Update app.py

app.py

@@ -1,21 +1,34 @@
-import gradio as gr
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-4k-instruct", trust_remote_code=True)
+torch.random.manual_seed(0)
+
+model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Phi-3-mini-4k-instruct", 
+    device_map="cuda", 
+    torch_dtype="auto", 
+    trust_remote_code=True, 
+)
 tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-4k-instruct")
 
-def chat(message):
-    inputs = tokenizer.encode(message, return_tensors="pt", add_special_tokens=True)
-    outputs = model.generate(inputs, max_length=50, do_sample=True)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+messages = [
+    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
+    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
+    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
+]
 
-demo = gr.Interface(
-    fn=chat,
-    inputs="text",
-    outputs="text",
-    title="Chat With LLMs",
-    description="Now Running [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)",
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
 )
-demo.launch()
+
+generation_args = {
+    "max_new_tokens": 500,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+output = pipe(messages, **generation_args)
+print(output[0]['generated_text'])