Pishtiko

Pishtiko's Stars

• QwenLM/Qwen2.5-Coder

  Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

  Language:Python4.5k361

• exo-explore/exo

  Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

  Language:Python23.3k1.4k

• microsoft/MoGe

  MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

  Language:Python73542

• instantX-research/InstantIR

  InstantIR: Blind Image Restoration with Instant Generative Reference 🔥

  Language:Python48649

• RoaringBitmap/RoaringBitmap

  A better compressed bitset in Java: used by Apache Spark, Netflix Atlas, Apache Pinot, Tablesaw, and many others

  Language:Java3.6k564

• microsoft/OmniParser

  A simple screen parsing tool towards pure vision based GUI agent

  Language:Jupyter Notebook11k838

• VectorSpaceLab/OmniGen

  OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

  Language:Jupyter Notebook3.6k301

• soimort/you-get

  :arrow_double_down: Dumb downloader that scrapes the web

  Language:Python54.9k9.7k

• kijai/ComfyUI-MochiWrapper

  Language:Python76068

• ucbepic/docetl

  A system for agentic LLM-powered data processing and ETL

  Language:Python1.7k151

• deepseek-ai/Janus

  Janus-Series: Unified Multimodal Understanding and Generation Models

  Language:Python16k2.1k

• DPDK/dpdk

  Data Plane Development Kit

  Language:C3.5k1.3k

• fudan-generative-vision/hallo2

  Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

  Language:Python3.5k504

• coder/coder

  Provision remote development environments via Terraform

  Language:Go9k789

• LituRout/RF-Inversion

  Rectified Flow Inversion (RF-Inversion)

  34114

• genmoai/mochi

  The best OSS video generation models

  Language:Python2.9k304

• Zyphra/Zamba2

  PyTorch implementation of models from the Zamba2 series.

  Language:Python17616

• facebookresearch/LayerSkip

  Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

  Language:Python27122

• facebookresearch/LWE-benchmarking

  This repository contains code to generate and preprocess Learning with Errors (LWE) data and implementations of four LWE attacks uSVP, SALSA, Cool&Cruel, and Dual Hybrid Meet-in-the-Middle (MitM). We invite contributors to reproduce our results, improve on these methods, and/or suggest new concrete attacks on LWE.

  Language:Python401

• alimama-creative/FLUX-Controlnet-Inpainting

  Language:Python58737

• VRSEN/agency-swarm

  The only reliable agent framework built on top of the latest OpenAI Assistants API.

  Language:Python3.4k866

• HKUDS/LightRAG

  "LightRAG: Simple and Fast Retrieval-Augmented Generation"

  Language:Python11.9k1.7k

• SWivid/F5-TTS

  Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

  Language:Python9.7k1.3k

• a-r-r-o-w/finetrainers

  Memory-optimized training scripts for video models based on Diffusers

  Language:Python85291

• openai/swarm

  Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

  Language:Python18.7k2k

• rhymes-ai/Aria

  Codebase for Aria - an Open Multimodal Native MoE

  Language:Jupyter Notebook99383

• huggingface/evaluation-guidebook

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

  Language:Jupyter Notebook1k62

• lapce/lapce

  Lightning-fast and Powerful Code Editor written in Rust

  Language:Rust35k1.1k

• NVlabs/EAGLE

  Eagle Family: Exploring Model Designs, Data Recipes and Training Strategies for Frontier-Class Multimodal LLMs

  Language:Python60638

• chaidiscovery/chai-lab

  Chai-1, SOTA model for biomolecular structure prediction

  Language:Python1.5k199