update name and envs

app.py

@@ -22,7 +22,7 @@ from src.display.utils import (
     ModelType,
     fields,
     WeightType,
-    Precision
+    Precision,
 )
 from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
 from src.populate import get_evaluation_queue_df, get_leaderboard_df
@@ -32,18 +32,29 @@ from src.submission.submit import add_new_eval
 def restart_space():
     API.restart_space(repo_id=REPO_ID)
 
+
 ### Space initialisation
 try:
     print(EVAL_REQUESTS_PATH)
     snapshot_download(
-        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
+        repo_id=QUEUE_REPO,
+        local_dir=EVAL_REQUESTS_PATH,
+        repo_type="dataset",
+        tqdm_class=None,
+        etag_timeout=30,
+        token=TOKEN,
     )
 except Exception:
     restart_space()
 try:
     print(EVAL_RESULTS_PATH)
     snapshot_download(
-        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
+        repo_id=RESULTS_REPO,
+        local_dir=EVAL_RESULTS_PATH,
+        repo_type="dataset",
+        tqdm_class=None,
+        etag_timeout=30,
+        token=TOKEN,
     )
 except Exception:
     restart_space()
@@ -57,6 +68,7 @@ LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS,
     pending_eval_queue_df,
 ) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
 
+
 def init_leaderboard(dataframe):
     if dataframe is None or dataframe.empty:
         raise ValueError("Leaderboard DataFrame is empty or None.")
@@ -80,9 +92,7 @@ def init_leaderboard(dataframe):
                 max=150,
                 label="Select the number of parameters (B)",
             ),
-            ColumnFilter(
-                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
-            ),
+            ColumnFilter(AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True),
         ],
         bool_checkboxgroup_label="Hide models",
         interactive=False,
@@ -95,7 +105,13 @@ with demo:
     gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
-        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
+        with gr.TabItem("🏅 Position Bias Analyzer", elem_id="llm-benchmark-tab-table", id=0):
+            leaderboard = init_leaderboard(LEADERBOARD_DF)
+
+        with gr.TabItem("🏅 LLMBar Natural", elem_id="llm-benchmark-tab-table", id=4):
+            leaderboard = init_leaderboard(LEADERBOARD_DF)
+
+        with gr.TabItem("🏅 LLMBar Adversarial (Manual)", elem_id="llm-benchmark-tab-table", id=5):
             leaderboard = init_leaderboard(LEADERBOARD_DF)
 
         with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
@@ -201,4 +217,4 @@ with demo:
 scheduler = BackgroundScheduler()
 scheduler.add_job(restart_space, "interval", seconds=1800)
 scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+demo.queue(default_concurrency_limit=40).launch()

src/about.py

@@ -1,6 +1,7 @@
 from dataclasses import dataclass
 from enum import Enum
 
+
 @dataclass
 class Task:
     benchmark: str
@@ -11,17 +12,17 @@ class Task:
 # Select your tasks here
 # ---------------------------------------------------
 class Tasks(Enum):
-    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
+    # task_key in the json file, metric_key in the json file, name to display in the leaderboard
     task0 = Task("anli_r1", "acc", "ANLI")
     task1 = Task("logiqa", "acc_norm", "LogiQA")
 
-NUM_FEWSHOT = 0 # Change with your few shot
-# ---------------------------------------------------
 
+NUM_FEWSHOT = 0  # Change with your few shot
+# ---------------------------------------------------
 
 
 # Your leaderboard name
-TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
+TITLE = """<h1 align="center" id="space-title">LLM as Judge Eval</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """

src/envs.py

@@ -4,17 +4,19 @@ from huggingface_hub import HfApi
 
 # Info to change for your repository
 # ----------------------------------
-TOKEN = os.environ.get("HF_TOKEN") # A read/write token for your org
+TOKEN = os.environ.get("HF_TOKEN")  # A read/write token for your org
 
-OWNER = "demo-leaderboard-backend" # Change to your org - don't forget to create a results and request dataset, with the correct format!
+OWNER = (
+    "CEIA-RL"  # Change to your org - don't forget to create a results and request dataset, with the correct format!
+)
 # ----------------------------------
 
-REPO_ID = f"{OWNER}/leaderboard"
-QUEUE_REPO = f"{OWNER}/requests"
-RESULTS_REPO = f"{OWNER}/results"
+REPO_ID = f"{OWNER}/LLMasJudgeEval"
+QUEUE_REPO = f"{OWNER}/judge_requests"
+RESULTS_REPO = f"{OWNER}/judge_results"
 
 # If you setup a cache later, just change HF_HOME
-CACHE_PATH=os.getenv("HF_HOME", ".")
+CACHE_PATH = os.getenv("HF_HOME", ".")
 
 # Local caches
 EVAL_REQUESTS_PATH = os.path.join(CACHE_PATH, "eval-queue")