Open pascal-pfeiffer opened 3 months ago
New advancements bringing quantized LoRA and FSDP together. https://github.com/AnswerDotAI/fsdp_qlora
Train larger models on consumer GPUs or older generation Data Center GPUs such as V100 Lets you finetune Llama-2 70B on dual 24GB GPUs.
Would be awesome! Looking forward to it.
🚀 Feature
New advancements bringing quantized LoRA and FSDP together. https://github.com/AnswerDotAI/fsdp_qlora
Motivation
Train larger models on consumer GPUs or older generation Data Center GPUs such as V100 Lets you finetune Llama-2 70B on dual 24GB GPUs.