3logic/
llama-3.1-8b-instruct-phactual_fp16_he20

273 1 year ago

Model finetuned starting with llama 3.1 8b using a full precision LoRA he20, rank 64, alpha 16

tools

1 model

llama-3.1-8b-instruct-phactual_fp16_he20:latest
5a9c2bcee0d6 • 16GB • 128K context window •
Text input • 1 year ago