Translation
Transformers
Safetensors
English
Chinese
marian
text2text-generation
Generated from Trainer
Instructions to use agentlans/zhtw-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use agentlans/zhtw-en with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="agentlans/zhtw-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("agentlans/zhtw-en") model = AutoModelForSeq2SeqLM.from_pretrained("agentlans/zhtw-en") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -60,7 +60,7 @@ It is a fine-tuned version of the [Helsinki-NLP/opus-mt-zh-en](https://huggingfa
|
|
| 60 |
|
| 61 |
</details>
|
| 62 |
|
| 63 |
-
##
|
| 64 |
|
| 65 |
```python
|
| 66 |
from transformers import pipeline
|
|
@@ -81,10 +81,10 @@ translator("《阿奇大戰鐵血戰士》是2015年4至7月黑馬漫畫和阿
|
|
| 81 |
# "Archie vs. Predator" is a limited four-issue comic book series published by Black Horse and Archie Comics in the United States from April to July 2015. It was created by Alex de Campi and drawn by Fernando Ruiz. It's a crossover work.
|
| 82 |
```
|
| 83 |
|
| 84 |
-
## More examples
|
| 85 |
|
| 86 |
<details>
|
| 87 |
-
<summary>Click here</summary>
|
| 88 |
|
| 89 |
```
|
| 90 |
Chinese: 地政局長陳淑美表示,南科是帶動臺南產業發展的引擎,目前積極辦理相關園區用地作業,可提供產業專用地面積總計約 122 公頃,配合周邊開發也已規畫完善足夠的生活機能用地,共 318.45 公頃。
|
|
@@ -120,7 +120,10 @@ English: Most annual precipitation occurs between the beginning of March and the
|
|
| 120 |
|
| 121 |
</details>
|
| 122 |
|
| 123 |
-
## Training
|
|
|
|
|
|
|
|
|
|
| 124 |
|
| 125 |
### Training Hyperparameters
|
| 126 |
|
|
@@ -136,9 +139,6 @@ The following hyperparameters were used during training:
|
|
| 136 |
|
| 137 |
### Training Results
|
| 138 |
|
| 139 |
-
<details>
|
| 140 |
-
<summary>Click here to see the training and validation losses</summary>
|
| 141 |
-
|
| 142 |
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 143 |
|:-------------:|:-----:|:------:|:---------------:|:-----------------:|
|
| 144 |
| 2.1687 | 1.0 | 41656 | 2.0160 | 22482354 |
|
|
@@ -152,11 +152,11 @@ The following hyperparameters were used during training:
|
|
| 152 |
| 1.4662 | 9.0 | 374904 | 1.8432 | 202377935 |
|
| 153 |
| 1.3969 | 10.0 | 416560 | 1.8426 | 224864981 |
|
| 154 |
|
| 155 |
-
</details>
|
| 156 |
-
|
| 157 |
### Framework Versions
|
| 158 |
|
| 159 |
- Transformers 4.51.3
|
| 160 |
- Pytorch 2.6.0+cu124
|
| 161 |
- Datasets 3.2.0
|
| 162 |
-
- Tokenizers 0.21.0
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
</details>
|
| 62 |
|
| 63 |
+
## How to use / 如何使用
|
| 64 |
|
| 65 |
```python
|
| 66 |
from transformers import pipeline
|
|
|
|
| 81 |
# "Archie vs. Predator" is a limited four-issue comic book series published by Black Horse and Archie Comics in the United States from April to July 2015. It was created by Alex de Campi and drawn by Fernando Ruiz. It's a crossover work.
|
| 82 |
```
|
| 83 |
|
| 84 |
+
## More examples / 更多範例
|
| 85 |
|
| 86 |
<details>
|
| 87 |
+
<summary>Click here / 點這裡</summary>
|
| 88 |
|
| 89 |
```
|
| 90 |
Chinese: 地政局長陳淑美表示,南科是帶動臺南產業發展的引擎,目前積極辦理相關園區用地作業,可提供產業專用地面積總計約 122 公頃,配合周邊開發也已規畫完善足夠的生活機能用地,共 318.45 公頃。
|
|
|
|
| 120 |
|
| 121 |
</details>
|
| 122 |
|
| 123 |
+
## Training procedure / 訓練過程
|
| 124 |
+
|
| 125 |
+
<details>
|
| 126 |
+
<summary>Click here / 點這裡</summary>
|
| 127 |
|
| 128 |
### Training Hyperparameters
|
| 129 |
|
|
|
|
| 139 |
|
| 140 |
### Training Results
|
| 141 |
|
|
|
|
|
|
|
|
|
|
| 142 |
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
| 143 |
|:-------------:|:-----:|:------:|:---------------:|:-----------------:|
|
| 144 |
| 2.1687 | 1.0 | 41656 | 2.0160 | 22482354 |
|
|
|
|
| 152 |
| 1.4662 | 9.0 | 374904 | 1.8432 | 202377935 |
|
| 153 |
| 1.3969 | 10.0 | 416560 | 1.8426 | 224864981 |
|
| 154 |
|
|
|
|
|
|
|
| 155 |
### Framework Versions
|
| 156 |
|
| 157 |
- Transformers 4.51.3
|
| 158 |
- Pytorch 2.6.0+cu124
|
| 159 |
- Datasets 3.2.0
|
| 160 |
+
- Tokenizers 0.21.0
|
| 161 |
+
|
| 162 |
+
</details>
|