Update README.md
Browse files
README.md
CHANGED
@@ -6,11 +6,11 @@ pipeline_tag: zero-shot-image-classification
|
|
6 |
---
|
7 |
|
8 |
## CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ
|
9 |
-
This is a version of the ViT-H-14 model based on timm's ```vit_huge_patch14_clip_224.laion2b``` quantized to 2-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/
|
10 |
|
11 |
This 2-bit model achieves a 0.716 zero-shot top-1 accuracy on Imagenet, outperforming a full-precision ViT-B-32 (0.664).
|
12 |
|
13 |
-
To run the model, install the HQQ library from https://github.com/mobiusml/hqq
|
14 |
``` Python
|
15 |
from hqq.models.vit import ViTHQQ
|
16 |
model = ViTHQQ.from_quantized("mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ")
|
|
|
6 |
---
|
7 |
|
8 |
## CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ
|
9 |
+
This is a version of the ViT-H-14 model based on timm's ```vit_huge_patch14_clip_224.laion2b``` quantized to 2-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/
|
10 |
|
11 |
This 2-bit model achieves a 0.716 zero-shot top-1 accuracy on Imagenet, outperforming a full-precision ViT-B-32 (0.664).
|
12 |
|
13 |
+
To run the model, install the HQQ library from https://github.com/mobiusml/hqq and use it as follows:
|
14 |
``` Python
|
15 |
from hqq.models.vit import ViTHQQ
|
16 |
model = ViTHQQ.from_quantized("mobiuslabsgmbh/CLIP-ViT-H-14-laion2B-2bit_g16_s128-HQQ")
|