Update app.py

app.py

@@ -1,25 +1,22 @@
-import subprocess
-import sys
-
-subprocess.check_call([sys.executable, "-m", "pip", "install", "transformers", "torch", "--quiet"])
-
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_name = "microsoft/DialoGPT-medium"
-
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained("sapientinc/HRM-Text-1B")
+model = AutoModelForCausalLM.from_pretrained("sapientinc/HRM-Text-1B")
 
 def chat(message, history):
     if not message:
         return ""
     
-    inputs = tokenizer.encode(message + tokenizer.eos_token, return_tensors='pt')
-    outputs = model.generate(inputs, max_length=200, pad_token_id=tokenizer.eos_token_id)
+    inputs = tokenizer(message, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=200)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     
     return response
 
-gr.ChatInterface(fn=chat).launch()
+with gr.Blocks(title="AI Queen") as demo:
+    gr.Markdown("# AI Queen")
+    gr.ChatInterface(fn=chat)
+
+demo.launch()