Instructions to use tencent/Hunyuan-MT-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Hunyuan-MT-7B 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="tencent/Hunyuan-MT-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tencent/Hunyuan-MT-7B") model = AutoModelForCausalLM.from_pretrained("tencent/Hunyuan-MT-7B") - Notebooks
- Google Colab
- Kaggle
Improve model card for Hunyuan-MT: Add pipeline tag, license, paper abstract, and comprehensive content from GitHub
#14
by nielsr HF Staff - opened
This PR significantly improves the model card for Hunyuan-MT by:
- Metadata Enhancements:
- Adding
pipeline_tag: translationto enable better discoverability on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=translation) and removing the redundanttags: - translation. - Explicitly adding
license: apache-2.0for clarity.
- Adding
- Content Expansion:
- Adding a clear top-level title, link to the Hunyuan-MT Technical Report, and the paper's abstract for quick understanding.
- Incorporating comprehensive sections from the project's GitHub README, including "Performance", "Training Data Format", "Train with LLaMA-Factory", "Quantization Compression", "Deployment", and "Contact Us", providing a more complete overview of the model.
- Updating the demo link to the more specific one found in the GitHub README.
- Ensuring that existing usage examples with
transformersand supported languages tables remain consistent and correctly formatted.
These updates aim to provide users with a richer and more informative model card.