This notebook walks through a more conventional way of fine-tuning GPT Neo before going on to use DeepSpeed to fine-tune the larger GPT Neo models.
Youtube video walkthrough can be found here
This notebook walks through a more conventional way of fine-tuning GPT Neo before going on to use DeepSpeed to fine-tune the larger GPT Neo models.
Youtube video walkthrough can be found here
GNU Affero General Public License v3.0