THUKEG&THUDM (THUDM)

THUKEG&THUDM

THUDM

Organization data from Github https://github.com/THUDM

ChatGLM, GLM-4, CogVLM, CodeGeeX, CogView, ImageReward, CogVideoX | CogDL, GraphMAE, AMiner | Knowledge Engineering Group (KEG) & Data Mining at Tsinghua

Location:FIT Building, Tsinghua University

Home Page:https://huggingface.co/THUDM

GitHub:@THUDM

Twitter:@thukeg

THUKEG&THUDM's repositories

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Language:PythonLicense:Apache-2.0Stargazers:13650Issues:99Issues:797

CogVideo

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Language:PythonLicense:Apache-2.0Stargazers:10943Issues:133Issues:571

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Language:PythonLicense:Apache-2.0Stargazers:5966Issues:36Issues:630

GLM-4-Voice

GLM-4-Voice | 端到端中英语音对话模型

Language:PythonLicense:Apache-2.0Stargazers:2750Issues:30Issues:141

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Language:PythonLicense:Apache-2.0Stargazers:2423Issues:25Issues:152

CogVLM2

GPT4V-level open-source multi-modal model based on Llama3-8B

Language:PythonLicense:Apache-2.0Stargazers:2303Issues:29Issues:182

WebGLM

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

Language:PythonLicense:Apache-2.0Stargazers:1583Issues:24Issues:70

ImageReward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Language:PythonLicense:Apache-2.0Stargazers:1328Issues:14Issues:99

SwissArmyTransformer

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

Language:PythonLicense:Apache-2.0Stargazers:1065Issues:31Issues:82

CogView4

CogView4, CogView3-Plus and CogView3(ECCV 2024)

Language:PythonLicense:Apache-2.0Stargazers:883Issues:15Issues:27

CogAgent

An open-sourced end-to-end VLM-based GUI Agent

Language:PythonLicense:Apache-2.0Stargazers:822Issues:18Issues:38

LongBench

LongBench v2 and LongBench (ACL 2024)

Language:PythonLicense:MITStargazers:798Issues:8Issues:101

ReST-MCTS

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

LongCite

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Language:PythonLicense:Apache-2.0Stargazers:479Issues:12Issues:16

WebRL

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

LongAlign

[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs

Language:PythonLicense:Apache-2.0Stargazers:241Issues:8Issues:15

VisualAgentBench

Towards Large Multimodal Models as Visual Foundation Agents

Language:PythonLicense:Apache-2.0Stargazers:191Issues:12Issues:14

VisionReward

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Language:PythonLicense:Apache-2.0Stargazers:170Issues:9Issues:8

GLM-Edge

GLM Series Edge Models

Language:PythonLicense:Apache-2.0Stargazers:130Issues:11Issues:13

T1

Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

License:MITStargazers:88Issues:13Issues:0

ComplexFuncBench

Complex Function Calling Benchmark.

Awesome-Parameter-Efficient-Fine-Tuning-for-Foundation-Models

Parameter-Efficient Fine-Tuning for Foundation Models

WhoIsWho

KDD'23 Web-Scale Academic Name Disambiguation: the WhoIsWho Benchmark, Leaderboard, and Toolkit

MotionBench

Official code for MotionBench

Language:PythonLicense:Apache-2.0Stargazers:25Issues:8Issues:3

SceneGenAgent

SceneGenAgent: Precise Industrial Scene Generation with Coding Agent

Language:PythonLicense:Apache-2.0Stargazers:16Issues:10Issues:1

MoELoRA_Riemannian

Source code of paper: A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models.

Language:PythonStargazers:13Issues:1Issues:0

DataSciBench

DataSciBench: An LLM Agent Benchmark for Data Science

Language:PythonStargazers:8Issues:0Issues:0

MathGLM-Vision

Official Pytorch Implementation for MathGLM-Vision

VisScience

Official Pytorch Implementation for VisScience

Stargazers:0Issues:8Issues:0