Preemo – Medium

Jun 7

Can We Prompt an LLM to Uncover its Dreams of Electric Sheep?

by Lucia Mocz, Ph.D. As the capabilities of large language models (LLMs) continue to advance, there is a growing curiosity among researchers and developers to understand the mechanisms behind them. However, the complete theory of these abilities still eludes us, and achieving it may rely on developing new interpretive mathematical…

Large Language Models

14 min read

Can We Prompt an LLM to Uncover its Dreams of Electric Sheep?

Large Language Models

14 min read

May 10

Performance bottlenecks in deploying LLMs—a primer for ML researchers

by Lucia Mocz, Ph.D. This is the first post in a series to help researchers understand the systems-level design choices involved in deploying LLMs. With the rise of Large Language Models (LLMs) come new challenges that must be addressed, especially when it comes to deploying these models at scale. Unlike…

Machine Learning

11 min read

Performance bottlenecks in deploying LLMs—a primer for ML researchers

Machine Learning

11 min read

Apr 22

Squeeze more out of your GPU for LLM inference—a tutorial on Accelerate & DeepSpeed

by Beite “Jupiter” Zhu A driving question “How do ML practitioners handle LLM inference without sacrificing latency or throughput?” During my most recent project, I wanted to test how current large language models (LLMs) from Hugging Face perform on code generation tasks against the HumanEval dataset. I spun up a P3 instance from…

Machine Learning

11 min read

Squeeze more out of your GPU for LLM inference—a tutorial on Accelerate & DeepSpeed

Machine Learning

11 min read

Apr 19

Fine-tuning the LLaMA model to speak English and Chinese

At Preemo, we’ve created a model that understands and produces both English and Chinese — by using an efficient, faster form of fine-tuning to enhance entirely open-source models and data. The new model, which we call Alpaca LoRA 30B, can be instructed with English and Chinese, and performs well in…

Machine Learning

6 min read

Fine-tuning a model to speak English and Chinese

Machine Learning

6 min read

Apr 10

Three traits of a task you can automate

Where will automation plug in? 1 of 3 in our Coding automation series. Do you trust a washing machine? Think about your washing machine. You put clothes in, set the dial, pour in detergent, and bam—clean clothes. Your washing machine just saved you an hour of scrubbing (and probably did it better than you could have). …

Machine Learning

4 min read

Machine Learning

4 min read

Apr 10

Three ways to think about coding automation

AI/ML tech is moving fast. Whether you’re an engineer, CTO, or somewhere in between, you’re likely wondering how to prepare for today and for tomorrow. To benefit from new tech, you have to figure out what problems it can solve for you. This is very true of LLMs. One way…

Machine Learning

1 min read

Machine Learning

1 min read