src/about.py

from dataclasses import dataclass
from enum import Enum


@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


# Select your tasks here
# ---------------------------------------------------
class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard
    task0 = Task("anli_r1", "acc", "ANLI")
    task1 = Task("logiqa", "acc_norm", "LogiQA")


NUM_FEWSHOT = 0  # Change with your few shot
# ---------------------------------------------------


# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">ARFBench Multimodal Time Series Reasoning Leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
**ARF**Bench (**A**nomaly **R**easoning **F**ramework Benchmark) is a
multimodal time-series reasoning benchmark consisting of 750 question-answer
(QA) pairs composed from real-world incident data collected at Datadog,
a leading observability platform.

The benchmark evaluates models across various aspects of time-series anomaly reasoning:
- **Presence**: Detecting if anomalies exist in the data
- **Identification**: Identifying specific anomalous metrics
- **Start Time**: Determining when anomalies began
- **End Time**: Determining when anomalies ended
- **Magnitude**: Assessing the severity of anomalies
- **Categorization**: Classifying anomaly types
- **Correlation**: Understanding relationships between anomalies
- **Indicator**: Identifying leading indicators
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
For more details on the benchmark, refer to the [ARFBench dataset card](https://huggingface.co/datasets/Datadog/ARFBench)

## Reproducibility
See the [ARFBench repository](https://github.com/Datadog/ARFBench) for more details on how to reproduce the benchmark.

"""

EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model

### 1) Make sure you can load your model and tokenizer using AutoClasses:
```python
from transformers import AutoConfig, AutoModel, AutoTokenizer
config = AutoConfig.from_pretrained("your model name", revision=revision)
model = AutoModel.from_pretrained("your model name", revision=revision)
tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
```
If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.

Note: make sure your model is public!
Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!

### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!

### 3) Make sure your model has an open license!
This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗

### 4) Fill up your model card
When we add extra information about models to the leaderboard, it will be automatically taken from the model card

## In case of model failure
If your model is displayed in the `FAILED` category, its execution stopped.
Make sure you have followed the above steps first.
If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
@inproceedings{xiearfbench,
  title={ARFBench: Benchmarking Multimodal Time Series Reasoning for Software Incident Response},
  author={Xie, Stephan and Cohen, Ben and Goswami, Mononito and Shen, Junhong and Khwaja, Emaad and Liu, Chenghao and Asker, David and Abou-Amal, Othmane and Talwalkar, Ameet},
  booktitle={1st ICLR Workshop on Time Series in the Age of Large Models}
}
"""