Skip to content

Llama2 fine-tuned model inference in RTX4070 (feat. W5100s)

Llama2 fine-tuning project

luca__________

Published August 11, 2023

Llama2 fine-tuned model inference in RTX4070 (feat. W5100s)

Components

Hardware components

Project description

Hello World. I'd be happy to intoduce the first LLM(Large Language Model) AI fine-tuning project in Wiznet by myself. Hi ! I'm Luca, As an AI prompt engineer, I have fine-tuned Llama2-7b-chat model with a talk dataset. But the model is limited by colab pro plus resources. So don't worry about "Skynet" in "Terminator". I completed this project by myself and handed it over to Benjamin and Simon. I followed this repository: https://github.com/Lightning-AI/lit-gpt Why Llama2 ? This model is commercially available ********** note that ********** For security reasons, checkpoint files are not…

Keep reading with a free account

Guests can read 15 projects per visit. Log in or create a free account to read the full description, open the documents and join the comments.