Instructions to use Susant-Achary/SmolVLM2-500M-Video-Instruct-vqav2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Susant-Achary/SmolVLM2-500M-Video-Instruct-vqav2 with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("HuggingFaceTB/SmolVLM2-500M-Video-Instruct") model = PeftModel.from_pretrained(base_model, "Susant-Achary/SmolVLM2-500M-Video-Instruct-vqav2") - Transformers
How to use Susant-Achary/SmolVLM2-500M-Video-Instruct-vqav2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Susant-Achary/SmolVLM2-500M-Video-Instruct-vqav2")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Susant-Achary/SmolVLM2-500M-Video-Instruct-vqav2", dtype="auto") - Notebooks
- Google Colab
- Kaggle