Instructions to use Seungjun/image_captioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Seungjun/image_captioner 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="Seungjun/image_captioner")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Seungjun/image_captioner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 118 Bytes
7f5b8c9 | 1 2 3 4 5 6 7 8 | {
"d_model": 512,
"dropout": 0.4,
"max_length": 32,
"num_heads": 8,
"num_layers": 4,
"vocab_size": 30522
} |