Update README.md

README.md

@@ -1,3 +1,41 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- ru
+- sah
+datasets:
+- lab-ii/yakut-translate
+base_model:
+- google/mt5-base
+library_name: transformers
+---
+### Model Prefixes    
+`"translate Russian to Sakha: "` - Ru-sah    
+`"translate Sakha to Russian: "` - sah-Ru    
+
+## How to Get Started with the Model
+
+```python
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
+tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")
+
+def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
+    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
+    result = model.generate(
+        **inputs.to(model.device),
+        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
+        num_beams=num_beams,
+        **kwargs
+    )
+    return tokenizer.batch_decode(result, skip_special_tokens=True)
+
+sentence: str = "Фотограф опубликовал снимки с прошедшего феста."
+
+translation = predict(sentence, prefix="translate Russian to Sakha: ")
+
+print(translation)
+
+# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
+```