quivr VS xTuring

3. Quivr | GitHub | tutorial

I used Ollama (with Mistral 7B) and Quivr to get a local RAG up and running and it works fine, but was surprised to find there are no easy user-friendly ways to do it. Most other local LLM UIs don't implement this use case (I looked here), even though it is one of the most useful local LLM use-cases I can think of: search and summarize information from sensitive / confidential documents.

In my opinion LLM based document search tools such as OSS Quivr may be better suited for documentation search for startups.

A highly customed Quivr with one of the 'Open Source LLMs' may provides great 'semantic search' for product documentation.

https://github.com/StanGirard/quivr

Hey thanks for creating this, will try later if i have time. Meanwhile, do you try some of other second brain app such as this, and how was the comparison? The one i mentioned was trending on github so i think its decent (been playing with it since last week or so, also). But i already starred your repo so i can come back later.

Explore the project on GitHub here.

If you're curious, I encourage you to: - Dive deeper with the LLaMA 2 tutorial here. - Explore the project on GitHub here. - Connect with our community on Discord here.

If you want best performance, you need to do both RAG and fine-tuning very well. There are plenty of resources on doing fine-tuning thought. I'm one of the contributors to https://github.com/stochasticai/xturing project focused on fine-tuning LLMs. You can find help in the discord channel listed on the GitHub.

What tools do you use and achieved great results ? … For me i have tried xturing and SFTTrainer and they got me a semi okay results.

Code: https://github.com/stochasticai/xTuring/blob/main/examples/llama/llama_lora_int8.py Colab: https://colab.research.google.com/drive/1SQUXq1AMZPSLD4mk3A3swUIc6Y2dclme?usp=sharing

We are a group of researchers out of Harvard working on open-source library called xTuring, focused on fine-tuning LLMs: https://github.com/stochasticai/xturing.

Fine tuning I was thinking about using this (low GPU memory footprint): https://github.com/stochasticai/xturing/blob/main/examples/int4_finetuning/README.md

I can't speak for QLORA, as I haven't had a chance to get an implementation working, but I've had success with StochasticAI's Xturing. It's by far the most streamlined method of finetuning I've come across, and they offer int8 and int4 fintuning (but only for llama-7B).