-
The Chinese University of Hong Kong
- Hong Kong
-
11:54
(UTC +08:00) - https://shengze-xu.github.io/
Lists (13)
Sort Name ascending (A-Z)
Stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Python tool for converting files and office documents to Markdown.
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
Convert PDF to markdown + JSON quickly with high accuracy
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Fully open reproduction of DeepSeek-R1
Image-to-Image Translation in PyTorch
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Janus-Series: Unified Multimodal Understanding and Generation Models
Tongyi Deep Research, the Leading Open-source Deep Research Agent
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
verl: Volcano Engine Reinforcement Learning for LLMs
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
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.
Solve Visual Understanding with Reinforced VLMs
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"