A fine-tuned text generation model for generating SEO-friendly descriptions from presentation template metadata. This model uses LoRA adapters to efficiently fine-tune Google Gemma-3-4B-IT for generating descriptions as part of the Field-Adaptive Dense Retrieval framework.

Model Description

This model generates 50-80 word SEO-friendly descriptions from presentation template metadata including titles, visual elements, industries, categories, and tags. It serves as a key component in the Field-Adaptive Dense Retrieval system for structured documents.

Base Model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
Model Type: Causal Language Model with LoRA
Language: English
License: Apache 2.0

Usage

With Transformers

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "mudasir13cs/Field-adaptive-description-generator"
)
tokenizer = AutoTokenizer.from_pretrained(
    "mudasir13cs/Field-adaptive-description-generator"
)

# Format prompt using Gemma chat template
prompt = """<start_of_turn>user
Generate a 50-80 word SEO-friendly description for this presentation template:
    Title: Modern Business Presentation
    Visual Elements: minimalist design, blue gradient background, geometric shapes
    Industries: Business, Marketing
    Categories: Corporate, Professional
    Tags: Modern, Clean, Professional

    Requirements:
        - Describe visual style naturally
        - Mention 2-3 specific use cases
        - Integrate keywords organically (no markdown/bold formatting)
        - Professional yet engaging tone
        - Exactly 50-80 words
        - Start directly with the description (no prefixes)
<end_of_turn>
<start_of_turn>model
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=512, temperature=0.7, do_sample=True)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)

With llama.cpp

bash

# Download the GGUF model
huggingface-cli download mudasir13cs/Field-adaptive-description-generator-gguf \
    description-generator-q4_k_m.gguf --local-dir . --local-dir-use-symlinks False

# Run inference
./llama-cli -m description-generator-q4_k_m.gguf \
    -p "<start_of_turn>user
Generate a 50-80 word SEO-friendly description for this presentation template:
    Title: Modern Business Presentation
    Visual Elements: minimalist design, blue gradient background, geometric shapes
    Industries: Business, Marketing
    Categories: Corporate, Professional
    Tags: Modern, Clean, Professional
<end_of_turn>
<start_of_turn>model
"

With Ollama

bash

# Import model to Ollama
ollama create field-adaptive-description-generator -f Modelfile

# Run inference
ollama run field-adaptive-description-generator "<start_of_turn>user
Generate a 50-80 word SEO-friendly description for this presentation template:
    Title: Modern Business Presentation
    Visual Elements: minimalist design, blue gradient background, geometric shapes
    Industries: Business, Marketing
    Categories: Corporate, Professional
    Tags: Modern, Clean, Professional
<end_of_turn>
<start_of_turn>model
"

Expected Output Format

The model generates a 50-80 word description starting directly with the content (no prefixes):

This modern business presentation template features a minimalist design with a sleek blue gradient background and geometric shapes. Perfect for corporate presentations, marketing pitches, and professional meetings. The clean, professional aesthetic makes it ideal for executive briefings, client proposals, and team updates. With its contemporary style, this template suits various business contexts while maintaining a polished, engaging appearance.

Prompt Format

Always use the Gemma chat template format:

<start_of_turn>user
Generate a 50-80 word SEO-friendly description for this presentation template:
    Title: [Template Title]
    Visual Elements: [element1, element2, element3]
    Industries: [Industry1, Industry2]
    Categories: [Category1, Category2]
    Tags: [Tag1, Tag2, Tag3]

    Requirements:
        - Describe visual style naturally
        - Mention 2-3 specific use cases
        - Integrate keywords organically (no markdown/bold formatting)
        - Professional yet engaging tone
        - Exactly 50-80 words
        - Start directly with the description (no prefixes)
<end_of_turn>
<start_of_turn>model

Model Details

Architecture: Google Gemma-3-4B-IT with LoRA adapters
Training: Parameter-Efficient Fine-Tuning (PEFT) with LoRA
LoRA Rank: 16
LoRA Alpha: 32
Training Epochs: 3
Learning Rate: 2e-4
Batch Size: 4

Evaluation

BLEU Score: ~0.75
ROUGE Score: ~0.80
Performance: Optimized for description generation quality in structured document retrieval

Citation

Paper

bibtex

@article{field_adaptive_dense_retrieval,
  title={Field-Adaptive Dense Retrieval of Structured Documents},
  author={Mudasir Syed},
  journal={DBPIA},
  year={2024},
  url={https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE12352544}
}

Model

bibtex

@misc{field_adaptive_description_generator,
  title={Field-adaptive-description-generator for Presentation Template Description Generation},
  author={Mudasir Syed},
  year={2024},
  howpublished={Hugging Face},
  url={https://huggingface.co/mudasir13cs/Field-adaptive-description-generator}
}

Base Model

bibtex

@misc{gemma_3_4b_it,
  title={Gemma: Open Models Based on Gemini Research and Technology},
  author={Gemma Team and others},
  year={2024},
  howpublished={Hugging Face},
  url={https://huggingface.co/google/gemma-3-4b-it}
}

Related Models

Field-Adaptive Query Generator - Generates search queries from template metadata

Author

Mudasir Syed (mudasir13cs)

GitHub: https://github.com/mudasir13cs
HuggingFace: https://huggingface.co/mudasir13cs
LinkedIn: https://pk.linkedin.com/in/mudasir-sayed