Base_model

Qwen/Qwen2.5-VL-7B-Instruct

Training Data

We use same dataset from Open-o3-video

Stage	Dataset
SFT	STGR-SFT.json
RL	STGR-RL.json

Usage

from transformers import AutoModelForCausalLM, AutoProcessor

model = AutoModelForCausalLM.from_pretrained("danaleee/VisionCoach-7B")
processor = AutoProcessor.from_pretrained("danaleee/VisionCoach-7B")