Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- loadin8bit: False
- loadin4bit: True
- llmint8threshold: 6.0
- llmint8skip_modules: None
- llmint8enablefp32cpu_offload: False
- llmint8hasfp16weight: False
- bnb4bitquant_type: nf4
- bnb4bitusedoublequant: True
- bnb4bitcompute_dtype: bfloat16
Framework versions
- PEFT 0.5.0
评论