Image-to-Text
Transformers
ONNX
Safetensors
vision-encoder-decoder
image-text-to-text
image-captioning
Instructions to use tarekziade/deit-tiny-distilgpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tarekziade/deit-tiny-distilgpt2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="tarekziade/deit-tiny-distilgpt2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("tarekziade/deit-tiny-distilgpt2") model = AutoModelForMultimodalLM.from_pretrained("tarekziade/deit-tiny-distilgpt2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from tarekziade/deit-tiny-distilgpt2: direct link, hf CLI and curl.
- Browser
- Download file 424 Bytes
-
https://huggingface.co/tarekziade/deit-tiny-distilgpt2/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://tarekziade/deit-tiny-distilgpt2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/tarekziade/deit-tiny-distilgpt2/resolve/main/preprocessor_config.json
424 Bytes
| { | |
| "crop_size": { | |
| "height": 224, | |
| "width": 224 | |
| }, | |
| "do_center_crop": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "DeiTFeatureExtractor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| } | |