This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or rejection sampling fine-tuning.
☆43Sep 22, 2024Updated last year
Alternatives and similar repositories for RAFT
Users that are interested in RAFT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…☆32Dec 5, 2024Updated last year
- Directional Preference Alignment☆62Sep 23, 2024Updated last year
- ☆276May 14, 2025Updated last year
- Visualization of mean field and neural tangent kernel regime☆23Jul 25, 2024Updated 2 years ago
- Codebase for Iterative DPO Using Rule-based Rewards☆275Apr 11, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A recipe for online RLHF and online iterative DPO.☆544Dec 28, 2024Updated last year
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆63Aug 23, 2024Updated last year
- CFG-GAN: Composite functional gradient learning of generative adversarial models☆15Jul 9, 2020Updated 6 years ago
- ☆14Oct 11, 2023Updated 2 years ago
- LogicIF: Towards Complex Logic Instruction Following☆18Jul 12, 2026Updated last month
- Self-Hinting Language Models Enhance Reinforcement Learning☆28Mar 28, 2026Updated 4 months ago
- ☆15Oct 19, 2024Updated last year
- Code for "Optimizing DDPM Sampling with Shortcut Fine-Tuning" (https://arxiv.org/abs/2301.13362), ICML 2023☆30Oct 6, 2023Updated 2 years ago
- ☆16Jul 29, 2025Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Explore what LLMs are really leanring over SFT☆28Mar 30, 2024Updated 2 years ago
- R1V, trained with AI feedback, answers open-ended visual questions.☆14Apr 12, 2025Updated last year
- Recipes to train the self-rewarding reasoning LLMs.☆231Mar 2, 2025Updated last year
- [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.☆56May 2, 2025Updated last year
- RewardBench: the first evaluation tool for reward models.☆731Feb 16, 2026Updated 5 months ago
- Accelerating GOT-OCRv2 with VLLM☆10Nov 15, 2024Updated last year
- A lightweight library for Bayesian analysis of LLM evals (ICML 2025 Spotlight Position Paper)☆25May 28, 2025Updated last year
- Code for the paper "Self-Detoxifying Language Models via Toxification Reversal" (EMNLP 2023)☆18Oct 17, 2023Updated 2 years ago
- Image Tokenizer Needs Post-Training☆24Oct 4, 2025Updated 10 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Code for Augment & Reduce, a scalable stochastic algorithm for large categorical distributions☆10May 16, 2018Updated 8 years ago
- Official PyTorch implementation of the paper "Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner"☆15Aug 9, 2023Updated 3 years ago
- ✨✨ [ICLR 2026] R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning☆292May 9, 2025Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆46Apr 21, 2024Updated 2 years ago
- This is the code used for the paper "PMGT-VR: A decentralized proximal-gradient algorithmic framework with variance reduction", prepint.☆15Jul 2, 2022Updated 4 years ago
- wePoker is a multi-player poker game for Android☆12Mar 20, 2013Updated 13 years ago
- PyTorch implementation of FAIR's paper "End-to-End Memory Network", NIPS 2015☆12Oct 19, 2017Updated 8 years ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆70Feb 21, 2025Updated last year
- PLATO dialog model with pre-trained parameters in pytorch version☆29May 20, 2022Updated 4 years 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.
- ☆11Oct 2, 2023Updated 2 years ago
- Code and data for the paper: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation☆35Jun 30, 2025Updated last year
- [NeurIPS 2025] RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning☆59Oct 23, 2025Updated 9 months ago
- Code for "Exponential Family Estimation via Adversarial Dynamics Embedding" (NeurIPS 2019)☆14Nov 26, 2019Updated 6 years ago
- ☆24Aug 4, 2022Updated 4 years ago
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆39Feb 25, 2026Updated 5 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Sep 24, 2024Updated last year