Translation
Transformers
Safetensors
Arabic
t5
text2text-generation
Syrian
Shami
MT
MSA
Dialect
ArabicNLP
text-generation-inference
Instructions to use Omartificial-Intelligence-Space/Shami-MT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Omartificial-Intelligence-Space/Shami-MT 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="Omartificial-Intelligence-Space/Shami-MT")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Omartificial-Intelligence-Space/Shami-MT") model = AutoModelForSeq2SeqLM.from_pretrained("Omartificial-Intelligence-Space/Shami-MT") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add pipeline tag and correct paper link
#1
by nielsr HF Staff - opened
This PR improves the model card for Omartificial-Intelligence-Space/Shami-MT by:
- Adding the
pipeline_tag: translationto the metadata, which ensures the model can be properly discovered on the Hugging Face Hub under the translation task filters (e.g., https://huggingface.co/models?pipeline_tag=translation). - Correcting the introductory paper link in the model card content to point to the actual paper, SHAMI-MT: A Syrian Arabic Dialect to Modern Standard Arabic Bidirectional Machine Translation System.
Omartificial-Intelligence-Space changed pull request status to merged