simpleblog
h2ogpt
| simpleblog | h2ogpt | |
|---|---|---|
| 1 | 28 | |
| 10 | 10,458 | |
| - | 3.0% | |
| 6.3 | 10.0 | |
| 8 months ago | 3 days ago | |
| Ruby | 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.
simpleblog
-
My personal wishlist for a decentralized social network
There's another dimension that nobody seems to talk about, and that's what happens with access to content is restricted. There is basically no censorship and no abuse from "those who can't get away with stuff on other networks" in the realm of SMS (or WhatsApp/WeChat/whatever your country uses). You can have a very healthy network if the authors are responsible for access control to their content. That's the idea behind my side-project of an easy-to-use, easy-to-selfhost private blog.[1]
When people want to use the platform to "become a thought leader" or "expand their network" then you're in the realm of public publishing which is where all the problems you cite become issues. The web makes privacy possible, and I don't understand why so few people are interested in that angle. For me I want to be able to share photos of my daughter with family and friends. I don't care if someone else wants to privately rant about the government to their friends--privacy enables both of these.
[1] https://github.com/mawise/simpleblog
h2ogpt
-
Ask HN: How do I train a custom LLM/ChatGPT on my own documents in Dec 2023?
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
-
chatgpt alternative
Here's the links: https://github.com/h2oai/h2ogpt/blob https://github.com/h2oai/h2ogpt/blob/main/docs/README_LangChain.md
-
Went down the rabbit hole of 100% local RAG, it works but are there better options?
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.
-
[SEEKING ADVICE] Looking for Existing Repos (Open-Source, VM-Hosted, & GPU-Compatible)
I've stumbled upon h2ogptas a potential starting point. Are there better solutions or repositories that can meet these requirements?
- H2Oai GPT CPU
-
Open source Q&A chatbot UI Recommendation?
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.
-
My experience on starting with fine tuning LLMs with custom data
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.
-
H2O.ai Introduces h2oGPT: A Suite of Open-Source Code Repositories for Democratizing Large Language Models (LLMs)
Github link: https://github.com/h2oai/h2ogpt
-
tokenizers error is driving me nuts
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
-
LLM for PDFs
privateGPT or h2ogpt
What are some alternatives?
quantizr - Quanta is an open-source CMS with ChatGPT and Social Media (Fediverse) features
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
privateGPT - Interact with your documents using the power of GPT, 100% privately, no data leaks [Moved to: https://github.com/zylon-ai/private-gpt]
llama_index - LlamaIndex is a data framework for your LLM applications
localGPT - Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.
local_llama - This repo is to showcase how you can run a model locally and offline, free of OpenAI dependencies.
h2o-llmstudio - H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.
Nuggt - An Autonomous LLM Agent that runs on Wizcoder-15B
bark - 🔊 Text-Prompted Generative Audio Model
llama_farm - Use local llama LLM or openai to chat, discuss/summarize your documents, youtube videos, and so on.
instructor-embedding - [ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings