Transformers
PyTorch
TensorBoard
English
encoder-decoder
text2text-generation
Generated from Trainer
seq2seq
Instructions to use abhi11nav/codebert-gpt2-commitgen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abhi11nav/codebert-gpt2-commitgen with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("abhi11nav/codebert-gpt2-commitgen") model = AutoModelForSeq2SeqLM.from_pretrained("abhi11nav/codebert-gpt2-commitgen") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,11 +16,12 @@ Siyuan Jiang and Collin McMillan. Heres is the link to the paper https://arxiv.o
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
| 19 |
-
|
|
|
|
| 20 |
|
| 21 |
## Intended uses & limitations
|
| 22 |
|
| 23 |
-
|
| 24 |
|
| 25 |
## Training and evaluation data
|
| 26 |
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
| 19 |
+
This is a sequence2sequence model with microsoft/codebert-base as encoder and gpt2 as decoder. Givena gitdiff file, this model can generate a short commit message summarizing the change.
|
| 20 |
+
|
| 21 |
|
| 22 |
## Intended uses & limitations
|
| 23 |
|
| 24 |
+
The intended use is to automate github commit message. One limitation to consider is that the model can generate a summary of changes, but is only confined to type of change and might not be able to provide details about the change or output specific keywords related to change.
|
| 25 |
|
| 26 |
## Training and evaluation data
|
| 27 |
|