Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ pipeline_tag: image-text-to-text
|
|
| 9 |
|
| 10 |
# Model Card for Model ID
|
| 11 |
|
| 12 |
-
![TaivisionLM]()
|
| 13 |
## Model Details
|
| 14 |
|
| 15 |
## English
|
|
@@ -23,7 +23,7 @@ Ready to experience the Traditional Chinese visual language model? Let's go!
|
|
| 23 |
|
| 24 |
|
| 25 |
## 繁體中文
|
| 26 |
-
#
|
| 27 |
|
| 28 |
🌟 TaiVisionLM 是一個小型的視覺語言模型（僅有 12 億參數），可以根據圖像輸入來回覆繁體中文指令！🌟
|
| 29 |
|
|
@@ -138,6 +138,7 @@ The following training hyperparameters are used in feature alignment and task sp
|
|
| 138 |
|
| 139 |
We use full-parameter finetuning for the projector and apply LoRA to the language model.
|
| 140 |
|
|
|
|
| 141 |
### Compute Infrastructure
|
| 142 |
- **Feature Alignment**
|
| 143 |
- 1xV100(32GB), took approximately 16 GPU hours.
|
|
|
|
| 9 |
|
| 10 |
# Model Card for Model ID
|
| 11 |
|
| 12 |
+
|
| 13 |
## Model Details
|
| 14 |
|
| 15 |
## English
|
|
|
|
| 23 |
|
| 24 |
|
| 25 |
## 繁體中文
|
| 26 |
+
# 台視: 台灣視覺語言模型!! 🚀
|
| 27 |
|
| 28 |
🌟 TaiVisionLM 是一個小型的視覺語言模型（僅有 12 億參數），可以根據圖像輸入來回覆繁體中文指令！🌟
|
| 29 |
|
|
|
|
| 138 |
|
| 139 |
We use full-parameter finetuning for the projector and apply LoRA to the language model.
|
| 140 |
|
| 141 |
+
|
| 142 |
### Compute Infrastructure
|
| 143 |
- **Feature Alignment**
|
| 144 |
- 1xV100(32GB), took approximately 16 GPU hours.
|