Image-to-Text
Transformers
PyTorch
ONNX
vision-encoder-decoder
image-text-to-text
image-captioning
Eval Results (legacy)
Instructions to use tarekziade/distilvit-pexels-frozen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tarekziade/distilvit-pexels-frozen 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/distilvit-pexels-frozen")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("tarekziade/distilvit-pexels-frozen") model = AutoModelForImageTextToText.from_pretrained("tarekziade/distilvit-pexels-frozen") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token_id": 50256, | |
| "do_sample": true, | |
| "early_stopping": true, | |
| "eos_token_id": 50256, | |
| "max_length": 50, | |
| "max_time": 5, | |
| "no_repeat_ngram_size": 2, | |
| "num_beams": 2, | |
| "pad_token_id": 50256, | |
| "repetition_penalty": 1.4, | |
| "seed": 12, | |
| "temperature": 0.8, | |
| "top_p": 0.9, | |
| "transformers_version": "4.33.2" | |
| } | |