from dataclasses import dataclass
from enum import Enum
@dataclass
class Task:
benchmark: str
metric: str
col_name: str
# Init: to update with your specific keys
class Tasks(Enum):
# task_key in the json file, metric_key in the json file, name to display in the leaderboard
task0 = Task("logiqa", "delta_abs", "LogiQA Δ")
task1 = Task("logiqa2", "delta_abs", "LogiQA2 Δ")
task2 = Task("lsat-ar", "delta_abs", "LSAT-ar Δ")
task3 = Task("lsat-lr", "delta_abs", "LSAT-lr Δ")
task4 = Task("lsat-rc", "delta_abs", "LSAT-rc Δ")
#METRICS = list(set([task.value.metric for task in Tasks]))
logo1_url = "https://raw.githubusercontent.com/logikon-ai/cot-eval/main/assets/AI2_Logo_Square.png"
logo2_url = "https://raw.githubusercontent.com/logikon-ai/cot-eval/main/assets/logo_logikon_notext_withborder.png"
LOGOS = f''
# Your leaderboard name
TITLE = f' Open CoT Leaderboard
{LOGOS}'
# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
The Open CoT Leaderboard tracks the reasoning skills of LLMs, measured as their ability to generate **effective chain-of-thought reasoning traces**.
The leaderboard reports **accuracy gains** achieved by using [chain-of-thought](https://logikon.ai/docs/delib_prompting) (CoT), i.e.: _accuracy gain Δ_ = _accuracy with CoT_ — _accuracy w/o CoT_.
See the "About" tab for more details and motivation.
"""
# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## How it works (roughly)
To assess the reasoning skill of a given `model`, we carry out the following steps for each `task` (test dataset) and different CoT `regimes`. (A CoT `regime` consists in a prompt chain and decoding parameters used to generate a reasoning trace.)
1. `model` generates CoT reasoning traces for all problems in the test dataset according to `regime`.
2. `model` answers the test dataset problems, we record the resulting _baseline accuracy_.
3. `model` answers the test dataset problems _with the reasoning traces appended_ to the prompt, we record the resulting _CoT accuracy_.
4. We compute the _accuracy gain Δ_ = _CoT accuracy_ — _baseline accuracy_ for the given `model`, `task`, and `regime`.
Each `regime` yields a different _accuracy gain Δ_, and the leaderboard reports (for every `model`/`task`) the best Δ achieved by any regime. All models are evaluated against the same set of regimes.
A notebook with detailed result exploration and visualization is available [here](https://github.com/logikon-ai/cot-eval/blob/main/notebooks/CoT_Leaderboard_Results_Exploration.ipynb).
## How is it different from other leaderboards?
Performance leaderboards like the [🤗 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) or [YALL](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard) do a great job in ranking models according to task performance.
Unlike these leaderboards, the Open CoT Leaderboard assesses a model's ability to effectively reason about a `task`:
### 🤗 Open LLM Leaderboard
* a. Can `model` solve `task`?
* b. Metric: absolute accuracy.
* c. Measures `task` performance.
* d. Covers broad spectrum of `tasks`.
### Open CoT Leaderboard
* a. Can `model` do CoT to improve in `task`?
* b. Metric: relative accuracy gain.
* c. Measures ability to reason (about `task`).
* d. Focuses on critical thinking `tasks`.
## Test dataset selection (`tasks`)
The test dataset problems in the CoT Leaderboard can be solved through clear thinking alone, no specific knowledge is required to do so. They are subsets of the [AGIEval benchmark](https://github.com/ruixiangcui/AGIEval) and re-published as [`logikon-bench`](https://huggingface.co/datasets/logikon/logikon-bench). The `logiqa` dataset has been newly translated from Chinese to English.
## Reproducibility
To learn more about the evaluation pipeline and reproduce our results, check out the repository [cot-eval](https://github.com/logikon-ai/cot-eval).
## Acknowledgements
We're grateful to community members for running evaluations and reporting results. To contribute, join us at [`cot-leaderboard`](https://huggingface.co/cot-leaderboard) organization.
"""
EVALUATION_QUEUE_TEXT = """
## Some good practices before submitting a model
### 1) Make sure you can load your model and tokenizer with `vLLM`:
```python
from vllm import LLM, SamplingParams
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
llm = LLM(model="/")
outputs = llm.generate(prompts, sampling_params)
```
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!
### 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
## Your model is stuck in the pending queue?
We're populating the Open CoT Leaderboard step by step. The idea is to grow a diverse and informative sample of the LLM space. Plus, with limited compute, we're currently prioritizing models that are popular, promising, and relatively small.
"""
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
Betz, G. and Cacean, S. and Richardson, K. (2024). Open CoT Leaderboard. Retrieved from https://huggingface.co/spaces/logikon/open_cot_leaderboard
"""