Downloads · 30 days
14
10% of all-time downloads
gallek-m2m100-v0.2
amurienne/gallek-m2m100-v0.2
gallek-m2m100-v0.2 is a translation model from amurienne. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as mit.
A French - Breton Translation Model called Gallek (meaning "French" in Breton). The current model version reached a BLEU score of 50 after 10 epochs on a 20% split of the training set. Only monodirectionally fr-br fin…
All-time downloads
139
Public
Parameters
484M
5.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
At a glance
- Task
- Translation
- Library
- transformers
- License
- mit
- Model type
- m2m_100
- Access
- Public
- Created
- Mar 6, 2025
- Updated
- Mar 6, 2025
- SHA
- 35f406f0
Try a prompt
Base models
Spaces
Model card
From the Hugging Face model README
Gallek
- A French -> Breton Translation Model called Gallek (meaning "French" in Breton).
- The current model version reached a BLEU score of 50 after 10 epochs on a 20% split of the training set.
- Only monodirectionally fr->br fine-tuned for now.
- Training details available on the GweLLM Github repository.
Sample test code:
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
modelcard = "amurienne/gallek-m2m100"
model = AutoModelForSeq2SeqLM.from_pretrained(modelcard)
tokenizer = AutoTokenizer.from_pretrained(modelcard)
translation_pipeline = pipeline("translation", model=model, tokenizer=tokenizer, src_lang='fr', tgt_lang='br', max_length=512, device="cpu")
french_text = "traduis de français en breton: j'apprends le breton à l'école."
result = translation_pipeline(french_text)
print(result[0]['translation_text'])
Demo is available on the Gallek Space
- Task
- Translation
- Library
- transformers
- Type
- m2m_100
- License
- mit
- Languages
- fr, br
- Created
- Mar 6, 2025
- Updated
- Mar 6, 2025