Downloads · 30 days
13
6% of all-time downloads
medsiglip-448-vindr-bin
aysangh/medsiglip-448-vindr-bin
medsiglip-448-vindr-bin is a image classification model from aysangh. Use it when you need a label for an image. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
231
Public
Parameters
429M
10.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- other
- Model type
- siglip
- Access
- Public
- Created
- Oct 19, 2025
- Updated
- Oct 21, 2025
- SHA
- 85ec8883
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
medsiglip-448-vindr-bin
This model is a fine-tuned version of google/medsiglip-448 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1123
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2129 | 0.6823 | 40 | 0.1123 |
Framework versions
- Transformers 4.55.0
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4
- Task
- Image Classification
- Library
- transformers
- Type
- siglip
- License
- other
- Created
- Oct 19, 2025
- Updated
- Oct 21, 2025