Image-to-Text
Transformers
Safetensors
Vietnamese
vision-encoder-decoder
image-text-to-text
image-captioning
vietnamese
deit
gpt2
Instructions to use slyviee/vietnamese-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use slyviee/vietnamese-image-captioning 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="slyviee/vietnamese-image-captioning")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("slyviee/vietnamese-image-captioning") model = AutoModelForImageTextToText.from_pretrained("slyviee/vietnamese-image-captioning") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 50257, | |
| "eos_token_id": [ | |
| 50257, | |
| 50256 | |
| ], | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 50257, | |
| "transformers_version": "5.0.0", | |
| "use_cache": true | |
| } | |