-
University of Chinese Academy of Sciences
- Beijing, China
Starred repositories
📚 An open-source textbook written at the college level. OpenIntro also offers a second college-level intro stat textbook and also a high school variant.
Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model
Doing simple retrieval from LLM models at various context lengths to measure accuracy
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
Working with any file in everywhere with vscode.
Reading Wikipedia to Answer Open-Domain Questions
Hearthstone simulator using C++ with some reinforcement learning
MTEB: Massive Text Embedding Benchmark
"Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?"
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.
Tools for merging pretrained large language models.
Co-LLM: Learning to Decode Collaboratively with Multiple Language Models
Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models
Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning