Get the latest tech news
Hermes 3: The First Fine-Tuned Llama 3.1 405B Model
Introducing Hermes 3 in partnership with Nous Research, the first fine-tune of Meta Llama 3.1 405B model. Train, fine-tune or serve Hermes 3 with Lambda
We are thrilled to announce our partner Nous Research’s launch of Hermes 3 —the first full-parameter fine-tune of Meta's groundbreaking Llama 3.1 405B model, trained on Lambda’s 1-Click Cluster. It excels in complex role-playing and creative writing, offering users more immersive character portrayals, deeper simulations, and unexpected fictional experiences. This optimization effectively reduces the model's VRAM and disk requirements by approximately 50%, allowing it to run on a single node.
Or read this on Hacker News
