Rename

.gitignore

@@ -1,4 +1,4 @@
-solbench/
+soliditybench/
 ignore/
 auto_evals/
 venv/

README.md

@@ -7,11 +7,11 @@ sdk: gradio
 app_file: app.py
 pinned: true
 datasets:
-- braindao/solbench-naive-judge-openzeppelin-v1
+- braindao/soliditybench-naive-judge-openzeppelin-v1
 - braindao/humaneval-for-solidity-25
 license: apache-2.0
 sdk_version: 4.40.0
 thumbnail: >-
   https://cdn-uploads.huggingface.co/production/uploads/5f19edf678d261307936f4c8/4v6TPbN8qa6JptyCFUy-J.png
-short_description: Solbench Leaderboard
+short_description: SolidityBench Leaderboard
 ---

app.py

@@ -254,5 +254,5 @@ scheduler.add_job(restart_space, "interval", seconds=900)
 scheduler.start()
 demo.queue(default_concurrency_limit=40).launch(
     server_name="0.0.0.0",
-    allowed_paths=["images/solbench.svg"],
+    allowed_paths=["images/soliditybench.svg"],
 )

src/about.py

@@ -29,7 +29,7 @@ class Tasks(Enum):
 # ---------------------------------------------------
 
 # Your leaderboard name
-TITLE = """<br><img src="file/images/solbench.svg" width="500"  style="display: block; margin-left: auto; margin-right: auto;">
+TITLE = """<br><img src="file/images/soliditybench.svg" width="500"  style="display: block; margin-left: auto; margin-right: auto;">
 <h2 align="center" id="space-title">Solidity Leaderboard | Powered by IQ</h2>"""
 
 # What does your leaderboard evaluate?

src/display/utils.py

@@ -38,7 +38,7 @@ auto_eval_column_dict = [
         "", "str", True, never_hidden=True)),
     ("model", ColumnContent, create_column_content(
         "Model", "markdown", True, never_hidden=True)),
-    ("solbench", ColumnContent, create_column_content("Score", "number", True)),
+    ("soliditybench", ColumnContent, create_column_content("Score", "number", True)),
     # ("average", ColumnContent, create_column_content("Average", "number", True)),
 ]
 

src/envs.py

@@ -18,7 +18,7 @@ REQUESTS_REPO = os.environ.get("REQUESTS_REPO")
 RESULTS_REPO = os.environ.get("RESULTS_REPO")
 
 # If you setup a cache later, just change HF_HOME
-CACHE_PATH = os.path.join(os.getenv("HF_HOME", "."), "solbench")
+CACHE_PATH = os.path.join(os.getenv("HF_HOME", "."), "soliditybench")
 
 # Local caches
 EVAL_REQUESTS_PATH = os.path.join(CACHE_PATH, "requests")

src/leaderboard/read_evals.py

@@ -127,7 +127,7 @@ class EvalResult:
             'human_eval_solidity_pass_3': self.results.get('human_eval_solidity_pass_3', 0)
         }
     
-        solbench = 0
+        soliditybench = 0
         non_zero_scores = {k: v for k, v in scores.items() if v != 0}
         if non_zero_scores:
             weights = {
@@ -136,7 +136,7 @@ class EvalResult:
                 'human_eval_solidity_pass_3': 0.2
             }
             total_weight = sum(weights[k] for k in non_zero_scores)
-            solbench = sum(scores[k] * weights[k] / total_weight for k in non_zero_scores)
+            soliditybench = sum(scores[k] * weights[k] / total_weight for k in non_zero_scores)
 
         data_dict = {
             "eval_name": self.eval_name,  # not a column, just a save name,
@@ -148,7 +148,7 @@ class EvalResult:
             AutoEvalColumn.model.name: make_clickable_model(self.model_name),
             AutoEvalColumn.revision.name: self.revision,
             # AutoEvalColumn.average.name: average,
-            AutoEvalColumn.solbench.name: solbench,
+            AutoEvalColumn.soliditybench.name: soliditybench,
             AutoEvalColumn.license.name: self.license,
             AutoEvalColumn.likes.name: self.likes,
             AutoEvalColumn.params.name: self.num_params,

src/populate.py

@@ -20,7 +20,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
 
     df = pd.DataFrame.from_records(all_data_json)
     # df = df.sort_values(by=[AutoEvalColumn.average.name], ascending=False)
-    df = df.sort_values(by=[AutoEvalColumn.solbench.name], ascending=False)
+    df = df.sort_values(by=[AutoEvalColumn.soliditybench.name], ascending=False)
     df = df[cols].round(decimals=2)
 
     # filter out if any of the benchmarks have not been produced