Update README.md
#13
by
ReactionControl
- opened
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 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 |
```
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- haoranxu/ALMA-13B-Pretrain
|
| 5 |
---
|
| 6 |
**[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!
|
| 7 |
```
|