Instructions to use HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit", trust_remote_code=True) 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("HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit", trust_remote_code=True) model = AutoModelForZeroShotImageClassification.from_pretrained("HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit about details ask
#10 opened about 1 year ago
by
Flink-ddd
Need details(?)
1
#9 opened over 1 year ago
by
akzsh
evaluation on imagenet1k
#8 opened almost 2 years ago
by
mia12mu12
I want to finetune this model, please tell me how to fine-tune
#6 opened about 2 years ago
by
linglingdan
When will transformers' s siglip supports FlashAtten?
2
#5 opened over 2 years ago
by
lucasjin
What processor to use?
9
#4 opened over 2 years ago
by
floschne
[Error] Error when executing the example code
👍 1
3
#3 opened over 2 years ago
by
StarCycle
Why the same input will be affected by batch size?
7
#2 opened over 2 years ago
by
yuzaa