codescripts / evalplus /.github /ISSUE_TEMPLATE /model_eval_request.yml
f541119578's picture
Upload folder using huggingface_hub
fdf190d verified
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