updated scripts

.idea/HumanLikeness.iml

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.11 (default)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="GOOGLE" />
+    <option name="myDocStringFormat" value="Google" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.11 (HumanLikeness)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (default)" project-jdk-type="Python SDK" />
+</project>

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import pandas as pd
 from apscheduler.schedulers.background import BackgroundScheduler
 from huggingface_hub import snapshot_download
+from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO
 
 import socket
 import src.display.about as about
@@ -9,6 +10,7 @@ from src.display.css_html_js import custom_css
 import src.display.utils as utils
 import src.envs as envs
 import src.populate as populate
+from src.populate import get_evaluation_queue_df, get_leaderboard_df
 import src.submission.submit as submit
 import os
 TOKEN = os.environ.get("H4_TOKEN", None)
@@ -31,9 +33,9 @@ def init_space():
         # sync model_type with open-llm-leaderboard
         ui_snapshot_download(repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30)
         ui_snapshot_download(repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30)
-    raw_data, original_df = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, "", COLS, BENCHMARK_COLS)
+    raw_data, original_df = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, "", utils.COLS, utils.BENCHMARK_COLS)
 
-    finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
+    finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df = get_evaluation_queue_df(EVAL_REQUESTS_PATH, utils.EVAL_COLS)
     return original_df, finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df
 
 original_df, finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df = init_space()