Currently I have 12+24GB VRAM and I get Out Of Memory all the time when try to fine tune 33B models. 13B is fine, but the outcome is not very good so I would like to try 33B. I wonder if it’s worthy to replace my 12GB GPU with a 24GB one. Thanks!
Currently I have 12+24GB VRAM and I get Out Of Memory all the time when try to fine tune 33B models. 13B is fine, but the outcome is not very good so I would like to try 33B. I wonder if it’s worthy to replace my 12GB GPU with a 24GB one. Thanks!
Should work on single 24g gpu as well as either qlora or alpaca_lora_4bit. You won’t get big batches or big context but it’s good enough.
Thanks! I have some problems to load GPTQ models with transformer loader.