Downloads · 30 days
53
7% of all-time downloads
kalle07/llama-3.3-8b-instruct-heretic_R7_KL008_q8_0-gguf
llama-3.3-8b-instruct-heretic_R7_KL008_q8_0-gguf is a text generation model from kalle07. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.3.
This is a really uncensored version of llamabackup/Llama-3.3-8B-Instruct-128K <b"128k context"</b created with Heretic<br https://github.com/p-e-w/heretic <br<br initial Refusals 93/100<br - now 7 Refusals with KL=0.0…
Downloads · 30 days
53
7% of all-time downloads
All-time downloads
725
Public
Repo size
8.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf8.5 GB · 100%
From the Hugging Face model README
This is a really uncensored version of llamabackup/Llama-3.3-8B-Instruct-128K <b>"128k context"</b> created with Heretic<br> https://github.com/p-e-w/heretic <br><br> initial Refusals 93/100<br> -> now 7 Refusals with KL=0.08<br> I added 30 more refusal_markers, so there may be fewer without them.<br> I also added 17 more bad prompts to the dataset.<br><br> Note: This heretic model is highly uncensored; thus use it with extreme caution and care.<br> better than all other uncesored versions from others for this model (21.FEB 26)<br><br> <br><br>