Modelpublic

javidlakha/Llama-2-7b-qlora-python

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes11downloads

Model Card

Training procedure

The following bitsandbytes quantization config was used during training:

—loadin8bit: True
—loadin4bit: False
—llmint8threshold: 6.0
—llmint8skip_modules: None
—llmint8enablefp32cpu_offload: False
—llmint8hasfp16weight: False
—bnb4bitquant_type: fp4
—bnb4bitusedoublequant: False
—bnb4bitcompute_dtype: float32

Framework versions

—PEFT 0.4.0