Chip Huyen analyzed 845 open source AI tool repositories on GitHub using keywords like gpt, llm, and generative ai. He categorized these into infrastructure, model development, application development, and applications layers. There was significant growth in application development and model development layers in 2023, with popular applications being coding, bots, and info aggregation. Tools like Qdrant, Pinecone, and LanceDB emerged in infrastructure layer. Notable contributors include lucidrains, ggerganov, Illyasviel, xtekky, and RNN-based models like RWKV.
This GitHub repository contains information on fine-tuning large language models (LLMs).
It includes a Jupyter Notebook file named "7 Steps to Fine-Tune LLMs.ipynb" that outlines the process.
Users can find information on setting up the environment, preparing data, fine-tuning models, evaluating performance, and saving fine-tuned models.
It includes a Jupyter Notebook file named "7 Steps to Fine-Tune LLMs.ipynb" that outlines the process.
Users can find information on setting up the environment, preparing data, fine-tuning models, evaluating performance, and saving fine-tuned models.
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
- The Open Interpreter repository provides a natural language interface for computers.
- It enables users to interact with their computer systems through a chat-like interface in the terminal.
- Open Interpreter supports various programming languages, including Python, Javascript, Shell, and more.
- The repository offers installation instructions, usage examples, and an interactive demo.
- It enables users to interact with their computer systems through a chat-like interface in the terminal.
- Open Interpreter supports various programming languages, including Python, Javascript, Shell, and more.
- The repository offers installation instructions, usage examples, and an interactive demo.
- GitHub repository for a tutorial series called "0 to LitGPT."
- Provides an overview of how to get started with LitGPT, which is an open-source implementation of GPT-3.
- Offers various resources such as codes, issues, pull requests, actions, security features, insights, and more related to the LitGPT project.
- Provides an overview of how to get started with LitGPT, which is an open-source implementation of GPT-3.
- Offers various resources such as codes, issues, pull requests, actions, security features, insights, and more related to the LitGPT project.
Swirl is open-source software that uses AI to simultaneously search multiple content and data sources, finds the best results using a reader LLM, then prompts Generative AI, enabling you to get answers from your own data.
HQQ is a fast and accurate model quantizer that skips the need for calibration data. It's super simple to implement (just a few lines of code for the optimizer). It can crunch through quantizing the Llama2-70B model in only 4 minutes!
