Update README.md

README.md

@@ -11,6 +11,42 @@ language:
 - en
 ---
 
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("hiieu/gemma-2-2b-it-lora-vi-en")
+tokenizer = tokenizer = AutoTokenizer.from_pretrained("hiieu/gemma-2-2b-it-lora-vi-en")
+conversations = [
+    [{"role": "user", "content": "Good morning everybody"}],
+    [{"role": "user", "content": "Xin chào mọi người"}]
+]
+
+batch_input_ids = tokenizer.apply_chat_template(
+    conversations,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    padding=True,
+    truncation=True
+).to(model.device)
+
+# Generate responses in a single batch
+outputs = model.generate(
+    batch_input_ids,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+
+responses = outputs[:, batch_input_ids.shape[-1]:]
+
+for response in responses:
+    print(tokenizer.decode(response, skip_special_tokens=True))
+
+>>> Chào mọi người .
+>>> Hello everyone .
+```
+
+
 # Uploaded  model
 
 - **Developed by:** hiieu