Update README.md

README.md

@@ -115,13 +115,37 @@ pip install git+https://github.com/ZagrosLLMModel/transformers.git@main
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "darsadilab/zagros-1.0-quick"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
 
-text = "سلام، چگونه میتونی به من کمک کنی؟"
-inputs = tokenizer(text, return_tensors="pt")
-outputs = model.generate(**inputs, max_length=50)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "یک وبسایت حرفه ای با استفاده از html طراحی کن که تک کد باشد و شامل css/js داخل همین html باشد."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=16384
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+print("content:", content)
 ```
 
 ### Deployment