Update app.py

app.py

@@ -1,63 +1,53 @@
+
+import re
+import torch
 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("Ajay12345678980/QA_GPT_J")
-
-
-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)",
-        ),
-    ],
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+# Load the model and tokenizer from Hugging Face repository
+model_repo_id = "Ajay12345678980/QA_GPT_J"  # Replace with your model repository ID
+
+# Initialize the model and tokenizer
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = GPT2LMHeadModel.from_pretrained(model_repo_id).to(device)
+tokenizer = GPT2Tokenizer.from_pretrained(model_repo_id)
+
+# Define the prediction function
+def generate_answer(question):
+    input_ids = tokenizer.encode(question, return_tensors="pt").to(device)
+    attention_mask = torch.ones_like(input_ids).to(device)
+    pad_token_id = tokenizer.eos_token_id
+
+    output = model.generate(
+        input_ids,
+        max_new_tokens=100,
+        num_return_sequences=1,
+        attention_mask=attention_mask,
+        pad_token_id=pad_token_id
+    )
+    decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
+    start_index = decoded_output.find("Answer")
+    end_index = decoded_output.find("<ANSWER_ENDED>")
+
+    if start_index != -1:
+        if end_index != -1:
+            answer_text = decoded_output[start_index + len("Answer"):end_index].strip()
+        else:
+            answer_text = decoded_output[start_index + len("Answer"):].strip()
+        return answer_text
+    else:
+        return "Sorry, I couldn't generate an answer."
+
+# Gradio interface setup
+interface = gr.Interface(
+    fn=generate_answer, 
+    inputs="text", 
+    outputs="text", 
+    title="GPT-2 Text Generation",
+    description="Enter a question and see what the model generates!"
 )
 
-
+# Launch the Gradio app
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()
+