Downloads · 30 days
24
5% of all-time downloads
mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1
grimjim/mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1
mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1 is a text generation model from grimjim. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied the majority of layers in this model, but only to mlp.downproj.weight layers. Unlike conventional ablit…
All-time downloads
492
Public
Parameters
12.2B
24.5 GB on disk
Likes
5
Public
Repo makeup
Click a slice to open those files.
.safetensors24.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025
- SHA
- f9b5a189
Try a prompt
Base models
Model card
From the Hugging Face model README
mistralai-Mistral-Nemo-Instruct-2407-12B-MPOA-v1
MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied the majority of layers in this model, but only to mlp.down_proj.weight layers. Unlike conventional abliteration, self_attn.o_proj.weight layers were left untouched.
Compliance was not maximized for this model. The model appears to be near an edge of chaos with regard to some safety refusals, which should be suitable for varied text completion.
More details to follow.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- en, fr, de, es, it, pt
- Featherless Ai
- live
- Created
- Nov 19, 2025
- Updated
- Nov 19, 2025