Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
pedestrianqa
qwen2.5-vl
vision-language
video-question-answering
autonomous-driving
pedestrian-intention-prediction
pedestrian-trajectory-prediction
rationale-generation
text-generation-inference
Instructions to use namansmishaps/PedestrianQA-TITAN-Qwen2.5-VL-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use namansmishaps/PedestrianQA-TITAN-Qwen2.5-VL-3B-Instruct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("namansmishaps/PedestrianQA-TITAN-Qwen2.5-VL-3B-Instruct") model = AutoModelForMultimodalLM.from_pretrained("namansmishaps/PedestrianQA-TITAN-Qwen2.5-VL-3B-Instruct") - Notebooks
- Google Colab
- Kaggle
| { | |
| "attn_implementation": "flash_attention_2", | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.05, | |
| "temperature": 1e-06, | |
| "transformers_version": "4.50.0" | |
| } | |