Translation
Transformers
TensorBoard
Safetensors
Welsh
English
m2m_100
text2text-generation
Generated from Trainer
mt-models-api-name:nllb200-cy-en
Instructions to use techiaith/nllb-200-1.3B-ft-cym-to-eng with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use techiaith/nllb-200-1.3B-ft-cym-to-eng 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="techiaith/nllb-200-1.3B-ft-cym-to-eng")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("techiaith/nllb-200-1.3B-ft-cym-to-eng") model = AutoModelForMultimodalLM.from_pretrained("techiaith/nllb-200-1.3B-ft-cym-to-eng") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/nllb-200-1.3B
tags:
- generated_from_trainer
- mt-models-api-name:nllb200-cy-en
metrics:
- bleu
model-index:
- name: nllb-200-1.3B-ft-cym-to-eng
results: []
language:
- cy
- en
pipeline_tag: translation
nllb-200-1.3B-ft-cym-to-eng
This model is a fine-tuned version of facebook/nllb-200-1.3B for improved Welsh to English translation. It achieves the following results on the evaluation set:
- Loss: 0.5352
- Bleu: 47.7998
- Gen Len: 21.638
WARNING
Machine translations can be unreliable. Always get a human proofreader to ensure accuracy and avoid errors.
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0