Python bindings to the Tree-sitter parsing library

aider is AI pair programming in your terminal

Build real-time multimodal AI applications 🤖🎙️📹

DeepSeek Coder: Let the Code Write Itself

🌟 Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.

Model components of the Llama Stack APIs

Finetuning Large Visual Models on Visual Question Answering

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Simple image captioning model

CLIPxGPT Captioner is Image Captioning Model based on OpenAI's CLIP and GPT-2.

Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.

Jitsi is an audio/video and chat communicator that supports protocols such as SIP, XMPP/Jabber, IRC and many other useful features.

Reverse Engineering: Decompiling Binary Code with Large Language Models

Transit Relay server for Magic-Wormhole

the rendezvous/mailbox server for magic-wormhole clients

Transparent proxy server that works as a poor man's VPN. Forwards over ssh. Doesn't require admin. Works with Linux and MacOS. Supports DNS tunneling.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

MINT-1T: A one trillion token multimodal interleaved dataset.

The devs are over here at devzat, chat over SSH!

Transformer implementation for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

SAM-Med3D: An Efficient General-purpose Promptable Segmentation Model for 3D Volumetric Medical Image

Official implementation of SAM-Med2D

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

[ICCV 2023] CLIP-Driven Universal Model; Rank first in MSD Competition.

Medical image registration, affine and deformable registration

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80 languages recognition, provide data annotation and synthesis tools, support training and…