Update app.py

app.py

@@ -1,63 +1,51 @@
 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
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+# Load the model and tokenizer from Hugging Face
+model_name = "ambrosfitz/history-qa-t5-base"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Set device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def generate_qa(text, max_length=512):
+    input_text = f"Generate question: {text}"
+    input_ids = tokenizer(input_text, return_tensors="pt", max_length=max_length, truncation=True).input_ids.to(device)
+    
+    with torch.no_grad():
+        outputs = model.generate(input_ids, max_length=max_length, num_return_sequences=1, do_sample=True, temperature=0.7)
+    
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    # Parse the generated text
+    parts = generated_text.split("Question: ")
+    if len(parts) > 1:
+        qa_parts = parts[1].split("Options:")
+        question = qa_parts[0].strip()
+        
+        options_and_answer = qa_parts[1].split("Correct Answer:")
+        options = options_and_answer[0].strip()
+        
+        answer_and_explanation = options_and_answer[1].split("Explanation:")
+        correct_answer = answer_and_explanation[0].strip()
+        explanation = answer_and_explanation[1].strip() if len(answer_and_explanation) > 1 else "No explanation provided."
+        
+        return f"Question: {question}\n\nOptions: {options}\n\nCorrect Answer: {correct_answer}\n\nExplanation: {explanation}"
+    else:
+        return "Unable to generate a proper question and answer. Please try again with a different input."
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=generate_qa,
+    inputs=gr.Textbox(lines=5, label="Enter historical text"),
+    outputs=gr.Textbox(label="Generated Q&A"),
+    title="History Q&A Generator",
+    description="Enter a piece of historical text, and the model will generate a related question, answer options, correct answer, and explanation."
 )
 
-
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()