Archer2.0 evolves from its predecessor by introducing ASPO, which overcomes fundamental PPO-Clip limitations to prevent premature convergence and unlock greater RL potential.
☆31Oct 10, 2025Updated 6 months ago
Alternatives and similar repositories for Archer2.0
Users that are interested in Archer2.0 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ArcherCodeR is an open-source initiative enhancing code reasoning in large language models through scalable, rule-governed reinforcement …☆45Aug 6, 2025Updated 8 months ago
- A set of examples based on verl for end-to-end RL training recipes.☆247Updated this week
- ☆16Jul 29, 2025Updated 8 months ago
- ☆12Nov 19, 2020Updated 5 years ago
- Simplified packaging for pybind11-based C++ extensions☆13Jun 3, 2022Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Contains the model patches and the eval logs from the passing swe-bench-lite run.☆10Jun 28, 2024Updated last year
- An email client in C# using WPF☆11May 14, 2015Updated 10 years ago
- 实现一个自己的小语言模型☆11Jun 15, 2024Updated last year
- FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning (EMNLP 2025)☆58Oct 10, 2025Updated 6 months ago
- 本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。☆137Updated this week
- 清华大学人工智能导论（龙明盛老师）课程课件，作业以及试题☆16Jun 26, 2023Updated 2 years ago
- 🎮 A beautiful little Sudoku game built with Svelte and TailwindCSS.☆28Jun 19, 2025Updated 10 months ago
- This is tensorflow 2.2 based SCAMET framework for remote sensing image captioning.☆13Aug 10, 2023Updated 2 years ago
- Solutions to Ireland, Rosen exercises in "A Classical Introduction to Modern Number Theory"☆14Nov 7, 2024Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Python powered music controlling webpage with websockets and bottle py (works with spotify, vlc, audacious, and others)☆11Jun 9, 2017Updated 8 years ago
- ☆20Apr 16, 2025Updated last year
- 刹那是永恒☆13Feb 26, 2020Updated 6 years ago
- NeurIPS 2025: Discriminative Constrained Optimization for Reinforcing Large Reasoning Models☆53Mar 14, 2026Updated last month
- Official resources of "The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reaso…☆21Jun 13, 2025Updated 10 months ago
- This repo is for anonymized review. We will keep updating and optimizing this program.☆16Oct 18, 2024Updated last year
- CBETA XML P5 版本 (2013 - 2018)☆16Jan 8, 2019Updated 7 years ago
- Kernel Playground - A playground to run large scale experiments on the Linux Kernel☆20Nov 8, 2025Updated 5 months ago
- 剧本分镜智能体（NLP）：剧本→分镜→片段→prompt | 基于 LangGraph+LLM，自动解析任意格式剧本，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词。保持角色/剧情跨片段一致，支持 MCP/REST API/函数调用 …☆49Apr 9, 2026Updated last week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings☆73Feb 3, 2025Updated last year
- A collection of plugin for j4status☆14Oct 2, 2023Updated 2 years ago
- Official code repository of Shuffle-R1☆25Feb 23, 2026Updated last month
- ☆16May 5, 2022Updated 3 years ago
- ☆15Nov 22, 2023Updated 2 years ago
- This repo contains the solutions of UC Berkeley CS 61B spring semester 2018, and materials including slides, lecture codes, exams and dis…☆15May 24, 2024Updated last year
- ☆43Oct 9, 2023Updated 2 years ago
- A command line tool for comparing JSON files by degree of similarity.☆12Oct 28, 2019Updated 6 years ago
- ☆32Dec 29, 2025Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- handy tools for user study☆21May 21, 2024Updated last year
- One-Shot Unsupervised Cross Domain Detection☆13Nov 22, 2022Updated 3 years ago
- WebResearcher: An Iterative Deep-Research Agent，迭代式深度研究智能体☆49Feb 13, 2026Updated 2 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆13Jan 26, 2025Updated last year
- ☆14Oct 28, 2023Updated 2 years ago
- An asynchronous streaming data management module for efficient post-training.☆49Updated this week
- MathLex JavaScript math entry system☆21Apr 29, 2025Updated 11 months ago