HuggingFaceM4/DocumentVQA
Viewer • Updated • 50k • 3.14k • 46
How to use Venkat-Ram-Rao/unsloth_finetune-QWEN-7b-docvqa with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Venkat-Ram-Rao/unsloth_finetune-QWEN-7b-docvqa", device_map="auto")This qwen2_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.