zlacker

[parent] [thread] 1 comments
1. carom+(OP)[view] [source] 2023-09-13 00:17:57
What are your thoughts on fine tuning vs low rank adaptations?
replies(1): >>brucet+AW2
◧
2. brucet+AW2[view] [source] 2023-09-13 21:15:03
>>carom+(OP)
Llama LORAs are very customizable, and range from "almost full finetuning" to "barely taking more VRAM than GPTQ inference"
[go to top]