| datasets: | |
| - matorus/coder | |
| [replit/replit-code-v1-3b](https://huggingface.co/replit/replit-code-v1-3b) finetuned on [matorus/coder](https://huggingface.co/datasets/matorus/coder). | |
| **HumanEval scores**: pass@1: 28.7%, pass@10: 43.3% | |
| <br> | |
| See [torusresearch/code-eval](https://github.com/torusresearch/code-eval) for evaluation code. | |
| Finetuning format: | |
| ``` | |
| {function_defintion} | |
| """ | |
| {task} | |
| """ | |
| {function_body} | |
| ``` |