Brendan McKeag - RunPod Blog

RunPod Blog

Sign in Subscribe

Brendan McKeag

Use alpha_value To Blast Through Context Limits In LLaMa-2 Models

Use alpha_value To Blast Through Context Limits In LLaMa-2 Models

With 4k context being the norm for Llama-2 and its finetunes, it's a far cry from the "bad old days" of the 2k limits found in Pygmalion-6b and other previous landmark models. But what if I told you that you could just set an arbitrarily high context limit for whatever

Save the Date October 11th, 2:00 PM EST: Fireside Chat With RunPod CEO Zhen Lu And Data Science Dojo CEO Raja Iqbal On GPU-Powered AI Transformation

Join us for an engaging fireside chat with RunPod on the cutting-edge GPU solutions that are revolutionizing the ML landscape and driving seamless AI transformation. RunPod and Data Science Dojo are excited to collaborate in this fireside chat and provide insights into the cutting-edge GPU solutions reshaping the ML landscape

Having Trouble With Your LLM Not Following Prompts? Just Ask It What It Wants

Text Generation

Having Trouble With Your LLM Not Following Prompts? Just Ask It What It Wants

No two large language models behave exactly alike, and with over 250,000 separate models and quantizations available to download, it's just not possible to get intimately acquainted with more than a handful of them. Models all have different strengths and weaknesses, and some are even used "off-label" for unique

How To Manage Funding Your RunPod Account

Runpod Platform

How To Manage Funding Your RunPod Account

At RunPod, we want to be wholly transparent about how how we manage billing clients, since we know that discussing financial matters can be a very charged conversation. We want to equip you with every tool available to ensure that your pods run smoothly without interruption due to a low

RunPod Partners With RandomSeed to Provide Accessible, User-Friendly Stable Diffusion API Access

RunPod is delighted to collaborate with RandomSeed by providing the serverless compute power required to create generative AI art through their API access. The mission of RandomSeed is to help developers build AI image generators by providing a hosted AUTOMATIC1111 API that can create images on-demand through API calls, saving

RunPod Partners with Data Science Dojo To Provide Compute For LLM Bootcamps

RunPod Partners with Data Science Dojo To Provide Compute For LLM Bootcamps

RunPod is delighted to collaborate with Data Science Dojo to offer a robust computing platform for their Large Language Model bootcamps. Leveraging our cutting-edge cloud services, RunPod empowers DSD's boot camp participants with a high-performance computing environment, enhancing the efficacy and competitiveness of their learning experience. You can check our

What You'll Need to Run Falcon 180B In a Pod

Text Generation

What You'll Need to Run Falcon 180B In a Pod

September 6th was a momentous day in large language model history, as Falcon-180 was released by the Technology Innovation Institute. To date, this is the single largest open-source LLM released to the public (edging out BLOOM-176b from 2022.) For quite some time, whether it was technical concerns or simply market

RunPod and Klangio Partner To Bring Music Transcription to Learners and Professionals Alike

RunPod and Klangio Partner To Bring Music Transcription to Learners and Professionals Alike

RunPod is pleased to be the service provider for Klangio, an up-and-coming name in audio space within the artificial intelligence community. Klangio leverages AI to automatically transcribe musical notes to human-readable notation, greatly accelerating the pace of music projects while seamlessly capturing every spontaneous facet of a live musical improvisation.

RunPod Roundup 5 - Visual/Language Comprehension, Code-Focused LLMs, and Bias Detection

RunPod Roundup 5 - Visual/Language Comprehension, Code-Focused LLMs, and Bias Detection

Welcome to the Runpod Roundup for the week ending August 26, 2023. In this issue, we'll be discussing the newest advancements in AI models over the past week, with a focus on new offerings that you can run in a RunPod instance right this second. In this issue, we'll be

RunPod Roundup 4 - Open Source LLM Evaluators, 3D Scene Reconstruction, Vector Search

RunPod Roundup 4 - Open Source LLM Evaluators, 3D Scene Reconstruction, Vector Search

Welcome to the Runpod Roundup for the week ending August 19, 2023. In this issue, we'll be discussing the newest advancements in AI models over the past week, with a focus on new offerings that you can run in a RunPod instance right this second. In this issue, we'll be

How to get Stable Diffusion Set Up With ComfyUI

Stable Diffusion

How to get Stable Diffusion Set Up With ComfyUI

Automatic1111 is an iconic front end for Stable Diffusion, with a user-friendly setup that has introduced millions to the joy of AI art. Anyone can spin up an A1111 pod and begin to generate images with no prior experience or training. The options are all laid out intuitively, and you

The Effects Of Rank, Epochs, and Learning Rate on Training Textual LoRAs

Text Generation

The Effects Of Rank, Epochs, and Learning Rate on Training Textual LoRAs

Have you ever wanted to have a large language model tell you stories in the voice and style of your favorite author? Well, through training a LoRA on their work, you can totally do that! There are so many different levers to flip when training a LoRA, though, and it

RunPod RoundUp 3 - AI Music and Stock Sound Effect Creation

RunPod RoundUp 3 - AI Music and Stock Sound Effect Creation

Welcome to the Runpod Roundup for the week ending August 05, 2023. In this issue, we'll be discussing the newest advancements in AI models over the past week, with a focus on new offerings that you can run in a RunPod instance right this second. In this issue, we'll be

RunPod RoundUp 2 - 32k Token Context LLMs and New StabilityAI Offerings

RunPod RoundUp 2 - 32k Token Context LLMs and New StabilityAI Offerings

Welcome to the Runpod Roundup for the week ending July 29, 2023. In this issue, we'll be discussing the newest advancements in AI models over the past week, with a focus on new offerings that you can run in a RunPod instance right this second. In this issue, we'll be

Stable Diffusion XL 1.0 Released And Available On RunPod

Stable Diffusion

Stable Diffusion XL 1.0 Released And Available On RunPod

As discussed in the RunPod Roundup, Stable Diffusion XL is now available for the public and we've got you covered if you'd like to give it a shot. The Fast Stable Diffusion Template in RunPod has already been updated to take advantage of SDXL. Getting up and running is just

RunPod Partners With OpenCV To Provide GPU Power To Students

RunPod Partners With OpenCV To Provide GPU Power To Students

The next generation of AI-powered solutions is going to require processing power – and lots of it. OpenCV is a non-profit organization centered around the Open Source Computer Vision Library, which is devoted to driving computer vision applications in the world at large. OpenCV was one of the original pioneering groups

Meta and Microsoft Release Llama 2 LLM as Open Source

Text Generation

Meta and Microsoft Release Llama 2 LLM as Open Source

When the original LlaMA was released earlier in 2023 by Meta, it was only provided to the research community. With the next iteration, Meta in collaboration with Microsoft appears to have a change of heart and has released it as an open-source model for anyone to use. Here's what you'll

RunPod Roundup 1 - Inaugural Issue

RunPod Roundup 1 - Inaugural Issue

Welcome to the RunPod Roundup! In this week we'll be discussing new text and image generation models, including an exciting new Stable Diffusion model. The goal of RunPod Roundup is to keep you abreast of new developments over the week that you might have missed, with a focus on new

How To Install SillyTavern in a RunPod Instance

Text Generation

How To Install SillyTavern in a RunPod Instance

While some might prefer the simple text-based entry of an oobabooga interface, others might want something a little more robust. SillyTavern offers a number of additional features above and beyond most methods of interfacing with an LLM, and there's been some demand on getting it set up and installed on

16k Context LLM Models Now Available On RunPod

Text Generation

16k Context LLM Models Now Available On RunPod

Hot off the heels of the 8192-token context SuperHOT model line, Panchovix has now released another set of models with an even higher context window, matching the 16384 token context possible in the latest version of text-generation-webui (Oobabooga). Such a large context window is going to vastly improve performacne in

RunPod Partners With Defined.ai To Democratize and Accelerate AI Development

Runpod Platform

RunPod Partners With Defined.ai To Democratize and Accelerate AI Development

RunPod is excited to announce its partnership with Defined.ai, the world's largest marketplace of ethically sourced training datasets for AI models. This collaboration seeks to provide AI developers working with text-to-speech, speech-to-text models, and those fine-tuning LLMs the opportunity to access enterprise-grade conversational speech and text datasets. DefinedAI's Marketplace

A Deep Dive Into Creating an Effective TavernAI Character

A Deep Dive Into Creating an Effective TavernAI Character

Roleplay has become a surprisingly popular use of AI over the past year, with entire services popping up devoted specifically to interacting with characters, fictional or not. It's begun to breach the realm of academic writing (such as this paper on ArXiv on LLM RP from EleutherAI from May 2023.

How To Use Very Large Language Models with RunPod - 65b (and higher) models

Text Generation

How To Use Very Large Language Models with RunPod - 65b (and higher) models

Many LLMs (such as the classic Pygmalion 6b) are small enough that they can fit easily in almost any RunPod GPU offering. Others such as Guanaco 65B GPTQ are quantized which is a compression method. to reduce memory usage, meaning that you will be able to fit the model into

SuperHot 8k Token Context Models Are Here For Text Generation

Text Generation

SuperHot 8k Token Context Models Are Here For Text Generation

Esteemed contributor TheBloke has done it again, and textgen enjoyers everywhere now have another avenue to further increase their AI storytelling partner's retention of what is occurring during a scene. Available on his GitHub are quantizations of several well known models, including but not limited to the following: WizardLM (7B,

Savings Plans Are Here For Secure Cloud Pods- How To Purchase a Monthly Plan And Save Big

Runpod Platform

Savings Plans Are Here For Secure Cloud Pods- How To Purchase a Monthly Plan And Save Big

If you are a frequent RunPod customer, you may be interested in our latest feature, Savings Plans. These plans allow you to invest in an up-front payment in a specific pod type that saves you more money the more you use you pod. For individuals with high workloads that anticipate