---
license: llama2
datasets:
- Ash-Hun/Welfare-QA
library_name: peft
pipeline_tag: text-generation
---

## Github
👉 [Github Repo](https://github.com/ash-hun/WelSSISKo)


## Training procedure

The following `bitsandbytes` quantization config was used during training:
- **load_in_4bit**: True
- **bnb_4bit_quant_type**: nf4
- **bnb_4bit_use_double_quant**: False
- **bnb_4bit_compute_dtype**: float16
  
### Framework versions

- PEFT 0.8.2.