Instructions to use Rzoro/Transformer_de_en_multi30K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rzoro/Transformer_de_en_multi30K 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="Rzoro/Transformer_de_en_multi30K")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Rzoro/Transformer_de_en_multi30K", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download params.json from Rzoro/Transformer_de_en_multi30K: direct link, hf CLI and curl.
- Browser
- Download file 250 Bytes
-
https://huggingface.co/Rzoro/Transformer_de_en_multi30K/resolve/main/params.json
- Command line
-
hf download hf://Rzoro/Transformer_de_en_multi30K/params.json
-
curl -L -o params.json https://huggingface.co/Rzoro/Transformer_de_en_multi30K/resolve/main/params.json
250 Bytes
| {"dk": 32, "dv": 32, "h": 8, "src_vocab_size": 8500, "target_vocab_size": 6500, "src_pad_idx": 2, "target_pad_idx": 2, "num_encoders": 3, "num_decoders": 3, "dim_multiplier": 4, "pdropout": 0.1, "lr": 0.0003, "N_EPOCHS": 50, "CLIP": 1, "patience": 5} |