Update app.py

app.py

@@ -1,35 +1,7 @@
-import os
-import torch
-import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, QuantoConfig
+from transformers import pipeline
 
-access_token = os.environ["GATED_ACCESS_TOKEN"]
-
-quantization_config = QuantoConfig(
-    weights = "int4"
-)
-
-tokenizer = AutoTokenizer.from_pretrained("ProbeMedicalYonseiMAILab/medllama3-v20", quantization_config=quantization_config, device_map="auto")
-model = AutoModelForCausalLM.from_pretrained("ProbeMedicalYonseiMAILab/medllama3-v20")
-
-# Function to generate text using the model
-def generate_text(prompt):
-    text = prompt
-    inputs = tokenizer(text, return_tensors="pt")
-    
-    outputs = model.generate(**inputs, max_new_tokens=512)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=generate_text,
-    inputs=[
-        gr.Textbox(lines=5, label="Input Prompt"),
-    ],
-    outputs=gr.outputs.Textbox(label="Generated Text"),
-    title="MisTRAL Text Generation",
-    description="Use this interface to generate text using the MisTRAL language model.",
-)
-
-# Launch the Gradio interface
-iface.launch()
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="bongbongs/NewMes-v15")
+pipe(messages)