Tools for merging pretrained large language models.

Toolkit for linearizing PDFs for LLM datasets/training

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers"

Tile primitives for speedy kernels

A Unified Tokenizer for Visual Generation and Understanding

HunyuanVideo GP: Large Video Generation Model - GPU Poor version

Wan: Open and Advanced Large-Scale Video Generative Models

Official repo for paper "MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"

FlashMLA: Efficient MLA decoding kernels

CLIP Based NSFW Detector

Minimalist ML framework for Rust

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Efficient DiT architecture for text2any tasks, ICLR2025

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

FFMPEG wrapper for Python

A reading list of video generation

Lightweight nudity detection

[CSUR] A Survey on Video Diffusion Models

Accelerating Diffusion Transformers with Token-wise Feature Caching

Video editing with Python

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

Sky-T1: Train your own O1 preview model within $450

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

NumPy & SciPy for GPU

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.