mansoorhamidzadeh/qwen3-0.6b-entity-attr-basalam-gguf

Model Details

⚠️ EXPERIMENTAL IMPLEMENTATION - NOT PRODUCTION-READY ⚠️
Proof-of-concept model for research purposes only

Model Type: This model is a fine-tuned version of qwen3-0.6b for generating product attributes and entities from product titles in Persian.

Fine-tuning Dataset: The model was fine-tuned on 20,000 samples from the BaSalam/entity-attribute-sft-dataset-GPT-4.0-generated-v1 dataset, which contains GPT-4 generated data for higher quality responses.

Training Environment:

• GPU: Kaggle P100 GPU with 16GB memory
• Epochs: 1
• Library: Unsloth library was used for fine-tuning

Intended Use

This model is designed to take a product title in Persian and generate a JSON output containing the product entity and its attributes. It is particularly useful for applications that require structured product information extraction from unstructured text.

Example Usage

Input:

prompt = """instruction': \"here is a product title from a Iranian marketplace. \n         give me the Product Entity and Attributes of this product in Persian language.\n         give the output in this json format: {'attributes': {'attribute_name' : <attribute value>, ...}, 'product_entity': '<product entity>'}.\n         Don't make assumptions about what values to plug into json. Just give Json not a single word more.\n         \nproduct title:"""
title = """: ست شابلون ژله ای دو قلو صریر 20سانتی 1 عدد
1 عدد ست شابلون ژله ای دو قلو سریر 20سانتی متر
با کیفیت مناسب و صادراتی
شامل دو تکه شابلون ژله ای
در چهار رنگ سبز، قرمز، نارنجی و آبی موجود است.
پخش لوازم التحریر کیان""""

Output

{
  "attributes": {
    "تعداد در بسته‌بندی": ["1 عدد"],
    "ابعاد": ["20 سانتی متر"],
    "رنگ": ["سبز", "قرمز", "نارنجی", "آبی"],
    "کیفیت": ["مناسب و صادراتی"],
    "محتویات بسته‌بندی": ["دو تکه شابلون ژله ای"]
  },
  "product_entity": ["لوازم التحریر کیان"]
}