Update app.py

app.py

@@ -1,63 +1,50 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    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
-
-        response += token
-        yield response
-
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Optimized Loading: Load in half precision if CUDA is available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load the model and tokenizer
+model_name = "Sephfox/A.I.R.R"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto"
+).to(device)
+
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
+    outputs = model.generate(
+        **inputs,
+        max_length=200,
+        num_return_sequences=1,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Create Gradio chat interface
+def chat_bot(user_input, history=[]):
+    bot_response = generate_response(user_input)
+    history.append((user_input, bot_response))
+    return history, history
+
+with gr.Blocks() as demo:
+    gr.Markdown("# A.I.R.R Chatbot (Optimized)")
+    chatbot = gr.Chatbot(label="Chat with A.I.R.R")
+    user_input = gr.Textbox(show_label=False, placeholder="Type your message here...")
+    state = gr.State([])
+    submit_button = gr.Button("Send")
+
+    submit_button.click(
+        fn=chat_bot,
+        inputs=[user_input, state],
+        outputs=[chatbot, state]
+    )
+
+demo.launch()