Instructions to use tencent/Hunyuan-MT-7B-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Hunyuan-MT-7B-fp8 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-fp8")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tencent/Hunyuan-MT-7B-fp8") model = AutoModelForCausalLM.from_pretrained("tencent/Hunyuan-MT-7B-fp8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add paper link, license, pipeline tag, and languages
#2
by nielsr HF Staff - opened
This PR improves the model card for Hunyuan-MT-Chimera-7B-fp8 by:
- Adding the
pipeline_tag: translationto the metadata, replacing the less specifictags: - translation. This improves discoverability on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=translation). - Including
license: apache-2.0in the metadata, as the model is produced by AngelSlim, which uses this license. - Adding a comprehensive list of
languagesto the metadata for better filtering and discoverability of its multilingual capabilities. - Adding a prominent link to the paper Hunyuan-MT Technical Report at the top of the model card.
- Removing the redundant `