This blog post provides instructions on how to fine tune LLaMA 2 models on Lambda Cloud using a $0.60/hr A10 GPU.
Building an AI Medical Assistant Part 1: LLama2 Fine-Tuning with Hugging Face Containers, QLoRA and PEFT With WANDB in AWS Sagemaker Spot Instances to cut LLM customization costs.”
Zongheng Yang on LinkedIn: Serving LLM 24x Faster On the Cloud with vLLM and SkyPilot
Fine-Tuning LLaMA 2 Models using a single GPU, QLoRA and AI Notebooks - OVHcloud Blog
How to Seamlessly Integrate Llama2 Models in Python Applications Using AWS Bedrock: A Comprehensive Guide, by Woyera
Fine-tune LLaMA 2 (7-70B) on SageMaker
A simple guide to fine-tuning Llama 2
Fine-tuning large language models in practice: LLaMA 2
Mitesh Agrawal on LinkedIn: GitHub - huggingface/community-events: Place where folks can contribute to…
The Lambda Deep Learning Blog
Fine-Tuning LLaMA 2 Models using a single GPU, QLoRA and AI Notebooks - OVHcloud Blog
2023 Year in Review: The Great GPU Shortage and the GPU Rich/Poor
Devon Brackbill