Upload README.md with huggingface_hub

README.md

@@ -1,63 +1,41 @@
----
-license: apache-2.0
-base_model: Helsinki-NLP/opus-mt-fr-en
-tags:
-- generated_from_trainer
-metrics:
-- bleu
-model-index:
-- name: french-wolof-marian-fr-to-wo
-  results: []
----
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# MarianMT French to Wolof Model
 
-# french-wolof-marian-fr-to-wo
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-fr-en](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en) on the galsenai/french-wolof-translation dataset.
 
-This model is a fine-tuned version of [Helsinki-NLP/opus-mt-fr-en](https://huggingface.co/Helsinki-NLP/opus-mt-fr-en) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4610
-- Bleu: 0.0157
+## Model Description
 
-## Model description
+This MarianMT model has been fine-tuned for the task of translating text from French to Wolof. The dataset used for fine-tuning is available [here](https://huggingface.co/datasets/galsenai/french-wolof-translation).
 
-More information needed
+## Training Procedure
 
-## Intended uses & limitations
+- **Learning Rate:** 2e-5
+- **Batch Size:** 16
+- **Number of Epochs:** 3
 
-More information needed
+## Evaluation Metrics
 
-## Training and evaluation data
+The model was evaluated using the BLEU metric:
+- BLEU: 0.015657591430909903
 
-More information needed
+## Usage
 
-## Training procedure
+You can use this model directly with the Hugging Face `transformers` library:
 
-### Training hyperparameters
+```python
+from transformers import MarianMTModel, MarianTokenizer
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3
-- mixed_precision_training: Native AMP
+model_name = "cibfaye/french-wolof-marian-fr-to-wo"
+tokenizer = MarianTokenizer.from_pretrained(model_name)
+model = MarianMTModel.from_pretrained(model_name)
 
-### Training results
+def translate(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    translated_tokens = model.generate(**inputs)
+    translation = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
+    return translation
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu   |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 454  | 1.5968          | 0.0050 |
-| 1.9266        | 2.0   | 908  | 1.4846          | 0.0144 |
-| 1.5498        | 3.0   | 1362 | 1.4572          | 0.0161 |
+text = "Bonjour, comment ça va ?"
+translation = translate(text)
+print("Translation:", translation)
 
-
-### Framework versions
-
-- Transformers 4.40.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1