Modelpublic

YieldInc/pythoncode

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes12downloads

README.md22 linesDownload Raw Back to root

1---2library_name: peft3---4## Training procedure5 6 7The following `bitsandbytes` quantization config was used during training:8- quant_method: bitsandbytes9- load_in_8bit: False10- load_in_4bit: True11- llm_int8_threshold: 6.012- llm_int8_skip_modules: None13- llm_int8_enable_fp32_cpu_offload: False14- llm_int8_has_fp16_weight: False15- bnb_4bit_quant_type: nf416- bnb_4bit_use_double_quant: True17- bnb_4bit_compute_dtype: bfloat1618### Framework versions19 20 21- PEFT 0.6.0.dev022