license: apache-2.0
language:
- en
base_model: - TrevorJS/gemma-4-E2B-it-uncensored
tags: - conversational
- TextOnly
- EnglishOnly
- Nsfw
- Heretic
- Ara
- Abliterated
- Visionremoved
- Audioremoved
- gemma4
- roleplay
After thorough usage and testing, I chose this UNCENSORED Gemma 4 E2B Model to be pruned (converted to English and Text-to-Text only) so I can use it on my potato laptop/phone.
The Source Model
** Gemma-4-E2B-it-uncensored **
- Profile: The most uncensored G4-E2B model.
- Stats: 3/686 manually checked refusals (according to the author).
This pruned model is an unhinged one, it will do anything you ask.
Modifications
What's Changed:
- Vision & Audio Modules: REMOVED (Just Text-to-Text now).
- Language Tokens: ~61,000 (23.1%) REMOVED This includes non-Latin, Cyrillic, Arabic, Asian languages, etc.
- Note: Languages using some Latin letters like German and Vietnamese are still there. Latin was not removed to keep the logic alive.
- Weights: Cut down from >2100 to 711 (loads fast as fahhhh).
What DID NOT Change:
- Layers
- Logic (as far as I tested)
- Context
- No training/retraining done
TL;DR: Overall, the pruned model is faster and significantly less resource-intensive.
Base Model Usage Settings
You might want to change these according to your preferences, but here is the baseline:
- Temperature: 1.0
- Top P: 0.95
- Top K: 64
- Jinja
--jinja(don't ignore this one, especially on llama.cpp!)
Colab Notebook I made and used to prune this model:
Thanks:
- TrevorJS
- Claude.ai (for coding the notebook)
- Kaggle.com (for the free resources)