Update app.py

app.py

@@ -1,58 +1,54 @@
 import gradio as gr
-from transformers import AutoModel, AutoProcessor
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
-import requests
-from PIL import Image
-from io import BytesIO
-
-fashion_items = ['top', 'trousers', 'jumper']
-
-# Load model and processor
-model_name = 'Marqo/marqo-fashionSigLIP'
-model = AutoModel.from_pretrained(model_name, trust_remote_code=True)
-processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
-
-# Preprocess and normalize text data
-with torch.no_grad():
-    # Ensure truncation and padding are activated
-    processed_texts = processor(
-        text=fashion_items,
-        return_tensors="pt",
-        truncation=True,  # Ensure text is truncated to fit model input size
-        padding=True      # Pad shorter sequences so that all are the same length
-    )['input_ids']
-    
-    text_features = model.get_text_features(processed_texts)
-    text_features = text_features / text_features.norm(dim=-1, keepdim=True)
-
-# Prediction function
-def predict_from_url(url):
-    # Check if the URL is empty
-    if not url:
-        return {"Error": "Please input a URL"}
-    
-    try:
-        image = Image.open(BytesIO(requests.get(url).content))
-    except Exception as e:
-        return {"Error": f"Failed to load image: {str(e)}"}
-    
-    processed_image = processor(images=image, return_tensors="pt")['pixel_values']
-    
-    with torch.no_grad():
-        image_features = model.get_image_features(processed_image)
-        image_features = image_features / image_features.norm(dim=-1, keepdim=True)
-        text_probs = (100 * image_features @ text_features.T).softmax(dim=-1)
-        
-    return {fashion_items[i]: float(text_probs[0, i]) for i in range(len(fashion_items))}
+
+# Load model (CPU-friendly, no token required)
+model_id = "replit/replit-code-v1_5-3b"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+# Ensure it's on CPU
+device = torch.device("cpu")
+model.to(device)
+
+def convert_python_to_r(python_code):
+    # Prompt to guide the model
+    prompt = f"""### Task:
+Convert the following Python code to equivalent R code.
+
+### Python code:
+{python_code}
+
+### R code:
+"""
+
+    # Tokenize input
+    input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.to(device)
+
+    # Generate
+    outputs = model.generate(
+        input_ids,
+        max_length=512,
+        temperature=0.2,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+    # Decode result
+    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Extract R code from the result (after prompt)
+    if "### R code:" in result:
+        result = result.split("### R code:")[-1].strip()
+
+    return result
 
 # Gradio interface
-demo = gr.Interface(
-    fn=predict_from_url, 
-    inputs=gr.Textbox(label="Enter Image URL"),
-    outputs=gr.Label(label="Classification Results"), 
-    title="Fashion Item Classifier",
-    allow_flagging="never"
-)
-
-# Launch the interface
-demo.launch()
+gr.Interface(
+    fn=convert_python_to_r,
+    inputs=gr.Textbox(lines=10, placeholder="Paste your Python code here..."),
+    outputs="text",
+    title="Python to R Code Converter",
+    description="Converts Python code to R using Replit Code Model (3B). Optimized for Hugging Face CPU Basic tier."
+).launch()