openchat
embedchain
| openchat | embedchain | |
|---|---|---|
| 18 | 6 | |
| 4,996 | 8,629 | |
| - | 3.3% | |
| 9.1 | 9.8 | |
| 2 days ago | 2 days ago | |
| Python | Python | |
| Apache License 2.0 | 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.
openchat
-
Alternative of bard,bing, claude
Depending on your use case, https://openchat.team/ might be woth looking into
- OpenChat Aura Running in Chatbot UI
-
Exponentially Faster Language Modelling
Even like OpenChat-3.5? (Probably the best 7B model out there) Demo: https://openchat.team/
HuggingFace: https://huggingface.co/openchat/openchat_3.5
- Orca 2: Teaching Small Language Models How to Reason
-
Openchat Installation
I've raised the issue to openchat on github, so maybe it'll be fixed soon hehe!
- OpenChat surpass ChatGPT and Grok on various benchmarks
- FLaNK Stack Weekly 06 Nov 2023
-
OpenChat 3.2 SUPER is Here!
🔎 Discover the power of OpenChat 3.2 SUPER on GitHub and Huggingface: - GitHub: OpenChat - Huggingface: OpenChat 3.2 SUPER weights
- OpenChat: Advancing Open-Source Language Models with Imperfect Data
embedchain
-
Ask HN: How do I train a custom LLM/ChatGPT on my own documents in Dec 2023?
You can use embedchain[1] to connect various data sources and then get a RAG application running on your local and production very easily. Embedchain is an open source RAG framework and It follows a conventional but configurable approach.
The conventional approach is suitable for software engineer where they may not be less familiar with AI. The configurable approach is suitable for ML engineer where they have sophisticated uses and would want to configure chunking, indexing and retrieval strategies.
[1]: https://github.com/embedchain/embedchain
- Embedchain
- Framework to easily create LLM powered bots over any dataset
-
[D] Hardest thing about building with LLMs?
Langchain is a big wrapper in itself and people can't be bothered to even use that to write 10 lines of code. Look at the traction this project is getting https://github.com/embedchain/embedchain, at it's heart it's just using few modules from langchain. The whole thing, chunking+embedding+retrieval+promoting can be done in 100 lines without langchain and embedchain.
-
AI — weekly megathread!
Embedchain: a framework to easily create LLM powered bots over any dataset [Link].
- EmbedChain: Framework to easily create LLM powered bots over any dataset.
What are some alternatives?
UltraFastBERT - The repository for the code of the UltraFastBERT paper
trulens - Evaluation and Tracking for LLM Experiments
can-ai-code - Self-evaluating interview for AI coders
HeimdaLLM - Constrain LLM output
Bartender - An OpenAI chatbot for Rocket.Chat written in Go
WebGLM - WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)
bark - 🔊 Text-Prompted Generative Audio Model
gpt-migrate - Easily migrate your codebase from one framework or language to another.
ggml - Tensor library for machine learning
searchGPT - Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.
chatbot-ui - AI chat for every model.
llmo - Your friendly terminal-based AI pair programmer