Instructions to use mispeech/r1-aqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/r1-aqa with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mispeech/r1-aqa") model = AutoModelForMultimodalLM.from_pretrained("mispeech/r1-aqa") - Notebooks
- Google Colab
- Kaggle
The provided demo file does not include any inference process?
#5
by Alex-Song - opened
The provided demo file does not include any inference process and directly outputs: Man .
The pretrained (SoTA) model only outputs the final answer, refering to the "GRPO + Prompt <2>" in our technical report. If you want to see the "thinking" porcess ("GRPO + Prompt <3>"), plz visit our GitHub homepage for more details.
frankenliu changed discussion status to closed