Update app.py

app.py

@@ -16,6 +16,10 @@ print('token = ',token)
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_id = "mistralai/Mistral-7B-v0.3"
+
+model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+
+
 tokenizer = AutoTokenizer.from_pretrained(model_id, token= token)
 
 model = AutoModelForCausalLM.from_pretrained(model_id, token= token)
@@ -32,9 +36,15 @@ def respond(
     temperature,
     top_p,
 ):
-    inputs = tokenizer("Hello my name is", return_tensors="pt")
+    messages = [
+    {"role": "user", "content": "What is your favourite condiment?"},
+    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
+    {"role": "user", "content": "Do you have mayonnaise recipes?"}
+]
+
+    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
 
-    outputs = model.generate(**inputs, max_new_tokens=20)
+    outputs = model.generate(inputs, max_new_tokens=20)
     gen_text=tokenizer.decode(outputs[0], skip_special_tokens=True)
    
     print(gen_text)