Commit
•
ea6b5bc
1
Parent(s):
20a153f
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,7 @@ We finetuned [Korean Llama-2](https://huggingface.co/beomi/llama-2-koen-13b) tha
|
|
| 19 |
The Flash-Attention2 and LoRA were utilized for efficient finetuning.
|
| 20 |
|
| 21 |
The KoRAE will be uploaded in [Open Ko-LLM Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)!
|
|
|
|
| 22 |
Stay tuned for the update of KoRAE!
|
| 23 |
|
| 24 |
## Model Details
|
|
|
|
| 19 |
The Flash-Attention2 and LoRA were utilized for efficient finetuning.
|
| 20 |
|
| 21 |
The KoRAE will be uploaded in [Open Ko-LLM Leaderboard](https://huggingface.co/spaces/upstage/open-ko-llm-leaderboard)!
|
| 22 |
+
In addition, the DPO trained version of KoRAE will be uploaded soon too!
|
| 23 |
Stay tuned for the update of KoRAE!
|
| 24 |
|
| 25 |
## Model Details
|