auto_evals/
venv/
__pycache__/
.env
.ipynb_checkpoints
*ipynb
.vscode/

gpt_4_evals/
human_evals/
eval-queue/
eval-results/
auto_evals/
eval-queue-bk/
eval-results-bk/
eval-results-bk_hhem21/
eval-results_hhem21/
hhem21_server/

src/assets/model_counts.html

generation_results/
Hallucination Leaderboard Results
dataset_stats.py
hhem_v21_eval.py

get_comparison.py
GPT-4-Turbo_v.s._GPT-4o.csv