GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
SESPOIR
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
SESPOIR
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGenerationmodel_id = "SESPOIR/ReGround-Qwen2.5-VL-7B"model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_id,dtype="auto",device_map="auto",)processor = AutoProcessor.from_pretrained(model_id)
For complete two-round visual inference and evaluation, follow the ReGround repository.
Stage 1 applies full-parameter supervised fine-tuning to
Qwen2.5-VL-7B-Instruct using structured visual reasoning trajectories. Stage 2
uses GRPO to optimize self-diagnosis, answer accuracy, and output format. The
training format uses <think>, <reground>, and <answer> blocks; portable
configurations for both stages are available in the project repository.
The model can produce incorrect reasoning or answers and may trigger visual re-examination unnecessarily. It is intended for research use and should not be relied on for high-stakes decisions without independent verification.