Instructions to use google/siglip-so400m-patch16-256-i18n with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip-so400m-patch16-256-i18n with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip-so400m-patch16-256-i18n") 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("google/siglip-so400m-patch16-256-i18n") model = AutoModelForZeroShotImageClassification.from_pretrained("google/siglip-so400m-patch16-256-i18n") - Notebooks
- Google Colab
- Kaggle
Merve Noyan commited on
Commit ·
932e6d2
1
Parent(s): 5d67b24
new config
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -5,10 +5,10 @@
|
|
| 5 |
"initializer_factor": 1.0,
|
| 6 |
"model_type": "siglip",
|
| 7 |
"text_config": {
|
|
|
|
| 8 |
"hidden_size": 1152,
|
| 9 |
"intermediate_size": 4304,
|
| 10 |
"model_type": "siglip_text_model",
|
| 11 |
-
"no_head": true,
|
| 12 |
"num_attention_heads": 16,
|
| 13 |
"num_hidden_layers": 27,
|
| 14 |
"vocab_size": 250000
|
|
|
|
| 5 |
"initializer_factor": 1.0,
|
| 6 |
"model_type": "siglip",
|
| 7 |
"text_config": {
|
| 8 |
+
"has_head": false,
|
| 9 |
"hidden_size": 1152,
|
| 10 |
"intermediate_size": 4304,
|
| 11 |
"model_type": "siglip_text_model",
|
|
|
|
| 12 |
"num_attention_heads": 16,
|
| 13 |
"num_hidden_layers": 27,
|
| 14 |
"vocab_size": 250000
|