Reinforcement Learning
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
vision-language
fine-grained-recognition
visual-reasoning
qwen
text-generation-inference
Instructions to use raja-kumar/DiVE-k-QWEN2.5-7B-CUB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use raja-kumar/DiVE-k-QWEN2.5-7B-CUB with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("raja-kumar/DiVE-k-QWEN2.5-7B-CUB") model = AutoModelForImageTextToText.from_pretrained("raja-kumar/DiVE-k-QWEN2.5-7B-CUB") - Notebooks
- Google Colab
- Kaggle
| global_step399 |