First Test

app.py

@@ -1,7 +1,16 @@
 import gradio as gr
+import subprocess
 
+dataset = "truthful_qa"
 def greet(model):
-    return "This model has a similarity score of: meh!"
+    global dataset
+    command = f"python detect-pretrain-code-contamination/src/run.py --target_model {model} --ref_model roneneldan/TinyStories-Instruct-1M --data {dataset} --output_dir detect-pretrain-code-contamination/out/{dataset} --ratio_gen 0.4"
+    result = subprocess.run(command, shell=True,capture_output=True, text=True)
+    
+    if result.returncode == 0:
+        return result.stdout
+    else:
+        return f"Error: {result.stderr}"
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text")
 iface.launch()

detect-pretrain-code-contamination

@@ -0,0 +1 @@
+Subproject commit 616114e2334dc8dc8b7b538f6dbcc639cc42cb2c

requirements.txt

@@ -0,0 +1,9 @@
+numpy
+openai
+torch
+transformers
+datasets
+ipdb
+matplotlib
+scikit-learn
+accelerate