application deployed

app.py

@@ -8,43 +8,56 @@
 
 #######################
 
-import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-
-model_id = "codellama/CodeLlama-7b-Instruct-hf"
-
-# Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")
-
-# Use text-generation pipeline
-generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+import spaces
+
+@spaces.GPU
+def main():
+    # Your existing Gradio app code here
+    import gradio as gr
+    from transformers import AutoTokenizer, AutoModelForCausalLM
+    import torch
+
+    model_id = "codellama/CodeLlama-7b-Instruct-hf"
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_id, 
+        device_map="auto", 
+        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
+    )
+    tokenizer.pad_token = tokenizer.eos_token
 
-# Define the function to handle the conversion
-def convert_python_to_r(python_code):
-    prompt = f"""### Task:
+    def convert_python_to_r(python_code):
+        prompt = f"""### Task:
 Convert the following Python code to equivalent R code.
 
 ### Python code:
 {python_code}
 
 ### R code:"""
-    #result = generator(prompt, max_length=1024, temperature=0.2, num_return_sequences=1)
-    result = generator(
-     prompt, 
-     max_length=1024, 
-     temperature=0.2, 
-     num_return_sequences=1, 
-     do_sample=True,                          # <-- Add this!
-     pad_token_id=tokenizer.eos_token_id      # <-- Safely set pad_token_id
-    )
-    return result[0]['generated_text']
-
-# Gradio Interface
-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 using CodeLlama",
-    description="Enter Python code, and this tool will convert it into equivalent R code using CodeLlama Instruct model."
-).launch()
+        input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids
+        if torch.cuda.is_available():
+            input_ids = input_ids.to("cuda")
+
+        outputs = model.generate(
+            input_ids,
+            max_length=1024,
+            do_sample=True,
+            temperature=0.2,
+            pad_token_id=tokenizer.eos_token_id,
+            num_return_sequences=1
+        )
+        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        if "### R code:" in generated_text:
+            generated_text = generated_text.split("### R code:")[-1].strip()
+        return generated_text
+
+    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 using CodeLlama 7B Instruct",
+        description="Enter Python code below, and the tool will convert it to R code using the CodeLlama 7B Instruct model."
+    ).launch()
+
+if __name__ == "__main__":
+    main()