Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE…

Bringing BERT into modernity via both architecture changes and scaling

Tools for checking ACL paper submissions

📐 Jekyll theme for building a personal site, blog, project documentation, or portfolio.

Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

A beautiful, simple, clean, and responsive Jekyll theme for academics

Jekyll plugin to propagate the `site.github` namespace and set default values for use with GitHub Pages.

Go ahead and axolotl questions

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Monitor GPU/CPU Usage on SSH servers, with NVIDIA and AMD support.

FisiQuímicamente / PhysiChemically / FisiQuímicament

Hierarchical Reasoning Model Official Release

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

The official repo of the paper "MMLongBench Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly"

Fully open reproduction of DeepSeek-R1

Syrup, a Honey alternative

Crosspost from Twitter/X to Bluesky and Mastodon directly in the web browser

BPE modification that implements removing of the intermediate tokens during tokenizer training.

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.

The context API to search, scrape, and interact with the web at scale. 🔥

Efficient Triton Kernels for LLM Training

A curated list of research papers and resources on Cultural LLM.

Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"

Extract structured text from pdfs quickly

Official inference library for pre-processing of Mistral models

Large Language Model Text Generation Inference

A high-throughput and memory-efficient inference and serving engine for LLMs

LLM training in simple, raw C/CUDA