Alternatives and similar repositories for TokenSwift

Users that are interested in TokenSwift are comparing it to the libraries listed below

• MiroMindAI / MiroMind-M1
  MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.
  ☆244Updated 3 months ago
• SuperGPQA / SuperGPQA
  ☆173Updated 7 months ago
• TIGER-AI-Lab / General-Reasoner
  General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]
  ☆204Updated this week
• lzhxmu / CPPO
  CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)
  ☆167Updated 3 weeks ago
• MiroMindAI / MiroRL
  MiroRL is an MCP-first reinforcement learning framework for deep research agent.
  ☆180Updated 3 months ago
• Tencent / llm.hunyuan.T1
  ☆85Updated 8 months ago
• GAIR-NLP / PC-Agent-E
  Efficient Agent Training for Computer Use
  ☆133Updated 2 months ago
• QwenLM / WorldPM
  ☆91Updated 6 months ago
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆137Updated last year
• Quehry / HelloBench
  HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models
  ☆52Updated last year
• Tongyi-Zhiwen / Qwen-Doc
  ☆300Updated 6 months ago
• DAMO-NLP-SG / LongPO
  [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
  ☆43Updated 9 months ago
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆112Updated 10 months ago
• inclusionAI / Ling-V2
  Ling-V2 is a MoE LLM provided and open-sourced by InclusionAI.
  ☆237Updated last month
• MiroMindAI / MiroTrain
  MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.
  ☆99Updated 3 months ago
• yyht / openrlhf_async_pipline
  ☆86Updated 3 months ago
• inclusionAI / PromptCoT
  A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…
  ☆129Updated last month
• open-compass / Ada-LEval
  The official implementation of "Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks"
  ☆55Updated 6 months ago
• Kwai-Klear / KlearReasoner
  Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
  ☆79Updated 2 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆223Updated 3 weeks ago
• TIGER-AI-Lab / CritiqueFineTuning
  Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]
  ☆179Updated 4 months ago
• zjunlp / LightThinker
  [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
  ☆123Updated 7 months ago
• MiniMax-AI / SynLogic
  [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  ☆187Updated 4 months ago
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆180Updated 4 months ago
• efficientscaling / Z1
  [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"
  ☆67Updated 7 months ago
• RUC-GSAI / YuLan-Mini
  A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.
  ☆222Updated 4 months ago
• SkyworkAI / MindLink
  ☆98Updated 3 months ago
• InternLM / POLAR
  Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.
  ☆160Updated 2 months ago
• yyDing1 / ScaleQuest
  [ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLM…
  ☆68Updated last year
• multimodal-art-projection / COIG-P
  ☆39Updated 4 months ago