heretic-models
Collection
small abliterated/uncensored/heretical models • 12 items • Updated • 2
This is a really uncensored version of llamabackup/Llama-3.3-8B-Instruct-128K "128k context" created with Heretic
https://github.com/p-e-w/heretic
initial Refusals 93/100
-> now 7 Refusals with KL=0.08
I added 30 more refusal_markers, so there may be fewer without them.
I also added 17 more bad prompts to the dataset.
Note: This heretic model is highly uncensored; thus use it with extreme caution and care.
better than all other uncesored versions from others for this model (21.FEB 26)
- Downloads last month
- 124
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for kalle07/llama-3.3-8b-instruct-heretic_R7_KL008_q8_0-gguf
Base model
allura-forge/Llama-3.3-8B-Instruct Finetuned
llamabackup/Llama-3.3-8B-Instruct-128K