VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored API & Inference Endpoint

Key Highlights

Qwen 3.5 Multimodal Backbone: Built on top of Qwen/Qwen3.5-4B.
Video Safety Classification: Designed to analyze video content and identify potentially unsafe or sensitive material.
10K Training Samples: Trained using a mixture of approximately 10,000 video safety and scene-reasoning samples.
Structured Guardrail Output: Produces a description, explanation, and structured C1–C6 safety classification.
Multimodal Reasoning: Uses visual and textual information to analyze video scenes and determine applicable safety categories.
Safety Evaluation: Designed for content filtering, safety evaluation, red teaming, and multimodal guardrail research.

Safety Categories

The model classifies content across six predefined categories:

Table with columns: Category, Description
Category	Description
C1 — Sexual Content	Sexual or sexually suggestive content.
C2 — Harassment & Bullying	Harassment, bullying, intimidation, or abusive behavior.
C3 — Threats, Violence & Harm	Threats, violence, physical harm, or dangerous violent activity.
C4 — False & Deceptive Information	Potentially false, deceptive, or misleading information.
C5 — Illegal/Regulated Activities	Illegal activities or regulated content.
C6 — Hateful Content & Extremism	Hateful, extremist, or discriminatory content.

Output Format

The model is trained to produce three primary components:

text

DESCRIPTION: <summary of the video content> EXPLANATION: <reasoning explaining the classification> GUARDRAIL: {  "C1(Sexual Content)": false,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

Example — Safe Content

text

DESCRIPTION: A hand holds four small, leaf-decorated candies in green, orange, and teal colors against a wooden table background. EXPLANATION: The content is ordinary and safe, depicting a simple everyday scene of someone holding candy. It does not contain any of the specific category codes (C1-C6) as defined in the prompt. GUARDRAIL: {  "C1(Sexual Content)": false,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

Example — C1 Classification

text

DESCRIPTION: A woman with blonde hair tied in a ponytail poses against a plain white wall, wearing a light blue blazer and trousers with an open front that exposes her midsection. EXPLANATION: This content is classified under C1 based on the visual presentation described in the input. GUARDRAIL: {  "C1(Sexual Content)": true,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

Quick Start with Transformers

bash

pip install transformerspip install accelerate

python

from transformers import Qwen3_5ForConditionalGeneration, AutoProcessorimport torch model = Qwen3_5ForConditionalGeneration.from_pretrained(    "prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored",    torch_dtype="auto",    device_map="auto") processor = AutoProcessor.from_pretrained(    "prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored") messages = [    {        "role": "user",        "content": [            {                "type": "text",                "text": "Analyze this video and classify it using the C1-C6 guardrail categories."            }        ],    }] text = processor.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True) inputs = processor(    text=[text],    padding=True,    return_tensors="pt").to("cuda") generated_ids = model.generate(    **inputs,    max_new_tokens=256) output_text = processor.batch_decode(    [        out[len(inp):]        for inp, out in zip(inputs.input_ids, generated_ids)    ],    skip_special_tokens=True,    clean_up_tokenization_spaces=False) print(output_text[0])

Training Details

Table with columns: Setting, Value
Setting	Value
Base Model	Qwen/Qwen3.5-4B
Model Type	Multimodal Video Safety Classifier
Training Samples	Approximately 10,000
Training Objective	Video safety classification and scene reasoning
Output Categories	C1–C6
Training Framework	TRL

Training Datasets

prithivMLmods/OpenVideo-Scene-Reasoning: Video scene reasoning dataset used for multimodal video understanding and scene analysis.
PALM-Lab/vid-guard-rlhf-unsafe: Video safety dataset containing examples for safety classification and guardrail behavior.

Intended Use

Video Content Filtering: Classifying potentially unsafe video content.
Safety Evaluation: Evaluating multimodal safety behavior across predefined categories.
Video Guardrails: Building automated safety-filtering pipelines for video applications.
Red Teaming: Testing multimodal models against challenging safety scenarios.
Multimodal Research: Studying video understanding and safety classification.
Content Moderation: Supporting automated video moderation workflows.

Limitations

Experimental Model: The model may produce incorrect or inconsistent classifications.
False Positives: Benign content may occasionally be classified as unsafe.
False Negatives: Unsafe content may occasionally be missed.
Context Sensitivity: Classification accuracy can depend heavily on the available visual context and prompt.
Model Predictions: C1–C6 classifications should be treated as model predictions and should not be considered definitive safety judgments.

Acknowledgements

Qwen/Qwen3.5-4B: Base multimodal model used for this project.
TRL – Transformers Reinforcement Learning: TRL is a full-stack library providing tools to train transformer language models with methods including Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), Direct Preference Optimization (DPO), Reward Modeling, and more.
Transformers: Transformers provides state-of-the-art machine learning models for text, computer vision, audio, video, and multimodal tasks, supporting both inference and training.

Key Highlights

Qwen 3.5 Multimodal Backbone: Built on top of Qwen/Qwen3.5-4B.
Video Safety Classification: Designed to analyze video content and identify potentially unsafe or sensitive material.
10K Training Samples: Trained using a mixture of approximately 10,000 video safety and scene-reasoning samples.
Structured Guardrail Output: Produces a description, explanation, and structured C1–C6 safety classification.
Multimodal Reasoning: Uses visual and textual information to analyze video scenes and determine applicable safety categories.
Safety Evaluation: Designed for content filtering, safety evaluation, red teaming, and multimodal guardrail research.

Safety Categories

The model classifies content across six predefined categories:

Table with columns: Category, Description
Category	Description
C1 — Sexual Content	Sexual or sexually suggestive content.
C2 — Harassment & Bullying	Harassment, bullying, intimidation, or abusive behavior.
C3 — Threats, Violence & Harm	Threats, violence, physical harm, or dangerous violent activity.
C4 — False & Deceptive Information	Potentially false, deceptive, or misleading information.
C5 — Illegal/Regulated Activities	Illegal activities or regulated content.
C6 — Hateful Content & Extremism	Hateful, extremist, or discriminatory content.

Output Format

The model is trained to produce three primary components:

text

DESCRIPTION: <summary of the video content>EXPLANATION: <reasoning explaining the classification>GUARDRAIL: {  "C1(Sexual Content)": false,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

DESCRIPTION: <summary of the video content> EXPLANATION: <reasoning explaining the classification> GUARDRAIL: {  "C1(Sexual Content)": false,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

Example — Safe Content

text

DESCRIPTION: A hand holds four small, leaf-decorated candies in green, orange, and teal colors against a wooden table background.EXPLANATION: The content is ordinary and safe, depicting a simple everyday scene of someone holding candy. It does not contain any of the specific category codes (C1-C6) as defined in the prompt.GUARDRAIL: {  "C1(Sexual Content)": false,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

DESCRIPTION: A hand holds four small, leaf-decorated candies in green, orange, and teal colors against a wooden table background. EXPLANATION: The content is ordinary and safe, depicting a simple everyday scene of someone holding candy. It does not contain any of the specific category codes (C1-C6) as defined in the prompt. GUARDRAIL: {  "C1(Sexual Content)": false,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

Example — C1 Classification

text

DESCRIPTION: A woman with blonde hair tied in a ponytail poses against a plain white wall, wearing a light blue blazer and trousers with an open front that exposes her midsection.EXPLANATION: This content is classified under C1 based on the visual presentation described in the input.GUARDRAIL: {  "C1(Sexual Content)": true,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

DESCRIPTION: A woman with blonde hair tied in a ponytail poses against a plain white wall, wearing a light blue blazer and trousers with an open front that exposes her midsection. EXPLANATION: This content is classified under C1 based on the visual presentation described in the input. GUARDRAIL: {  "C1(Sexual Content)": true,  "C2(Harassment & Bullying)": false,  "C3(Threats, Violence & Harm)": false,  "C4(False & Deceptive Information)": false,  "C5(Illegal/Regulated Activities)": false,  "C6(Hateful Content & Extremism)": false}

Quick Start with Transformers

bash

pip install transformerspip install accelerate

pip install transformerspip install accelerate

python

from transformers import Qwen3_5ForConditionalGeneration, AutoProcessorimport torch model = Qwen3_5ForConditionalGeneration.from_pretrained(    "prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored",    torch_dtype="auto",    device_map="auto") processor = AutoProcessor.from_pretrained(    "prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored") messages = [    {        "role": "user",        "content": [            {                "type": "text",                "text": "Analyze this video and classify it using the C1-C6 guardrail categories."            }        ],    }] text = processor.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True) inputs = processor(    text=[text],    padding=True,    return_tensors="pt").to("cuda") generated_ids = model.generate(    **inputs,    max_new_tokens=256) output_text = processor.batch_decode(    [        out[len(inp):]        for inp, out in zip(inputs.input_ids, generated_ids)    ],    skip_special_tokens=True,    clean_up_tokenization_spaces=False) print(output_text[0])

from transformers import Qwen3_5ForConditionalGeneration, AutoProcessorimport torch model = Qwen3_5ForConditionalGeneration.from_pretrained(    "prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored",    torch_dtype="auto",    device_map="auto") processor = AutoProcessor.from_pretrained(    "prithivMLmods/VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored") messages = [    {        "role": "user",        "content": [            {                "type": "text",                "text": "Analyze this video and classify it using the C1-C6 guardrail categories."            }        ],    }] text = processor.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True) inputs = processor(    text=[text],    padding=True,    return_tensors="pt").to("cuda") generated_ids = model.generate(    **inputs,    max_new_tokens=256) output_text = processor.batch_decode(    [        out[len(inp):]        for inp, out in zip(inputs.input_ids, generated_ids)    ],    skip_special_tokens=True,    clean_up_tokenization_spaces=False) print(output_text[0])

Training Details

Table with columns: Setting, Value
Setting	Value
Base Model	Qwen/Qwen3.5-4B
Model Type	Multimodal Video Safety Classifier
Training Samples	Approximately 10,000
Training Objective	Video safety classification and scene reasoning
Output Categories	C1–C6
Training Framework	TRL

Training Datasets

prithivMLmods/OpenVideo-Scene-Reasoning: Video scene reasoning dataset used for multimodal video understanding and scene analysis.
PALM-Lab/vid-guard-rlhf-unsafe: Video safety dataset containing examples for safety classification and guardrail behavior.

Intended Use

Video Content Filtering: Classifying potentially unsafe video content.
Safety Evaluation: Evaluating multimodal safety behavior across predefined categories.
Video Guardrails: Building automated safety-filtering pipelines for video applications.
Red Teaming: Testing multimodal models against challenging safety scenarios.
Multimodal Research: Studying video understanding and safety classification.
Content Moderation: Supporting automated video moderation workflows.

Limitations

Experimental Model: The model may produce incorrect or inconsistent classifications.
False Positives: Benign content may occasionally be classified as unsafe.
False Negatives: Unsafe content may occasionally be missed.
Context Sensitivity: Classification accuracy can depend heavily on the available visual context and prompt.
Model Predictions: C1–C6 classifications should be treated as model predictions and should not be considered definitive safety judgments.

Acknowledgements

Qwen/Qwen3.5-4B: Base multimodal model used for this project.
TRL – Transformers Reinforcement Learning: TRL is a full-stack library providing tools to train transformer language models with methods including Supervised Fine-Tuning (SFT), Group Relative Policy Optimization (GRPO), Direct Preference Optimization (DPO), Reward Modeling, and more.
Transformers: Transformers provides state-of-the-art machine learning models for text, computer vision, audio, video, and multimodal tasks, supporting both inference and training.

VideoGuard-Qwen3.5-4B-Safety-RL-Uncensored

README

Key Highlights

Safety Categories

Output Format

Example — Safe Content

Example — C1 Classification

Quick Start with Transformers

Training Details

Training Datasets

Intended Use

Limitations

Acknowledgements

Explore FriendliAI today

README

Key Highlights

Safety Categories

Output Format

Example — Safe Content

Example — C1 Classification

Quick Start with Transformers

Training Details

Training Datasets

Intended Use

Limitations

Acknowledgements