| license: cc-by-nc-4.0 | |
| datasets: | |
| - HuggingFaceH4/ultrafeedback_binarized | |
| Trained for one epoch on ultrafeedback_binarized using cDPO. Evaluation pending. |
| license: cc-by-nc-4.0 | |
| datasets: | |
| - HuggingFaceH4/ultrafeedback_binarized | |
| Trained for one epoch on ultrafeedback_binarized using cDPO. Evaluation pending. |