# Load model directly
from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
processor = AutoProcessor.from_pretrained("Shadowmachete/CLIP")
model = AutoModelForZeroShotImageClassification.from_pretrained("Shadowmachete/CLIP")Quick Links
CLIP
This model is a fine-tuned version of openai/clip-vit-base-patch16 on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1492
- eval_runtime: 526.0225
- eval_samples_per_second: 10.614
- eval_steps_per_second: 0.663
- epoch: 1.0
- step: 1396
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Framework versions
- Transformers 4.46.0
- Pytorch 2.6.0+cu126
- Datasets 2.19.0
- Tokenizers 0.20.1
- Downloads last month
- 4
Model tree for Shadowmachete/CLIP
Base model
openai/clip-vit-base-patch16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Shadowmachete/CLIP") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )