Update app.py

app.py

@@ -1,64 +1,56 @@
 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)",
-        ),
-    ],
+from datasets import load_dataset
+from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments
+
+# Load dataset (replace 'daily_dialog' with your dataset)
+
+dataset = load_dataset("nazlicanto/persona-based-chat")
+
+# Choose a base model (DialoGPT)
+model_name = "microsoft/DialoGPT-small"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Preprocess the dataset
+def preprocess_data(example):
+    input_text = "User: " + example["dialog"][0] + " Bot: " + example["dialog"][1]
+    return tokenizer(input_text, truncation=True, padding="max_length", max_length=128)
+
+tokenized_dataset = dataset.map(preprocess_data, batched=True)
+
+# Training arguments
+training_args = TrainingArguments(
+    output_dir="./chatbot_model",
+    evaluation_strategy="steps",
+    eval_steps=500,
+    save_steps=1000,
+    per_device_train_batch_size=4,
+    per_device_eval_batch_size=4,
+    num_train_epochs=3,
+    save_total_limit=2
 )
 
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_dataset["train"],
+    eval_dataset=tokenized_dataset["validation"],
+    tokenizer=tokenizer,
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Train the model
+def train_model():
+    trainer.train()
+    model.save_pretrained("trained_chatbot")
+    tokenizer.save_pretrained("trained_chatbot")
+    return "Training Complete!"
+
+# Chat interface
+def chatbot(user_input):
+    inputs = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
+    outputs = model.generate(inputs, max_length=150, pad_token_id=tokenizer.eos_token_id)
+    return tokenizer.decode(outputs[:, inputs.shape[-1]:][0], skip_special_tokens=True)
+
+# Gradio UI
+iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", live=True)
+iface.launch()