{"id":5696,"date":"2024-01-11T02:06:05","date_gmt":"2024-01-11T02:06:05","guid":{"rendered":"https:\/\/www.salesforce.com\/?p=5696"},"modified":"2024-01-11T02:06:07","modified_gmt":"2024-01-11T02:06:07","slug":"adapt-or-train-your-own-llm","status":"publish","type":"post","link":"https:\/\/www.salesforce.com\/ap\/blog\/adapt-or-train-your-own-llm\/","title":{"rendered":"How To Unlock the Power of Generative AI Without Building Your Own LLM"},"content":{"rendered":"\n

Everyone wants generative AI applications and their groundbreaking capabilities, such as creating content, summarising text, answering questions, translating documents, and even reasoning on their own to complete tasks.<\/p>\n\n\n\n

But where do you start? How do you add large language models (LLMs) to your infrastructure to start powering these applications? Should you train your own LLM? Customise a pre-trained open-source model? Use existing models through APIs?<\/p>\n\n\n\n

Training your own LLM is a daunting and expensive task. The good news is that you don’t have to. Using existing LLMs through APIs allows you to unlock the power of generative AI today, and deliver game-changing AI innovation fast.<\/p>\n\n\n\n

How can a generic LLM generate relevant outputs for your company? By adding the right instructions and grounding data to the prompt, you can give an LLM the information it needs to learn \u201cin context,\u201d and generate personalised and relevant results, even if it wasn\u2019t trained on your data.<\/p>\n\n\n\n

Your data belongs to you, and passing it to an API provider might raise concerns about compromising sensitive information. That\u2019s where the Einstein Trust Layer<\/a> comes in. (More on this later.)<\/p>\n\n\n\n

\n\t
\n\n\t\t
\n\t\t\t

What is an LLM?<\/strong><\/h2>\n\t\t\t\t\t\t\t

Large language models (LLMs) are a type of AI that can generate human-like responses by processing natural-language inputs. <\/p>\n\t\t\t\n\t\t\t\n\t\t\t\t\t\t\t

\n\t\t\t\t\tCheck out our AI glossary<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\n\t\t
\n\t\t\t\t\t<\/div>\n\t<\/div>\n\n\t\t\t
<\/div>\n\t\n\t\t\t\n\t\t\"\"\n\n\t\t\n\t\t\t\t\t\"\"\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\t\t\t\"\"\n\t\t\n\t<\/div>\n\n\n\n

In this blog post, we\u2019ll review the different strategies to work with LLMs, and take a deeper look at the easiest and most commonly used option: using existing LLMs through APIs. <\/p>\n\n\n\n

As Salesforce\u2019s SVP of technical audience relations, I often work with my team to test things out around the company. I\u2019m here to take you through each option so you can make an informed decision.<\/p>\n\n\n\n

1. Train your own LLM (Hint: You don’t have to)<\/strong><\/h2>\n\n\n\n

Training your own model gives you full control over the model architecture, the training process, and the data your model learns from. For example, you could train your own LLM on data specific to your industry: This model would likely generate more accurate outputs for your domain-specific use cases than a general-purpose model. <\/p>\n\n\n\n

But training your own LLM from scratch has some drawbacks, as well:<\/p>\n\n\n\n