Update app.py

app.py

@@ -7,7 +7,7 @@ from sentence_transformers import SentenceTransformer
 import chromadb
 from datasets import load_dataset
 import gradio as gr
-from transformers import GPT2Tokenizer, GPT2Model
+from transformers import GPT2Tokenizer, GPT2LMHeadModel, Trainer, TrainingArguments
 
 model_name = "Amitesh007/text_generation-finetuned-gpt2"
 
@@ -15,7 +15,7 @@ model_name = "Amitesh007/text_generation-finetuned-gpt2"
 tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 
 # Load the model with from_tf=True
-model = GPT2Model.from_pretrained(model_name, from_tf=True)
+model = GPT2LMHeadModel.from_pretrained(model_name, from_tf=True)
 
 # Function to clear the cache
 def clear_cache(model_name):
@@ -80,6 +80,41 @@ class VectorStore:
 vector_store = VectorStore("embedding_vector")
 vector_store.populate_vectors(dataset=None)
 
+# Fine-tuning function
+def fine_tune_model():
+    # Load your dataset
+    dataset = load_dataset('Thefoodprocessor/recipe_new_with_features_full', split='train[:1500]', streaming=False)
+
+    # Prepare the data for training
+    def tokenize_function(examples):
+        return tokenizer(examples['title_cleaned'] + " " + examples['recipe_new'], padding="max_length", truncation=True)
+
+    tokenized_datasets = dataset.map(tokenize_function, batched=True)
+
+    # Define training arguments
+    training_args = TrainingArguments(
+        output_dir="./results",
+        evaluation_strategy="epoch",
+        learning_rate=2e-5,
+        per_device_train_batch_size=8,
+        per_device_eval_batch_size=8,
+        num_train_epochs=3,
+        weight_decay=0.01,
+    )
+
+    # Initialize Trainer
+    trainer = Trainer(
+        model=model,
+        args=training_args,
+        train_dataset=tokenized_datasets,
+    )
+
+    # Train the model
+    trainer.train()
+
+# Fine-tune the model
+fine_tune_model()
+
 # Define the chatbot response function
 conversation_history = []