Update app.py

app.py

@@ -1,64 +1,62 @@
 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
-
+from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments
+from datasets import load_dataset
+
+# Load Dataset
+dataset_url = "tahiryaqoob/bise-lahore-dataset"  # Replace with your dataset repository
+dataset = load_dataset(dataset_url, split="train")
+
+# Load Pretrained Model and Tokenizer
+model_name = "microsoft/DialoGPT-medium"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Fine-tuning Function
+def preprocess_data(example):
+    inputs = tokenizer(example['question'], truncation=True, padding=True, max_length=128)
+    outputs = tokenizer(example['answer'], truncation=True, padding=True, max_length=128)
+    inputs['labels'] = outputs['input_ids']
+    return inputs
+
+# Tokenize Dataset
+tokenized_dataset = dataset.map(preprocess_data, batched=True)
+
+# Fine-Tune the Model
+training_args = TrainingArguments(
+    output_dir="./results",
+    num_train_epochs=1,
+    per_device_train_batch_size=2,
+    save_steps=500,
+    save_total_limit=2,
+)
 
-"""
-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.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)",
-        ),
-    ],
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_dataset,
 )
 
+# Train the Model
+trainer.train()
+
+# Save the Fine-Tuned Model
+model.save_pretrained("./bise_chatbot_model")
+tokenizer.save_pretrained("./bise_chatbot_model")
+
+# Define Chatbot Function
+def chatbot_response(user_input):
+    inputs = tokenizer.encode(user_input, return_tensors="pt")
+    outputs = model.generate(inputs, max_length=100, num_return_sequences=1, do_sample=True)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Create Gradio Interface
+iface = gr.Interface(
+    fn=chatbot_response,
+    inputs="text",
+    outputs="text",
+    title="BISE Lahore Chatbot",
+    description="Ask your questions about BISE Lahore services."
+)
 
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()