---
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}
```