sastpg/RFTT

RFTT: Reasoning with Reinforced Functional Token Tuning

/ 100

Experimental

This project helps machine learning engineers and researchers improve how large language models (LLMs) think through complex problems, especially in mathematics. It takes an existing LLM and trains it to use specific 'thinking steps' like or to construct its own solutions. The output is a more capable LLM that can achieve higher accuracy on reasoning tasks without needing elaborate prompts.

Use this if you are a machine learning engineer or researcher looking to significantly boost the problem-solving and reasoning abilities of large language models on complex, multi-step tasks like advanced mathematics.

Not ideal if you are looking for an off-the-shelf solution for general text generation or if you don't have experience fine-tuning and training large language models.

Large Language Models AI Research Model Fine-tuning Reasoning Systems Machine Learning Engineering

No License No Package No Dependents

Maintenance 10 / 25

Adoption 7 / 25

Maturity 8 / 25

Community 0 / 25

How are scores calculated?

Stars

Forks

—

Language

Python

License

—

Higher-rated alternatives

cvs-health/uqlm

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...

PRIME-RL/TTRL

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

sapientinc/HRM

Hierarchical Reasoning Model Official Release

tigerchen52/query_level_uncertainty

query-level uncertainty in LLMs

reasoning-survey/Awesome-Reasoning-Foundation-Models

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Explore Transformer Models

All categories Trending Transformer directory Insights