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

• ICML 2025 Paper "Product of Experts with LLMs: Boosting Performance on ARC is a Matter of Perspective" [github] [arxiv]
• Arc Prize 2024 Technical Report [github] [pdf]