Upload Duckbot.py

Duckbot.py

@@ -0,0 +1,60 @@
+import pandas as pd
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, Trainer, TrainingArguments
+from Features.chat_interface import start_chat_interface 
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, Trainer, TrainingArguments
+from Features.chat_interface import start_chat_interface
+import start_chat_interface, generate_response  # Import needed functions
+import os
+
+# --- Step 1: Prepare Your Data ---
+data = pd.read_csv("your_chatbot_data.csv")  # Replace with your dataset file
+data = data[["user_input", "chatbot_response"]]  # Adjust column names if needed
+data_path = "data/chatbot_data.csv"
+data = pd.read_csv(data_path) 
+
+# --- Step 2: Choose a Pre-trained Model ---
+model_name = "microsoft/DialoGPT-medium"  # A good starting point, experiment with others! 
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+# --- Step 3: Tokenize the Data ---
+def preprocess(examples):
+    inputs = [ex + tokenizer.eos_token for ex in examples["user_input"]]
+    targets = examples["chatbot_response"]
+    model_inputs = tokenizer(inputs, max_length=128, truncation=True, padding=True)
+
+    with tokenizer.as_target_tokenizer():
+        model_inputs["labels"] = tokenizer(targets, max_length=128, truncation=True, padding=True).input_ids
+
+    return model_inputs
+
+tokenized_data = data.apply(preprocess, axis=1) 
+
+# --- Step 4: Fine-Tune the Model ---
+training_args = TrainingArguments(
+    "my-chatbot",  # Output folder name 
+    evaluation_strategy="steps",
+    learning_rate=2e-5,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    num_train_epochs=3, 
+    weight_decay=0.01,
+    save_steps=500,  # Save model checkpoint every 500 steps
+    push_to_hub=True,  # Push the model to your Hugging Face Hub
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_data,
+    eval_dataset=tokenized_data,  
+)
+
+trainer.train()
+
+# --- Step 5: Use Your Fine-Tuned Model (After Training) ---
+def generate_response(user_input):
+  input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
+  output_sequences = model.generate(input_ids=input_ids)
+  response = tokenizer.decode(output_sequences[0], skip_special_tokens=True) 
+  return response