| library_name: peft | |
| base_model: concise/LLaMa_V2-13B-Chat-Unquantized-HF | |
| ## Training procedure | |
| The following `bitsandbytes` quantization config was used during training: | |
| - load_in_8bit: False | |
| - load_in_4bit: True | |
| - 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: nf4 | |
| - bnb_4bit_use_double_quant: False | |
| - bnb_4bit_compute_dtype: float16 | |
| ### Framework versions | |
| - PEFT 0.5.0.dev0 | |