|
|
--- |
|
|
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](https://huggingface.co/Unbabel/TowerInstruct-v0.1) for more details on the model. |
|
|
|
|
|
## Intended uses & limitations (from the [original model card](https://huggingface.co/Unbabel/TowerInstruct-v0.1)) |
|
|
|
|
|
The model was initially fine-tuned on a filtered and preprocessed supervised fine-tuning dataset ([TowerBlocks](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1)), 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](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1) here. |
|
|
|
|
|
|
|
|
## Use with mlx |
|
|
|
|
|
```bash |
|
|
pip install mlx-lm |
|
|
``` |
|
|
|
|
|
```python |
|
|
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. |
|
|
``` |
|
|
|
