Book a Call

Srihari Unnikrishnan

Srihari is an NLP Engineer at Ionio. That's about it really.

Fastest Token First: Benchmarking OpenLLMs by inference speed

Latency, especially in the context of Large Language Models LLMs), plays a crucial role in determining their practical utility, especially in real-time applications where responsiveness is paramount.

Srihari Unnikrishnan

January 31, 2024

A Complete Beginners guide to localllm

localllm is a set of tools and libraries that provides easy access to quantized models from HuggingFace through a command-line utility. It's pretty awesome for developers who want to dive into big language models (LLMs) but don't have a fancy GPU to work with. This whole setup gives you everything you need to get these LLMs running on just your CPU and whatever memory you've got, whether you're on Google Cloud Workstation or just your own computer. So, you don't need to worry about having a top-tier GPU to get into the game. It's all about making the power of LLMs accessible for everyone, wherever you're coding from.

Srihari Unnikrishnan

January 31, 2024

Predicting stock market movements with Machine Learning and err... twitter?

In the fast-paced world of stock market forecasting, the fusion of machine learning techniques with insights from Twitter is creating new possibilities. Research has shown that analyzing sentiments from both social media and traditional news can significantly impact our understanding of market dynamics. So we at Ionio decided to implement this technology ourselves and report our findings.

Srihari Unnikrishnan

January 31, 2024

How to Train Your Language Model (In a single day with one GPU): Cramming

Language models have become crucial in understanding and generating human language. Traditionally, training these models requires hefty computational resources, often inaccessible to many researchers and enthusiasts. But what if they could train a competent language model on just a single GPU in one day?

Srihari Unnikrishnan

January 31, 2024

Layman’s guide to getting what you want with LLMs: INTERS (Part-1)

LLMs are really good at lots of tasks involving language. But, they don't do as well in finding specific information because the things they're looking for don't come up a lot in normal language. Even when we give LLMs clear instructions, they still struggle with these tasks. So, they're not as helpful in this area as we'd like. INTERS addresses this issue.

Srihari Unnikrishnan

January 31, 2024

Featured
No items found.
Categories
No items found.
We can help you grow your business

Sign up for our AI newsletter.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Ionio LLC

Copyrights © All Rights Reserved by Ionio.io
+1-910-315-0746 2055 Limestone Rd STE 200C IN Wilmington Wilmington, DE 19808
company
Privacy PolicyTerms of Service