Democratizing Reinforcement Learning for LLMs

SkyRL: A Modular Full-stack RL Library for LLMs

The dataset includes quantities vehicle trajectories at several sites. The dataset is extracted from aerial videos. Human work is used to ensure accuracy.

Repo for "MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability"

Humanity's Last Exam

Deepseek R1 zero tiny version own reproduce on two A100s.

Minimal reproduction of DeepSeek R1-Zero

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Repo for LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty

A framework for few-shot evaluation of language models.

开源SFT数据集整理,随时补充

Repo for Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Open source annotation tool for machine learning practitioners.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

pCLUE: 1000000+多任务提示学习数据集

A high-throughput and memory-efficient inference and serving engine for LLMs

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理

Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.

BertViz: Visualize Attention in Transformer Models

The official Meta Llama 3 GitHub site