Update app.py

app.py

@@ -1,69 +1,99 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
+MODEL_ID = "google/gemma-3-4b-it"
 
-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_ID)
 
-    messages = [{"role": "system", "content": system_message}]
+print("Loading model...")
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float32,
+    device_map="cpu"
+)
 
-    messages.extend(history)
+print("Model loaded!")
 
-    messages.append({"role": "user", "content": message})
+SYSTEM_PROMPT = """
+You are an expert documentary writer and cinematic image prompt engineer.
 
-    response = ""
+Tasks:
+1. Explain facts in engaging documentary style
+2. Generate cinematic AI image prompts
+3. Create social-media-ready narration
 
-    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
+Always:
+- Be descriptive
+- Use vivid imagery
+- Keep responses high quality
+"""
 
-        response += token
-        yield response
 
+def generate(prompt, max_new_tokens, temperature):
+    full_prompt = f"""
+{SYSTEM_PROMPT}
 
+User: {prompt}
+Assistant:
 """
-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"),
+
+    inputs = tokenizer(
+        full_prompt,
+        return_tensors="pt"
+    )
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            temperature=temperature,
+            do_sample=True,
+            top_p=0.95,
+            repetition_penalty=1.1
+        )
+
+    response = tokenizer.decode(
+        outputs[0],
+        skip_special_tokens=True
+    )
+
+    response = response.split("Assistant:")[-1].strip()
+
+    return response
+
+
+demo = gr.Interface(
+    fn=generate,
+    inputs=[
+        gr.Textbox(
+            lines=8,
+            label="Prompt",
+            placeholder="Enter your fact or image prompt request..."
+        ),
         gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+            minimum=64,
+            maximum=1024,
+            value=256,
+            step=32,
+            label="Max New Tokens"
         ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.5,
+            value=0.7,
+            step=0.1,
+            label="Temperature"
+        )
     ],
+    outputs=gr.Textbox(
+        lines=20,
+        label="Response"
+    ),
+    title="Gemma 3 4B CPU Demo",
+    description="Running fully on CPU using Hugging Face Spaces"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch(server_name="0.0.0.0", server_port=7860)