Update app.py

app.py

@@ -1,63 +1,60 @@
+from transformers import GPT2Tokenizer, GPT2LMHeadModel, Trainer, TrainingArguments
+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("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)",
-        ),
-    ],
+
+# Define the training arguments
+training_args = TrainingArguments(
+    per_device_train_batch_size=4,
+    num_train_epochs=3,
+    logging_dir='./logs',
+)
+
+# Load the pre-trained GPT-2 model and tokenizer
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+model = GPT2LMHeadModel.from_pretrained("gpt2")
+
+# Example training data
+training_data = [
+    "What is your name?",
+    "How are you?",
+    "What do you do?",
+    "Tell me about yourself."
+]
+
+# Tokenize the training data
+input_ids = tokenizer(training_data, return_tensors="pt", padding=True, truncation=True)["input_ids"]
+
+# Define a dummy data collator (required by Trainer)
+class DummyDataCollator:
+    def __call__(self, features):
+        return features
+
+# Define a Trainer instance
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    data_collator=DummyDataCollator(),
+    train_dataset=input_ids
 )
 
+# Train the model
+trainer.train()
+
+# Define the chatbot function
+def chatbot(input_text):
+    # Tokenize input text
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+    # Generate response from the model
+    output_ids = model.generate(input_ids, max_length=50, pad_token_id=tokenizer.eos_token_id)
+    
+    # Decode the generated response
+    response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    
+    return response
+
+# Create the Gradio interface
+chatbot_interface = gr.Interface(chatbot, "textbox", "textbox", title="Chatbot")
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio interface
+chatbot_interface.launch()