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.
☆39Sep 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☆58Sep 23, 2024Updated last year
- Visualization of mean field and neural tangent kernel regime☆23Jul 25, 2024Updated last year
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆10Dec 30, 2024Updated last year
- CFG-GAN: Composite functional gradient learning of generative adversarial models☆15Jul 9, 2020Updated 5 years ago
- A recipe for online RLHF and online iterative DPO.☆545Dec 28, 2024Updated last year
- code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"☆62Aug 23, 2024Updated last year
- MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision☆28May 26, 2025Updated 9 months ago
- ☆266May 14, 2025Updated 10 months ago
- [NeurIPS 2025] RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning☆52Oct 23, 2025Updated 5 months ago
- ☆16Jul 29, 2025Updated 7 months ago
- Recipes to train reward model for RLHF.☆1,521Apr 24, 2025Updated 10 months ago
- THOUGHTSCULPT, a general reasoning and search method for complex tasks☆13Dec 13, 2024Updated last year
- R1V, trained with AI feedback, answers open-ended visual questions.☆14Apr 12, 2025Updated 11 months ago
- We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.☆61Oct 3, 2024Updated last year
- Explore what LLMs are really leanring over SFT☆28Mar 30, 2024Updated last year
- AgenTracer: A Lightweight Failure Attributor for Agentic Systems☆81Nov 12, 2025Updated 4 months ago
- Recipes to train the self-rewarding reasoning LLMs.☆231Mar 2, 2025Updated last year
- [ICLR 2026] RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling☆36Feb 25, 2026Updated 3 weeks ago
- [ICCV 2025 Highlight] LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs☆20Nov 16, 2025Updated 4 months ago
- ☆27Apr 11, 2023Updated 2 years ago
- Your efficient and accurate answer verification system for RL training.☆41Jun 23, 2025Updated 9 months ago
- The Code for Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models☆18Oct 4, 2024Updated last year
- (ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"☆26Mar 2, 2026Updated 3 weeks ago
- Codes for Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback (ACL 2024 Findings)☆16Jul 2, 2024Updated last year
- Code for the paper "Self-Detoxifying Language Models via Toxification Reversal" (EMNLP 2023)☆18Oct 17, 2023Updated 2 years ago
- Official PyTorch implementation of the paper "Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner"☆15Aug 9, 2023Updated 2 years ago
- Code and data for the paper: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation☆35Jun 30, 2025Updated 8 months ago
- PyTorch implementation of FAIR's paper "End-to-End Memory Network", NIPS 2015☆12Oct 19, 2017Updated 8 years ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆45Apr 21, 2024Updated last year
- [VLDB'2025] LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data☆19Nov 3, 2025Updated 4 months ago
- RewardBench: the first evaluation tool for reward models.☆704Feb 16, 2026Updated last month
- ☆10Aug 26, 2022Updated 3 years ago
- Reproduced the DFT method without using Verl. https://arxiv.org/abs/2508.05629☆21Oct 14, 2025Updated 5 months ago
- 🎉 TrustJudge is accepted to ICLR 2026!☆38Sep 27, 2025Updated 5 months ago
- ☆35Jul 5, 2023Updated 2 years ago
- This is the code used for the paper "PMGT-VR: A decentralized proximal-gradient algorithmic framework with variance reduction", prepint.☆16Jul 2, 2022Updated 3 years ago
- ☆12Apr 25, 2025Updated 10 months ago
- Python package to augment multilingual data☆15Feb 15, 2023Updated 3 years ago