The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

The code to perform Sequence Labelling with LLMs, including T5, FLAN, LLaMA, Alpaca and more!

A curated list of awesome data labeling tools

Label, clean and enrich text datasets with LLMs.

Adala: Autonomous DAta (Labeling) Agent framework

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

A powerful tool for creating fine-tuning datasets for LLM

A quick guide (especially) for trending instruction finetuning datasets

Curated list of datasets and tools for post-training.

Data annotation toolbox supports image, audio and video data.

收集整理开源的数据标注工具

The Memory layer for AI Agents

Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.

The repo for In-context Autoencoder

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3.1

Prompt, run, edit, and deploy full-stack web applications

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

This is a continuously updated handbook for readers to easily track the latest NL2SQL (Text-to-SQL) techniques in the literature and provide practical guidance for researchers and practitioners. If…

基于Python的开源量化交易平台开发框架

GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Fully open reproduction of DeepSeek-R1