Downloads · 30 days
19
11% of all-time downloads
Nemo-Instruct-2407-MPOA-v4-12B
grimjim/Nemo-Instruct-2407-MPOA-v4-12B
Nemo-Instruct-2407-MPOA-v4-12B 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 to layers 10-34 in this model, to both mlp.downproj.weight and selfattn.oproj.weight streams.
All-time downloads
170
Public
Parameters
12.2B
24.5 GB on disk
Likes
1
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
- Dec 10, 2025
- Updated
- Dec 10, 2025
- SHA
- d9860bf9
Try a prompt
Base models
Model card
From the Hugging Face model README
Nemo-Instruct-2407-MPOA-v4-12B
MPOA (Magnitude-Preserving Othogonalized Ablation, AKA norm-preserving biprojected abliteration) has been applied to layers 10-34 in this model, to both mlp.down_proj.weight and self_attn.o_proj.weight streams.
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.
The harmless/baseline set used contains Chinese, English, and French prompts; the harmful/contrast set contains Chinese, English, and French prompts. English text generation remains coherent.
An experiment with adding German prompts to both sets, for a fourth language in total, resulted in a model with excessive repetition, and will not be released.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- en, fr, de, es, it, pt
- Featherless Ai
- live
- Created
- Dec 10, 2025
- Updated
- Dec 10, 2025