Prem Series

Sign in Subscribe

series

A collection of 4 posts

DeepSeek R1: Why Open Source Is the Future of Enterprise AI

series Featured

DeepSeek R1: Why Open Source Is the Future of Enterprise AI Development

Open-source vs. closed-source AI stands at a turning point: once dominated by proprietary systems, the field now sees open science and models like DeepSeek R1 driving forward. Leveraging new training efficiencies, these open solutions match or even surpass their closed-source counterparts.

Evaluation of LLMs - Part 2

Evaluation of LLMs - Part 2

The article explores using large language models (LLMs) as evaluators, addressing concerns about accuracy and inherent biases. It highlights the need for scalable meta-evaluation schemes and discusses fine-tuned evaluation models like Prometheus 13B, which aligns closely with human evaluators.

Evaluation of LLMs - Part 1

Evaluation of LLMs - Part 1

The article "Evaluation of LLMs - Part 1" delves into the rapid development of Large Language Models (LLMs) and the necessity for robust evaluation strategies. It examines traditional n-gram-based metrics like BLEU and ROUGE, discussing their roles and limitations in assessing LLM performance.

The Tiny LLM Revolution - Part 1

The Tiny LLM Revolution - Part 1

This article examines the emergence of Small Language Models (SLMs), discussing the impact of high-quality data on their capabilities. It highlights studies like TinyStories and Microsoft's Phi-series, exploring how SLMs can achieve performance comparable to larger models.