Show HN: LoRA can make distributed fine-tuning far faster
ericyu3.notion.site
Show HN: LoRA can make distributed fine-tuning far faster
1–4 of 4 posts
Re: Show HN: LoRA can make distributed fine-tuning far faster
#2LoRA AWS swarms are 60x 1 GPU throughput for fine-tuning?? Kind of a big find
Re: Show HN: LoRA can make distributed fine-tuning far faster
#3How is the model performance? I heard lora on LLM generally get inferior results comparing to no LORA finetuning
Re: Show HN: LoRA can make distributed fine-tuning far faster
#4How is the model performance? I heard lora on LLM generally get inferior results comparing to no LORA finetuning
Generally good as long as you target all layers.