Update app.py

app.py

@@ -1,3 +1,7 @@
+# =============================
+# Shay Chatbot — Hugging Face Space
+# =============================
+
 import warnings
 warnings.filterwarnings("ignore", category=ResourceWarning)
 warnings.filterwarnings("ignore", category=RuntimeWarning)
@@ -33,16 +37,14 @@ def generate_chat(user_message, history, max_tokens, temperature, top_p, top_k):
     if history is None:
         history = []
 
-    # Build prompt with conversation history
-    prompt = "<|system|>You are Shay, a highly intelligent, unbiased, emotionless AI assistant.\n"
-    for user_msg, bot_msg in history:
-        prompt += f"<|user|>{user_msg}<|end|>\n<|assistant|>{bot_msg}<|end|>\n"
+    # Build prompt including full conversation
+    prompt = "<|system|>You are Shay, an intelligent, unbiased, emotionless AI assistant.\n"
+    for u, b in history:
+        prompt += f"<|user|>{u}<|end|>\n<|assistant|>{b}<|end|>\n"
     prompt += f"<|user|>{user_message}<|end|>\n<|assistant|>"
 
-    # Tokenize
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 
-    # Generate response
     output = model.generate(
         **inputs,
         max_new_tokens=int(max_tokens),
@@ -53,8 +55,7 @@ def generate_chat(user_message, history, max_tokens, temperature, top_p, top_k):
         do_sample=True
     )
 
-    reply = tokenizer.decode(output[0], skip_special_tokens=True)
-    reply = reply.split("<|assistant|>")[-1].strip()
+    reply = tokenizer.decode(output[0], skip_special_tokens=True).split("<|assistant|>")[-1].strip()
     history.append((user_message, reply))
     return history
 
@@ -79,13 +80,13 @@ button { background-color: #333; color: #eee; border: 1px solid #555; }
 """
 
 # -----------------------------
-# Gradio Interface
+# Gradio UI
 # -----------------------------
 with gr.Blocks() as app:
     gr.Markdown(
         "## Shay — Ultra Reliable AI Assistant\n"
         "Unbiased, emotionless, and able to converse on any topic.\n\n"
-        "**Adjust generation parameters below.**"
+        "**Adjust generation parameters below:**"
     )
 
     chatbot = gr.Chatbot(height=600)
@@ -96,12 +97,12 @@ with gr.Blocks() as app:
     copy_all_btn = gr.Button("Copy Full History", variant="secondary")
 
     # Sliders for generation parameters
-    max_tokens_slider = gr.Slider(minimum=32, maximum=1024, value=256, step=32, label="Max New Tokens")
-    temperature_slider = gr.Slider(minimum=0.1, maximum=1.5, value=0.7, step=0.05, label="Temperature")
-    top_p_slider = gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.01, label="Top-p")
-    top_k_slider = gr.Slider(minimum=1, maximum=200, value=50, step=1, label="Top-k")
+    max_tokens_slider = gr.Slider(32, 1024, value=256, step=32, label="Max New Tokens")
+    temperature_slider = gr.Slider(0.1, 1.5, value=0.7, step=0.05, label="Temperature")
+    top_p_slider = gr.Slider(0.1, 1.0, value=0.9, step=0.01, label="Top-p")
+    top_k_slider = gr.Slider(1, 200, value=50, step=1, label="Top-k")
 
-    # Bind actions
+    # Chat actions
     user_input.submit(
         generate_chat,
         [user_input, chatbot, max_tokens_slider, temperature_slider, top_p_slider, top_k_slider],
@@ -116,6 +117,10 @@ with gr.Blocks() as app:
     copy_last_btn.click(copy_last, chatbot, None)
     copy_all_btn.click(copy_all, chatbot, None)
 
-# Queue and launch
+# Queue to handle multiple users efficiently
 app.queue(max_size=64)
+
+# -----------------------------
+# Launch App (Single Launch)
+# -----------------------------
 app.launch(server_name="0.0.0.0", server_port=7860, ssr_mode=False, css=DARK_CSS)