@WilliamBarrHeld: To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models…

X AI KOLs Following Papers

Summary

Marin AI researchers, led by William Barr Held, introduce Delphi, a methodology that pretrains small models to accurately predict the training outcomes of larger 25B-parameter runs. This research aims to establish predictable scaling for more efficient open-source AI model development.

To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models with one recipe, then extrapolated 300× to predict a 25B-param / 600B-token run with just 0.2% error. Getting there took some work 🧵 https://t.co/HmlVFl11ag
Original Article
View Cached Full Text

Cached at: 05/11/26, 08:43 PM

To train better open models, we need predictable scaling.

Delphi is Marin’s first step: we pretrained many small models with one recipe, then extrapolated 300× to predict a 25B-param / 600B-token run with just 0.2% error.

Getting there took some work 🧵 https://t.co/HmlVFl11ag

Similar Articles

Introducing improvements to the fine-tuning API and expanding our custom models program

OpenAI Blog

OpenAI introduces improvements to its fine-tuning API with new features including epoch-based checkpoints, comparative playground for model evaluation, third-party integrations, and enhanced dashboard capabilities. The company also expands its custom models program to give developers more control and flexibility in building domain-specific AI solutions.

Model Distillation in the API

OpenAI Blog

OpenAI introduces a Model Distillation offering in its API, enabling developers to use outputs from frontier models like o1-preview and GPT-4o to fine-tune smaller, cost-efficient models like GPT-4o mini through an integrated pipeline including Stored Completions, Evals, and Fine-tuning.