fangevo/KD-efficient-text-summarization

The project leverages a larger model, Qwen2.5-14B, to generate high-quality reference summaries, which are then used to fine-tune the SLM (Qwen2.5-0.5B), enabling the SLM to generate accurate news summaries. The LLM is optimized to run efficiently on free Google Colab (15GB VRAM), using 4-bit quantization and LoRA.

30
/ 100
Emerging

This project helps AI developers create a smaller, faster AI model that can summarize news articles accurately. It takes a large, high-quality AI model's summaries and uses them to teach a much smaller AI model. The outcome is an efficient summarization tool that can run on standard cloud computing resources, ideal for developers building AI-powered applications.

Use this if you are an AI developer who needs to create an efficient, lightweight text summarization model capable of summarizing news articles without requiring extensive computational resources.

Not ideal if you are an end-user simply looking to summarize text without any development or model training involvement.

AI-model-training text-summarization NLP-development computational-efficiency machine-learning-engineering
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 7 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Python

License

Last pushed

Feb 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/fangevo/KD-efficient-text-summarization"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.