Update README.md
Browse files
README.md
CHANGED
|
@@ -13,14 +13,13 @@ tags:
|
|
| 13 |
|
| 14 |
|
| 15 |
## Llama-VARCO-8B-Instruct-GGUF
|
| 16 |
-
|
| 17 |
## Thanks to https://huggingface.co/NCSOFT/Llama-VARCO-8B-Instruct
|
| 18 |
-
## <Translate the original text>
|
| 19 |
|
|
|
|
|
|
|
| 20 |
## Llama-VARCO-8B-Instruct
|
| 21 |
|
| 22 |
### About the Model
|
| 23 |
-
|
| 24 |
**Llama-VARCO-8B-Instruct** is a *generative model* built with Llama, specifically designed to excel in Korean through additional training. The model uses continual pre-training with both Korean and English datasets to enhance its understanding and generation capabilites in Korean, while also maintaining its proficiency in English. It performs supervised fine-tuning (SFT) and direct preference optimization (DPO) in Korean to align with human preferences.
|
| 25 |
|
| 26 |
- **Developed by:** NC Research, Language Model Team
|
|
|
|
| 13 |
|
| 14 |
|
| 15 |
## Llama-VARCO-8B-Instruct-GGUF
|
|
|
|
| 16 |
## Thanks to https://huggingface.co/NCSOFT/Llama-VARCO-8B-Instruct
|
|
|
|
| 17 |
|
| 18 |
+
|
| 19 |
+
## **Translate the original text**
|
| 20 |
## Llama-VARCO-8B-Instruct
|
| 21 |
|
| 22 |
### About the Model
|
|
|
|
| 23 |
**Llama-VARCO-8B-Instruct** is a *generative model* built with Llama, specifically designed to excel in Korean through additional training. The model uses continual pre-training with both Korean and English datasets to enhance its understanding and generation capabilites in Korean, while also maintaining its proficiency in English. It performs supervised fine-tuning (SFT) and direct preference optimization (DPO) in Korean to align with human preferences.
|
| 24 |
|
| 25 |
- **Developed by:** NC Research, Language Model Team
|