Create app.py

app.py

@@ -0,0 +1,43 @@
+# Install dependencies (run once in your environment):
+# pip install git+https://github.com/huggingface/transformers.git
+# pip install accelerate
+# pip install torch
+
+import torch
+from transformers import pipeline
+
+# Initialize the text-generation pipeline with Zephyr model
+pipe = pipeline(
+    "text-generation",
+    model="HuggingFaceH4/zephyr-7b-beta",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+# Define the chat messages with roles and content
+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?"
+    }
+]
+
+# Use the tokenizer's chat template to format the messages correctly
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+# Generate response with sampling parameters for creativity
+outputs = pipe(
+    prompt,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.7,
+    top_k=50,
+    top_p=0.95
+)
+
+# Print the generated pirate-style response
+print(outputs[0]["generated_text"])