In the realm of Large Language Models (LLMs), function calling plays a pivotal role by seamlessly integrating natural language understanding with code execution. Serving as an intermediary, the LLM undertakes the task of parsing and interpreting textual input to discern the specific function within a codebase that should be executed. As users input requests or questions, the LLM analyzes the content, pinpointing the relevant function to be called. This transformative capability shifts the LLM from a passive information provider to an active agent capable of performing tasks, executing calculations, or retrieving data based on user input. Function calling in LLMs marks a significant advancement, ushering in a new era of more dynamic and interactive applications of artificial intelligence.
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closedsource models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs.
