--- library_name: peft base_model: decapoda-research/llama-7b-hf --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0