Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
**[ALMA-R](https://arxiv.org/abs/2401.08417)** builds upon [ALMA models](https://arxiv.org/abs/2309.11674), with further LoRA fine-tuning with our proposed **Contrastive Preference Optimization (CPO)** as opposed to the Supervised Fine-tuning used in ALMA. CPO fine-tuning requires our [triplet preference data](https://huggingface.co/datasets/haoranxu/ALMA-R-Preference) for preference learning. ALMA-R now can matches or even exceeds GPT-4 or WMT winners!
|
| 5 |
-
|
| 6 |
@misc{xu2024contrastive,
|
| 7 |
title={Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation},
|
| 8 |
author={Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
|
|
@@ -11,7 +11,7 @@ license: mit
|
|
| 11 |
archivePrefix={arXiv},
|
| 12 |
primaryClass={cs.CL}
|
| 13 |
}
|
| 14 |
-
|
| 15 |
# Download ALMA(-R) Models and Dataset 🚀
|
| 16 |
|
| 17 |
We release six translation models presented in the paper:
|
|
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
**[ALMA-R](https://arxiv.org/abs/2401.08417)** builds upon [ALMA models](https://arxiv.org/abs/2309.11674), with further LoRA fine-tuning with our proposed **Contrastive Preference Optimization (CPO)** as opposed to the Supervised Fine-tuning used in ALMA. CPO fine-tuning requires our [triplet preference data](https://huggingface.co/datasets/haoranxu/ALMA-R-Preference) for preference learning. ALMA-R now can matches or even exceeds GPT-4 or WMT winners!
|
| 5 |
+
```
|
| 6 |
@misc{xu2024contrastive,
|
| 7 |
title={Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation},
|
| 8 |
author={Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
|
|
|
|
| 11 |
archivePrefix={arXiv},
|
| 12 |
primaryClass={cs.CL}
|
| 13 |
}
|
| 14 |
+
```
|
| 15 |
# Download ALMA(-R) Models and Dataset 🚀
|
| 16 |
|
| 17 |
We release six translation models presented in the paper:
|