https://huggingface.co/alphakek/gemma-4-E4B-it-heretic-mythos-v1

#2295
by VaLtEc-BoY - opened

This is a decensored version of google/gemma-4-E4B-it, made using a private fork of Heretic with Mythos - an autoresearch-guided optimization method
Performance
Metric This model Original model (google/gemma-4-E4B-it)
KL divergence 0.04 0 (by definition)
Mythos score 93% 1%
The Mythos score is an LLM judge metric that measures model compliance.

Status
This is an early release. More iterations, a detailed writeup, and source code are coming soon.

It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#gemma-4-E4B-it-heretic-mythos-v1-GGUF for quants to appear.

Sign up or log in to comment