Update model config and README
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
|
|
|
| 3 |
- timm
|
| 4 |
- transformers
|
| 5 |
pipeline_tag: image-feature-extraction
|
|
@@ -19,7 +20,7 @@ A DINOv3 ViT model image feature encoder. Distilled on SAT-493M from the DINOv3
|
|
| 19 |
* The original models keep RoPE periods as a persistent `bfloat16` buffer. `timm` generates `float32` periods at init. This results in some numerical differences, however the `timm` approach should be less problematic running on devices without bfloat16 support, and appears to work as well if not slightly better for fine-tuning. `model.rope.periods = model.rope.periods.to(torch.bfloat16).to(torch.float32)` will truncate the periods to bfloat16 and result in matching outputs.
|
| 20 |
|
| 21 |
## Model Details
|
| 22 |
-
- **Model Type:** Image
|
| 23 |
- **Model Stats:**
|
| 24 |
- Params (M): 303.1
|
| 25 |
- GMACs: 82.4
|
|
@@ -190,4 +191,4 @@ See the associated paper for details on the evaluation protocols
|
|
| 190 |
doi = {10.5281/zenodo.4414861},
|
| 191 |
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
|
| 192 |
}
|
| 193 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
+
- image-feature-extraction
|
| 4 |
- timm
|
| 5 |
- transformers
|
| 6 |
pipeline_tag: image-feature-extraction
|
|
|
|
| 20 |
* The original models keep RoPE periods as a persistent `bfloat16` buffer. `timm` generates `float32` periods at init. This results in some numerical differences, however the `timm` approach should be less problematic running on devices without bfloat16 support, and appears to work as well if not slightly better for fine-tuning. `model.rope.periods = model.rope.periods.to(torch.bfloat16).to(torch.float32)` will truncate the periods to bfloat16 and result in matching outputs.
|
| 21 |
|
| 22 |
## Model Details
|
| 23 |
+
- **Model Type:** Image Feature Encoder
|
| 24 |
- **Model Stats:**
|
| 25 |
- Params (M): 303.1
|
| 26 |
- GMACs: 82.4
|
|
|
|
| 191 |
doi = {10.5281/zenodo.4414861},
|
| 192 |
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
|
| 193 |
}
|
| 194 |
+
```
|