Try

app.py

@@ -1,40 +1,3 @@
 import gradio as gr
-from transformers import pipeline
-import torch
-import subprocess
-import spaces
-import os
 
-
-
-# Initialize the model pipeline
-generator = pipeline('text-generation', model='okeanos/uptimeai-8273')
-@spaces.GPU
-def generate_text(prompt):
-    # Generate text using the model
-    generator.model.cuda()
-    generator.device = torch.device("cuda")
-    prompt = f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
-    outputs = generator(
-        prompt, 
-    )
-    # Extract the generated text and return it
-    generated_text = outputs[0]['generated_text']
-    return generated_text
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=generate_text,
-    inputs=[
-        gr.Textbox(label="Prompt", lines=2, placeholder="Type a prompt..."),
-        gr.Slider(minimum=0.1, maximum=2.0, step=0.01, value=0.8, label="Temperature"),
-        gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.95, label="Top p"),
-        gr.Slider(minimum=0, maximum=100, step=1, value=40, label="Top k"),
-        gr.Slider(minimum=1.0, maximum=2.0, step=0.01, value=1.10, label="Repetition Penalty"),
-        gr.Slider(minimum=5, maximum=4096, step=5, value=1024, label="Max Length")
-    ],
-    outputs=gr.Textbox(label="Generated Text"),
-    title="ChatHercules-2.5-Mistral-7B",
-    description="Try out the ChatHercules-2.5-Mistral-7B model for free!"
-)
-
-iface.launch()
+gr.Interface.load("models/Ejafa/vicuna_7B_vanilla_1.1").launch()