#
Jiaxin-Wen
Follow
Starred repositories
PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker/Zotero
The nnsight package enables interpreting and manipulating the internals of deep learned models.
Stanford NLP Python library for understanding and improving PyTorch models via interventions
🔥Highlighting the top ML papers every week.
All credits go to HuggingFace's Daily AI papers (https://huggingface.co/papers) and the research community. 🔉Audio summaries here (https://t.me/daily_ai_papers).
Flash Hyperbolic Attention in ~[...] lines of CUDA
The official repository for the Scientific Paper Idea Proposer (SciPIP)
CiteME is a benchmark designed to test the abilities of language models in finding papers that are cited in scientific texts.
aider is AI pair programming in your terminal
Extract full next-token probabilities via language model APIs
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目
《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀
Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.