metadata
license: apache-2.0
Trained polyglot 1.3B with the QLORA method using the nsmc dataset.
The hyper-parameters used for training are as follows.
- batch-size: 16
- max_steps: 10000
- Learning rate: 3e-4
- Lora r: 8
- Lora target modules: query_key_value
Prompt Template:
### 문장: {문장}
### 감정: {긍정 또는 부정}