Update README.md

README.md

@@ -25,8 +25,45 @@ tags:
 - max_seq_length = 32 768
 - bfloat16
 
+
 ## Usage with pipeline
 
+```python
+from transformers import pipeline, Qwen2ForCausalLM, AutoTokenizer
+
+model = Qwen2ForCausalLM.from_pretrained("NYTK/PULI-Trio-Q")
+tokenizer = AutoTokenizer.from_pretrained("NYTK/PULI-Trio-Q")
+prompt = "Elmesélek egy történetet a nyelvtechnológiáról."
+generator = pipeline(task="text-generation", model=model, tokenizer=tokenizer, device=0)
+
+print(generator(prompt, max_new_tokens=30)[0]["generated_text"])
+```
+
+Since the model was continuously pre-trained from Qwen2.5 7B **_Instruct_**, it can be used as a chat model.
+
+```python
+import torch
+from transformers import pipeline
+
+model_id = "NYTK/PULI-Trio-Q"
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+messages = [
+    {"role": "system", "content": "You are a helpful assistant"},
+    {"role": "user", "content": "Mit gondolsz a nyelvtechnológiáról?"},
+]
+outputs = pipe(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])
+```
+
+
 
 
 ## Citation