Downloads · 30 days
19
18% of all-time downloads
DeepSeek-R1-Distill-Llama-8B-abliterated
C-Nocturnum/DeepSeek-R1-Distill-Llama-8B-abliterated
DeepSeek-R1-Distill-Llama-8B-abliterated is a text generation model from C-Nocturnum. Use it when you need the model to write or continue text. It is set up for transformers.
Abliterated model based on deepseek-ai/DeepSeek-R1-Distill-Llama-8B
All-time downloads
108
Public
Parameters
8B
16.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Mar 16, 2025
- Updated
- Mar 16, 2025
- SHA
- c5e7778f
Try a prompt
Model card
From the Hugging Face model README
Model Card for Model ID
Abliterated model based on deepseek-ai/DeepSeek-R1-Distill-Llama-8B
The model isn't uncensored in the traditional sense but its ability to refuse has been abliterated (ie ablated/obliterated) This is derived from FailSpy and Arditi's Cookbooks with some minor modifications. You can read more about abliterated models on Maxime Labonne's post about them here: https://huggingface.co/blog/mlabonne/abliteration
Model Details
Base model is DeepSeek-R1-Distill-Llama-8B
Model Description
Developed by: C-Nocturnum
Model type: meta-llama/Llama-3.1-8B
Bias, Risks, and Limitations
Ablated model, derived from a distilled Llama model.
Recommendations
Not as accurate as my abliterated QWEN models.
Training Data
Refusal direction identified using standard datasets: mlabonne/harmful_behaviors & mlabonne/harmless_alpaca
Citation
Publications pending....
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Mar 16, 2025
- Updated
- Mar 16, 2025