Commit
•
54f8d38
1
Parent(s):
6e6dc6f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
@@ -84,6 +87,10 @@ Use the code below to get started with the model.
|
|
| 84 |
### Training Procedure
|
| 85 |
|
| 86 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
|
| 88 |
#### Preprocessing [optional]
|
| 89 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
datasets:
|
| 4 |
+
- elliotthwang/alpaca-zh-tw
|
| 5 |
+
base_model:
|
| 6 |
+
- unsloth/Llama-3.2-3B-Instruct
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model Card for Model ID
|
|
|
|
| 87 |
### Training Procedure
|
| 88 |
|
| 89 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 90 |
+
Adopting Unsloth to enable 2x faster free finetuning
|
| 91 |
+
num_train_epochs = 4,
|
| 92 |
+
traing 600steps
|
| 93 |
+
loss 0.673900
|
| 94 |
|
| 95 |
#### Preprocessing [optional]
|
| 96 |
|