Instructions to use Salesforce/blip-vqa-capfilt-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Salesforce/blip-vqa-capfilt-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Salesforce/blip-vqa-capfilt-large")# Load model directly from transformers import AutoProcessor, AutoModelForVisualQuestionAnswering processor = AutoProcessor.from_pretrained("Salesforce/blip-vqa-capfilt-large") model = AutoModelForVisualQuestionAnswering.from_pretrained("Salesforce/blip-vqa-capfilt-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update tokenizer_config.json
#1
by ybelkada - opened
- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,10 @@
|
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"processor_class": "BlipProcessor",
|
| 11 |
"sep_token": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"special_tokens_map_file": null,
|
| 13 |
"strip_accents": null,
|
| 14 |
"tokenize_chinese_chars": true,
|
|
|
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"processor_class": "BlipProcessor",
|
| 11 |
"sep_token": "[SEP]",
|
| 12 |
+
"model_input_names": [
|
| 13 |
+
"input_ids",
|
| 14 |
+
"attention_mask"
|
| 15 |
+
],
|
| 16 |
"special_tokens_map_file": null,
|
| 17 |
"strip_accents": null,
|
| 18 |
"tokenize_chinese_chars": true,
|