Instructions to use zer0int/CLIP-GmP-ViT-L-14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zer0int/CLIP-GmP-ViT-L-14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="zer0int/CLIP-GmP-ViT-L-14") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("zer0int/CLIP-GmP-ViT-L-14") model = AutoModelForZeroShotImageClassification.from_pretrained("zer0int/CLIP-GmP-ViT-L-14", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add HuggingFace format full model + text encoder only
Browse filesThe "HF-format" models use the syntax of HF for the model structure, ensuring compatibility with downstream tasks that depend on it.
ViT-L-14-BEST-smooth-GmP-HF-format.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46a201afae2516c95b6d0cc798aca637161f07b8d0d7dc7776fb6f691f5476f1
|
| 3 |
+
size 931448048
|
ViT-L-14-BEST-smooth-GmP-TE-only-HF-format.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1bc257ac78ef7cf40c145b4319e759525557609b96820831f6eea2e49da99b5
|
| 3 |
+
size 323409740
|