Modelpublic

icedveins23/python_problem_solving

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes8downloads

README.md21 linesDownload Raw Back to root

1---2library_name: peft3---4## Training procedure5 6 7The following `bitsandbytes` quantization config was used during training:8- load_in_8bit: False9- load_in_4bit: True10- llm_int8_threshold: 6.011- llm_int8_skip_modules: None12- llm_int8_enable_fp32_cpu_offload: False13- llm_int8_has_fp16_weight: False14- bnb_4bit_quant_type: nf415- bnb_4bit_use_double_quant: False16- bnb_4bit_compute_dtype: float1617### Framework versions18 19 20- PEFT 0.4.021