Stars
Research projects built on top of Transformers
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
A Python implementation of the DESeq2 pipeline for bulk RNA-seq DEA.
The python library for real-time communication
Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
Unofficial Python client library for Semantic Scholar APIs.
aider is AI pair programming in your terminal
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Repository for StripedHyena, a state-of-the-art beyond Transformer architecture
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
A scientific instrument for investigating latent spaces
Creation of interactive networks using d3 Javascript
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Training LLMs with QLoRA + FSDP
A library for generating and evaluating synthetic tabular data for privacy, fairness and data augmentation.
Low-code framework for building custom LLMs, neural networks, and other AI models
QLoRA: Efficient Finetuning of Quantized LLMs
High accuracy RAG for answering questions from scientific documents with citations
Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
INSIGHT is an autonomous AI that can do medical research!
A playbook for systematically maximizing the performance of deep learning models.