Modelpublic

clemmillet/lora-gptq-quotations_30steps

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes4downloads

Model Card

Training procedure

The following bitsandbytes quantization config was used during training:

—quant_method: gptq
—bits: 4
—tokenizer: None
—dataset: None
—group_size: 128
—damp_percent: 0.01
—desc_act: False
—sym: True
—true_sequential: True
—usecudafp16: False
—model_seqlen: None
—blocknameto_quantize: None
—modulenameprecedingfirstblock: None
—batch_size: 1
—padtokenid: None
—disable_exllama: True

Framework versions

—PEFT 0.5.0