-Q8_0.gguf
and the embedding model toAlibaba-NLP/gte-multilingual-base
. - I opted for smaller models due to limited CPU resources.
- Note: Since the original repository broke, I’ve created a new one here: https://huggingface.co/spaces/sergey21000/chatbot-rag.