Instructions to use CLAck/indo-mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CLAck/indo-mixed 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="CLAck/indo-mixed")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("CLAck/indo-mixed") model = AutoModelForSeq2SeqLM.from_pretrained("CLAck/indo-mixed") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1 +1,20 @@
|
|
| 1 |
-
This model is pretrained on Chinese and Indonesian languages, and fine-tuned on Indonesian language.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
This model is pretrained on Chinese and Indonesian languages, and fine-tuned on Indonesian language.
|
| 2 |
+
|
| 3 |
+
### Training results
|
| 4 |
+
MIXED
|
| 5 |
+
| Epoch | Bleu |
|
| 6 |
+
|:-----:|:-------:|
|
| 7 |
+
| 1.0 | 24.2579 |
|
| 8 |
+
| 2.0 | 30.6287 |
|
| 9 |
+
| 3.0 | 34.4417 |
|
| 10 |
+
| 4.0 | 36.2577 |
|
| 11 |
+
| 5.0 | 37.3488 |
|
| 12 |
+
|
| 13 |
+
FINETUNING
|
| 14 |
+
| Epoch | Bleu |
|
| 15 |
+
|:-----:|:-------:|
|
| 16 |
+
| 6.0 | 34.1676 |
|
| 17 |
+
| 7.0 | 35.2320 |
|
| 18 |
+
| 8.0 | 36.7110 |
|
| 19 |
+
| 9.0 | 37.3195 |
|
| 20 |
+
| 10.0 | 37.9461 |
|