RajuEEE/RewardModelForQuestionAnswering_LLama2_RevisedData

1---2library_name: peft3---4## Training procedure5 6 7The following `bitsandbytes` quantization config was used during training:8- quant_method: bitsandbytes9- load_in_8bit: True10- load_in_4bit: False11- 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: fp416- bnb_4bit_use_double_quant: False17- bnb_4bit_compute_dtype: float3218### Framework versions19 20 21- PEFT 0.6.0.dev022