Translation
Transformers
Safetensors
m2m_100
text2text-generation
nllb-200
formosan-languages
low-resource
Eval Results (legacy)
Instructions to use FormosanBank/nllb200-zh-formosan-spm8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FormosanBank/nllb200-zh-formosan-spm8k 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="FormosanBank/nllb200-zh-formosan-spm8k")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("FormosanBank/nllb200-zh-formosan-spm8k") model = AutoModelForSeq2SeqLM.from_pretrained("FormosanBank/nllb200-zh-formosan-spm8k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "schema_version": 1, | |
| "profile_id": "formosan-mt-standard-v3", | |
| "implementation_sha256": "2062106642f27053616728f6f962f7d3ffea022bf737dbe98a8d4af1e6de3831", | |
| "unicode_normalization": "NFC", | |
| "policy": { | |
| "unwrap_letter_infixes": true, | |
| "remove_clitic_boundaries": true, | |
| "remove_null_morphemes": true, | |
| "remove_intraword_hyphens": true, | |
| "remove_intraword_tildes": true, | |
| "remove_intraword_pluses": true, | |
| "include_optional_intraword_segments": true, | |
| "select_first_simple_alternative": true, | |
| "strip_wiki_heading_markup": true, | |
| "strip_trailing_superscript_footnotes": true | |
| }, | |
| "source_overrides": [], | |
| "unresolved_annotation_characters": [ | |
| "<", | |
| ">", | |
| "=", | |
| "Ø", | |
| "∅", | |
| "*", | |
| "_", | |
| "{", | |
| "}", | |
| "|", | |
| "\\" | |
| ] | |
| } | |