File size: 372 Bytes
f5bb20f 75b5080 f5bb20f 75b5080 f5bb20f 75b5080 |
1 2 3 4 5 6 7 8 9 10 11 |
---
library_name: transformers
datasets:
- HuggingFaceH4/ultrafeedback_binarized
base_model:
- glorgao/Qwen2.5-7B-SFT
---
This model is fine-tuned from the glorgao/Qwen2.5-7B-SFT model using the SelectiveDPO algorithm on the Ultrafeedback_binarized dataset.
For the recipe to reproduce this model, please visit our [GitHub page](https://github.com/glorgao/SelectiveDPO). |