Downloads · 30 days
17
0% of all-time downloads
Mistral-NeMo-Minitron-8B-ARChitects-ReArc1200-bnb-4bit
da-fr/Mistral-NeMo-Minitron-8B-ARChitects-ReArc1200-bnb-4bit
Mistral-NeMo-Minitron-8B-ARChitects-ReArc1200-bnb-4bit is a machine learning model from da-fr. 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 other.
Mistral-NeMo-Minitron-8B-ARChitects-ReArc1200-bnb-4bit is a retrained variant of Nvidia Mistral-NeMo-Minitron-8B-Base, finetuned specifically to solve ARC-AGI tasks. In order to save GPU memory, the embedding and voca…
All-time downloads
177K
Public
Parameters
7.6B
3.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.8 GB · 100%
Parameter types
How the weights are stored.
U87.6B · 100%
Model card
From the Hugging Face model README
Mistral-NeMo-Minitron-8B-ARChitects-ReArc1200-bnb-4bit
Model Overview
Mistral-NeMo-Minitron-8B-ARChitects-ReArc1200-bnb-4bit is a retrained variant of Nvidia Mistral-NeMo-Minitron-8B-Base, finetuned specifically to solve ARC-AGI tasks. In order to save GPU memory, the embedding and vocabulary size have been reduced to only 77 tokens. The model achieved a score of 71.6% (with test-time retraining) on the ARC-AGI public evaluation set, with only the ReArc data set being used during finetuning. Please refer to our github repository for more details. For more models tuned for ARC-AGI, check out our model collection.
Finetuning Datasets
This model was finetuned on the following datasets:
- the ReArc data set by Michael Hodel
License
This model is released under the NVIDIA Open Model License Agreement.
Usage
This model can be used with the transformers or unsloth packages. For more information on preprocessing the ARC Prize tasks to generate prompts for the model, please refer to our github repository.
References
- Type
- mistral
- License
- other
- Created
- May 16, 2025
- Updated
- Jun 11, 2025