Brendan McKeag

This Runpod Roundup covers the arrival of 8k–16k token context models, the release of Stable Diffusion XL, and the launch of Llama 2 by Meta and Microsoft. All are now available to run on Runpod.

Llama 2 is now open source, offering a native 4k context window and strong performance. This post walks through how to download it from Meta or use TheBloke’s quantized versions.

This guide walks through setting up SillyTavern—a powerful, customizable roleplay frontend—on a Runpod instance. It covers port exposure, GitHub installation, whitelist config, and connecting to models like Oobabooga or KoboldAI.

Runpod now supports Panchovix’s 16k-token context models, allowing for much deeper context retention in long-form generation. These models require higher VRAM and may trade off some performance, but are ideal for extended sessions like roleplay or complex Q&A.

Runpod announces a partnership with Defined.ai to offer ethically sourced speech and text datasets to AI developers, starting with a pilot program to fine-tune LLMs and accelerate NLP research.

New 8k context models from TheBloke—like WizardLM, Vicuna, and Manticore—allow longer, more immersive text generation in Oobabooga. With more room for character memory and story progression, these models enhance AI storytelling.

Learn how to use Runpod's new Savings Plans to save up to 20% on Secure Cloud pods with monthly or quarterly commitments—ideal for users with high GPU workloads.