Translation
Transformers
Safetensors
English
urj
marian
windyword
english
uralic
finnish
estonian
hungarian
sami
Instructions to use WindyWord/translate-en-urj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WindyWord/translate-en-urj 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="WindyWord/translate-en-urj")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WindyWord/translate-en-urj", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download lora/generation_config.json from WindyWord/translate-en-urj: direct link, hf CLI and curl.
- Browser
- Download file 288 Bytes
-
https://huggingface.co/WindyWord/translate-en-urj/resolve/main/lora/generation_config.json
- Command line
-
hf download hf://WindyWord/translate-en-urj/lora/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/WindyWord/translate-en-urj/resolve/main/lora/generation_config.json
288 Bytes
| { | |
| "bad_words_ids": [ | |
| [ | |
| 58919 | |
| ] | |
| ], | |
| "bos_token_id": 0, | |
| "decoder_start_token_id": 58919, | |
| "eos_token_id": 0, | |
| "forced_eos_token_id": 0, | |
| "max_length": 512, | |
| "num_beams": 4, | |
| "pad_token_id": 58919, | |
| "renormalize_logits": true, | |
| "transformers_version": "4.45.1" | |
| } | |