Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)

OpenAI 接口接入适配，支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek，等兼容OpenAI接口，仅单可执行文件，配置超级简单，一键部署，开箱即用. Seamlessly integrate with OpenAI and compatible APIs using a single executable for quick setup and depl…

Local & Open Source Alternative to CharacterAI

[EMNLP 2023]This the repository of Harry Potter Dialogue Dataset.

Reference implementation for DPO (Direct Preference Optimization)

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut …

✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024

CodeBERT

Code for "Small Models are Valuable Plug-ins for Large Language Models"

Paper List for In-context Learning 🌷

Let ChatGPT teach your own chatbot in hours with a single GPU!

Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression

[EMNLP 2022] Language Model Pre-Training with Sparse Latent Typing

Mirror: Plug-and-Play Data Query, Summarization and Visualization with Natural Language Interface

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Training and serving large-scale neural networks with auto parallelization.

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Data and code for our paper "Exploring and Predicting Transferability across NLP Tasks", to appear at EMNLP 2020.

Implementation of paper "Towards a Unified View of Parameter-Efficient Transfer Learning" (ICLR 2022)