Update README.md

README.md

@@ -23,23 +23,9 @@ It achieves the following results on the evaluation set:
 - Bleu: 8.3292
 - Gen Len: 34.4959
   
-The finetuning was conducted using a A**100-40GB** and took **23 hours**. 
-
-
-## Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 22
-- eval_batch_size: 22
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 88
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 40
+The finetuning was conducted using a **A100-40GB** and took **23 hours**. 
 
+Try it out on our dedicated [Terjman-Large Space](https://huggingface.co/spaces/atlasia/Terjman-Large) 🤗
 
 ## Usage
 
@@ -73,9 +59,9 @@ print("Translation:", output_text)
 
 Let's see an example of transliterating Moroccan Darija Arabizi to Arabic:
 
-**Input**: "Hello my friend, how's life in Morocco"
+**Input**: "Hi my friend, can you tell me a joke in moroccan darija? I'd be happy to hear that from you!"
 
-**Output**: "مرحبا يا صاحبي, كيفاش الحياة فالمغرب"
+**Output**: "مرحبا صديقي، يمكن لك تقول لي نكتة في داريجا المغربية؟ سأكون سعيدا بسماعها منك!"
 
 ## Limiations
 
@@ -88,6 +74,20 @@ We're continuously striving to improve our model's performance and usability and
 If you have any feedback, suggestions, or encounter any issues, please don't hesitate to reach out to us.
 
 
+## Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 22
+- eval_batch_size: 22
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 88
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 40
+
 ## Training results
 
 | Training Loss | Epoch   | Step  | Validation Loss | Bleu   | Gen Len |