Translation
Transformers
Safetensors
English
Mi'kmaq
m2m_100
text2text-generation
nllb
migmaq
listuguj
research
Instructions to use ajaxdavis/mobtranslate-migmaq-listuguj-v1-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ajaxdavis/mobtranslate-migmaq-listuguj-v1-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="ajaxdavis/mobtranslate-migmaq-listuguj-v1-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ajaxdavis/mobtranslate-migmaq-listuguj-v1-base") model = AutoModelForSeq2SeqLM.from_pretrained("ajaxdavis/mobtranslate-migmaq-listuguj-v1-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
MobTranslate Mi'kmaq Listuguj v1 adapter base
ajaxdavis/mobtranslate-migmaq-listuguj-v1-base is the immutable custom-vocabulary base required to reproduce
the v3.3 compact LoRA release. It is published as a dependency and historical
research artifact, not as the recommended translator. Its mic_Latn token is
ID 256204. The frozen release tag is v1.0.0-rc1. Use
ajaxdavis/mobtranslate-migmaq-listuguj-v3-3 for the selected compact adapter.
The model descends from facebook/nllb-200-distilled-600M and is licensed
CC BY-NC 4.0. It is noncommercial research software, not an authoritative or
speaker-validated translation service.
- Downloads last month
- 27