Update

app.py

@@ -1,10 +1,31 @@
 import gradio as gr
+from transformers import pipeline
 
-with gr.Blocks(fill_height=True) as demo:
-    with gr.Sidebar():
-        gr.Markdown("# Inference Provider")
-        gr.Markdown("This Space showcases the mistralai/Mixtral-8x7B-Instruct-v0.1 model, served by the hf-inference API. Sign in with your Hugging Face account to use this API.")
-        button = gr.LoginButton("Sign in")
-    gr.load("models/mistralai/Mixtral-8x7B-Instruct-v0.1", accept_token=button, provider="hf-inference")
-    
-demo.launch()
+# Initialize the model pipeline only once
+text_generator = pipeline("text-generation", model="mistralai/Mixtral-8x7B-Instruct-v0.1", device_map="auto")
+
+class Inference:
+    def __init__(self, pipe):
+        self.pipe = pipe
+
+    def get_results(self, prompt, max_new_tokens=256, temperature=0.7):
+        output = self.pipe(prompt, max_new_tokens=max_new_tokens, temperature=temperature)
+        return output[0]["generated_text"]
+
+inference = Inference(text_generator)
+
+def generate_text(prompt, max_tokens, temperature):
+    return inference.get_results(prompt, max_tokens, temperature)
+
+# Create a simple Gradio interface
+gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(lines=4, label="Prompt"),
+        gr.Slider(minimum=10, maximum=1024, value=256, label="Max New Tokens"),
+        gr.Slider(minimum=0.1, maximum=1.5, value=0.7, step=0.1, label="Temperature"),
+    ],
+    outputs=gr.Textbox(label="Generated Text"),
+    title="Mixtral-8x7B Text Generator",
+    description="Enter a prompt to generate text using Mixtral-8x7B-Instruct."
+).launch()