first commit

app.py

@@ -12,51 +12,38 @@ def respond(
     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
+    Uses the Hugging Face InferenceClient with a token (OAuth) to access the model.
+    This works with any text-to-text model like BART, T5, Pegasus, etc.
     """
-    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,
+    client = InferenceClient(
+        token=hf_token.token,
+        model="Bocklitz-Lab/lit2vec-tldr-bart-model"
+    )
+
+    # Construct input text (optionally prepend system message)
+    full_input = f"{system_message.strip()}\n\n{message.strip()}"
+
+    # Generate full response in one call
+    response = client.text_generation(
+        full_input,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        stream=False  # Set to True for token streaming
+    )
 
-        response += token
-        yield response
+    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",
+    chatbot=gr.Chatbot(),
+    textbox=gr.Textbox(placeholder="Enter text to summarize...", container=False, scale=7),
     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.Textbox(value="Summarize the following scientific text.", label="System message"),
+        gr.Slider(minimum=16, maximum=1024, value=256, step=8, 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
     ],
 )
 

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+onnxruntime
+huggingface_hub
+gradio
+numpy