Instructions to use distill-lab/distill-n4_00-01_combined_cls_v1b2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use distill-lab/distill-n4_00-01_combined_cls_v1b2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="distill-lab/distill-n4_00-01_combined_cls_v1b2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoTokenizer, AutoModelForImageClassification tokenizer = AutoTokenizer.from_pretrained("distill-lab/distill-n4_00-01_combined_cls_v1b2") model = AutoModelForImageClassification.from_pretrained("distill-lab/distill-n4_00-01_combined_cls_v1b2") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,28 @@ current batches:
|
|
| 9 |
|
| 10 |
`nv3[v0] (1700) | nv4[v1-2k] (4000) | nv4[v1-210k] (b1b2: 4000)`
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
|
|
|
|
| 9 |
|
| 10 |
`nv3[v0] (1700) | nv4[v1-2k] (4000) | nv4[v1-210k] (b1b2: 4000)`
|
| 11 |
|
| 12 |
+
metrics:
|
| 13 |
+
```
|
| 14 |
+
636 ***** train metrics *****
|
| 15 |
+
1637 epoch = 20.0
|
| 16 |
+
1638 total_flos = 66966619017GF
|
| 17 |
+
1639 train_loss = 0.2338
|
| 18 |
+
1640 train_runtime = 0:58:49.65
|
| 19 |
+
1641 train_samples_per_second = 56.736
|
| 20 |
+
1642 train_steps_per_second = 0.89
|
| 21 |
+
|
| 22 |
+
1644 ***** eval metrics *****
|
| 23 |
+
1645 epoch = 20.0
|
| 24 |
+
1646 eval_accuracy = 0.7521
|
| 25 |
+
1647 eval_loss = 0.8814
|
| 26 |
+
1648 eval_runtime = 0:00:12.42
|
| 27 |
+
1649 eval_samples_per_second = 142.171
|
| 28 |
+
1650 eval_steps_per_second = 2.977
|
| 29 |
+
```
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
## Model details:
|
| 33 |
+
|
| 34 |
|
| 35 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 36 |
|