Yes, Llama 3 (8B and 70B) is supported for fine-tuning with LoRA adapters, which can be deployed via our serverless and on-demand options for inference.

Capabilities include:

  • LoRA adapter training for flexible model adjustments
  • Serverless deployment support for scalable, cost-effective usage
  • On-demand deployment options for high-performance inference
  • A variety of base model options to suit different use cases

For a complete list of models available for fine-tuning, refer to our documentation.