Efficient On-Device LLMs: Function Calling and Fine-Tuning Strategies | HackerNoonThe deployment of smaller-scale Large Language Models (LLMs) on edge devices is progressing despite challenges.7B and 13B models have shown significant capabilities in function calling, rivaling GPT-4.
Octopus v2: An On-Device Language Model for Super Agent | HackerNoonOn-device language models can outperform GPT-4 by enhancing accuracy and reducing latency drastically in function calling tasks.
OpenAI Developer Day 2024 (SF) Announces Real-Time API, Vision Fine-Tuning, and MoreOpenAI introduced a Real-Time API for instant voice interactions, enhancing functionality for virtual assistants and real-time translation.