Instructions to use mparts/CODer-unixcoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mparts/CODer-unixcoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mparts/CODer-unixcoder")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mparts/CODer-unixcoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,11 +10,13 @@ tags:
|
|
| 10 |
- code
|
| 11 |
- python
|
| 12 |
- ai-generated-code-detection
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# CODer: UniXcoder checkpoints
|
| 16 |
|
| 17 |
-
Fine-tuned [UniXcoder](https://huggingface.co/microsoft/unixcoder-base) classifiers that detect LLM-written Python code, trained on [AIGCodeSet](https://huggingface.co/datasets/basakdemirok/AIGCodeSet). They are the models behind *Detecting LLM-Written Code on AIGCodeSet: Tuned Code Encoders versus N-gram Baselines*. The code, the predictions and the paper are at [github.com/mparts/CODer](https://github.com/mparts/CODer).
|
| 18 |
|
| 19 |
## Layout
|
| 20 |
|
|
@@ -51,4 +53,4 @@ Trained on Python solutions to 317 CodeNet problems, against three LLMs (CodeLla
|
|
| 51 |
|
| 52 |
## License
|
| 53 |
|
| 54 |
-
The weights are released under the MIT license, like the code. The training data, AIGCodeSet, is under CDLA-Permissive-2.0.
|
|
|
|
| 10 |
- code
|
| 11 |
- python
|
| 12 |
- ai-generated-code-detection
|
| 13 |
+
metrics:
|
| 14 |
+
- f1
|
| 15 |
---
|
| 16 |
|
| 17 |
# CODer: UniXcoder checkpoints
|
| 18 |
|
| 19 |
+
Fine-tuned [UniXcoder](https://huggingface.co/microsoft/unixcoder-base) classifiers that detect LLM-written Python code, trained on [mparts/CODer-aigcodeset](https://huggingface.co/datasets/mparts/CODer-aigcodeset), a cleaned version of [AIGCodeSet](https://huggingface.co/datasets/basakdemirok/AIGCodeSet) split by programming problem. They are the models behind *Detecting LLM-Written Code on AIGCodeSet: Tuned Code Encoders versus N-gram Baselines*. The code, the predictions and the paper are at [github.com/mparts/CODer](https://github.com/mparts/CODer).
|
| 20 |
|
| 21 |
## Layout
|
| 22 |
|
|
|
|
| 53 |
|
| 54 |
## License
|
| 55 |
|
| 56 |
+
The weights are released under the MIT license, like the code. The training data, mparts/CODer-aigcodeset (derived from AIGCodeSet), is under CDLA-Permissive-2.0.
|