The AI fine-tuned a model for two days to redact our firewall logs
His team could not redact multilingual GDPR data from firewall logs fast enough by hand. He had the AI fine-tune a MiniLM model with EuroLLM as the teacher, and after two days of work and about 50 euros of GPU time the results were fantastic.
How it works
- Sets the AI to fine-tune a MiniLM model with EuroLLM as the teacher
- The AI works for two days straight using about 50 euros of GPU time
- The trained model redacts the logs and the results are fantastic
Why it’s worth knowing
The AI ran on its own for two days straight, teaching a small model to strip private data out of firewall logs.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗