issues
search
qwopqwop200
/
GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
Apache License 2.0
2.99k
stars
459
forks
source link
LoRa and diff with bitsandbytes
#281
Open
RonanKMcGovern
opened
1 year ago
RonanKMcGovern
commented
1 year ago
What changes would I need to make for GPTQ to support LoRa for Llama 2?
What's the main difference between GPTQ vs bitsandbytes? Is it that GPTQ re-adjusts the weights to keep the same loss function shape?