metadata
license: apache-2.0
datasets:
- MVISU-Bench/MVISU-Bench
language:
- en
- zh
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
Qwen2.5-VL-3B-Mobile-Aider
Qwen2.5-VL-3B-Mobile-Aider is a fine-tuned version of Qwen2.5-VL-3B-Instruct, specifically optimized for mobile agent tasks.
Model Details
- Developed by: MVISU-Bench Team
- Model type: Vision-Language Model
- Language(s): English, Chinese
- License: Apache-2.0
- Finetuned from: Qwen2.5-VL-3B-Instruct
Model Sources
- Dataset: MVISU-Bench Dataset
How to Get Started
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("MVISU-Bench/Qwen2.5-VL-3B-Mobile-Aider")
tokenizer = AutoTokenizer.from_pretrained("MVISU-Bench/Qwen2.5-VL-3B-Mobile-Aider")