Instructions to use sooh-j/VQA-for-VIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sooh-j/VQA-for-VIP with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="sooh-j/VQA-for-VIP")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("sooh-j/VQA-for-VIP") model = AutoModelForMultimodalLM.from_pretrained("sooh-j/VQA-for-VIP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from sooh-j/VQA-for-VIP: direct link, hf CLI and curl.
- Browser
- Download file 136 Bytes
-
https://huggingface.co/sooh-j/VQA-for-VIP/resolve/main/generation_config.json
- Command line
-
hf download hf://sooh-j/VQA-for-VIP/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/sooh-j/VQA-for-VIP/resolve/main/generation_config.json
136 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 2, | |
| "eos_token_id": 50118, | |
| "pad_token_id": 1, | |
| "transformers_version": "4.41.2" | |
| } | |