Alternatives and similar repositories for VinePPO:

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

• Edward-Sun / easy-to-hard
  Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
  ☆119Updated 6 months ago
• abdulhaim / LMRL-Gym
  ☆81Updated 8 months ago
• YifeiZhou02 / ArCHer
  Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
  ☆149Updated 11 months ago
• GFNOrg / gfn-lm-tuning
  ☆172Updated last year
• genrm-star / genrm-critiques
  GenRM-CoT: Data release for verification rationales
  ☆51Updated 5 months ago
• architsharma97 / dpo-rlaif
  ☆95Updated 8 months ago
• WeiXiongUST / Building-Math-Agents-with-Multi-Turn-Iterative-Preference-Learning
  This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…
  ☆22Updated 3 months ago
• PRIME-RL / ImplicitPRM
  Repo of paper "Free Process Rewards without Process Labels"
  ☆136Updated last week
• ryoungj / ObsScaling
  [NeurIPS'24 Spotlight] Observational Scaling Laws
  ☆53Updated 5 months ago
• vwxyzjn / summarize_from_feedback_details
  ☆135Updated 3 months ago
• jwhj / OREO
  ☆102Updated 2 months ago
• thu-wyz / inference_scaling
  ☆61Updated 4 months ago
• hughbzhang / o1_inference_scaling_laws
  Replicating O1 inference-time scaling laws
  ☆83Updated 3 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆103Updated 11 months ago
• hkust-nlp / llm-compression-intelligence
  Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]
  ☆130Updated 6 months ago
• waterhorse1 / LLM_Tree_Search
  (ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training
  ☆259Updated 9 months ago
• HKUNLP / diffusion-vs-ar
  [ICLR 2025] Code for the paper "Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning"
  ☆42Updated last month
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.
  ☆224Updated last week
• SalesforceAIResearch / LaTRO
  ☆111Updated last month
• facebookresearch / rlfh-gen-div
  This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity
  ☆40Updated last year
• ars22 / scaling-LLM-math-synthetic-data
  Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"
  ☆29Updated 9 months ago
• hkust-nlp / dart-math
  [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
  ☆97Updated 3 months ago
• WindyLee0822 / Process_Q_Model
  official implementation of paper "Process Reward Model with Q-value Rankings"
  ☆51Updated last month
• activatedgeek / calibration-tuning
  ☆47Updated 7 months ago
• expz / quiet-star
  Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)
  ☆53Updated 7 months ago
• alexrame / rewardedsoups
  Rewarded soups official implementation
  ☆55Updated last year
• amazon-science / PAE
  ☆52Updated 2 weeks ago
• gregorbachmann / Next-Token-Failures
  ☆81Updated last year