Update app.py

app.py

@@ -1,69 +1,35 @@
+# app.py
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-
-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")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-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)",
-        ),
-    ],
+# Load model once at startup
+tokenizer = AutoTokenizer.from_pretrained("BrainChip-AI/tenns-llm-1b")
+model = AutoModelForCausalLM.from_pretrained(
+    "BrainChip-AI/tenns-llm-1b",
+    trust_remote_code=True,
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+def chat(message, history):
+    # Build a simple prompt from history + new message
+    prompt = ""
+    for user_msg, bot_msg in history:
+        prompt += f"User: {user_msg}\nAssistant: {bot_msg}\n"
+    prompt += f"User: {message}\nAssistant:"
+
+    output = model.generate_text(
+        prompt,
+        tokenizer,
+        max_new_tokens=256,
+        temperature=0.8,
+        top_k=50,
+    )
+
+    # Strip the prompt from the output (model returns full text)
+    response = output[len(prompt):].strip()
+    return response
+
+gr.ChatInterface(
+    fn=chat,
+    title="TENNs LLM 1B",
+    description="Chat with BrainChip's 1B parameter SSM language model",
+).launch()