AlinaKl

ljb-llama3.1-8b-syntax-mix

AlinaKl/ljb-llama3.1-8b-syntax-mix

ljb-llama3.1-8b-syntax-mix is a machine learning model from AlinaKl. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

A LoRA adapter (rank 16, alpha 32) for meta-llama/Llama-3.1-8B, trained for 1 epoch using SFT on a 10% stratified sample of the Tulu-SFT-Mix. The dataset originally contains a 10:90 safety/non-safety ratio which is re…