first

app.py

@@ -1,63 +1,43 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    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,
-    ):
-        token = message.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
-"""
-demo = 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)",
-        ),
-    ],
-)
+import torch
+
+# Import libraries from transformers
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+
+# Define model and tokenizer
+model_name = "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+
+
+def answer_question(context, question):
+  # Encode the context and question
+  inputs = tokenizer(context, question, return_tensors="pt")
+
+  # Perform question answering
+  outputs = model(**inputs)
 
+  # Get the predicted start and end token positions
+  start_scores, end_scores = outputs.start_logits, outputs.end_logits
+
+  # Decode the answer based on predicted positions
+  answer_start = torch.argmax(start_scores)
+  answer_end = torch.argmax(end_scores) + 1
+
+  # Get answer tokens and convert them to string
+  answer = tokenizer.convert_ids_to_tokens(inputs["input_ids"][0][answer_start:answer_end])
+  answer = "".join(answer)
+
+  return answer
+
+# Define the Gradio interface
+interface = gr.Interface(
+    fn=answer_question,
+    inputs=[gr.Textbox("Context"), gr.Textbox("Question")],
+    outputs="text",
+    title="Question Answering with BERT",
+    description="Ask a question about the provided context and get an answer powered by Google BERT model.",
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app
+interface.launch()