Update app.py

app.py

@@ -1,69 +1,49 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
+# Small model for CPU
+model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+print("Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-    messages = [{"role": "system", "content": system_message}]
+print("Loading model...")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float32,
+    device_map="cpu"
+)
 
-    messages.extend(history)
+print("Model loaded successfully!")
 
-    messages.append({"role": "user", "content": message})
+def chat(message):
 
-    response = ""
+    prompt = f"""
+You are a helpful assistant.
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+User: {message}
+Assistant:
+"""
 
-        response += token
-        yield response
+    inputs = tokenizer(prompt, return_tensors="pt")
 
+    output = model.generate(
+        **inputs,
+        max_new_tokens=100,
+        temperature=0.7
+    )
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = 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)
+
+    return response
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
 
+demo = gr.Interface(
+    fn=chat,
+    inputs=gr.Textbox(label="Ask something"),
+    outputs=gr.Textbox(label="AI Response"),
+    title="Auric AI Model Test"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()