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
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
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&