metadata
language: en
license: apache-2.0
tags:
- fashion
- ecommerce
- product-description
- roman-urdu
- watches
- opalhours
datasets:
- nvidia/Llama-Nemotron-Post-Training-Dataset
metrics:
- accuracy
base_model:
- MuzammilKhosa/opalhours-ai
new_version: deepseek-ai/DeepSeek-R1
pipeline_tag: text-classification
library_name: adapter-transformers
OpalHours AI
OpalHours AI is a lightweight language model designed to assist with watch-related e-commerce content. It helps generate product descriptions, respond to customer queries, and maintain a consistent brand tone—especially for businesses communicating in both English and Roman Urdu.
Model Capabilities
- Create elegant product descriptions for wristwatches
- Generate quick replies for customer messages (WhatsApp-style)
- Suggest taglines, captions, and headlines
- Supports basic Roman Urdu generation (e.g., "yeh watch classy aur modern lagti hai")
Example Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("opalhours/opalhours-ai")
model = AutoModelForCausalLM.from_pretrained("opalhours/opalhours-ai")
prompt = "Describe a minimal silver dial men's watch with a black leather strap."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))