Lists (1)
Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
A library for efficient similarity search and clustering of dense vectors.
DuckDB is an analytical in-process SQL database management system
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
🤗 smolagents: a barebones library for agents that think in code.
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
Train transformer language models with reinforcement learning.
Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
A framework for few-shot evaluation of language models.
The official repository of Mozilla's Firefox web browser.
Large Language Model Text Generation Inference
The open source codebase powering HuggingChat
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
A course on aligning smol models.
A scikit-learn compatible neural network library that wraps PyTorch
Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…
Probabilistic time series modeling in Python
Source code for pbrt, the renderer described in the third edition of "Physically Based Rendering: From Theory To Implementation", by Matt Pharr, Wenzel Jakob, and Greg Humphreys.
A lightweight data processing framework built on DuckDB and 3FS.
Jupyter notebooks for the Natural Language Processing with Transformers book
The simplest, fastest repository for training/finetuning small-sized VLMs.
Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.