Update app.py

app.py

@@ -1,10 +1,21 @@
-from transformers import AutoModelForCausalLM
- 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cpu" # the device to load the model onto
+
 model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
-model.to("cpu")
- 
-generated_ids = model.generate(tokens, max_new_tokens=1000, do_sample=True)
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
+
+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?"}
+]
+
+encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+
+model_inputs = encodeds.to(device)
+model.to(device)
 
-# decode with mistral tokenizer
-result = tokenizer.decode(generated_ids[0].tolist())
-print(result)
+generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
+decoded = tokenizer.batch_decode(generated_ids)
+print(decoded[0])