-
4
Gemma3 License Plate Detection
📈Gemma 3 for license plate detection
-
ariG23498/gemma-3-4b-pt-object-detection
Object Detection • 4B • Updated • 1.74k • 4 -
ariG23498/license-detection-paligemma
Viewer • Updated • 8.82k • 536 • 6 -
sergiopaniego/gemma-3-4b-pt-object-detection
Image-Text-to-Text • 4B • Updated • 257
Aritra Roy Gosthipaty PRO
ariG23498
AI & ML interests
Deep Representation Learning
Recent Activity
updated
a dataset
about 2 hours ago
model-metadata/custom_code_execution_files
updated
a dataset
about 2 hours ago
model-metadata/custom_code_execution_files
updated
a dataset
about 2 hours ago
model-metadata/custom_code_execution_files
Organizations
Deploy models to Spaces and Consume them through an API
All the CLIP models in one place
-
openai/clip-vit-base-patch16
Zero-Shot Image Classification • Updated • 4.22M • 127 -
openai/clip-vit-base-patch32
Zero-Shot Image Classification • Updated • 16.7M • 720 -
openai/clip-vit-large-patch14
Zero-Shot Image Classification • 0.4B • Updated • 11.5M • 1.79k -
openai/clip-vit-large-patch14-336
Zero-Shot Image Classification • Updated • 5.02M • 252
Random mistral models that were reduced in size for the TensorFlow port. The link to the porting PR: https://github.com/huggingface/transformers/pull/
-
facebook/mask2former-swin-tiny-ade-semantic
Image Segmentation • Updated • 3.84k • 2 -
facebook/mask2former-swin-tiny-cityscapes-semantic
Image Segmentation • 0.0B • Updated • 3.01k • • 3 -
facebook/mask2former-swin-tiny-coco-instance
Image Segmentation • 0.0B • Updated • 357k • 11 -
facebook/mask2former-swin-tiny-cityscapes-instance
Image Segmentation • 0.0B • Updated • 53
This is a collection of models to showcase various goodies with the `TimmWrapper`.
-
1
Food Classification
🦀Food classifier
-
7
Timm + Transformers
😻Any timm model with the transformers integration
-
ariG23498/vit_base_patch16_224.orig_in21k_ft_in1k.ft_food101
Image Classification • Updated • 23 -
ariG23498/vit_base_patch16_224.augreg2_in21k_ft_in1k.ft_food101
Image Classification • Updated • 27
Quantized Diffusion Models useful for inference on a free tier colab notebook.
This collection will hold tiny models that will be used in the test suite of KerasNLP.
All the models for SAM
Place to store everything for our experiments
-
4
Gemma3 License Plate Detection
📈Gemma 3 for license plate detection
-
ariG23498/gemma-3-4b-pt-object-detection
Object Detection • 4B • Updated • 1.74k • 4 -
ariG23498/license-detection-paligemma
Viewer • Updated • 8.82k • 536 • 6 -
sergiopaniego/gemma-3-4b-pt-object-detection
Image-Text-to-Text • 4B • Updated • 257
-
facebook/mask2former-swin-tiny-ade-semantic
Image Segmentation • Updated • 3.84k • 2 -
facebook/mask2former-swin-tiny-cityscapes-semantic
Image Segmentation • 0.0B • Updated • 3.01k • • 3 -
facebook/mask2former-swin-tiny-coco-instance
Image Segmentation • 0.0B • Updated • 357k • 11 -
facebook/mask2former-swin-tiny-cityscapes-instance
Image Segmentation • 0.0B • Updated • 53
Deploy models to Spaces and Consume them through an API
This is a collection of models to showcase various goodies with the `TimmWrapper`.
-
1
Food Classification
🦀Food classifier
-
7
Timm + Transformers
😻Any timm model with the transformers integration
-
ariG23498/vit_base_patch16_224.orig_in21k_ft_in1k.ft_food101
Image Classification • Updated • 23 -
ariG23498/vit_base_patch16_224.augreg2_in21k_ft_in1k.ft_food101
Image Classification • Updated • 27
Quantized Diffusion Models useful for inference on a free tier colab notebook.
This collection will hold tiny models that will be used in the test suite of KerasNLP.
All the CLIP models in one place
-
openai/clip-vit-base-patch16
Zero-Shot Image Classification • Updated • 4.22M • 127 -
openai/clip-vit-base-patch32
Zero-Shot Image Classification • Updated • 16.7M • 720 -
openai/clip-vit-large-patch14
Zero-Shot Image Classification • 0.4B • Updated • 11.5M • 1.79k -
openai/clip-vit-large-patch14-336
Zero-Shot Image Classification • Updated • 5.02M • 252
All the models for SAM
Random mistral models that were reduced in size for the TensorFlow port. The link to the porting PR: https://github.com/huggingface/transformers/pull/
Place to store everything for our experiments