Create app.py

app.py

@@ -0,0 +1,60 @@
+import json
+import os
+import gradio as gr
+from transformers import GPT2LMHeadModel, PreTrainedTokenizerFast
+
+# File to store chat memory
+MEMORY_FILE = "cass_memory.json"
+MAX_MEMORY = 50  # max number of message pairs to keep
+
+# Load model and tokenizer
+model_name = "DSDUDEd/Cass-Beta1.3"
+model = GPT2LMHeadModel.from_pretrained(model_name)
+tokenizer = PreTrainedTokenizerFast.from_pretrained(model_name)
+
+# Load memory if exists
+if os.path.exists(MEMORY_FILE):
+    with open(MEMORY_FILE, "r") as f:
+        memory = json.load(f)
+else:
+    memory = []
+
+def save_memory():
+    with open(MEMORY_FILE, "w") as f:
+        json.dump(memory[-MAX_MEMORY:], f, indent=2)
+
+def chat_with_cass(user_input):
+    # Combine memory into context
+    context = " ".join([f"User: {u} Cass: {c}" for u, c in memory])
+    input_text = context + f" User: {user_input} Cass:"
+    
+    inputs = tokenizer(input_text, return_tensors="pt")
+    
+    outputs = model.generate(
+        **inputs,
+        max_length=150,
+        do_sample=True,
+        temperature=0.8,
+        top_p=0.9,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    
+    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    new_reply = reply.split("Cass:")[-1].strip()
+    
+    # Add to memory and save
+    memory.append((user_input, new_reply))
+    save_memory()
+    
+    return memory, memory
+
+# Gradio Interface
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot(value=memory)
+    msg = gr.Textbox(label="You")
+    clear = gr.Button("Clear")
+    
+    msg.submit(chat_with_cass, [msg], [chatbot])
+    clear.click(lambda: [], None, chatbot)
+
+demo.launch()