Stars
A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.
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…
Translate PDF, EPub, webpage, metadata, annotations, notes to the target language. Support 20+ translate services.
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
line drawing colorization using chainer
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
A lightweight framework for building LLM-based agents
MoBA: Mixture of Block Attention for Long-Context LLMs
Deep learning with cats (^._.^)
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
[ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
Megvii FILE Library - Working with Files in Python same as the standard library
[NIPS 2025 DB Oral] Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
[ACL 2024 Findings] MathBench: A Comprehensive Multi-Level Difficulty Mathematics Evaluation Dataset
🎬 3.7× faster video generation E2E 🖼️ 1.6× faster image generation E2E ⚡ ColumnSparseAttn 9.3× vs FlashAttn‑3 💨 ColumnSparseGEMM 2.5× vs cuBLAS
The official implementation of "Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks"
A multi-language code evaluation tool.
An object detection codebase based on MegEngine.
2017秋季编译课程项目，采用flex+bison工具并使用.NET开发一个简单语言的语法分析工具。