Overview
Upstage AI Talk Event Recap: Where AI experts gather to shape the future
Check out the recap of the Upstage AI Talk Event, where AI experts come together to shape the future. Discover valuable insights into LLMs and explore the future of artificial intelligence.
Small Models, Big Impact: How Upstage Built a Highly Accurate SLM for Proofreading
Explore how Upstage built a highly accurate Small Language Model (SLM) that outperforms fine-tuned GPT-4o mini for proofreading.
Understanding Fine-Tuning of Large Language Models: A Comprehensive Overview
Fine-tuning Large Language Models (LLMs) is crucial for customizing AI to meet specific business needs. This blog delves into the two primary types of fine-tuning: instruction tuning, which enhances a model's ability to follow complex commands, and alignment tuning, which ensures outputs align with human values. By understanding these processes, businesses can effectively leverage AI for customer support, content creation, and more.
Exploring Real-World LLM Solutions with Solar - Webinar Summary
Dive into the six ideas presented at the "Exploring Real-World LLM Solutions with Solar" webinar and discover a variety of use cases that bring LLMs into real-world applications.
![[Prompt Engineering - Part 2] The Essence of Prompt Engineering: A Comprehensive Guide to Maximizing LLM Usage](https://images.squarespace-cdn.com/content/v1/659384103b38c97cdaf368bd/1723078816174-ZQL4GH8K5FDO8D0MFUHT/Prompt+Engineering+Guide+%281%29.jpg)
[Prompt Engineering - Part 2] The Essence of Prompt Engineering: A Comprehensive Guide to Maximizing LLM Usage
Delve into the significance of Prompt Engineering and explore both fundamental and advanced Prompt Engineering techniques. Follow our comprehensive guide to maximizing the potential of Large Language Models.
Empowering Vietnam's AI Potential: A Recap of Upstage's Event and Interview Content with Vietnam Experts
Explore Vietnam's AI scene through Upstage event recaps and interviews with Vietnamese experts. Discover more about our efforts in taking new steps towards global expansion.
![[Prompt Engineering - Part 1] Maximizing the Use of LLM with Prompt Design](https://images.squarespace-cdn.com/content/v1/659384103b38c97cdaf368bd/52c31365-df8e-48f8-8dcb-517640735b81/Prompt+Engineering+Guide.jpg)
[Prompt Engineering - Part 1] Maximizing the Use of LLM with Prompt Design
To fully leverage the power of LLMs, crafting effective prompts is imperative. In this blog, we will explore the concept of Prompt Engineering using SolarLLM and examine methodologies to elicit optimal results from Generative AI.
Building end-to-end RAG system using Solar LLM and MongoDB Atlas
Discover how enterprises can build an internal RAG application using Solar LLM and MongoDB Atlas to improve employees' access to information and boost work productivity.
Event Recap - Exploring Japan's AI scene with Upstage Solar Mini ja
Exploring Japan's AI scene with Upstage Solar Mini ja! Discover the impact of Generative AI on global industries within the race for development. Check out our stories to see how we're expanding language support across the Asia-Pacific region.
SAAS - Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
Introducing "SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models," a groundbreaking research paper by Upstage AI, Mathpresso Inc., and KT Corp. This novel approach leverages sequential learning, combining Chain-of-Thought (CoT) and Program-of-Thought (PoT) methodologies to significantly boost the mathematical reasoning and problem-solving skills of Large Language Models (LLMs). Our findings show that SAAS achieves state-of-the-art performance on benchmarks like GSM8K and MATH, outperforming larger models and setting new standards in AI-driven mathematical reasoning. Discover how SAAS can elevate your LLM’s capabilities.
Solar LLM with Predibase: The Best LLM for Fine-Tuning that beats GPT-4
Introducing Solar LLM, the best LLM for fine-tuning that beats GPT-4! Delve into the details on why Solar LLM excels in fine-tuning and explore a fast, reliable, and cost-effective platform for developers to fine-tune the Solar model.
Our journey to expanding the LLM ecosystem: #OpenSource #Hackathon #SchoolTour
Dive into our AI journey to expand the LLM ecosystem in this blog post. Learn about the importance of building a vibrant LLM ecosystem and how Upstage is empowering engineers globally to develop innovative LLM applications.
Next Generation for AGI: Upstage’s On-Device LLM, WriteUp
Experience the power of AI at your fingertips with Upstage's on-device LLM, WriteUp. Enjoy AI assistance for writing tasks without the need for an internet connection, thanks to advanced model optimization and quantization technologies. Perfect for remote locations, WriteUp ensures data privacy and high performance on your personal device.
Introducing Solar Mini Chat ja: Expanding Language Support to Japanese
We are thrilled to announce that Solar mini chat now includes Japanese, alongside English and Korean. Specially fine-tuned for multi-turn chat, Solar mini chat ja excels in Japanese language interactions, offering high performance and an enhanced user experience. Ideal for applications demanding nuanced and context-aware communication, it surpasses many open-source models in key NLP tasks. Seamlessly integrate it with your existing API keys and elevate your Japanese chat applications!
Breaking Barriers: Revolutionize Your Work with Our Next-Level Embedding Model
Experience the Next Leap in Embedding Technology with Solar Embedding-1-Large: Our groundbreaking Solar Embedding-1-Large model is set to transform your work processes. With superior performance compared to OpenAI's models and a commitment to tackling even the toughest tasks, it's time to elevate your search systems and beyond.
Deploying Solar with BentoML
Deploying Solar with BentoML offers a seamless solution for enterprises seeking powerful, cost-efficient large language model (LLM) deployment. Learn how to leverage Solar's compact yet potent 10.7B model with BentoML's deployment capabilities, ensuring optimal performance and scalability. Explore the integration steps and unlock the potential of Solar for your AI initiatives.
Evalverse: Revolutionizing Large Language Model Evaluation with a Unified, User-Friendly Framework
Discover Evalverse: A groundbreaking framework revolutionizing Large Language Model evaluation. With its unified approach and user-friendly features, Evalverse simplifies assessment, making AI advancements inclusive and comprehensive. Explore its key features and architecture, and witness its practical application in our demonstrative video. Join us in driving innovation and accessibility in AI technology with Evalverse!
Case Study: RAG-based natural language question response
Explore the transformative potential of Retrieval-Augmented Generation (RAG) in revolutionizing information retrieval and response generation. Learn how Upstage's bespoke RAG systems, exemplified by the BIG KINDS AI for news searches, harness advanced AI capabilities and real-time data integration to deliver precise, contextually relevant responses. With a focus on enhancing user experience and mitigating hallucination, Upstage sets a new standard in RAG technology, offering tailored solutions that exceed client expectations.
Case Study: Client-specific Large Language Model
Discover how Upstage addresses the challenges of e-commerce data extraction with a tailored, private Large Language Model (LLM). With a focus on Attribute-Value Extraction (AVE) and sentiment analysis, Upstage's innovative approach streamlines product listing processes and enhances user experience on platforms like Connectwave. Leveraging a Mixture-of-Experts architecture and AWS SageMaker, Upstage sets a new standard in commerce-specific LLM development, driving efficiency and productivity in the e-commerce sector.
Solar LLM Rises in the East via AWS SageMaker Jumpstart
Explore the strengths of our Solar LLM and try it now on Amazon Sagemaker Jumpstart and AWS Marketplace.