| | --- |
| | library_name: peft |
| | base_model: meta-llama/Llama-2-7b-chat-hf |
| | inference: true |
| | pipeline_tag: text-generation |
| | --- |
| | ## Training procedure |
| |
|
| |
|
| | The following `bitsandbytes` quantization config was used during training: |
| | - quant_method: bitsandbytes |
| | - 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 0.6.0.dev0 |
