Modelpublic

Rexe/Deci-Decicoder-1b-lora-coder

sourceHugging Faceupdated 3y agoView on Hugging Face

1likes7downloads

Model Card

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 0.6.0.dev0