baumhaus.digital/Miscellanous/Presentations/AE54/Make Your Language-Model-Driven Community Engine/Adapting an MLM to suit Your needs
Essentially, You have three options:
fine-tuning (in every training step, training process updates billions and billions of parameters)
training a LoRa (instead of updating billions of parameters, You update just few millions)
do Retrieval Augmented Generation
1 Axones
- ❌ this knot is_parent 🔗 (ID: 1508 · weight 1)