---
library_name: peft
base_model: meta-llama/Llama-2-7b-chat-hf
author: Minh Dinh, Arthur Tang, Nhiem Tran, Tom Huynh, Nhat Bui, Giang Nguyen, Luan Vo, Nguyen Nguyen, Bao Vo  
---
## 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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions


- PEFT 0.6.0.dev0