← Back
Hugging Face Blog

Palette: teaching a small model to build decks in your design language

•9 min read•
#llm
Level:Advanced
For:AI Engineers
✦TL;DR

Palette demonstrates that a 20B open‑weight model fine‑tuned with LoRA on synthetic IBM Design Language data can generate slide decks that outperform frontier models on the PresentBench benchmark, ranking first on two of three measured domains. The system splits deck creation into a “designer” phase that produces a structured JSON brief and a “coder” phase that emits pptxgenjs JavaScript for each slide, enabling parallel generation and a 6–7× speedup. This approach lets enterprises keep models and data on‑prem while achieving high‑quality, brand‑consistent decks.

⚡ Key Takeaways

  • 20B model fine‑tuned with LoTS (LoRA) ranks first on two of three PresentBench domains.
  • Architecture separates responsibilities: a designer model writes a JSON brief, a coder model writes pptxgenjs code.
  • Parallel coder execution yields a 6–7× reduction in deck generation latency.
  • Integration uses the pptxgenjs JavaScript library for slide rendering.
  • Requires synthetic training data aligned with the IBM Design Language and a LoRA adapter; full fine‑tuning is not used.
💡 Why It Matters

Engineers can now host a modest‑size model in‑house to produce brand‑consistent slide decks without exposing confidential content, while still matching or beating large proprietary models on benchmark quality.

✅ Practical Steps

  1. Generate synthetic training data that follows your organization’s design language (e.g., IBM Design Language) and train a LoRA adapter on a 20B base model.
  2. Deploy the trained adapter to produce a JSON brief (designer) and then feed each slide spec to the coder model, which outputs pptxgenjs code.
  3. Run the coder model in parallel across slides to achieve the reported 6–7× speedup.

Want the full story? Read the original article.

Read on Hugging Face Blog ↗

More like this

Censored vs. Truncated Regression in Python, Explained

Towards Data Science•#llm

How Google Duplex evolved to also call businesses for you in Gemini

Google Research•#agents

Q&A: Enabling more human-like interactions and understanding in multimodal foundation models

MIT News AI•#llm

Welcome Inkling 2 Mini, Cutting-edge Performance for your Local Setup

Hugging Face Blog•#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING