Downloads · 30 days
10
1% of all-time downloads
CLIP-ViT-H-14-448
ostris/CLIP-ViT-H-14-448
CLIP-ViT-H-14-448 is a zero-shot image classification model from ostris. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
You probably do not need this unless you are training your own IP Adapters.
All-time downloads
1.9K
Public
Parameters
633M
1.3 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Zero-Shot Image Classification
- Library
- transformers
- License
- mit
- Model type
- clip_vision_model
- Access
- Public
- Created
- Jan 6, 2024
- Updated
- Jan 6, 2024
- SHA
- 37035b9e
Model card
From the Hugging Face model README
You probably do not need this unless you are training your own IP Adapters.
Modified version of the vision encoder of CLIP-ViT-H-14-laion2B-s32B-b79K to handle 448 x 448 inputs vs the original 224 x 224 inputs. It will probbaly not work for classification (as is), but will DIP work for for IP+ adapters that use CLIP-ViT-H, though they will need to be fine tuned a little more.
Hidden layer outputs go from (257, 1280) to (1025, 1280), which can be digested by the Resampler without modification or weight resizing.
- Task
- Zero-Shot Image Classification
- Library
- transformers
- Type
- clip_vision_model
- License
- mit
- Created
- Jan 6, 2024
- Updated
- Jan 6, 2024