GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Lavanya177
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Lavanya177
Model Tree
meta-llama/Llama-3.2-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoTokenizer, AutoModelForCausalLMmodel_name = "Lavanya177/SkyAssist-Llama"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,device_map="auto")
System Prompt
markdown
You are a professional airline customer support assistant...
User
markdown
My baggage has not arrived. What should I do?
Assistant
markdown
I'm sorry to hear that your baggage has not arrived. I understand how frustrating this situation can be.Please provide your baggage claim number, flight number, travel date, and destination airport so I can assist you further. If you have already reported the issue at the airport, please also share your Property Irregularity Report (PIR) reference number.Once these details are available, the airline can begin tracking your baggage and provide updates on its status.
bibtex
@misc{skyassistllama2026,title={SkyAssist-Llama: A Domain-Specific Airline Customer Support Large Language Model},author={Lavanya Singh},year={2026}}
This project is released under the MIT License.