321 B
321 B
license, language
| license | language | |
|---|---|---|
| apache-2.0 |
|
4season/model_eval_test3
Introduction
This model is test version, alignment-tuned model.
We utilize state-of-the-art instruction fine-tuning methods including direct preference optimization (DPO). After DPO training, we linearly merged models to boost performance.