Instructions to use iamcode6/dinov2-l-ccmt-mi300x with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use iamcode6/dinov2-l-ccmt-mi300x with timm:
import timm model = timm.create_model("hf_hub:iamcode6/dinov2-l-ccmt-mi300x", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| nohup: ignoring input | |
| /opt/venv/lib/python3.10/site-packages/apex/transformer/functional/fused_rope.py:54: UserWarning: Using the native apex kernel for RoPE. | |
| warnings.warn("Using the native apex kernel for RoPE.", UserWarning) | |
| epoch 1 | acc=0.8586 f1=0.8633 414 img/s | |
| epoch 2 | acc=0.8508 f1=0.8532 425 img/s | |
| epoch 3 | acc=0.8769 f1=0.8809 425 img/s | |
| epoch 4 | acc=0.8950 f1=0.8968 421 img/s | |
| epoch 5 | acc=0.9106 f1=0.9113 425 img/s | |
| epoch 6 | acc=0.9207 f1=0.9240 424 img/s | |
| epoch 7 | acc=0.9289 f1=0.9326 425 img/s | |
| epoch 8 | acc=0.9438 f1=0.9453 421 img/s | |
| epoch 9 | acc=0.9498 f1=0.9492 425 img/s | |
| epoch 10 | acc=0.9553 f1=0.9563 424 img/s | |
| epoch 11 | acc=0.9629 f1=0.9618 421 img/s | |
| epoch 12 | acc=0.9656 f1=0.9654 421 img/s | |
| epoch 13 | acc=0.9677 f1=0.9670 421 img/s | |
| epoch 14 | acc=0.9680 f1=0.9670 425 img/s | |
| epoch 15 | acc=0.9686 f1=0.9682 426 img/s | |
| [train] best val_macro_f1=0.9682 artifacts in runs/dinov2_l_v1 | |