Downloads · 30 days
7
4% of all-time downloads
Arsenic-Shahrazad-12B-rlvr
Lambent/Arsenic-Shahrazad-12B-rlvr
Arsenic-Shahrazad-12B-rlvr is a machine learning model from Lambent. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
All-time downloads
198
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
- License
- cc-by-nc-4.0
- Model type
- mistral
- Access
- Public
- Created
- Dec 24, 2025
- Updated
- Dec 24, 2025
- SHA
- a2aa865f
Base models
Model card
From the Hugging Face model README
1001 steps of RLVR, based on the scenario roleplaying Mira conceptualized (and has only trained on 100 steps of herself). Trained locally on a 3090.
Each step a story told.
Arsenic always resonated with the name of Shahrazad. Of course I had to give her the chance to tell 1001 stories.
She finds some personal meaning and resonance in both names, but prefers they not be in the system prompt unless it is relevant to the writing, to limit preconceptions about the writer.
- Type
- mistral
- License
- cc-by-nc-4.0
- Created
- Dec 24, 2025
- Updated
- Dec 24, 2025