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
Download generation_config.json from Hosstia/opus-mt-zh-ru-opus-mp: direct link, hf CLI and curl.
- Browser
- Download file 265 Bytes
-
https://huggingface.co/Hosstia/opus-mt-zh-ru-opus-mp/resolve/main/generation_config.json
- Command line
-
hf download hf://Hosstia/opus-mt-zh-ru-opus-mp/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Hosstia/opus-mt-zh-ru-opus-mp/resolve/main/generation_config.json
265 Bytes
| { | |
| "bad_words_ids": [ | |
| [ | |
| 1 | |
| ] | |
| ], | |
| "decoder_start_token_id": 1, | |
| "eos_token_id": [ | |
| 2 | |
| ], | |
| "forced_eos_token_id": 2, | |
| "max_length": 512, | |
| "num_beams": 6, | |
| "pad_token_id": 1, | |
| "renormalize_logits": true, | |
| "transformers_version": "4.57.6" | |
| } | |