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 config.json from Hosstia/opus-mt-zh-ru-opus-mp: direct link, hf CLI and curl.
- Browser
- Download file 1.28 kB
-
https://huggingface.co/Hosstia/opus-mt-zh-ru-opus-mp/resolve/main/config.json
- Command line
-
hf download hf://Hosstia/opus-mt-zh-ru-opus-mp/config.json
-
curl -L -o config.json https://huggingface.co/Hosstia/opus-mt-zh-ru-opus-mp/resolve/main/config.json
1.28 kB
| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "swish", | |
| "add_bias_logits": false, | |
| "add_final_layer_norm": false, | |
| "architectures": [ | |
| "MarianMTModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "classif_dropout": 0.0, | |
| "classifier_dropout": 0.0, | |
| "d_model": 512, | |
| "decoder_attention_heads": 8, | |
| "decoder_ffn_dim": 2048, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 6, | |
| "decoder_start_token_id": 1, | |
| "decoder_vocab_size": 32000, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "encoder_attention_heads": 8, | |
| "encoder_ffn_dim": 2048, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 6, | |
| "eos_token_id": 2, | |
| "extra_pos_embeddings": 32000, | |
| "forced_eos_token_id": 2, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "max_length": null, | |
| "max_position_embeddings": 512, | |
| "model_type": "marian", | |
| "normalize_before": false, | |
| "normalize_embedding": false, | |
| "num_beams": null, | |
| "num_hidden_layers": 6, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "share_encoder_decoder_embeddings": true, | |
| "static_position_embeddings": true, | |
| "transformers_version": "4.57.6", | |
| "use_cache": false, | |
| "vocab_size": 32000 | |
| } | |