Instructions to use tencent/HY-MT1.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/HY-MT1.5-7B 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/HY-MT1.5-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tencent/HY-MT1.5-7B") model = AutoModelForCausalLM.from_pretrained("tencent/HY-MT1.5-7B") - Notebooks
- Google Colab
- Kaggle
Why such an absurdly restrictive license?
Absolutely no usage permitted in the EU and UK, really? Why?
I guess this is a result of EU, UK and South Korea's regulation policies. Tencent has to make such a license.
Most models are released in the EU, UK and South Korea with no issues at all. I would assume it's a political issue first and foremost that they don't want these countries to use this model.
This. Tencent is the only company using such an absurdly restrictive license.
Nope. As far as I know, Llama also has some restrictions in EU.
@ilintar FYI:
https://slator.com/meta-rolls-out-multimodal-llama-3-2-but-not-in-europe/
https://www.llama.com/llama3_2/use-policy/
By the way, I would not complain the license. I would say thank you to anyone who has released model weights.