Harnessing LLMs for Computational Neuroscience with Llama-3–8b-Smith-Neuroscience

27/12/2024 15 min
Harnessing LLMs for Computational Neuroscience with Llama-3–8b-Smith-Neuroscience

Listen "Harnessing LLMs for Computational Neuroscience with Llama-3–8b-Smith-Neuroscience"

Episode Synopsis

Medium Article: https://medium.com/@jsmith0475/harnessing-large-language-models-for-computational-neuroscience-bridging-biology-and-artificial-448c6ad1bc0f

Dr. Jerry Smith's Medium article details the development and application of Llama-3–8b-Smith-Neuroscience, a fine-tuned large language model specializing in computational neuroscience. This model, based on unsloth/llama-3–8b-Instruct-bnb-4bit, uses techniques like LoRA and QLoRA for efficient processing and offers domain-specific expertise in areas such as spiking neural networks and neuromorphic computing. Its accessibility and capabilities are highlighted, along with its potential uses in research, education, and AI development. The article also addresses the model's limitations and future development.

More episodes of the podcast Deep Dive - Frontier AI with Dr. Jerry A. Smith