Instructions to use Helsinki-NLP/opus-mt-gem-gem with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Helsinki-NLP/opus-mt-gem-gem 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="Helsinki-NLP/opus-mt-gem-gem")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-gem-gem") model = AutoModelForSeq2SeqLM.from_pretrained("Helsinki-NLP/opus-mt-gem-gem", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
set `renormalize_logits=True` for better performance (see `transformers` issue #4290)
2aa5dfe
-
Adding generation config file(s)
43504a8
-
Add TF weights
Joao Gante96e9492
-
Changed num_beams to 4
92e2653
-
Update README.md
06d965b -
Update README.md
1de90d1 -
Update metadata.json
a465e45
-
Update README.md
856d8b9 -
Update config.json
b2c77d2 -
Update metadata.json
ea28d04 -
Update tokenizer_config.json
cf3e4d9 -
Update vocab.json
57d9463 -
Update README.md
8a964dc -
Update metadata.json
aca29a9
-
Update README.md
e7b4c3b -
Update config.json
ba24580 -
Update metadata.json
4b97af9 -
Update tokenizer_config.json
8ed6aa2 -
Update vocab.json
69154a4 -
Update README.md
410048e -
Update README.md
6772981 -
Update metadata.json
c0b6f60
-
Update README.md
2216e67 -
Update README.md
b79673e -
Update README.md
661780a -
Update README.md
4d8da33
-
Update vocab.json
125f803 -
Update tokenizer_config.json
6627048 -
Update target.spm
e542ee9 -
Update source.spm
2f484d7 -
Update pytorch_model.bin
513e143 -
Update config.json
856819d -
initial commit
d647837