Downloads · 30 days
48
11% of all-time downloads
nbeerbower/mistral-nemo-gutenberg2-12B-test
mistral-nemo-gutenberg2-12B-test is a text generation model from nbeerbower. 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.
mistralai/Mistral-Nemo-Instruct-2407 finetuned on nbeerbower/gutenberg2-dpo.
Downloads · 30 days
48
11% of all-time downloads
All-time downloads
436
Public
Parameters
12.2B
24.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors24.5 GB · 100%
From the Hugging Face model README
mistralai/Mistral-Nemo-Instruct-2407 finetuned on nbeerbower/gutenberg2-dpo.
This model is a test for the sake of benchmarking my gutenberg2 dataset.
Finetuned using an RTX 3090 for 3 epochs.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.73 |
| IFEval (0-Shot) | 33.85 |
| BBH (3-Shot) | 32.04 |
| MATH Lvl 5 (4-Shot) | 10.20 |
| GPQA (0-shot) | 8.95 |
| MuSR (0-shot) | 10.97 |
| MMLU-PRO (5-shot) | 28.39 |