We’re open-sourcing PorTAL, our framework for shared task representations and cross model LoRA adaptation.
It now spans from hybrid attention models to multimodal systems including Gemma 4 E2B, Mistral 7B & @thinkymachines' Inkling.
Code: ramp-public/portallib
Models: @huggingface /RampPublic
Show more
We had access to Opus 5, and found a distinctly Fable-shaped addition to the Pareto frontier.
We’re launching Ramp Router, our LLM gateway.
It processes trillions of tokens a day across Ramp’s external products and internal AI workflows, giving us one place to manage reliability, latency, and cost.
Reserve access today.
Show more
Introducing PorTAL: Portable Task Adapters for LLMs. A novel recipe to cheaply port fine-tuning between models. It matches per task LoRA accuracy at half the cost, lowering the switching overhead of adapting tasks across LLMs.
At Ramp, every new model release used to mean retraining our fine-tunes from scratch. PorTAL learns the task once, then efficiently refits it onto any new base model, even across model families.
Show more
