ML-Intern in HuggingChat Ran the Whole Distillation Pipeline End to End

Gradio · x · 2026-09-23

Gradio reveals how the project ran: ML-Intern in HuggingChat executed it end to end — writing 8,797 requests in 18 languages, labeling with Qwen's original 9B teacher, filtering, training both students with TRL, evaluating on text and rendered images, and pushing everything to the Hub. Humans just approved the budget and read the report.

Related event: Gradio's Distillation Project Cost Just $16, Run End-to-End by AI(2 posts)→

Original post →

More from coding & agent

coding & agent channel →