Instructions to use fancyfeast/so400m-long with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fancyfeast/so400m-long with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="fancyfeast/so400m-long") 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("fancyfeast/so400m-long") model = AutoModelForZeroShotImageClassification.from_pretrained("fancyfeast/so400m-long") - Notebooks
- Google Colab
- Kaggle
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -2005,7 +2005,7 @@
|
|
| 2005 |
"do_lower_case": true,
|
| 2006 |
"eos_token": "<eos>",
|
| 2007 |
"extra_special_tokens": {},
|
| 2008 |
-
"max_length":
|
| 2009 |
"model_input_names": [
|
| 2010 |
"input_ids"
|
| 2011 |
],
|
|
|
|
| 2005 |
"do_lower_case": true,
|
| 2006 |
"eos_token": "<eos>",
|
| 2007 |
"extra_special_tokens": {},
|
| 2008 |
+
"max_length": 256,
|
| 2009 |
"model_input_names": [
|
| 2010 |
"input_ids"
|
| 2011 |
],
|