pipeline_tag: video-text-to-text
library_name: transformers
tags:

• text-generation-inference
• llama-cpp
• reinforcement-learning
• video-text-to-text
• alignment-training
• RLHF
• RFT
• video-understanding
• video-classification
• video-safety
• content-safety
• content-moderation
• safety-classifier
• guardrail
  datasets:
• prithivMLmods/OpenVideo-Scene-Reasoning
• PALM-Lab/vid-guard-rlhf-unsafe
  license: apache-2.0
  language:
• en
  base_model:
• prithivMLmods/VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored

VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored-GGUF

VideoGuard-Qwen3.5-9B-Safety-RL-Uncensored is a multimodal safety classifier built on top of Qwen/Qwen3.5-9B. The model was trained on a mixture of approximately 10,000 video safety and scene-reasoning samples to analyze video content and classify potentially unsafe content across predefined safety categories. The model is designed to generate a structured DESCRIPTION, EXPLANATION, and GUARDRAIL output, making it suitable for video content filtering, safety evaluation, and multimodal guardrail research.

[!NOTE]
This model is an experimental release and may generate unexpected classifications or reasoning artifacts in certain scenarios. Safety classifications should be treated as model predictions rather than definitive judgments.

[!NOTE]
Use BF16 / FP16 for better reasoning and safety evaluations.

Model Files

llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp