Update src/about.py
Browse files- src/about.py +5 -4
src/about.py
CHANGED
|
@@ -21,19 +21,20 @@ NUM_FEWSHOT = 0 # Change with your few shot
|
|
| 21 |
|
| 22 |
|
| 23 |
# Your leaderboard name
|
| 24 |
-
TITLE = """<h1 align="center" id="space-title">
|
| 25 |
|
| 26 |
# What does your leaderboard evaluate?
|
| 27 |
INTRODUCTION_TEXT = """
|
| 28 |
-
|
|
|
|
| 29 |
"""
|
| 30 |
|
| 31 |
# Which evaluations are you running? how can people reproduce what you have?
|
| 32 |
LLM_BENCHMARKS_TEXT = f"""
|
| 33 |
-
|
| 34 |
|
| 35 |
## Reproducibility
|
| 36 |
-
|
| 37 |
|
| 38 |
"""
|
| 39 |
|
|
|
|
| 21 |
|
| 22 |
|
| 23 |
# Your leaderboard name
|
| 24 |
+
TITLE = """<h1 align="center" id="space-title">ARFBench Multimodal Time Series Reasoning Leaderboard</h1>"""
|
| 25 |
|
| 26 |
# What does your leaderboard evaluate?
|
| 27 |
INTRODUCTION_TEXT = """
|
| 28 |
+
**ARF**Bench (**A**nomaly **R**easoning **F**ramework Benchmark) is a multimodal time-series reasoning benchmark consisting of 550 question-answer (QA) pairs composed from
|
| 29 |
+
real-world incident data collected at Datadog, a leading observability platform.
|
| 30 |
"""
|
| 31 |
|
| 32 |
# Which evaluations are you running? how can people reproduce what you have?
|
| 33 |
LLM_BENCHMARKS_TEXT = f"""
|
| 34 |
+
For more details on the benchmark, refer to the [ARFBench dataset card](https://huggingface.co/datasets/Datadog/ARFBench)
|
| 35 |
|
| 36 |
## Reproducibility
|
| 37 |
+
Coming soon!
|
| 38 |
|
| 39 |
"""
|
| 40 |
|