-
Tsinghua University
- Beijing, China
Highlights
- Pro
Stars
MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and qua…
Scalable RL solution for advanced reasoning of language models
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"
Codes and checkpoints of paper "Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules"
Plug-and-Play Document Modules for Pre-trained Models
Instruction Tuning with GPT-4
Codes for Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement (EMNLP 2018)
An index of algorithms for learning causality with data
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
An Open-Source Package for Network Embedding (NE)
An Open-Source Package for Neural Relation Extraction (NRE)
Free English to Chinese Dictionary Database
清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University
xcjthu / REKCARC-TSC-UHT
Forked from PKUanonym/REKCARC-TSC-UHT清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
scikit-learn: machine learning in Python
An Efficient Lexical Analyzer for Chinese