Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
</div>
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
-
<img width="
|
| 18 |
|
| 19 |
# Model Card for Bailong-orpo 7B
|
| 20 |
This model card contains the information and the results of our released Bailong (白龍) project. Bailong, which stands for **B**ilingual tr**A**nsfer learn**I**ng based on q**LO**ra and zip-tie embeddi**NG**, is our newest project aimed at enhancing the Traditional Chinese performance in open-source large language model (LLM). All the consequences are listed as follows:
|
|
@@ -33,6 +33,7 @@ algorithm, [ORPO](https://arxiv.org/abs/2403.07691), we further fine-tune Bailon
|
|
| 33 |
- Context length: 2048
|
| 34 |
- Vocabulary size: 59241
|
| 35 |
- Language: English and Traditional Chinese
|
|
|
|
| 36 |
|
| 37 |
## Applications (Bailong-orpo 7B)
|
| 38 |
The following tables present, but are not limited to, several possible scenarios for the applications of Bailong-orpo 7B. All the following model outputs are generated under the same generation configuration (temperature=0.6, top-p=0.9, top-k=40, repetition_penalty=1.1)
|
|
|
|
| 14 |
</div>
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
+
<img width="800" src="https://raw.githubusercontent.com/blaze7451/Bailong/main/Bailong_pics/B3.png" alt="Bailong Logo">
|
| 18 |
|
| 19 |
# Model Card for Bailong-orpo 7B
|
| 20 |
This model card contains the information and the results of our released Bailong (白龍) project. Bailong, which stands for **B**ilingual tr**A**nsfer learn**I**ng based on q**LO**ra and zip-tie embeddi**NG**, is our newest project aimed at enhancing the Traditional Chinese performance in open-source large language model (LLM). All the consequences are listed as follows:
|
|
|
|
| 33 |
- Context length: 2048
|
| 34 |
- Vocabulary size: 59241
|
| 35 |
- Language: English and Traditional Chinese
|
| 36 |
+
- Developer: Lung-Chuan Chen
|
| 37 |
|
| 38 |
## Applications (Bailong-orpo 7B)
|
| 39 |
The following tables present, but are not limited to, several possible scenarios for the applications of Bailong-orpo 7B. All the following model outputs are generated under the same generation configuration (temperature=0.6, top-p=0.9, top-k=40, repetition_penalty=1.1)
|