Instructions to use Salesforce/blip2-itm-vit-g-coco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip2-itm-vit-g-coco with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Salesforce/blip2-itm-vit-g-coco") 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("Salesforce/blip2-itm-vit-g-coco") model = AutoModelForZeroShotImageClassification.from_pretrained("Salesforce/blip2-itm-vit-g-coco") - Notebooks
- Google Colab
- Kaggle
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -63,7 +63,7 @@
|
|
| 63 |
"strip_accents": null,
|
| 64 |
"tokenize_chinese_chars": true,
|
| 65 |
"tokenizer_class": "BertTokenizer",
|
| 66 |
-
"tokenizer_file":
|
| 67 |
"truncation_side": "right",
|
| 68 |
"unk_token": "[UNK]"
|
| 69 |
}
|
|
|
|
| 63 |
"strip_accents": null,
|
| 64 |
"tokenize_chinese_chars": true,
|
| 65 |
"tokenizer_class": "BertTokenizer",
|
| 66 |
+
"tokenizer_file": null,
|
| 67 |
"truncation_side": "right",
|
| 68 |
"unk_token": "[UNK]"
|
| 69 |
}
|