Update README.md

README.md

@@ -81,4 +81,73 @@ The following hyperparameters were used during training:
 - Transformers 4.21.0
 - Pytorch 1.10.0+cu113
 - Datasets 2.4.0
-- Tokenizers 0.12.1
+- Tokenizers 0.12.1
+
+---
+
+# Model inference
+### 1. Install dependencies
+```bash
+pip install transformers sentencepiece torch ctranslate2
+```
+
+### 2. Inference
+## Vanilla model
+```Python
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+model_path = "anzorq/m2m100_418M_ft_ru-kbd_44K"  
+tgt_lang="zu"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
+
+def translate(text, num_beams=4, num_return_sequences=4):
+    inputs = tokenizer(text, return_tensors="pt")
+    num_return_sequences = min(num_return_sequences, num_beams)
+
+    translated_tokens = model.generate(
+        **inputs, forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang], num_beams=num_beams, num_return_sequences=num_return_sequences
+    )
+
+    translations = [tokenizer.decode(translation, skip_special_tokens=True) for translation in translated_tokens]
+    return text, translations
+
+# Test the translation
+text = "Текст для перевода"
+print(translate(text))
+```
+
+## CTranslate2 model (quantized model, much faster inference)
+```Python
+import ctranslate2
+import transformers
+
+translator = ctranslate2.Translator("ctranslate") # Ensure correct path to the ctranslate2 model directory
+tokenizer = transformers.AutoTokenizer.from_pretrained("anzorq/m2m100_418M_ft_ru-kbd_44K")
+tgt_lang="zu"
+
+def translate(text, num_beams=4, num_return_sequences=4):
+    num_return_sequences = min(num_return_sequences, num_beams)
+
+    source = tokenizer.convert_ids_to_tokens(tokenizer.encode(text))
+    target_prefix = [tokenizer.lang_code_to_token[tgt_lang]]
+    results = translator.translate_batch(
+        [source],
+        target_prefix=[target_prefix],
+        beam_size=num_beams,
+        num_hypotheses=num_return_sequences
+    )
+    
+    translations = []
+    for hypothesis in results[0].hypotheses:
+        target = hypothesis[1:]
+        decoded_sentence = tokenizer.decode(tokenizer.convert_tokens_to_ids(target))
+        translations.append(decoded_sentence)
+    
+    return text, translations
+
+# Test the translation
+text = "Текст для перевода"
+print(translate(text))
+```