Instructions to use Helsinki-NLP/opus-mt_tiny_kor-eng with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt_tiny_kor-eng 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="Helsinki-NLP/opus-mt_tiny_kor-eng")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt_tiny_kor-eng") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt_tiny_kor-eng", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update final.model.npz.best-perplexity.npz.decoder.yml
Browse files
final.model.npz.best-perplexity.npz.decoder.yml
CHANGED
|
@@ -1,9 +1,3 @@
|
|
| 1 |
-
relative-paths: false
|
| 2 |
-
models:
|
| 3 |
-
- /mnt/student_dir/model.npz.best-perplexity.npz
|
| 4 |
-
vocabs:
|
| 5 |
-
- /mnt/vocab/vocab.spm
|
| 6 |
-
- /mnt/vocab/vocab.spm
|
| 7 |
beam-size: 1
|
| 8 |
normalize: 1
|
| 9 |
word-penalty: 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
beam-size: 1
|
| 2 |
normalize: 1
|
| 3 |
word-penalty: 0
|