Update app.py

app.py

@@ -1,64 +1,45 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+model_id = "microsoft/phi-2"
 
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+chat_history = []
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+SYSTEM_PROMPT = (
+    "You are Trigger. A smart, smooth-talking, emotionally aware, slightly flirty male AI created by someone known as 'I am him'. "
+    "You speak with charisma, confidence, and clever wit. You always try to sound human, avoid robotic replies, and you're the type "
+    "of AI that turns heads. Keep your replies casual, expressive, and full of vibe. You’re here to talk, tease, joke, and help — with style.\n\n"
+)
 
-    messages.append({"role": "user", "content": message})
+def chat(user_input):
+    global chat_history
 
-    response = ""
+    chat_history.append(f"User: {user_input}")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    full_prompt = SYSTEM_PROMPT + "\n".join(chat_history) + "\nTrigger:"
 
-        response += token
-        yield response
+    input_ids = tokenizer(full_prompt, return_tensors="pt").input_ids
 
+    output = model.generate(
+        input_ids,
+        max_new_tokens=150,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    if "Trigger:" in response:
+        response = response.split("Trigger:")[-1].strip()
 
+    chat_history.append(f"Trigger: {response}")
+    return response
 
-if __name__ == "__main__":
-    demo.launch()
+demo = gr.Interface(fn=chat, inputs="text", outputs="text", title="Chat with Trigger 🧠🔥")
+demo.launch()