Resources
Tutorials
Llama3 8B Fine-tuning
Tutorial to fine-tune Llama3 8B for text summarization on MoAI using up to 32 AMD GPUs.
Llama3 70B Fine-tuning
One-day tutorial to fine-tune Llama3 70B using 32 AMD GPUs without any manual (model) parallelization.
Mistral 7B Fine-tuning
Tutorial to fine-tune Mistral 7B for code generation on MoAI using up to 32 AMD GPUs.
More Tutorials...
Experience MoAI through various real examples with Llama, Mistral, GPT, Qwen, and Baichuan2 models.
Learn more about the MoAI Platform!
READ THE DOCS
