Downloads · 30 days
0
ndavidson/llama-3-6B
llama-3-6B is a machine learning model from ndavidson. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.
Pruning strategy to delete optimal layers of Llama-8B instruct model. Discarded 25% of the layers, model still produces legible text. Next steps include healing PEFT steps
Downloads · 30 days
0
Access
Public
Updated Apr 23, 2024
Repo size
—
Likes
0
Public
Click a slice to open those files.
Other1.5 KB · 89%
From the Hugging Face model README
Pruning strategy to delete optimal layers of Llama-8B instruct model. Discarded 25% of the layers, model still produces legible text. Next steps include healing PEFT steps