Show HN: Number of layers for efficient fine-tuning. Experiments(qdrant.tech)
qdrant.tech
Show HN: Number of layers for efficient fine-tuning. Experiments
https://qdrant.tech/articles/embedding-recycler/
Model fine-tuning allows you to improve the quality of the pre-trained models with just a fraction of the resources spent on training the original model. Qdrant team has run several experiments to test the number of layers to fine-tune.
0 comments
—