This is a Frankenstein tune i created by asking the question "What if i ran Heretic on the model i already ran Heretic on" And so this model was created. I brought down the refusal rate from 5% down to 3% while keeping KL Divergence at 0.00 Hopefully it turns out fine.

Downloads last month
6
Safetensors
Model size
0.6B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bruhmoment4242/Qwen3-0.6B-Heretic-Heresy-Edition

Finetuned
Qwen/Qwen3-0.6B
Finetuned
(1)
this model
Quantizations
2 models