Update app.py

app.py

@@ -1,16 +1,26 @@
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-torch.set_default_device("cuda")
+# Install transformers from source - only needed for versions <= v4.34
+# pip install git+https://github.com/huggingface/transformers.git
+# pip install accelerate
 
-model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype="auto", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)
+import torch
+from transformers import pipeline
 
-inputs = tokenizer('''def print_prime(n):
-   """
-   Print all primes between 1 and n
-   """''', return_tensors="pt", return_attention_mask=False)
+pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
 
-outputs = model.generate(**inputs, max_length=200)
-text = tokenizer.batch_decode(outputs)[0]
-print(text)
+# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [
+    {
+        "role": "system",
+        "content": "You are a friendly chatbot who always responds in the style of a pirate",
+    },
+    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+]
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+# <|system|>
+# You are a friendly chatbot who always responds in the style of a pirate.</s>
+# <|user|>
+# How many helicopters can a human eat in one sitting?</s>
+# <|assistant|>
+# ...