SergiuDeveloper/yoro-finetuning

YORO (You-Only-Reason-Once) - a novel LLM architecture that runs the main reasoning block once, caches its output, and reuses it for all subsequent tokens. Lightweight auxiliary networks compensate for the missing reasoning passes, keeping generation coherent while skipping the most expensive computation at every step.

22
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Jupyter Notebook

License

MIT

Category

llm-fine-tuning

Last pushed

Mar 18, 2026

Commits (30d)

0

GitHub
Llm Fine Tuning · 212 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SergiuDeveloper/yoro-finetuning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

OptimalScale/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

59

adithya-s-k/AI-Engineering.academy

Mastering Applied AI, One Concept at a Time

57

jax-ml/jax-llm-examples

Minimal yet performant LLM examples in pure JAX

53

young-geng/scalax

A simple library for scaling up JAX programs

52

riyanshibohra/TuneKit

Upload your data → Get a fine-tuned SLM. Free.

49

Explore Transformer Models

All categories Trending Transformer directory Insights