Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ pipeline_tag: image-to-text
|
|
| 10 |
# Model Card for Model ID
|
| 11 |
|
| 12 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
-
AI
|
| 14 |
|
| 15 |
## How to Get Started with the Model
|
| 16 |
|
|
@@ -84,9 +84,4 @@ https://huggingface.co/datasets/Joctor/cn_bokete_oogiri_caption
|
|
| 84 |
微调方式：数据量充足，采用SFT微调
|
| 85 |
微调参数：max_length=1024(短就是好!), num_train_epochs=1, per_device_train_batch_size=1, gradient_accumulation_steps=1
|
| 86 |
训练设备：10 * 4090D
|
| 87 |
-
训练时长：22小时
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
### Results
|
| 91 |
-
|
| 92 |
-
https://www.gcores.com/articles/188405
|
|
|
|
| 10 |
# Model Card for Model ID
|
| 11 |
|
| 12 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
AI大喜利，简介 https://www.gcores.com/articles/188405
|
| 14 |
|
| 15 |
## How to Get Started with the Model
|
| 16 |
|
|
|
|
| 84 |
微调方式：数据量充足，采用SFT微调
|
| 85 |
微调参数：max_length=1024(短就是好!), num_train_epochs=1, per_device_train_batch_size=1, gradient_accumulation_steps=1
|
| 86 |
训练设备：10 * 4090D
|
| 87 |
+
训练时长：22小时
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|