Add model card
Browse files
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Description
|
2 |
+
|
3 |
+
CodeT5-small model, fine-tuned on the code summarization subtask of CodeXGLUE (Ruby programming language).
|
4 |
+
|
5 |
+
# Usage
|
6 |
+
|
7 |
+
Here's how to use this model:
|
8 |
+
|
9 |
+
```python
|
10 |
+
from transformers import RobertaTokenizer, T5ForConditionalGeneration
|
11 |
+
|
12 |
+
model_name = "nielsr/codet5-small-code-summarization-ruby"
|
13 |
+
tokenizer = RobertaTokenizer.from_pretrained(model_name)
|
14 |
+
model = T5ForConditionalGeneration.from_pretrained(model_name)
|
15 |
+
|
16 |
+
code = """
|
17 |
+
def update_with_file_contents(digest, filename)
|
18 |
+
File.open(filename) do |io|
|
19 |
+
while (chunk = io.read(1024 * 8))
|
20 |
+
digest.update(chunk)
|
21 |
+
end
|
22 |
+
end
|
23 |
+
end
|
24 |
+
"""
|
25 |
+
|
26 |
+
input_ids = tokenizer(code, return_tensors="pt").input_ids
|
27 |
+
outputs = model.generate(input_ids)
|
28 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
29 |
+
# Update the digest with the contents of the given file
|
30 |
+
```
|