-
Tsinghua University
- Beijing, China
Stars
Towards Large Multimodal Models as Visual Foundation Agents
CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
GPT4V-level open-source multi-modal model based on Llama3-8B
PyMongo with proxy support
The first large protein language model trained follows structure instructions.
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI
Extensive Self-Contrast Enables Feedback-Free Language Model Alignment
SciGLM: Training Scientific Language Models with Self-Reflective Instruction Annotation and Tuning
A guidance language for controlling large language models.
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety.
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
AgentTuning: Enabling Generalized Agent Abilities for LLMs
a state-of-the-art-level open visual language model | 多模态预训练模型
ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Experts via Clustering
prompt2model - Generate Deployable Models from Natural Language Instructions
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
[ACL 2024] LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Approaching (Almost) Any Machine Learning Problem