content.py

"""
This file contains the text content for the leaderboard client.
"""
HEADER_MARKDOWN = """
# 🇨🇿 BenCzechMark [Beta Preview]

Welcome to the leaderboard!  
Here you can compare models on tasks in Czech language and/or submit your own model. We use our modified fork of [lm-evaluation-harness](https://github.com/DCGM/lm-evaluation-harness) to evaluate every model under same protocol.

- Head to **Submission** page to learn about submission details.
- See **About** page for brief description of our evaluation protocol & win score mechanism, citation information, and future directions for this benchmark.

"""
LEADERBOARD_TAB_TITLE_MARKDOWN = """
   ## Leaderboard
   """

SUBMISSION_TAB_TITLE_MARKDOWN = """
    ## How to submit
    1. Head down to our modified fork of [lm-evaluation-harness](https://github.com/DCGM/lm-evaluation-harness). 
    Follow the instructions and evaluate your model on all 🇨🇿 BenCzechMark tasks, while logging your lm harness outputs into designated folder.

    2. Use our script [compile_log_files.py](https://huggingface.co/spaces/CZLC/BenCzechMark/blob/main/compile_log_files.py) for processing log files from your designated folder into single compact submission file that contains everything we need.  
    Example usage:
   - Download sample outputs for csmpt7b from [csmpt_logdir.zip](https://czechllm.fit.vutbr.cz/csmpt7b/sample_results/csmpt_logdir.zip).
   - Unzip.
   - Run the script as with python (with libs jsonlines and tqdm)
   ```bash 
   python compile_log_files.py \
   -i "<your_local_path_to_folder>/csmpt_logdir/csmpt/eval_csmpt7b*" \
   -o "<your_local_path_to_outfolder>/sample_submission.json"
   ```

    3. Upload your file, and fill the form below!
    
    ## Submission
    To submit your model, please fill in the form below.
    
    - *Team name:* The name of your team, as it will appear on the leaderboard
    - *Model name:* The name of your model
    - *Model type:* The type of your model (chat, pretrained, ensemble)
    - *Parameters (B):* The number of parameters of your model in billions (10⁹)
    - *Input length (# tokens):* The number of input tokens that led to the results
    - *Precision:* The precision with which the results were obtained
    - *Description:* Short description of your submission (optional)
    - *Link to model:* Link to the model's repository or documentation
    - *Upload your results:* Results json file to submit
    
    After filling in the form, click the **Pre-submit model** button. 
    This will run a comparison of your model with the existing leaderboard models. 
    After the tournament is complete, you will be able to submit your model to the leaderboard.
"""

RANKING_AFTER_SUBMISSION_MARKDOWN = """
                    This is how will ranking look like after your submission:
                    """
SUBMISSION_DETAILS_MARKDOWN = """
                    Do you really want to submit a model? This action is irreversible.
                    """
MORE_DETAILS_MARKDOWN = """
## Model details:
"""

MODAL_SUBMIT_MARKDOWN = """
Are you sure you want to submit your model?
"""

ABOUT_MARKDOWN = """
# About
- **BenCzechMark Authors & Contributors:**
  - **BUT FIT**
    - Martin Fajčík
    - Martin Dočekal
    - Jan Doležal
    - Karel Ondřej
    - Karel Beneš
    - Jan Kapsa
    - Michal Hradiš
  - **FI MUNI**
    - Zuzana Nevěřilová
    - Aleš Horák
    - Michal Štefánik
  - **CIIRC CTU**
    - Adam Jirkovský
    - David Adamczyk
    - Jan Hůla
    - Jan Šedivý
  - **Hugging Face**
    - Hynek Kydlíček


**Correspondence to:**
- Martin Fajčík
- Brno University of Technology
- Brno, Czech Republic
- Email: [martin.fajcik@vut.cz](mailto:martin.fajcik@vut.cz)
"""