Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ language:
|
|
| 4 |
- yue
|
| 5 |
---
|
| 6 |
|
| 7 |
-
**This is a preview version, and this repository will be deleted once the new version is released. We are currently in the process of finding the balance between overfitting and generalization in DPO training. For more details about the problems we encountered in this version, please refer to the Limitation section
|
| 8 |
|
| 9 |
Continual pretraining model of the [Yi-6B](https://huggingface.co/01-ai/Yi-6B) model on a Cantonese corpus, which consisted of translated Hong Kong news, Wikipedia articles, subtitles, and open-sourced dialogue corpora. Additionally, we extended the vocabulary to include common Cantonese words.
|
| 10 |
|
|
|
|
| 4 |
- yue
|
| 5 |
---
|
| 6 |
|
| 7 |
+
**This is a preview version, and this repository will be deleted once the new version is released. We are currently in the process of finding the balance between overfitting and generalization in DPO training. For more details about the problems we encountered in this version, please refer to the Limitation section. Please join our [Discord server](https://discord.gg/gG6GPp8XxQ) to give us your feedback**
|
| 8 |
|
| 9 |
Continual pretraining model of the [Yi-6B](https://huggingface.co/01-ai/Yi-6B) model on a Cantonese corpus, which consisted of translated Hong Kong news, Wikipedia articles, subtitles, and open-sourced dialogue corpora. Additionally, we extended the vocabulary to include common Cantonese words.
|
| 10 |
|