Sync model repo (text/metadata)
Browse files- README.md +1 -1
- metadata.yaml +2 -0
README.md
CHANGED
|
@@ -62,7 +62,7 @@ Compared to the FP32 baseline:
|
|
| 62 |
|
| 63 |
DeiT-Tiny is a data-efficient Vision Transformer for ImageNet-1K classification, distilled and trained by Facebook AI Research. This is the INT8-quantized, Ethos-U85-targeted export of that model — no finetuning of weights was performed beyond quantization.
|
| 64 |
|
| 65 |
-
- **
|
| 66 |
- **Model type:** Image Classification (Vision Transformer / DeiT)
|
| 67 |
- **License:** Apache 2.0
|
| 68 |
- **Base model:** [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) — quantized, not finetuned
|
|
|
|
| 62 |
|
| 63 |
DeiT-Tiny is a data-efficient Vision Transformer for ImageNet-1K classification, distilled and trained by Facebook AI Research. This is the INT8-quantized, Ethos-U85-targeted export of that model — no finetuning of weights was performed beyond quantization.
|
| 64 |
|
| 65 |
+
- **Original developer:** Facebook AI Research (Meta)
|
| 66 |
- **Model type:** Image Classification (Vision Transformer / DeiT)
|
| 67 |
- **License:** Apache 2.0
|
| 68 |
- **Base model:** [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) — quantized, not finetuned
|
metadata.yaml
CHANGED
|
@@ -10,6 +10,8 @@ description: >-
|
|
| 10 |
id: Arm/deit-tiny-int8-ethos-u-executorch
|
| 11 |
filename: deit-tiny-int8-ethos-u-executorch.pte
|
| 12 |
base_model_id: facebook/deit-tiny-patch16-224
|
|
|
|
|
|
|
| 13 |
profile: Arm-Optimized
|
| 14 |
weight_dtype: int8
|
| 15 |
quantization:
|
|
|
|
| 10 |
id: Arm/deit-tiny-int8-ethos-u-executorch
|
| 11 |
filename: deit-tiny-int8-ethos-u-executorch.pte
|
| 12 |
base_model_id: facebook/deit-tiny-patch16-224
|
| 13 |
+
vendor: Meta
|
| 14 |
+
base_model_url: https://huggingface.co/facebook/deit-tiny-patch16-224
|
| 15 |
profile: Arm-Optimized
|
| 16 |
weight_dtype: int8
|
| 17 |
quantization:
|