Translation
Transformers
Safetensors
Chinese
Russian
marian
text2text-generation
opus-mt
mnn
android
on-device
Instructions to use Hosstia/opus-mt-zh-ru-opus-mp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hosstia/opus-mt-zh-ru-opus-mp 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="Hosstia/opus-mt-zh-ru-opus-mp")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Hosstia/opus-mt-zh-ru-opus-mp") model = AutoModelForSeq2SeqLM.from_pretrained("Hosstia/opus-mt-zh-ru-opus-mp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload zh_ru_tokenizer_meta.json with huggingface_hub
Browse files
zh_ru_tokenizer_meta.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token_id": 2,
|
| 3 |
+
"unk_token_id": 0,
|
| 4 |
+
"pad_token_id": 1
|
| 5 |
+
}
|