Downloads · 30 days
34
14% of all-time downloads
resnet50_7.9um_scroll1_frags
scrollprize/resnet50_7.9um_scroll1_frags
resnet50_7.9um_scroll1_frags is a feature extraction model from scrollprize. Use it when you need embeddings to search or compare text. It is set up for transformers.
Model details: nclasses=1139 windowsize=256 nlayers=18
All-time downloads
246
Public
Parameters
85.7M
343 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors343 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- resnetscrollprize
- Access
- Public
- Created
- Dec 12, 2024
- Updated
- Dec 17, 2024
- SHA
- f3975de3
Model card
From the Hugging Face model README
Fragments Resnet503D weights
Model details:
n_classes=1139
window_size=256
n_layers=18
Pretrained on Pherc.Paris4 on Fragments and Fragment Hidden layers:
['20240814211913','20231210121321','frag2','frag6','frag1','frag3','frag4','frag5','20240813112037','20240813194718','20240814122007','20240814124338','20240814125124','20240815194445','20240818211653','20240820102547','20240820102554','20240820103254','20240820133348','20240816164032','20240814230136','20240820150159','20240906213422','20240907121934']
To get started with this model, follow the instructions:
https://github.com/ScrollPrize/villa/tree/main/ink-detection
- Task
- Feature Extraction
- Library
- transformers
- Type
- resnetscrollprize
- Created
- Dec 12, 2024
- Updated
- Dec 17, 2024