Hugging Face publishes Palette method for generating presentations with small models
What happened
IBM introduced the Palette method on the Hugging Face blog: a 20B open-weight model is fine-tuned with LoRA, splitting slide creation into two roles. A designer first writes a JSON brief, then a coder writes pptxgenjs code from it. Training data covers about 1,000 slide decks and nearly 10,000 pages, and the output follows IBM Design Language. Only the method has been published so far; the report does not say whether model weights or code are open, or what the evaluation results are.
Written by AI from the reports · updated 3 h ago
Timeline
Follow the reports to see the event from each side.
- Hugging Face BlogPalette: teaching a small model to build decks in your design language
We fine-tuned a 20B model to build decks the way people do: a designer plans the deck and a coder draws each slide. Its training data follows the IBM Design Language, and on PresentBench it ranks first on two of the three domains we measured.
Heat of this event
Current heat 9·Peak in the comparable range 9（Nov 4 04:00）·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.