Product catalog generator

This is a custom LLM fine tuned on LLama 2 based on Basalam products to infer enitty (product types) and attributes based on product data. You can use it on any similar dataset.

Github repo: https://github.com/basalam/product-catalog-generator

Sample 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""""

Model response

{
  "attributes": {
    "تعداد تکه": "2",
    "طول": "20 سانتی‌متر",
    "رنگ‌ها": "سبز، قرمز، نارنجی، آبی",
    "کیفیت": "مناسب و صادراتی"
  },
  "product_entity": "ست شابلون ژله ای"
}
Downloads last month
75
Safetensors
Model size
6.74B params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train BaSalam/Llama2-7b-entity-attr-v1

Collection including BaSalam/Llama2-7b-entity-attr-v1