Update README.md

README.md

@@ -86,34 +86,31 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 
 model_name = "MohammedNasser/silma_9b_instruct_ft"
+user_question = "إذا كان لديك ثلاث سيارات، وبعت واحدة منها، كم سيارة ستبقى لديك؟"
 
 # Load model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.float16,
-    device_map="auto",
-)
+import torch
+from transformers import pipeline
 
 # Create pipeline
-qa_pipeline = pipeline(
+pipe = pipeline(
     "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-    max_new_tokens=50,
-    do_sample=True,
-    temperature=0.7,
-    top_p=0.95,
-    return_full_text=False
+    model=model_name,
+    torch_dtype= torch.bfloat16,
+    device="cuda",
+    return_full_text=False, 
 )
 
+messages = [
+    {"role": "user", "content": user_question },
+]
+
 # Example usage
-question = "إذا كان لديك ثلاث سيارات، وبعت واحدة منها، كم سيارة ستبقى لديك؟"
-prompt = f"Question: {question}\nAnswer:"
-response = qa_pipeline(prompt)[0]['generated_text']
+response = pipe(messages, max_new_tokens=128)
+assistant_response = outputs[0]["generated_text"]
 
-print(f"Question: {question}")
-print(f"Answer: {response}")
+print(f"Question: {user_question}")
+print(f"Answer: {assistant_response}")
 ```
 
 ## Performance