Instructions to use NiuTrans/LMT-60-1.7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NiuTrans/LMT-60-1.7B-Base 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="NiuTrans/LMT-60-1.7B-Base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NiuTrans/LMT-60-1.7B-Base") model = AutoModelForCausalLM.from_pretrained("NiuTrans/LMT-60-1.7B-Base") - Notebooks
- Google Colab
- Kaggle
Improve metadata: add library_name, update pipeline_tag, add tags, correct language typo
#1
by nielsr HF Staff - opened
This PR enhances the model card by making the following improvements to its metadata:
- Adding
library_name: transformersto ensure the automated "how to use" widget appears on the model page, leveraging the explicit usage of the Transformers library in theQuickstartsection. - Updating the
pipeline_tagfromtranslationtotext-generation. This better reflects that the model is an LLM performing translation via text generation, aligning with common practices for categorizing generative LLMs on the Hub. - Correcting a typo in the
languagelist, changingfalsetono(Norwegian), based on the "Support Languages" table. - Adding relevant
tags(multilingual,translation,llm,qwen3) to improve the model's discoverability and categorization.
The existing content, including the paper link, GitHub link, and usage example, remains unchanged as it is already comprehensive and adheres to the specified guidelines.