Instructions to use Salesforce/blip-image-captioning-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-image-captioning-base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base") model = AutoModelForImageTextToText.from_pretrained("Salesforce/blip-image-captioning-base") - Notebooks
- Google Colab
- Kaggle
Update tokenizer_config.json
Browse fileshttps://github.com/huggingface/transformers/pull/23362#discussion_r1194703956
- tokenizer_config.json +5 -1
tokenizer_config.json
CHANGED
|
@@ -13,5 +13,9 @@
|
|
| 13 |
"strip_accents": null,
|
| 14 |
"tokenize_chinese_chars": true,
|
| 15 |
"tokenizer_class": "BertTokenizer",
|
| 16 |
-
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
}
|
|
|
|
| 13 |
"strip_accents": null,
|
| 14 |
"tokenize_chinese_chars": true,
|
| 15 |
"tokenizer_class": "BertTokenizer",
|
| 16 |
+
"unk_token": "[UNK]",
|
| 17 |
+
"model_input_names": [
|
| 18 |
+
"input_ids",
|
| 19 |
+
"attention_mask"
|
| 20 |
+
]
|
| 21 |
}
|