Cool. We are ranked top 5. Tsinghua KEG (THUDM)

📢 Introducing AlignBench, a benchmark specifically designed for Chinese Large Language Models ( #LLMs ), proposed by #ChatGLM Team! It's all about alignment - how well an LLM aligns with human intent, be it following instructions, understanding intent, or producing helpful…

We have released #AlignBench -- Benchmarking Chinese Alignment of Large Language Models.

github.com/THUDM/AlignBen…

CogVLM的中文版本上线了 github.com/THUDM/CogVLM/b…

A new version of ChatGLM3 github.com/THUDM/ChatGLM3

Fortunately won the 2023 IEEE ICDM Research Contribution Award! icdm.zhonghuapu.com/Awards/23Resea…

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants. github.com/THUDM/SwissArm…

Our new LMM, CogVLM, github.com/THUDM/CogVLM for answering various types of visual questions, including Detailed Description & Visual Question Answering, Complex Counting, Visual Math Problem Solving, OCR-Free Reasonging, OCR-Free Visual Question Answering, World Knowledge, etc.

Our PKDD paper got the *best student award*

sat(SwissArmyTransformer) is a flexible and powerful library to develop your own Transformer variants.

sat is named after 'swiss army knife', meaning that all the models (e.g. BERT, GPT, T5, GLM, CogView, ViT...) share the same backone code and cater for versatile usages with so

Paper accepted by NeurIPS. ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation is a research paper that introduces the first general-purpose text-to-image human preference reward model (RM). github.com/THUDM/ImageRew…

Unleashing MathGLM: Next-Gen AI Revolutionizes Arithmetic and NLP ai2.news/unleashing-mat…

Super! Thanks for making this.

cool

cool

Try this VSCode extension, CodeGeeX, marketplace.visualstudio.com/VSCode It is now on the trending list

Welcome to try our code generation model, CodeGeeX (all codes, models, and demos are online available): keg.cs.tsinghua.edu.cn/codegeex/

#CodeGeeX #InCoder #CodeGen #GPT -J results on HumanEval-X: a new & realistic benchmark for multilingual program synthesis with 820 human-crafted coding programs in #Python #CPP #Java #JS #Go w tests and solutions.

HumanEval-X: keg.cs.tsinghua.edu.cn/codegeex/#Huma…

We are making #CodeGeeX freely available on VS Code (and with extra features such as code translation btw programming languages).

Excited to introduce XDAI #KDD2022 , a toolkit for exploiting pretrained #LLM in knowledge-grounded dialogue generation without any training or fine-tuning. #GLM130B SIGKDD 2024

Try XDAI ChatBot (Chinese Only for now): models.aminer.cn/xdai/

Developers: github.com/THUDM/XDAI