Update README.md
Browse files
README.md
CHANGED
|
@@ -82,19 +82,28 @@ This model is a SentenceTransformer fine-tuned from [`Shuu12121/CodeModernBERT-O
|
|
| 82 |
|
| 83 |
```python
|
| 84 |
from sentence_transformers import SentenceTransformer
|
| 85 |
-
|
| 86 |
-
model = SentenceTransformer("your-model-id")
|
| 87 |
-
sentences = [
|
| 88 |
-
"def add(a, b): return a + b",
|
| 89 |
-
"def sum(x, y): return x + y"
|
| 90 |
-
]
|
| 91 |
-
embeddings = model.encode(sentences)
|
| 92 |
-
|
| 93 |
from torch.nn.functional import cosine_similarity
|
| 94 |
import torch
|
| 95 |
|
| 96 |
-
|
| 97 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
```
|
| 99 |
|
| 100 |
---
|
|
|
|
| 82 |
|
| 83 |
```python
|
| 84 |
from sentence_transformers import SentenceTransformer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
from torch.nn.functional import cosine_similarity
|
| 86 |
import torch
|
| 87 |
|
| 88 |
+
# Load the fine-tuned model
|
| 89 |
+
model = SentenceTransformer("Shuu12121/CodeCloneDetection-ModernBERT-Owl")
|
| 90 |
+
|
| 91 |
+
# Two code snippets to compare
|
| 92 |
+
code1 = "def add(a, b): return a + b"
|
| 93 |
+
code2 = "def sum(x, y): return x + y"
|
| 94 |
+
|
| 95 |
+
# Encode the code snippets
|
| 96 |
+
embeddings = model.encode([code1, code2], convert_to_tensor=True)
|
| 97 |
+
|
| 98 |
+
# Compute cosine similarity
|
| 99 |
+
similarity_score = cosine_similarity(embeddings[0].unsqueeze(0), embeddings[1].unsqueeze(0)).item()
|
| 100 |
+
|
| 101 |
+
# Print the result
|
| 102 |
+
print(f"Cosine Similarity: {similarity_score:.4f}")
|
| 103 |
+
if similarity_score >= 0.5:
|
| 104 |
+
print("🟢 These code snippets are considered CLONES.")
|
| 105 |
+
else:
|
| 106 |
+
print("🔴 These code snippets are NOT considered clones.")
|
| 107 |
```
|
| 108 |
|
| 109 |
---
|