Stars
The official repository of Mozilla's Firefox web browser.
Index your Gmail account to a SQLite DB and play with the data.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Official inference repo for FLUX.1 models
[Extended verision ICLR 2025 Blog Track] Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
Haiku-Search is a high-performance fuzzy search library designed for web applications. It is built using Rust and compiled to WebAssembly
Inference and training library for high-quality TTS models.
Svart: A high-performance vector database in Rust. Named after the Swedish word for 'black,' Svart aims for sleek and efficient data indexing and retrieval.
A coding agent for open models like Kimi K3
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Making Ascon cipher easier to play with
QLoRA: Efficient Finetuning of Quantized LLMs
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Book repository "Analysis and Design of Elementary MOS Amplifier Stages"
A book teaching assembly language programming on the ARM 64 bit ISA. Along the way, good programming practices and insights into code development are offered which apply directly to higher level la…
Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Publication-ready NN-architecture schematics.
A latent text-to-image diffusion model
Self-hostable maps stack, powered by OpenStreetMap.