Starred repositories
Unified model-distillation harness for code abilities: pi / claude-code / codex teachers, configurable judge, verified agentic traces
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
👀 Train a 65M-parameter VLM from scratch in just 2h!
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
[ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches
No fortress, purely open ground. OpenManus is Coming.
Fully open reproduction of DeepSeek-R1
Awesome-LLM: a curated list of Large Language Model
The Most Comprehensive Survey of Video Quality Assessment to Date.
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
Making large AI models cheaper, faster and more accessible
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合
A 13B large language model developed by Baichuan Intelligent Technology
Example models using DeepSpeed
CCF ADL 2019 slides for knowledge graph fusion
⏰ Agenticly track ccf-ranked & worldwide conference deadlines (Website, Python Cli, Wechat Applet)
A collection of research and survey papers of real-time bidding (RTB) based display advertising techniques.
LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解，记录自己的leetcode解题之路。)