Update app.py

app.py

@@ -1,16 +1,17 @@
 import os
+import torch
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 access_token = os.environ["GATED_ACCESS_TOKEN"]
 
 # Load the tokenizer and model
-model_id = "mistralai/Mixtral-8x22B-v0.1"
+model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 tokenizer = AutoTokenizer.from_pretrained(model_id, token=access_token)
-model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto", token=access_token)
 
 # Function to generate text using the model
-def generate_text(prompt, max_length=500, temperature=0.7, top_k=50, top_p=0.95, num_return_sequences=1):
+def generate_text(prompt):
     text = prompt
     inputs = tokenizer(text, return_tensors="pt")
     
@@ -22,11 +23,6 @@ iface = gr.Interface(
     fn=generate_text,
     inputs=[
         gr.inputs.Textbox(lines=5, label="Input Prompt"),
-        gr.inputs.Slider(minimum=100, maximum=1000, default=500, step=50, label="Max Length"),
-        gr.inputs.Slider(minimum=0.1, maximum=1.0, default=0.7, step=0.1, label="Temperature"),
-        gr.inputs.Slider(minimum=1, maximum=100, default=50, step=1, label="Top K"),
-        gr.inputs.Slider(minimum=0.1, maximum=1.0, default=0.95, step=0.05, label="Top P"),
-        gr.inputs.Slider(minimum=1, maximum=10, default=1, step=1, label="Num Return Sequences"),
     ],
     outputs=gr.outputs.Textbox(label="Generated Text"),
     title="MixTRAL 8x22B Text Generation",