GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Khalidahmad01
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
Khalidahmad01
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This repository contains the LoRA adapter developed for the Cortex Copilot Engineering Challenge.
The adapter fine-tunes Qwen2.5-3B-Instruct using QLoRA to improve responses for industrial energy management, electrical engineering concepts, Indian electricity tariff logic, and Cortex-specific metrics.
Qwen/Qwen2.5-3B-Instruct
The model was fine-tuned on 399 instruction-response pairs covering:
| Parameter | Value |
|---|---|
| Epochs | 3 |
| Batch Size | 2 |
| Gradient Accumulation | 4 |
| Learning Rate | 2e-4 |
| Max Sequence Length | 2048 |
| GPU | Tesla T4 |
This adapter is intended for educational purposes as part of the Cortex Copilot Engineering Challenge.
It specializes the base model for industrial energy management while relying on external telemetry data for real-time information.
Khalid Ahmad Raza
B.Tech Computer Engineering
National Institute of Technology Kurukshetra