This repository contains the OPPO model weights for multimodal emotion recognition and reasoning.
1from transformers import AutoProcessor, Qwen2_5OmniThinkerForConditionalGeneration
2
3model_id = "AaronHan/OPPO"
4processor = AutoProcessor.from_pretrained(model_id)
5model = Qwen2_5OmniThinkerForConditionalGeneration.from_pretrained(
6 model_id,
7 torch_dtype="auto",
8 device_map="auto",
9)
The repository includes the sharded model weights, weight index, model and generation configurations, tokenizer files, chat template, and multimodal preprocessor configurations required to load the model.
