Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
Generative AI in the Enterprise with AMD Accelerators
Introduction Concepts
Overview
Large language models
Inferencing
Retrieval augmented generation
Fine-tuning
Solution Architecture Validation Results Performance Characterization Dell Professional Services and Consulting Conclusion References Configuration file for LLM fine-tuning

Large language models

Home > AI Solutions > Gen AI > Guides > Generative AI in the Enterprise with AMD Accelerators > Large language models

Large language models

  • LLMs are advanced natural language processing models that use deep learning techniques to understand and generate human language. LLMs can include a range of architectures and approaches, such as recurrent neural networks (RNNs), transformers, or rule-based systems. Generative Pre-trained Transformer (GPT) is a popular and influential example of an LLM that is based on transformer architecture, which is a deep neural network architecture designed to handle sequential data efficiently. Transformers use self-attention mechanisms to process input sequences and learn contextual relationships between words, enabling them to generate coherent and contextually relevant language.

    A foundation model is an LLM that has been trained on a large dataset for a general task before it is fine-tuned or adapted for a more specialized task. These models are typically trained on vast amounts of general data to learn basic features, patterns, and context within the data. Foundation models are crucial because they provide a starting point that already understands a broad range of concepts and language patterns. 

    In this design, we focus on Meta Llama 3. It features pretrained and instruction-fine-tuned language models with 8 B and 70 B parameters and supports a broad range of use cases. This next generation of Llama demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.

    When choosing an LLM's parameter size, consider model quality, learning capability, computational demands, model size classes, and technical challenges. Larger models often perform better on complex tasks due to their increased complexity and adaptability, but they also require more computational resources and storage space. However, for specific tasks, a smaller model can achieve similar performance. Always consider your specific use case and requirements when making your choice. If you are considering Llama 3, it is recommended to begin with smaller model sizes (8 B), escalating to larger sizes only if the smaller ones fail to meet your needs. This recommendation is applicable for both inferencing and fine-tuning.

    See Meta’s Responsible Use Guide and Community License Agreement for using Llama in your enterprise deployment.