| name: "🤗 Model Evaluation Request" | |
| description: Request EvalPlus maintainers to evaluate your model independently and update it on our leaderboard. | |
| title: "🤗 [REQUEST] - FILL_THE_MODEL_NAME_HERE" | |
| labels: ["model eval"] | |
| body: | |
| - type: textarea | |
| id: about | |
| attributes: | |
| label: "Model introduction" | |
| description: Provide a brief introduction to the model. | |
| placeholder: The models is created by ... and is used for ... | |
| validations: | |
| required: true | |
| - type: input | |
| id: url | |
| attributes: | |
| label: "Model URL" | |
| description: Indicate the URL (e.g., huggingface or other release pages) of the model | |
| placeholder: https://huggingface.co/[???]/[???] | |
| validations: | |
| required: true | |
| - type: textarea | |
| id: other | |
| attributes: | |
| label: "Additional information (Optional)" | |
| description: Special steps indicating how to run the model with preferably scripts/codes. | |
| placeholder: What data type precision should be used? What is the minimal hardware requirement? Can it be accelerated by tools such as vLLM? | |
| validations: | |
| required: false | |
| - type: textarea | |
| id: decomtamination | |
| attributes: | |
| label: "Decontamination" | |
| description: How does the authors avoid contamination for their training data? | |
| placeholder: Please clarify the decontamination steps and quantify it, e.g., N-gram match of ground-truth code in the training dataset. | |
| validations: | |
| required: true | |
| - type: dropdown | |
| id: author | |
| attributes: | |
| label: "Author" | |
| description: "Are you (one of) the author(s) of the model?" | |
| multiple: false | |
| options: | |
| - "Yes" | |
| - "No" | |
| validations: | |
| required: true | |
| - type: dropdown | |
| id: data | |
| attributes: | |
| label: "Data" | |
| description: "Is the training/fine-tuning data available in public?" | |
| multiple: false | |
| options: | |
| - "Yes (If so please specify in 'Additional information')" | |
| - "No" | |
| validations: | |
| required: true | |
| - type: checkboxes | |
| id: security | |
| attributes: | |
| label: "Security" | |
| options: | |
| - label: "I confirm that the model is safe to run which is not designed to produce malicious code or content." | |
| required: true | |
| - type: checkboxes | |
| id: integrity | |
| attributes: | |
| label: "Integrity" | |
| options: | |
| - label: "I confirm that the model comes from unique and original work and does not contain any plagiarism." | |
| required: true | |