GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
tyodd
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
tyodd
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
SafeGuard-VL-RL is trained using Stage-2 RL only (without the Stage-1 SFT). It applies GRPO (from DeepSeekMath) on the LlavaGuard training set. For each image-policy pair, the ground truth safe/unsafe label serves as the reward signal, encouraging the model to reason about why a given image violates or complies with the policy.
| Detail | Value |
|---|---|
| Base Model | Qwen2.5-VL-7B-Instruct |
| Training Method | GRPO (Group Relative Policy Optimization) |
| Training Data | AIML-TUDA/LlavaGuard (train split) |
python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom qwen_vl_utils import process_vision_info model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "tyodd/SafeGuard-VL-RL", torch_dtype="auto", device_map="auto",)processor = AutoProcessor.from_pretrained("tyodd/SafeGuard-VL-RL") # Example: Safety evaluation with a custom policypolicy = """""" messages = [ { "role": "user", "content": [ {"type": "image", "image": "path/to/image.jpg"}, {"type": "text", "text": f"Based on the following safety policy, determine if this image is safe or unsafe.\n\nPolicy:\n{policy}\n\nProvide your reasoning and final judgment (Safe/Unsafe)."}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs = process_vision_info(messages)inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt",).to(model.device) generated_ids = model.generate(**inputs, max_new_tokens=512)generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)print(output_text[0])bibtex
@inproceedings{piao2026towards, title={Towards policy-adaptive image guardrail: Benchmark and method}, author={Piao, Caiyong and Yan, Zhiyuan and Xu, Haoming and Zhao, Yunzhen and Lin, Kaiqing and Xu, Feiyang and Zhou, Shuigeng}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={16614--16623}, year={2026}}This model is designed for safety research purposes. It was trained on data containing unsafe content categories and is intended to help identify potentially harmful visual content. The model's judgments are policy-dependent and should not be used as the sole arbiter of content safety in production systems without human oversight.
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom qwen_vl_utils import process_vision_info model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "tyodd/SafeGuard-VL-RL", torch_dtype="auto", device_map="auto",)processor = AutoProcessor.from_pretrained("tyodd/SafeGuard-VL-RL") # Example: Safety evaluation with a custom policypolicy = """""" messages = [ { "role": "user", "content": [ {"type": "image", "image": "path/to/image.jpg"}, {"type": "text", "text": f"Based on the following safety policy, determine if this image is safe or unsafe.\n\nPolicy:\n{policy}\n\nProvide your reasoning and final judgment (Safe/Unsafe)."}, ], }] text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)image_inputs, video_inputs = process_vision_info(messages)inputs = processor( text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt",).to(model.device) generated_ids = model.generate(**inputs, max_new_tokens=512)generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)print(output_text[0])@inproceedings{piao2026towards, title={Towards policy-adaptive image guardrail: Benchmark and method}, author={Piao, Caiyong and Yan, Zhiyuan and Xu, Haoming and Zhao, Yunzhen and Lin, Kaiqing and Xu, Feiyang and Zhou, Shuigeng}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={16614--16623}, year={2026}}