---
library_name: peft
license: mit
---
## Training procedure


The following `bitsandbytes` quantization config was used during training:
- quant_method: gptq
- bits: 4
- tokenizer: None
- dataset: None
- group_size: -1
- damp_percent: 0.1
- desc_act: True
- sym: True
- true_sequential: True
- use_cuda_fp16: False
- model_seqlen: 4096
- block_name_to_quantize: model.layers
- module_name_preceding_first_block: ['model.embed_tokens']
- batch_size: 1
- pad_token_id: None
- disable_exllama: True
- max_input_length: None

The following `bitsandbytes` quantization config was used during training:
- quant_method: gptq
- bits: 4
- tokenizer: None
- dataset: None
- group_size: -1
- damp_percent: 0.1
- desc_act: True
- sym: True
- true_sequential: True
- use_cuda_fp16: False
- model_seqlen: 4096
- block_name_to_quantize: model.layers
- module_name_preceding_first_block: ['model.embed_tokens']
- batch_size: 1
- pad_token_id: None
- disable_exllama: True
- max_input_length: None

The following `bitsandbytes` quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: float16
### Framework versions

- PEFT 0.5.0
- PEFT 0.5.0

- PEFT 0.5.0