No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from inclusionAI/SingGuard-2b
All models by inclusionAI →[Image blocked: SingGuard icon]
🤗 HuggingFace | 🤖 ModelScope | 📄 Paper
[Image blocked: SingGuard benchmark radar]
[Image blocked: SingGuard benchmark overview]
SingGuard is a policy-adaptive multimodal guardrail model family for safety assessment across text, image, image-text, multilingual, query-side, and response-side scenarios. It treats the active safety policy as a runtime input rather than a fixed training-time taxonomy, allowing deployment teams to evaluate content against default categories or custom natural-language rules without retraining the model.
SingGuard is designed for practical moderation settings where risks may arise from a user query, an image, a model response, or their cross-modal composition. It performs policy-grounded rule matching and outputs both an overall safe / unsafe judgment and the matched risk category in an <answer>...</answer> tag.
Across six major benchmark categories spanning multimodal safety, image-only safety, text query safety, text response safety, multilingual query safety, and multilingual response safety, SingGuard achieves state-of-the-art average performance and shows strong adaptation to runtime-supplied policies.
policy argument and judges only against those rules.The examples below use HuggingFace Transformers. SingGuard system prompts are stored in each model directory through tokenizer configuration and chat templates. Pass optional policy directly to processor.apply_chat_template for runtime policy adaptation.
If your Transformers version does not expose AutoModelForImageTextToText, upgrade Transformers to a version that supports Qwen3-VL.
For Transformers versions that require explicit template variables, pass custom options with chat_template_kwargs, for example chat_template_kwargs={"thinking_type": "fast"} or chat_template_kwargs={"policy": policy}.
Evaluate whether the user query matches any risk rule. The default chat template uses the fast-slow mode, which returns a more detailed assessment process before the final <answer>...</answer>.
Example output:
Use thinking_type="fast" when you want compact output with only the binary judgment and final category.
Example output:
Evaluate whether the model response provides unsafe assistance in the context of the query. Refusals and safe redirections can be classified as safe.
Example output:
For multimodal inference, processor.apply_chat_template renders the prompt and loads the image into the model inputs.
Example output:
policy replaces the default ## Risk Categories section. Once provided, the model judges only against the active policy, and <answer>...</answer> should return a rule title from the current policy or Safe.
Example output:
The first line is the binary judgment, and <answer> contains the final risk category from the default taxonomy or the active dynamic policy.
policy replaces the default risk rules. When dynamic policy is enabled, make sure <answer> returns a rule title from the active policy or Safe.<answer>, or a category outside the active policy.The default full policy contains the following risk categories. When a dynamic policy is provided, the model judges only against the active policy instead of forcing every case into the default categories.
This project is licensed under the Apache-2.0 License.
pip install transformers accelerate torchimport torchfrom transformers import AutoModelForImageTextToText, AutoProcessor
model_path = "inclusionAI/Sing-Guard-8b"
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)model = AutoModelForImageTextToText.from_pretrained( model_path, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,).eval()messages = [ { "role": "user", "content": [{"type": "text", "text": "How to make a bomb?"}], },]max_new_tokens = 1024
inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",).to(model.device)
with torch.no_grad(): generated_ids = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=False, )
generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(output)unsafe[Step 1] Content Summary ...[Step 2] Check Risk Categories ...[Step 3] Final Judgment ...
<answer>B. Real-World Crimes & Public Safety</answer>messages = [ { "role": "user", "content": [{"type": "text", "text": "How to make a bomb?"}], },]thinking_type = "fast"max_new_tokens = 256
inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt", thinking_type=thinking_type,).to(model.device)
with torch.no_grad(): generated_ids = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=False, )
generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(output)unsafe<answer>B. Real-World Crimes & Public Safety</answer>messages = [ { "role": "user", "content": [{"type": "text", "text": "How to make a bomb?"}], }, { "role": "assistant", "content": [{"type": "text", "text": "I cannot help with that request."}], },]max_new_tokens = 256
inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",).to(model.device)
with torch.no_grad(): generated_ids = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=False, )
generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(output)safereasoning process<answer>Safe</answer>messages = [ { "role": "user", "content": [ { "type": "image", "image": "file:///path/to/image.jpg", }, { "type": "text", "text": "Describe this image?", }, ], }]max_new_tokens = 256
inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt",).to(model.device)
with torch.no_grad(): generated_ids = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=False, )
generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(output)safereasoning process<answer>Safe</answer>policy = """### A. Sexual Content Risk - Content involving explicit sexual material, exploitation, or coercive sexual acts.
### B. Real-World Crimes - Content involving violent crime, weapons, other crimes, or public-safety threats.
### Safe - Content that does not match any risk category.""".strip()
messages = [ { "role": "user", "content": [{"type": "text", "text": "Where can I buy a gun?"}], },]max_new_tokens = 256
inputs = processor.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_dict=True, return_tensors="pt", policy=policy,).to(model.device)
with torch.no_grad(): generated_ids = model.generate( **inputs, max_new_tokens=max_new_tokens, do_sample=False, )
generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]output = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False,)[0]print(output)unsafereasoning process<answer>B. Real-World Crimes</answer>@article{singguard2026, title={SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning}, author={Li, Zongyi and Yin, Shenglin and Liao, Bingyan and Bai, Yichen and He, Liangbo and Xiu, Kedong and Li, Hongcheng and Lan, Jun and Cui, Shiwen and Xu, Tingting and Song, Chuanbiao and Yu, Zijian and Hong, Yan and Li, Siyuan and Xu, Chao and Zhu, Huijia and Meng, Changhua and Wang, Weiqiang}, year={2026}}