Alternatives and similar repositories for SplitReason

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

• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆45Updated 7 months ago
• RyanLiu112 / GenPRM
  Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".
  ☆73Updated last month
• THU-KEG / AdaptThink
  ☆89Updated last week
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆49Updated 3 months ago
• uservan / ThinkPO
  ☆19Updated 3 months ago
• nick7nlp / FastCuRL
  FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models
  ☆49Updated this week
• uservan / speculative_thinking
  ☆20Updated this week
• john-hewitt / implicit-ins
  Codebase for Instruction Following without Instruction Tuning
  ☆34Updated 8 months ago
• MingyuJ666 / Disentangling-Memory-and-Reasoning
  [ACL'25] We propose a novel fine-tuning method, Separate Memory and Reasoning, which combines prompt tuning with LoRA.
  ☆54Updated 2 weeks ago
• YangLing0818 / SuperCorrect-llm
  [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
  ☆70Updated 2 months ago
• OpenSparseLLMs / MoM
  ☆83Updated last month
• inclusionAI / PromptCoT
  ☆50Updated this week
• efficientscaling / Z1
  Repo for "Z1: Efficient Test-time Scaling with Code"
  ☆59Updated last month
• namespace-Pt / UltraGist
  ☆18Updated 6 months ago
• alessiodevoto / l2compress
  Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."
  ☆13Updated 5 months ago
• xuyige / SoftCoT
  ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…
  ☆21Updated this week
• Shwai-He / MEO
  The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":
  ☆38Updated last year
• mathllm / Step-Controlled_DPO
  ☆22Updated 10 months ago
• qiuzh20 / gated_attention
  The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
  ☆38Updated 3 weeks ago
• kamanphoebe / Look-into-MoEs
  [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models
  ☆52Updated 3 months ago
• RUCAIBox / EASYEP
  ☆18Updated last month
• zhiyuanhubj / LongRecipe
  LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
  ☆75Updated 7 months ago
• horseee / CoT-Valve
  CoT-Valve: Length-Compressible Chain-of-Thought Tuning
  ☆69Updated 3 months ago
• GuanghaoYe / Emergence-of-Thinking
  ☆53Updated 3 months ago
• bethgelab / sober-reasoning
  A Sober Look at Language Model Reasoning
  ☆52Updated this week
• OpenSparseLLMs / Linear-MoE
  ☆93Updated 2 weeks ago
• MozerWang / AMPO
  [arxiv: 2505.02156] Adaptive Thinking via Mode Policy Optimization for Social Language Agents
  ☆27Updated 2 weeks ago
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆98Updated 3 weeks ago
• yyDing1 / ScaleQuest
  [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.
  ☆63Updated 7 months ago
• WooooDyy / MathCritique
  Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".
  ☆54Updated 6 months ago