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.
So you are given some Python project which creates an API endpoint which does some AI/ML inference. You need to run this on your own infra, a cloud VM or whatever. What do you do?
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.
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.
At Prem, we believe that the future of AI is Sovereign. This is why we are building a comprehensive ecosystem to enable companies worldwide to fully benefit from the potential of generative AI while retaining ownership and control of their data. Today, I am excited to share that we have
Today, we are excited to announce the open-source release of the “Prem-Operator,” A Kubernetes operator that eases the deployment of AI and ML workloads, with an initial focus on inference. The launch of the Prem Operator marks a major advancement in our goal to provide AI that you can fully
With great enthusiasm, we unveil the Prem-1B series, an open-source, multipurpose large language model developed by Prem AI. This cutting-edge SLM offers the open community and enterprises the opportunity to harness capabilities that were once exclusively available through closed-model APIs, empowering them to build their advanced language models. The weights
We believe in giving back to the community. So today we introduce Prem Benchmarks. This is a fully open-source project with its primary objective being to benchmark popular LLM inference engines (currently 13 + engines) like vLLM, TensorRT LLM, HuggingFace Transformers, etc on different precisions like float32, float16, int4, and int8.
Imagine a student taking a closed-book exam, relying solely on what they've memorized. This is how traditional large language models (LLMs) operate, using only the data they were trained on. Retrieval-augmented generation (RAG) changes this by allowing the model, like a student now taking an open-book exam, to
Imagine you've spent countless hours training a large language model, pouring in vast amounts of data and computing power, only to realize that you must fine-tune it for a specific task. Traditional fine-tuning methods often require updating all the model parameters, which can be time-consuming and resource-intensive, especially
The announcement of Mixtral 8x7B and DeepMind's Mixture-of-Depths, among others, has once again made the Mixture of Experts (MoE) architecture for transformers a popular choice in the NLP community. Continuing our previous blog on fine-tuning, we discuss the popular scaling of LLMs via sparse experts, referred to as
The alignment of generative models with human feedback has significantly improved the performance of natural language generation tasks. For large language models (LLMs), alignment methods like reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) have consistently worked better than just supervised fine-tuning (SFT) alone based on current
Welcome to our third series of serverless LLM deployments. In our first blog, we explored Modal Labs and deployed Mistral 7B serverless. We did the same with Google Gemma in our second blog with Beam cloud. In this blog, we are going to deploy the latest Mistral 7B v0.2
In our previous blog, we showed you how to deploy a Large Language Model like Mistral 7B going serverless using Modal Labs. Today's blog explores Beam Cloud which provides similar services. We'll demonstrate how to deploy the Google Gemma 2B model with HuggingFace and Beam Cloud.
Most of our blogs primarily delve deep into research topics. From Mixture of Experts, synthetic datasets, and Model merging to LLM Evaluations, our blog covers it all. This post is a bit different and includes a more hands-on approach to how we can deploy Large Language Models going fully serverless.
In recent months, the landscape of language models has been enriched by the emergence of several small language models (e.g. TinyLlama, Phi2, Gemma, and StableLM2) prompting investigations into their capabilities and potential applications. Key questions have arisen regarding the emergent capabilities of these compact models, their practical utility, and
LLMs
Our study aims to explore how different providers use different techniques in order to serve LLMs influencing the overall quality of the models. To achieve this, we conduct empirical tests using various prompts, allowing us to systematically compare the outcomes across various service providers. This approach helps us identify significant
LLMs
Large Language Models (LLMs) are in the spotlight, mainly due to their emerging capabilities. Please refer to our previous blog post on Emergent abilities in LLMs for a deeper dive into this topic. As the old saying goes, You can't make a silk purse out of a sow&
🦹♀️Imagine you have a bunch of superheroes, each trained in a specific skill. Iron Man's got the tech smarts, Black Widow's got the fighting moves, and Captain America...well, Captain America is just generally awesome. But wouldn't it be cool to combine their powers
LLMs
Emergence, a concept well-studied in fields like physics, biology, and mathematics, describes how complex systems can exhibit new, unforeseen properties as their complexity increases. Inspired by P.W. Anderson's influential idea that "More is Different," suggesting that complexity can lead to unexpected behaviors not evident from
LLMs
In this second part of the series, we delve into how LLMs can serve as evaluators, a concept referred to as "LLM as judge." Building on the previous blog, which introduced early benchmarks and metrics for evaluating large language models (LLMs) and highlighted issues with these evaluation methods,
LLMs
The rapid development of Large Language Models (LLMs) also necessitates advancing robust evaluation strategies and systems. For a broader understanding of these technological advancements, look at our previous exploration in The Tiny LLM Revolution. In this blog post, we do a deep dive into existing evaluation benchmarks and discuss future
⚠️ The Grant Program has been terminated. We have launched a GenAI Development Platform that allows you to fully harness the power of AI without needing to be an expert. Prem's platform offers a streamlined approach to integrating Generative AI into your products through a unified API, ensuring high
Mamba is a very recent deep-learning architecture and it is fundamentally different from transformer-based models. Mamba's performance is on par with the current Small/Large Language models like Phi-2, Mistral, Llama 2, etc. The Structured State Space for Sequence Models (S4), a State Space Model, is considered the