hallucination-leaderboard VS h2ogpt

To checkout the Hallucination leaderboard click here

Nice to see yet another open source approach to LLM/RAG. For those who do not want to meddle with the complexity of do-it-youself, Vectara (https://vectara.com) provides a RAG-as-a-service approach - pretty helpful if you want to stay away from having to worry about all the details, scalability, security, etc - and just focus on building your RAG application.

Check this leaderboard, it is specific for RAG use case: https://github.com/vectara/hallucination-leaderboard

You should also check us out (https://vectara.com) - we provide RAG as a service so you don't have to do all the heavy lifting and putting together the pieces yourself.

Llama 2 (and variants). Has the lowest hallucination rate (https://github.com/vectara/hallucination-leaderboard), and its open source and so we know what went into it, and the community can improve it

This is just typical of so much work in the field. They pick and choose which models to compare against and on which benchmarks. If this model was truly great, they would be comparing against Claude 2 and GPT4 across a bunch of different benchmarks. Instead they compare against Palm 2, which in a lot of tests is a weak model (https://venturebeat.com/ai/google-bard-fails-to-deliver-on-i....) and prone to hallucination (https://github.com/vectara/hallucination-leaderboard).

As others have said you want RAG.

The most feature complete implementation I've seen is h2ogpt[0] (not affiliated).

The code is kind of a mess (most of the logic is in an ~8000 line python file) but it supports ingestion of everything from YouTube videos to docx, pdf, etc - either offline or from the web interface. It uses langchain and a ton of additional open source libraries under the hood. It can run directly on Linux, via docker, or with one-click installers for Mac and Windows.

It has various model hosting implementations built in - transformers, exllama, llama.cpp as well as support for model serving frameworks like vLLM, HF TGI, etc or just OpenAI.

You can also define your preferred embedding model along with various other parameters but I've found the out of box defaults to be pretty sane and usable.

[0] - https://github.com/h2oai/h2ogpt

Here's the links: https://github.com/h2oai/h2ogpt/blob https://github.com/h2oai/h2ogpt/blob/main/docs/README_LangChain.md

Take a look at h2ogpt. It's open and local with API (incoming and outgoing) and impressive feature set, including RAG from docs, images, and web search.

I've stumbled upon h2ogptas a potential starting point. Are there better solutions or repositories that can meet these requirements?

Any recommendations for an open source repos that support web based chat ui where you can upload docs,pds,links,etc? So far i found https://github.com/openchatai/OpenChat but it doesnt support llama, claude, etc. Theres also https://github.com/h2oai/h2ogpt but their gradio UI is overly complicated (meant for technical people) and not user friendly.

I'm also working on the finetuning of models for Q&A and I've finetuned llama-7b, falcon-40b, and oasst-pythia-12b using HuggingFace's SFT, H2OGPT's finetuning script and lit-gpt.

Github link: https://github.com/h2oai/h2ogpt

quite a number of AI tools written in Python do not work for me and usually because of the same error: RuntimeError: Failed to import transformers.models.auto because of the following error (look up to see its traceback): No module named 'tokenizers.tokenizers' This time it's https://github.com/h2oai/h2ogpt

privateGPT or h2ogpt