rft

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.

LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

Implementation of the Rhythm Formant Analysis methodology for identifying speech rhythms and rhythm variation in the low frequency spectrum and spectrogram.

[AAMAS 2025] Privacy-preserving and Personalized RLHF, with convergence guarantees. The Code contains experiments for training multiple instances of GPT-2 for personalized sentiment aligned text generation.

The My Pocket Token Foundation will make the blockchain better, by bridging the blockchain with the worldwide web. Some of the best Developers in the world.

The course teaches how to fine-tune LLMs using Group Relative Policy Optimization (GRPO)—a reinforcement learning method that improves model reasoning with minimal data. Learn RFT concepts, reward design, LLM-as-a-judge evaluation, and deploy jobs on the Predibase platform.

Contention-aware scheduler for Agave SVM. Continuous automated fuzz testing with 40M+ verified state transitions per CI session

A small Hugging Face LLM for planning and reasoning

Random Factorio Things mod for Factorio

Smart contract and unit tests for Refungible Token / Fractional NFT

On-chain institutional layer for Solana — O(1) supply distribution, SIRM invariant enforcement, 2.5B+ fuzz runs, 14 security findings addressed.

Research laboratory for deterministic execution topology, invariant systems, and high-concurrency runtime architecture.

AGOPD：优势门控在线蒸馏——缓解小模型数学推理中的教师监督负迁移

Generate MsWord file using php

Training Qwen3 to solve Wordle using SFT and GRPO