BrainChulo
Oobabooga_libs
BrainChulo | Oobabooga_libs | |
---|---|---|
10 | 2 | |
143 | 1 | |
2.1% | - | |
9.0 | 2.8 | |
8 months ago | about 1 year ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
BrainChulo
-
Alternative to LangChain for open LLMs?
On BrainChulo, we’re going 100% guidance mode, see for instance an implementation of Chain of Thoughts on top of a thin guidance wrapper: https://github.com/ChuloAI/BrainChulo/blob/main/app/guidance_tooling/guidance_agent/agent.py
-
Running local LLM for info retrieval of technical documents
Awesome resource! If I may suggest that you'd add one, some friends and I are working on data retrieval with llm project as well, with our differentiating marker being that we are trying to implement guidance in order to improve the agent efficiency. If you guys wanna take a look :) https://github.com/ChuloAI/BrainChulo
- LlamaCPP and LangChain Agent Quality
- Training a 13B LLaMA on information from documents.
-
Chat with Documents using Open source LLMs
Plug: https://github.com/iGavroche/BrainChulo - BrainChulo currently works on top of Ooba but uses its own UI interface. Its first goal is to provide a production-level way to do Retrieveal Augmentation on Open Source LLMs via vector stores and good prompt engineering.
-
What features would everyone like to see in oog?
Regarding this, I've joined a project that is doing some nice progress on this front. Still WIP but we're getting there, checkout BrainChulo :)
-
7B models use with Langchainn for Chatbox importing of txt or pdf's
This is exactly what BrainChulo aims to do. You should check it out: https://github.com/CryptoRUSHGav/BrainChulo/ and feel free to drop on the discord to give us your feedback, your use-case, or if you need help getting started.
- [Local Llama] Aggiunta di memoria a lungo termine a LLM personalizzati: domiamo Vicuna insieme!
-
adding models to oobabooga
The download script is broken. I posted a working version on my repo: https://github.com/CryptoRUSHGav/BrainChulo
-
Adding Long-Term Memory to Custom LLMs: Let's Tame Vicuna Together!
I'm hoping that many of you brilliant people can join me in our common quest to add long-term memory to our favorite camelid, Vicuna. The repository is called BrainChulo, and it's just waiting for your contributions.
Oobabooga_libs
- How do I get the api extension enabled on every time it starts up? I read that you can use the --extensions option. But have no clue where to put it in the start_windows.bat. It gets annoying having to load up the interface tab and enable api and restart the interface every time.
-
What features would everyone like to see in oog?
I have had a lot of success with superbooga for document querying, it is pretty much plug and play for that. What I want is to be able to send urls and paths to superbooga via the oobabooga api so I can automatically update the knowledge of the model via some simple python code, and can then integrate the model into some other code. It uses chromadb and has pretty good performance as far as answering relevantly is concerned. [Here](https://github.com/MRobinBatman/Oobabooga_libs/blob/main/Superbooga_query.py) is an example of a python api call I made that takes advantage of superbooga and a pretty good general instruction to answer questions about documents and webpages.
What are some alternatives?
gpt4-pdf-chatbot-langchain - GPT4 & LangChain Chatbot for large PDF docs
AgentOoba - An autonomous AI agent extension for Oobabooga's web ui
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
ChatALL - Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火, 文心一言 and more, discover the best answers
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
outlines - Structured Text Generation
long_term_memory - A gradio web UI for running Large Language Models like GPT-J 6B, OPT, GALACTICA, LLaMA, and Pygmalion.
gpt-llama.cpp - A llama.cpp drop-in replacement for OpenAI's GPT endpoints, allowing GPT-powered apps to run off local llama.cpp models instead of OpenAI.
visio-gptq
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.