# Load model directly
from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
processor = AutoProcessor.from_pretrained("mtilerisoyy/medsiglip-448-ft-crc100k")
model = AutoModelForZeroShotImageClassification.from_pretrained("mtilerisoyy/medsiglip-448-ft-crc100k", device_map="auto")Quick Links
medsiglip-448-ft-crc100k
This model is a fine-tuned version of google/medsiglip-448 on the imagefolder dataset.
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use adamw_torch 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: 2
Training results
Framework versions
- Transformers 4.56.1
- Pytorch 2.3.0+cu121
- Datasets 4.1.1
- Tokenizers 0.22.0
- Downloads last month
- 4
Model tree for mtilerisoyy/medsiglip-448-ft-crc100k
Base model
google/medsiglip-448
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="mtilerisoyy/medsiglip-448-ft-crc100k") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )