Update README.md

README.md

@@ -1,10 +1,12 @@
 ---
 license: cc-by-nc-4.0
+language:
+- uk
 ---
 
 # Model Card for Spivavtor-Large
 
-This model was obtained by fine-tuning the corresponding `bigscience/mt0-large` model on the Spivavtor dataset. All details of the dataset and fine tuning process can be found in our paper and repository.
+This model was obtained by fine-tuning the corresponding `bigscience/mt0-large` model on the Spivavtor dataset. All details of the dataset and fine tuning process can be found in our paper.
 
 **Paper:** Spivavtor: An Instruction Tuned Ukrainian Text Editing Model
 
@@ -18,7 +20,7 @@ This model was obtained by fine-tuning the corresponding `bigscience/mt0-large`
 - **Finetuned from model:** bigscience/mt0-large
 
 ## How to use
-We make available the following models presented in our paper. 
+We make the following models available from our paper. 
 
 <table>
   <tr>
@@ -29,12 +31,12 @@ We make available the following models presented in our paper.
   <tr>
     <td>Spivavtor-large</td>
     <td>1.2B</td>
-    <td>Spivavtor-mt0-large</td>
+    <td>SPIVAVTOR-MT0-LARGE</td>
   </tr>
   <tr>
     <td>Spivavtor-xxl</td>
     <td>11B</td>
-    <td>Spivavtor-aya-101</td>
+    <td>SPIVAVTOR-AYA-101</td>
   </tr>  
 </table>
 
@@ -45,8 +47,9 @@ tokenizer = AutoTokenizer.from_pretrained("grammarly/spivavtor-large")
 model = AutoModelForSeq2SeqLM.from_pretrained("grammarly/spivavtor-large")
 
 input_text = 'Виправте граматику в цьому реченнi: Дякую за iнформацiю! ми з Надiєю саме вийшли з дому'
+# English translation of text: "Paraphrase the sentence: What is the greatest compliment that you ever received from anyone?"
 
-input_ids = tokenizer(input_text, return_tensors="pt").input_ids
-outputs = model.generate(input_ids, max_length=256)
+inputs = tokenizer.encode(input_text, return_tensors="pt")
+output = model.generate(inputs, max_length=256)
 output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
 ```