Update app.py

app.py

@@ -1,12 +1,19 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import transformers
+import torch
 import gradio as gr
 
-gr.load("models/google/gemma-7b-it").launch()
+model_id = "gg-hf/gemma-7b-it"
+dtype = torch.bfloat16
 
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="cuda",
+    torch_dtype=dtype,
+)
 
-examples=[["I'm planning a vacation to Japan. Can you suggest a one-week itinerary including must-visit places and local cuisines to try?", None, None, None, None, None, ],
-          ["Can you write a short story about a time-traveling detective who solves historical mysteries?", None, None, None, None, None,],
-          ["I'm trying to learn French. Can you provide some common phrases that would be useful for a beginner, along with their pronunciations?", None, None, None, None, None,],
-          ["I have chicken, rice, and bell peppers in my kitchen. Can you suggest an easy recipe I can make with these ingredients?", None, None, None, None, None,],
-          ["Can you explain how the QuickSort algorithm works and provide a Python implementation?", None, None, None, None, None,],
-          ["What are some unique features of Rust that make it stand out compared to other systems programming languages like C++?", None, None, None, None, None,],
-         ]
+chat = [
+    { "role": "user", "content": "Write a hello world program" },
+]
+prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)