Re:Qwen2 LLM Released
by danielhanchen on Friday June 07, 2024 @01:35AM
(#40605620)
For finetuning, I made a Colab notebook to finetune Qwen2 7b 2x faster and use 70% less VRAM than HF+FA2! https://colab.research.google.com/drive/1mvwsIQWDs2EdZxZQF9p...
[ Parent
| on HN ]
There are no comments on this comment yet.