Author trains and releases six small models in two days with ML-Intern
What happened
On 8 October 2026, Hugging Face Blog published a first-hand report stating that the author used ML-intern in HuggingChat to train and release six models in two days through natural-language prompts, including a citrus disease VLM, Huggy LoRA, a camera viewpoint LoRA, Doodle-in LoRA, Pocket Rewriter 0.8B/2B and the Agate 4-step distilled model, at a total compute cost of about $103. The report did not disclose the specific training details, data sources or evaluation results of each model, nor explain how the two-day timeframe and the $103 cost were measured. So far this is the only report on the matter, with no follow-up or contradiction with earlier coverage.
Written by AI from the reports · updated 7 d ago
Timeline
Follow the reports to see the event from each side.
- Hugging Face BlogSelectedThe model that didn't exist, so you made it yourself
Last week, I wanted a small version of the prompt rewriter that ships with Qwen-Image 2.1. The official one is a 9B model that needs about 20 GB of memory and thinks for thousands of tokens before writing a single paragraph. On the Hub, I found only compressed copies of that same 9B model.
Heat of this event
Current heat 3·Peak in the comparable range 4（Oct 9 17:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.