Predibase has released the first Reinforcement Fine-Tuning platform, promising a groundbreaking approach to customizing LLMs using reinforcement learning. Use RFT to train open-source LLMs that outperform GPT-4, even when labeled data is limited.

Predibase is a low-code AI platform that makes it easy for engineers and data scientists to build, optimize and deploy state-of-the-art models - from linear regressions to large language models - with just a few lines of code.

All 25 fine-tuned models… 📈 Outperform GPT-4, GPT-3.5-turbo, and mistral-7b-instruct for specific tasks ⚡️ Are cost-effectively served from a single GPU through LoRAX 💰 Were trained for less than $8 each on average

The Predibase Inference Engine, powered by LoRA eXchange, Turbo LoRA, and seamless GPU autoscaling, serves fine-tuned SLMs at speeds 3-4 times faster than traditional methods and confidently handles enterprise workloads of 100s of requests per second.