Modelpublic

cmu-lti/sotopia-pi-mistral-7b-BC_SR

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes6downloads

Model Card

https://arxiv.org/pdf/2403.08715

Training procedure

The following bitsandbytes quantization config was used during training:

—quantmethod: QuantizationMethod.BITSAND_BYTES
—loadin8bit: False
—loadin4bit: True
—llmint8threshold: 6.0
—llmint8skip_modules: None
—llmint8enablefp32cpu_offload: False
—llmint8hasfp16weight: False
—bnb4bitquant_type: nf4
—bnb4bitusedoublequant: True
—bnb4bitcompute_dtype: float16

Framework versions

—PEFT 0.5.0