README.md

metadata

language:
  - en
  - de
  - fr
  - zh
  - pt
  - nl
  - ru
  - ko
  - it
  - es
license: cc-by-nc-4.0
tags:
  - mlx
metrics:
  - comet
pipeline_tag: translation

mlx-community/TowerInstruct-v0.1-bfloat16-mlx

This model was converted to MLX format from Unbabel/TowerInstruct-v0.1. Refer to the original model card for more details on the model.

Intended uses & limitations (from the original model card)

The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset (TowerBlocks), which contains a diverse range of data sources:

• Translation (sentence and paragraph-level)
• Automatic Post Edition
• Machine Translation Evaluation
• Context-aware Translation
• Terminology-aware Translation
• Multi-reference Translation
• Named-entity Recognition
• Paraphrase Generation
• Synthetic Chat data
• Code instructions

You can find the dataset and all data sources of TowerBlocks here.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/TowerInstruct-v0.1-bfloat16-mlx")
prompt="Translate the following text from Portuguese into French.\nPortuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.\nFrench:"
response = generate(model, tokenizer, prompt=prompt, verbose=True)
# Un groupe d'investigateurs a lancé un nouveau modèle pour les tâches liées à la traduction.