Anindyadeep Sannigrahi - Prem

Sign in Subscribe

Anindyadeep Sannigrahi

PremSQL: Towards end-to-end Local First Text to SQL pipelines

PremSQL: Towards end-to-end Local First Text to SQL pipelines

PremSQL is a local-first, open-source Text-to-SQL solution that ensures data privacy and control by avoiding third-party models. With support for small language models, PremSQL simplifies natural language querying and provides autonomous, AI-driven data analysis.

Evaluating LLMs for text to SQL with Prem text2sql

Evaluating LLMs for text to SQL with Prem text2sql

Explore the latest Text-to-SQL advancements in our new blog. We evaluate top models like GPT-4o and Llama using the newly released text2sql package on BIRDBench. Learn about Execution Accuracy, Valid Efficiency Score, and how open-source models are challenging closed-source alternatives.

2024 AI Wrapped: Innovations, Challenges, and What’s Next for PremAI

2024 AI Wrapped: Innovations, Challenges, and What’s Next for PremAI

2024 marked a transformative year in AI, with breakthroughs from OpenAI, Anthropic, and Meta, the rise of open-source models like Llama 3.1, and the emergence of advanced reasoning systems such as DeepSeek R1. Discover how innovations, challenges, and PremAI’s contributions.

Are Agentic Frameworks an Overkill? Benefits, Challenges, and Alternatives

Are Agentic Frameworks an Overkill?

Agentic frameworks offer advanced adaptability and automation but come with high complexity and cost. This article explores their benefits, limitations, and practical alternatives to help you decide whether they are the right solution for your AI and automation needs.

Prem-1B-SQL: Fully Local Performant SLM for Text to SQL

Last week, we open-sourced PremSQL, a local first library that created customized Text-to-SQL solutions. When deploying RAG-based services (whether on documents or databases) for enterprises, it becomes crucial that the underlined data is not exposed to third-party APIs. With PremSQL, you can use our ready-made pipelines or customize and create

State of Text2SQL 2024

State of Text2SQL 2024

Text to SQL is a task that aims to convert natural language questions into corresponding SQL queries that can be executed in relational databases. Interestingly, this problem statement has been through research before the rise of Large Language Models.

Introducing Benchmarks v2

Introducing Benchmarks v2

Prem's Benchmarks v2 is an open-source project evaluating 13+ LLM inference engines, including vLLM and TensorRT LLM, across precisions like float32, float16, int4, and int8. It helps the open-source community and enterprises understand LLM inference performance.

Serverless Deployment of Mistral 7B v0.2 using Runpod

Serverless Deployment of Mistral 7B v0.2 using Runpod

The article provides a step-by-step guide to deploying the Mistral 7B v0.2 model on RunPod's serverless GPU cloud infrastructure. It covers setting up the environment, writing deployment scripts, and configuring the Docker environment for efficient AI application scaling.

Serverless Deployment with Google Gemma using Beam Cloud

Serverless Deployment with Google Gemma using Beam Cloud

Deploy Google Gemma 2B on Beam Cloud using FastAPI for serverless inference. This guide covers model setup, Hugging Face token authentication, autoscaling, and seamless deployment. Learn how Beam Cloud simplifies LLM hosting with scalable infrastructure.

Serverless Deployment of Mistral 7B with Modal Labs and HuggingFace

Serverless Deployment of Mistral 7B with Modal Labs and HuggingFace

Learn how to deploy Mistral-7B-Instruct serverlessly using Modal Labs for cost-efficient, scalable AI inference. This guide covers serverless benefits, cost savings, cold starts, and a step-by-step deployment process with Hugging Face Transformers.

Mamba Simplified - Part 2 - S4 and Mamba

Mamba Simplified - Part 2 - S4 and Mamba

This article delves into State Space Models, focusing on the S4 and Mamba architectures. It discusses their mathematical foundations, including differential equations and convolutions, and examines how these models balance parallelizable training with efficient inference in sequence modeling.

Mamba Simplified - Part 1 - Essential Pre-Requisites

Mamba Simplified - Part 1 - Essential Pre-Requisites

This article introduces foundational concepts like derivatives, differential equations, and neural networks, essential for understanding Mamba—a Small Language Model based on State Space Models (SSMs). It serves as a refresher to grasp Mamba's architecture effectively.

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.

LLM360, A true Open Source LLM

LLM360, A true Open Source LLM

LLM360 introduces true open-source AI with its 7B parameter models, Amber and CrystalCoder, providing full transparency by sharing training datasets, preprocessing code, model configurations, intermediate checkpoints, and evaluation metrics, fostering collaborative and reproducible AI research.

The Synthetic Data Revolution

The Synthetic Data Revolution

This article delves into the emergence of synthetic data in AI, discussing its generation methods, applications across various data types, and its significance in overcoming data scarcity and privacy challenges, ultimately contributing to the pursuit of Artificial General Intelligence (AGI)

MoEs comeback in GenAI with Mixtral

MoEs comeback in GenAI with Mixtral

This article takes a deep dive into Mixture of Experts models, spotlighting Mistral's latest release. Learn how this architecture enhances AI scalability, efficiency, and performance, paving the way for next-gen AI systems that balance resource optimization with powerful capabilities.

RAGs are cool, but what about their privacy?

RAGs are cool, but what about their privacy?

This article explores privacy concerns in Retrieval-Augmented Generation (RAG) applications, highlighting data protection challenges and offering actionable solutions to ensure secure and compliant AI systems while leveraging the benefits of RAG.