Zero-Shot Image Classification
Transformers
Safetensors
siglip2_vision_model
feature-extraction
vision
Instructions to use ostris/siglip2-base-patch16-style-naflex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ostris/siglip2-base-patch16-style-naflex with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="ostris/siglip2-base-patch16-style-naflex") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ostris/siglip2-base-patch16-style-naflex") model = AutoModel.from_pretrained("ostris/siglip2-base-patch16-style-naflex") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +18 -0
- model.safetensors +3 -0
- processor_config.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +28 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Siglip2VisionModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"intermediate_size": 3072,
|
| 10 |
+
"layer_norm_eps": 1e-06,
|
| 11 |
+
"model_type": "siglip2_vision_model",
|
| 12 |
+
"num_attention_heads": 12,
|
| 13 |
+
"num_channels": 3,
|
| 14 |
+
"num_hidden_layers": 12,
|
| 15 |
+
"num_patches": 256,
|
| 16 |
+
"patch_size": 16,
|
| 17 |
+
"transformers_version": "5.8.1"
|
| 18 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d786f94dc0503e4794e00a3b8f58ab79c9aac6b158bb5a51234f2b3a92545098
|
| 3 |
+
size 371746008
|
processor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Siglip2ImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"max_num_patches": 256,
|
| 18 |
+
"patch_size": 16,
|
| 19 |
+
"resample": 2,
|
| 20 |
+
"rescale_factor": 0.00392156862745098
|
| 21 |
+
},
|
| 22 |
+
"processor_class": "Siglip2Processor"
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7756bd0dd6d4dd2873588f2bfeda29c3c42fc9cdba81d26bb179851cfdebc2e
|
| 3 |
+
size 34356427
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"mask_token": "<mask>",
|
| 10 |
+
"max_length": 64,
|
| 11 |
+
"model_input_names": [
|
| 12 |
+
"input_ids"
|
| 13 |
+
],
|
| 14 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
+
"pad_to_multiple_of": null,
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"pad_token_type_id": 0,
|
| 18 |
+
"padding_side": "right",
|
| 19 |
+
"processor_class": "Siglip2Processor",
|
| 20 |
+
"sp_model_kwargs": {},
|
| 21 |
+
"spaces_between_special_tokens": false,
|
| 22 |
+
"stride": 0,
|
| 23 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 24 |
+
"truncation_side": "right",
|
| 25 |
+
"truncation_strategy": "longest_first",
|
| 26 |
+
"unk_token": "<unk>",
|
| 27 |
+
"use_default_system_prompt": false
|
| 28 |
+
}
|