Update app.py

app.py

@@ -1,55 +1,29 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
-import os
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 from memory import update_memory, check_memory
 
-# ✅ Load persona instructions
-try:
-    with open("persona.txt", "r", encoding="utf-8") as f:
-        personality = f.read()
-except FileNotFoundError:
-    personality = "You are a romantic AI chatbot designed to chat with Moin."
-
-# ✅ Fix: Use Correct Model Name
-model_name = "syedmoinms/MoinRomanticBot"  # Correct Hugging Face model path
-# model_name = "./MoinRomanticBot"  # Uncomment if using local model folder
-
-# ✅ Load Model & Tokenizer with Hugging Face Authentication
-HF_TOKEN = os.getenv("HF_TOKEN")  # Use token if model is private
-
-try:
-    tokenizer = AutoTokenizer.from_pretrained(model_name, token=HF_TOKEN)
-    model = AutoModelForCausalLM.from_pretrained(
-        model_name, 
-        token=HF_TOKEN, 
-        torch_dtype=torch.float16, 
-        device_map="auto"
-    )
-except Exception as e:
-    print(f"❌ Error loading model: {e}")
-    exit()
-
-# ✅ Function to Generate Response with Memory
+with open("persona.txt", "r", encoding="utf-8") as f:
+    personality = f.read()
+
+model_name = "TheBloke/Pygmalion-7B-GPTQ"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)
+
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
 def chatbot(input_text):
     memory_response = check_memory(input_text)
     if memory_response:
         return memory_response
-    
-    prompt = f"{personality}\nMoin: {input_text}\nAI:"
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
-    
-    with torch.no_grad():
-        outputs = model.generate(**inputs, max_length=150)
-    
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    prompt = f"{personality}\nUser: {input_text}\nAI:"
+    outputs = generator(prompt, max_length=200, do_sample=True, temperature=0.7, top_p=0.9)
+    response = outputs[0]["generated_text"].split("AI:")[-1].strip()
+
     update_memory(input_text, response)
-    
     return response
 
-# ✅ Gradio Interface
 iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="MoinRomanticBot")
 
-# ✅ Launch App
 if __name__ == "__main__":
     iface.launch(server_name="0.0.0.0", server_port=7860)