test

app.py

@@ -1,70 +1,71 @@
+# app.py
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+import os
 
+# ---- Config ----
+MODEL_ID = os.getenv("HF_MODEL_ID", "GroNLP/gpt2-small-dutch")
+# Set CPU threads modestly to avoid aggressive memory/CPU usage in Spaces
+torch.set_num_threads(2)
 
-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")
+# ---- Model load ----
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID)
 
-    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,
-    type="messages",
-    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)",
-        ),
-    ],
+# Create a pipeline suitable for CPU (device=-1)
+generator = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    device=-1,
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+# ---- Simple prompt-based simplifier ----
+def simplify(text: str, max_new_tokens: int = 60) -> str:
+    if not text or not text.strip():
+        return "Voer eerst wat tekst in."
+    # Prompt: instruct the model to produce a simplified version.
+    prompt = (
+        "Vereenvoudig de volgende tekst naar helder, begrijpelijk Nederlands.\n\n"
+        "Brontekst:\n"
+        f"{text}\n\n"
+        "Vereenvoudigde versie:"
+    )
+    # deterministic generation (no sampling) to keep output stable on CPU
+    out = generator(
+        prompt,
+        max_new_tokens=int(max_new_tokens),
+        do_sample=False,
+        num_return_sequences=1,
+    )[0]["generated_text"]
+    # strip prompt portion; keep everything after the marker
+    if "Vereenvoudigde versie:" in out:
+        simplified = out.split("Vereenvoudigde versie:")[-1].strip()
+    else:
+        # fallback: remove prompt prefix if present
+        simplified = out.replace(prompt, "").strip()
+    # Keep result reasonably short
+    return simplified
 
+# ---- Gradio UI ----
+with gr.Blocks(css=".gradio-container {max-width:1100px}") as demo:
+    gr.Markdown("# NL tekst vereenvoudiger (test)\nGebruik een klein Nederlands model: GroNLP/gpt2-small-dutch")
+    with gr.Row():
+        txt = gr.Textbox(label="Brontekst (Nederlands)", lines=8, placeholder="Plak hier een artikel of paragraaf...")
+        out = gr.Textbox(label="Vereenvoudigde tekst", lines=8)
+    with gr.Row():
+        tokens = gr.Slider(minimum=20, maximum=300, value=80, step=10, label="Max nieuwe tokens (lengte)")
+        run_btn = gr.Button("Vereenvoudig")
+    run_btn.click(fn=simplify, inputs=[txt, tokens], outputs=out)
+    gr.Examples(
+        examples=[
+            ["De Europese Commissie heeft vandaag een nieuw pakket maatregelen aangekondigd om de energiezekerheid te versterken, waarbij landen gevraagd worden hun strategische reserves aan te vullen."],
+            ["Het experiment toont aan dat de respons van de sensor significant varieert afhankelijk van temperatuur en luchtvochtigheid."],
+        ],
+        inputs=txt,
+    )
+    gr.Markdown("**Tips:** Als de Space tijdens build OOM geeft, kies een kleiner model of verlaag `max_new_tokens`.")
 
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio>=3.39
+transformers>=4.30.0
+torch>=2.0.0