Update app.py

app.py

@@ -1,32 +1,56 @@
-import gradio as gr
-from fastai.text.all import load_learner
+import torch
+from fastai.text.all import *
 from huggingface_hub import hf_hub_download
 
-# Step 8: Download the model from Hugging Face and load it
-def load_model():
-    try:
-        # Download the .pth file from Hugging Face
-        model_path = hf_hub_download(
-            repo_id="rahul7star/fastai-rahul-text-model-v02", 
-            filename="rahul9star.pth"
-        )
-        
-        # Load the model using FastAI's load_learner method
-        learn = load_learner(model_path)
-        print("Model loaded successfully from Hugging Face.")
-        return learn
-    except Exception as e:
-        print(f"Error loading the model: {e}")
-        return None
+# Step 1: Recreate the DataLoaders used during training
+def create_dataloaders():
+    data = [
+        {"input": "Who is rahul7star?", "output": "Rahul7star is a software developer living in NSW."},
+        {"input": "What is Rahul7star's profession?", "output": "Rahul7star is an AI creator and software developer."},
+        {"input": "What does Rahul7star do?", "output": "Rahul7star works as a developer and enjoys solving complex coding problems."},
+        {"input": "Tell me about Rahul7star", "output": "Rahul7star is a talented developer, AI creator, and a fan of traveling."},
+        {"input": "What is Rahul7star known for?", "output": "Rahul7star is known for his work in AI, software development, and his love for coding."}
+    ]
+    
+    # Split into training and validation sets
+    train_data = data[:4]  # First 4 examples for training
+    valid_data = data[4:]  # Last example for validation
+
+    # Define the DataBlock (use the same structure as during training)
+    dblock = DataBlock(
+        blocks=(TextBlock.from_df(text_cols='input'), CategoryBlock),
+        get_x=lambda x: x['input'],
+        get_y=lambda x: x['output'],
+        splitter=RandomSplitter(valid_pct=0.2, seed=42)
+    )
 
-# Load the model
-learn = load_model()
+    # Create DataLoaders
+    dls = dblock.dataloaders(train_data, bs=2)  # Batch size of 2 for quick experimentation
+    return dls
+
+# Step 2: Load the model weights
+def load_model_weights():
+    model_path = hf_hub_download(
+        repo_id="rahul7star/fastai-rahul-text-model-v02", 
+        filename="rahul9star.pth"
+    )
+    
+    # Load the model architecture (you need to define the same architecture used during training)
+    learn = text_classifier_learner(create_dataloaders(), AWD_LSTM, metrics=accuracy)
+    
+    # Load the weights into the model
+    learn.load(model_path)
+    print("Model loaded successfully from Hugging Face.")
+    return learn
+
+# Step 3: Use the model in your Gradio interface
+learn = load_model_weights()
 
 # Check if the model is loaded successfully
 if learn is None:
     raise ValueError("Failed to load the model")
 
-# Step 9: Define the Gradio Interface
+# Step 4: Define the Gradio Interface
 def predict(input_text):
     try:
         # Get prediction from the model
@@ -35,5 +59,6 @@ def predict(input_text):
     except Exception as e:
         return f"Error during prediction: {e}"
 
-# Step 10: Create Gradio Interface
+# Step 5: Create Gradio Interface
+import gradio as gr
 gr.Interface(fn=predict, inputs="text", outputs="text").launch()