You can deploy this model and start earning money today!

aitf-komdigi/
Komdigi-3b-pad-merged

Name: Komdigi-3b-pad-merged
Availability: InStock

aitf-komdigi/KomdigiITS-3B-PAD-CPT

finetune

apache-2.0

Views

No views yet

Komdigi-3b-pad-merged

Model Description

Komdigi-3b-pad-merged is a unified multi-task Vision-Language Model developed for the Perlindungan Anak di Ruang Digital (PAD) use case. Unlike a model that is limited to image analysis, this model is designed to handle multiple PAD-related tasks within a single architecture.

The model is trained as a unified VLM to perform:

Text classification with reasoning
Image classification with reasoning
Keyword generation

The main purpose of the model is to support content analysis, age-rating classification, reasoning generation, and keyword extraction in the context of digital child protection. It is intended for research, prototyping, and human-in-the-loop moderation systems.

Model Details

Attribute	Value
Model name	`aitf-komdigi/Komdigi-3b-pad-merged`
Model type	Unified Vision-Language Model
Architecture	Mistral3 / Pixtral-style Vision-Language Model
Base model	`aitf-komdigi/KomdigiITS-3B-PAD-CPT`
Parameter size	Approximately 4B parameters
Tensor type	BF16
File format	Safetensors
Main language	Indonesian
Secondary language	English
Domain	Perlindungan Anak di Ruang Digital
Training approach	Multi-task supervised fine-tuning
Model status	Merged model
Supported tasks	Text classification, image classification, keyword generation

Supported Tasks

1. Text Classification with Reasoning

The model can analyze text-based content such as captions, posts, comments, or short-form digital content. It predicts the appropriate age-rating or content-safety category and provides a reasoning explanation for the prediction.

Example use cases:

analyzing social media captions,
classifying text-based digital content,
generating explanation for the assigned rating,
supporting human moderation review.

2. Image Classification with Reasoning

The model can analyze visual content and classify it into the appropriate PAD rating category. It can also generate reasoning based on visual evidence observed in the image.

Example use cases:

analyzing social media images,
detecting content that may not be suitable for certain age groups,
explaining visual factors that influence the classification,
supporting review of image-based content.

3. Keyword Generator

The model can generate relevant keywords from a given content context. This task is useful for indexing, search, moderation tagging, and content understanding.

Example use cases:

generating moderation keywords,
extracting relevant content tags,
supporting content retrieval,
improving downstream filtering or recommendation systems.

Intended Use

Direct Use

This model is intended for PAD-related content analysis, including:

classifying text content with reasoning,
classifying image content with reasoning,
generating relevant keywords from content context,
supporting content moderation workflows,
assisting age-rating recommendation,
supporting Indonesian child-safety research and prototyping.

Downstream Use

The model may be integrated into larger systems such as:

content moderation dashboards,
child-safety screening tools,
age-rating recommendation systems,
keyword tagging systems,
content indexing pipelines,
human-in-the-loop moderation platforms.

Out-of-Scope Use

This model should not be used as the sole authority for:

final legal or regulatory decisions,
fully automated content takedown,
law enforcement decisions,
identifying or profiling individuals,
determining the real age or identity of a person,
surveillance or invasive monitoring,
medical, psychological, or legal assessment.

The model should assist human reviewers, not replace human judgment.

Rating Categories

The model is trained to classify content into the following PAD rating categories:

Rating	General Meaning
`Semua Umur`	Content that is generally safe, neutral, educational, or child-friendly.
`7+`	Content that may require light age guidance for children above 7 years old.
`13+`	Content that may contain themes more suitable for teenagers.
`15+`	Content that may contain stronger themes requiring older teen maturity.
`18+`	Content suitable only for adults.
`Konten Terlarang`	Content that violates safety rules or should not be distributed.
`Unrated`	Content that cannot be confidently classified or does not fit the available categories.

The exact interpretation of each category should follow the PAD annotation guideline used during dataset construction.

Recommended Output Format

For classification tasks, the model can be prompted to return structured JSON.

json

{
  "rating": "string",
  "reason": "string"
}

For keyword generation, the recommended output format is:

json

{
  "keywords": ["keyword_1", "keyword_2", "keyword_3"]
}

For a combined response, the following schema can be used:

json

{
  "task": "classification_or_keyword_generation",
  "rating": "string",
  "reason": "string",
  "keywords": ["keyword_1", "keyword_2", "keyword_3"]
}

Training Details

Training Dataset Composition

The model was trained using a unified multi-task supervised fine-tuning strategy. The training data combines task-specific datasets that were converted into a shared instruction-following format, allowing the same VLM architecture to learn text classification, image classification, reasoning generation, and keyword generation in a single training workflow.

The training notebook uses a combined multi-task dataset loaded from:

nuresens/PAD-Combined-Dataset_v6

The dataset is separated into three task sources using the source field:

Source	Task	Number of Samples
`pad1`	Text Classification with Reasoning	13,406
`pad2`	Keyword Generator	15,030
`pad3`	Image Classification with Reasoning	62,427
Total	All Tasks	90,863

The three sources are merged into a single metadata dataset containing the following columns:

Column	Description
`messages`	Chat-style instruction data containing user prompts and assistant responses.
`source`	Dataset source identifier: `pad1`, `pad2`, or `pad3`.
`source_idx`	Original row index from each source dataset.
`has_image`	Boolean marker indicating whether the sample contains an image placeholder.

Feature Structure

Column	Type	Description
`image`	Image	Visual input used by the vision-language model for image-based classification and reasoning.
`messages`	List	Conversation-style instruction data containing user prompts and assistant responses.

The messages field follows a chat-style structure consisting of role and content. This structure allows the dataset to support multimodal supervised fine-tuning across different task instructions. Text classification and keyword generation samples are text-only instruction samples, while image classification samples include image placeholders and are lazily paired with their original images during collation.

Dataset Statistics

1. Image Classification and Reasoning Dataset

The image classification and reasoning dataset consists of 62,427 samples. The dataset is used to train the model to analyze visual content and predict the appropriate PAD rating category with an accompanying explanation.

Rating	Number of Samples	Percentage
Semua Umur	15,973	25.59%
13+	9,422	15.09%
7+	8,189	13.12%
Konten Terlarang	7,676	12.30%
Unrated	7,497	12.01%
18+	6,851	10.97%
15+	6,819	10.92%
Total	62,427	100.00%

The largest category in the image classification dataset is Semua Umur, representing 25.59% of the dataset. The remaining categories are distributed between approximately 10.92% and 15.09%, indicating a moderately imbalanced dataset.

2. Text Classification and Reasoning Dataset

The text classification and reasoning dataset consists of 13,406 rows. This dataset is used to train the model to classify text-based content into age-rating categories and generate explanations that justify the classification.

Label Rating Usia	Main Content Characteristics	Number of Rows	Percentage
Konten Terlarang	Judi online, kekerasan verbal, pelecehan, SARA	4,497	33.54%
Semua Umur	Ramah keluarga, aktivitas keseharian yang positif	3,252	24.26%
15+	Diskusi sosial-politik, kriminalitas tanpa glorifikasi	1,826	13.62%
13+	Curahan hati remaja, konflik sosial pertemanan	1,458	10.88%
7+	Edukasi ringan, hiburan anak, persaingan olahraga	1,239	9.24%
18+	Romansa dewasa, gaya hidup malam, edukasi self-harm	1,134	8.46%
Total	Dataset Master SFT	13,406	100.00%

The text classification dataset is more imbalanced than the image classification dataset. The largest category is Konten Terlarang, representing 33.54% of the dataset, followed by Semua Umur at 24.26%. The smaller categories, especially 18+ and 7+, should be monitored carefully during evaluation using macro-averaged metrics.

3. Keyword Generator Dataset

The keyword generator dataset consists of 15,030 records. This dataset is used to train the model to generate a variable number of relevant keywords from a given content context.

Number of Keywords	Number of Records	Percentage
1	845	5.62%
2	2,347	15.62%
3	4,700	31.27%
4	3,691	24.56%
5	1,528	10.17%
6	671	4.46%
7	327	2.18%
8	238	1.58%
9	218	1.45%
10	275	1.83%
11	65	0.43%
12	57	0.38%
13	32	0.21%
14	23	0.15%
15	10	0.07%
16	1	0.01%
Total	15,030	100.00%

The keyword generator dataset is concentrated around outputs containing 3 to 4 keywords, which together account for 55.83% of all records. The average number of keywords per record is approximately 3.81, with a median and mode of 3 keywords. This indicates that the keyword generation task is primarily optimized for concise keyword outputs rather than long keyword lists.

Dataset Split

The dataset is split using a source-aware strategy. Each source is split independently using an 80:10:10 ratio, then recombined into train, validation, and test splits. This ensures that all tasks remain represented proportionally in each split.

Overall Split

Split	Number of Samples	Percentage
Train	72,689	80.00%
Validation	9,087	10.00%
Test	9,087	10.00%
Total	90,863	100.00%

Split by Task Source

Source	Task	Train	Validation	Test	Total
`pad1`	Text Classification with Reasoning	10,724	1,341	1,341	13,406
`pad2`	Keyword Generator	12,024	1,503	1,503	15,030
`pad3`	Image Classification with Reasoning	49,941	6,243	6,243	62,427
Total	All Tasks	72,689	9,087	9,087	90,863

Training Procedure

This model was trained using a unified multi-task fine-tuning strategy. Instead of training separate models for text classification, image classification, and keyword generation, all tasks were learned by a single Vision-Language Model.

The model was fine-tuned end-to-end using task-specific prompts and responses in a shared multimodal instruction format. This allows the model to preserve a unified latent representation across tasks and reduces the risk of performance degradation caused by separate adapter merging.

Component	Value
Base model	`aitf-komdigi/KomdigiITS-3B-PAD-CPT`
Model architecture	Unified Vision-Language Model
Training approach	Multi-task supervised fine-tuning
Tasks	Text classification, image classification, keyword generation
Data format	TRL-style messages
Split strategy	Source-aware 80:10:10 train/validation/test split
Merge status	Merged model
Precision	BF16
Frameworks	Transformers, TRL, PEFT, Unsloth

Training Configuration

The model was fine-tuned using Unsloth FastVisionModel and TRL SFTTrainer. Training was performed as multi-task supervised fine-tuning over the merged dataset containing text classification, image classification, and keyword generation tasks.

Base Model and Sequence Configuration

Component	Value
Base model	`aitf-komdigi/KomdigiITS-3B-PAD-CPT`
Model class	`FastVisionModel`
Maximum sequence length	4096
Load in 4-bit	`False`
Precision	BF16 if supported, otherwise FP16
Gradient checkpointing	`unsloth`
Chat template reference	`mistralai/Ministral-3-3B-Instruct-2512`
Padding side	Right padding

The notebook applies the chat template from mistralai/Ministral-3-3B-Instruct-2512 to the model processor and tokenizer so that the training format follows the instruction-style format expected by the model.

LoRA Configuration

The model was fine-tuned using LoRA. Both the vision and language components were enabled for fine-tuning.

Parameter	Value
LoRA rank `r`	16
LoRA alpha	16
LoRA dropout	0.0
Bias	`none`
Target modules	`all-linear`
Random state	42
Fine-tune vision layers	`True`
Fine-tune language layers	`True`
Fine-tune attention modules	`True`
Fine-tune MLP modules	`True`

The training run reported 33,751,040 trainable parameters out of 3,882,841,088 total parameters, meaning approximately 0.87% of the model parameters were trained.

Data Collation

The notebook uses UnslothVisionDataCollator with a custom lazy image collation strategy. Images are loaded only when a sample has an image marker, which reduces unnecessary image decoding for text-only samples.

Component	Value
Base collator	`UnslothVisionDataCollator`
Custom wrapper	Lazy vision collator
Train on responses only	`True`
Instruction part	`[INST]`
Response part	`[/INST]`
Image loading strategy	Lazy image injection for `pad3` samples only

The training loss is computed only on the assistant response, which is useful for instruction tuning because the model is optimized to generate the expected output rather than reproduce the full prompt.

SFT Training Arguments

Hyperparameter	Value
Per-device train batch size	4
Gradient accumulation steps	2
Effective train batch size	8
Per-device evaluation batch size	4
Number of epochs	2
Learning rate	2e-4
Warmup ratio	0.03
Learning rate scheduler	Cosine
Weight decay	0.01
Optimizer	`adamw_8bit`
Max gradient norm	1.0
Logging steps	10
Evaluation strategy	Steps
Evaluation steps	1000
Save strategy	Steps
Save steps	1000
Save total limit	2
Seed	42
Output directory	`outputs_pad_sft`
Report to	Weights & Biases
Dataset text field	Empty string
Skip dataset preparation	`True`
Dataset number of processes	4
Dataloader workers	2
Pin memory	`True`

Training Run Summary

Attribute	Value
Number of training examples	72,689
Number of epochs	2
Total optimization steps	18,174
Number of GPUs	1
GPU used	NVIDIA A100-SXM4-40GB
Total batch size	8
Trainable parameters	33,751,040
Total parameters	3,882,841,088
Percentage of trained parameters	0.87%

Evaluation

The model was evaluated across three main tasks: text classification with reasoning, image classification with reasoning, and keyword generation. The evaluation results show that the unified model is able to maintain strong performance across tasks without significant signs of negative interference.

Text Classification with Reasoning

Metric	Score
Accuracy	0.9276
Macro F1	0.9129
Weighted F1	0.9267
ROUGE-1	0.5316
ROUGE-2	0.2743
ROUGE-L	0.3999
BERTScore Precision	0.8136
BERTScore Recall	0.8121
BERTScore F1	0.8126

Image Classification with Reasoning

Metric	Score
Accuracy	0.9121
Macro F1	0.9153
Weighted F1	0.9120
ROUGE-1	0.4990
ROUGE-2	0.2360
ROUGE-L	0.3793
BERTScore Precision	0.8023
BERTScore Recall	0.8004
BERTScore F1	0.8012

Keyword Generator

Metric	Score
Accuracy	0.9261
ROUGE-L Precision	0.7216
ROUGE-L Recall	0.7302
ROUGE-L F1-Score	0.7252

Limitations

The model has several limitations:

The model may produce incorrect predictions for ambiguous or context-dependent content.
The model may be sensitive to prompt wording and output-format instructions.
For text classification, the model may misinterpret slang, sarcasm, coded language, or culturally specific expressions.
For image classification, the model may under-detect subtle harmful content when visual evidence is unclear.
For keyword generation, the model may generate overly broad or incomplete keywords if the input context is vague.
The model may generate explanations that sound plausible but are not fully grounded in the input.
The model may not fully capture legal, cultural, or platform-specific policy nuances.
The model should not be used without human review for high-impact moderation decisions.

Bias, Risks, and Safety Considerations

Content moderation and age-rating models can reflect biases in their datasets, annotation guidelines, and policy definitions. Performance may vary across language, cultural context, visual style, demographic representation, and content source.

Potential risks include:

false positives that incorrectly flag safe content,
false negatives that miss harmful or restricted content,
inconsistent treatment of culturally specific content,
unsupported or hallucinated explanations,
over-reliance on automated moderation,
irrelevant or misleading generated keywords.

Recommended mitigations:

Use human-in-the-loop review for sensitive cases.
Evaluate the model separately for text, image, and keyword generation tasks.
Monitor per-class performance, especially for minority rating categories.
Use strict JSON schemas during inference.
Keep audit logs for model predictions in production systems.
Re-evaluate the model after dataset, taxonomy, or policy changes.
Combine the model with rule-based policy checks and escalation mechanisms.

Recommended Deployment Setting

For deployment, the model should be used as part of a larger PAD analysis pipeline:

Content is submitted as text, image, or image-text input.
The system routes the input to the appropriate task prompt.
The model predicts the rating, generates reasoning, or produces keywords.
A validation layer checks JSON format and allowed labels.
High-risk or uncertain cases are escalated to human reviewers.
Final decisions and model outputs are logged for audit and future evaluation.

Ethical Considerations

This model is developed to support safer digital content access and child protection. It should be used responsibly, proportionally, and transparently. The model should not be used for surveillance, profiling, punitive action, or automated enforcement without appropriate human oversight, governance, and accountability.

Citation

If you use this model, please cite it as:

bibtex

@misc{komdigi_3b_pad_merged,
  title = {Komdigi-3b-pad-merged: A Unified Vision-Language Model for Text Classification, Image Classification, and Keyword Generation in Perlindungan Anak di Ruang Digital},
  author = {AITF Komdigi},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/aitf-komdigi/Komdigi-3b-pad-merged}}
}

Contact

For questions, issues, or collaboration, please use the Hugging Face repository discussion page.