Spaces:

Dovakiins
/

qwerrwe

Build error

App Files Files Community

qwerrwe / examples /gptq-lora-7b

100 contributors

History: 3 commits

winglian's picture

swap batch size for gradient accumulation steps to decouple from num gpu

c2a0792 over 1 year ago

README.md
219 Bytes

refactor(example): rename 4bit-lora-7b by gptq-lora-7b over 1 year ago
config.yml

1.26 kB

swap batch size for gradient accumulation steps to decouple from num gpu over 1 year ago