LightRFT (Light Reinforcement Fine-Tuning) is an advanced reinforcement learning fine-tuning framework designed for Large Language Models (LLMs) and Vision-Language Models (VLMs).
☆19Jan 12, 2026Updated 9 months ago
Alternatives and similar repositories for LightRFT
Users that are interested in LightRFT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆19Jun 14, 2026Updated 4 months ago
- ☆23Jun 11, 2026Updated 4 months ago
- All Claude Code Prompts☆14Apr 2, 2026Updated 6 months ago
- [COLM 2025] Official code for "When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoni…☆15Oct 31, 2025Updated 11 months ago
- Secure Personal AI Assistant with TEE Support☆22Apr 11, 2026Updated 6 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- This repo support auto line plot for multi-seed event file from TensorBoard☆12Jun 23, 2022Updated 4 years ago
- 用提示词实现一百个idea☆27Oct 9, 2026Updated 2 weeks ago
- ☆16Aug 26, 2026Updated 2 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆18Dec 19, 2024Updated last year
- A learnable Meta Optimizer for Combinatorial Optimization☆12Nov 29, 2024Updated last year
- ☆17Dec 12, 2020Updated 5 years ago
- A living literature repository for Token Economics for LLM Agents: A Dual-View Study from Computing and Economics.☆42May 13, 2026Updated 5 months ago
- Self-Knowledge Guided Retrieval Augmentation for Large Language Models (EMNLP Findings 2023)☆27Dec 8, 2023Updated 2 years ago
- Radix Tree KV Cache with Turn-Aware Growth☆12Jul 21, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2023] Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optim…☆11Dec 19, 2023Updated 2 years ago
- Building open-ended embodied agent in battle royale FPS game☆40Feb 6, 2024Updated 2 years ago
- Pytorch implementation of HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models☆28Mar 22, 2024Updated 2 years ago
- Nano vLLM Triton☆14Aug 27, 2025Updated last year
- Implements the Messenger environment and EMMA model.☆25Jun 14, 2023Updated 3 years ago
- GLM-5.3-Flash adaptation + offload perf patches for FreeToken v0.1.2 (17.8→36.7 tok/s on one RTX PRO 6000)☆20Oct 2, 2026Updated 3 weeks ago
- Writeups by zer00d4y☆11Oct 20, 2026Updated last week
- Learning and Debugging for FSDP/FSDP2 Training☆18Feb 7, 2026Updated 8 months ago
- ☆10Oct 22, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆11Oct 25, 2024Updated 2 years ago
- ⚛ MOSAIC is a visual-first platform that enables researchers to configure, run, and compare experiments results across RL, LLM, VLM, and …☆32Sep 27, 2026Updated last month
- [EOL] Process Polygon Package to DOMjudge Package.☆12Apr 24, 2021Updated 5 years ago
- ☆17Jun 30, 2020Updated 6 years ago
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design☆26May 29, 2025Updated last year
- ICLR 2025: Needle Threading☆11May 24, 2025Updated last year
- A library for for First-order Reinforcement Learning algorithms☆11Mar 14, 2024Updated 2 years ago
- A benchmark suited especially for deep learning operators☆43Feb 13, 2023Updated 3 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICML 2026] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs☆35Apr 27, 2026Updated 6 months ago
- The Walnut Plan☆11Oct 10, 2024Updated 2 years ago
- Simple intermediate representation language for learning and research.☆22Mar 27, 2020Updated 6 years ago
- Code for NeurIPS 2020 paper 'Self-imitation Learning via Generalized Lower bound Q-learning'☆12Feb 13, 2021Updated 5 years ago
- ☆10May 23, 2025Updated last year
- ESPN: Embedding from Storage Pipelined Network. GDS implementation for multi-vector embedding retrieval and bindings.☆13May 18, 2024Updated 2 years ago
- Official Repository for NeurIPS 2025 Paper: "A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning"☆14Nov 10, 2025Updated 11 months ago