replit/replit-code-v1-3b finetuned on matorus/coder.

HumanEval scores: pass@1: 28.7%, pass@10: 43.3%
See torusresearch/code-eval for evaluation code.

Finetuning format:

{function_defintion}
  """
  {task}
  """
  {function_body}
Downloads last month
18
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support model that require custom code execution.

Dataset used to train matorus/replit-coder