---
library_name: peft
license: apache-2.0
language:
- ja
---

## Sample

![](https://huggingface.co/p1atdev/ja-stablelm-base-alpha-7b-kogo-translation-peft/resolve/main/images/sample1.jpg)

## 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