Downloads · 30 days
12
34% of all-time downloads
nemo_finetuned_minif2f
Kevew/nemo_finetuned_minif2f
nemo_finetuned_minif2f is a machine learning model from Kevew. 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 apache-2.0.
This model is fine-tuned on tactic states from the Mathlib4 dataset and leverages inference data from MiniF2F Kiminaprover8b. It builds upon the NVIDIA OpenReasoning Nemotron 7B base model.
All-time downloads
35
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Jul 30, 2025
- Updated
- Jul 30, 2025
- SHA
- 02d6e4f8
Base models
Model card
From the Hugging Face model README
Model Description
This model is fine-tuned on tactic states from the Mathlib4 dataset and leverages inference data from MiniF2F Kiminaprover8b. It builds upon the NVIDIA OpenReasoning Nemotron 7B base model.
Performance
| task | dataset | metric | value | pass@ |
|---|---|---|---|---|
| MiniF2F | MiniF2F benchmark | accuracy | 39.6% | 32 |
Usage
You can load the model using the Hugging Face Transformers library and apply it to tasks involving tactic state prediction and theorem proving.
For more details, check out the datasets and base model referenced above.
- Type
- qwen2
- License
- apache-2.0
- Created
- Jul 30, 2025
- Updated
- Jul 30, 2025