fix

.python-version

@@ -1 +0,0 @@
-3.10.15

README.md

@@ -29,4 +29,4 @@ tags:
 This repository has been cleaned to properly manage binary files with Git-LFS.
 
 For the original repository with full history, please visit:
-https://huggingface.co/spaces/llm-jp/open-japanese-llm-leaderboard
+https://huggingface.co/spaces/llm-jp/open-japanese-llm-leaderboard-v2

app.py

@@ -32,10 +32,8 @@ from src.display.utils import (
     ApplyChatTemplate,
     AutoEvalColumn,
     EnableThinking,
-    LLMJpEvalVersion,
     ModelType,
     Precision,
-    VllmVersion,
     fields,
 )
 from src.envs import API, CONTENTS_REPO, EVAL_REQUESTS_PATH, QUEUE_REPO, REPO_ID
@@ -96,8 +94,6 @@ def filter_models(
     size_query: list[str],
     precision_query: list[str],
     add_special_tokens_query: list[str],
-    version_query: list[str],
-    vllm_query: list[str],
     enable_thinking_query: list[str],
     apply_chat_template_query: list[str],
 ) -> pd.DataFrame:
@@ -122,12 +118,6 @@ def filter_models(
     # Filter by special tokens setting
     df = df[df["Add Special Tokens"].isin(add_special_tokens_query)]
 
-    # Filter by evaluator version
-    df = df[df["llm-jp-eval version"].isin(version_query)]
-
-    # Filter by vLLM version
-    df = df[df["vllm version"].isin(vllm_query)]
-
     # Filter by enable_thinking
     df = df[df["Enable Thinking"].isin(enable_thinking_query)]
 
@@ -179,8 +169,6 @@ def update_table(
     precision_query: list[str],
     size_query: list[str],
     add_special_tokens_query: list[str],
-    version_query: list[str],
-    vllm_query: list[str],
     enable_thinking_query: list[str],
     apply_chat_template_query: list[str],
     query: str,
@@ -193,8 +181,6 @@ def update_table(
         size_query,
         precision_query,
         add_special_tokens_query,
-        version_query,
-        vllm_query,
         enable_thinking_query,
         apply_chat_template_query,
     )
@@ -217,8 +203,6 @@ if len(leaderboard_df) > 0:
         list(NUMERIC_INTERVALS.keys()),
         [i.value.name for i in Precision],
         [i.value.name for i in AddSpecialTokens],
-        [i.value.name for i in LLMJpEvalVersion],
-        [i.value.name for i in VllmVersion],
         [i.value.name for i in EnableThinking],
         [i.value.name for i in ApplyChatTemplate],
     )
@@ -425,18 +409,6 @@ with gr.Blocks() as demo_leaderboard:
                 value=[i.value.name for i in AddSpecialTokens],
                 elem_id="filter-columns-add-special-tokens",
             )
-            filter_columns_version = gr.CheckboxGroup(
-                label="llm-jp-eval version",
-                choices=[i.value.name for i in LLMJpEvalVersion],
-                value=[i.value.name for i in LLMJpEvalVersion],
-                elem_id="filter-columns-version",
-            )
-            filter_columns_vllm = gr.CheckboxGroup(
-                label="vllm version",
-                choices=[i.value.name for i in VllmVersion],
-                value=[i.value.name for i in VllmVersion],
-                elem_id="filter-columns-vllm",
-            )
             filter_columns_enable_thinking = gr.CheckboxGroup(
                 label="Enable Thinking",
                 choices=[i.value.name for i in EnableThinking],
@@ -489,8 +461,6 @@ with gr.Blocks() as demo_leaderboard:
             filter_columns_precision.change,
             filter_columns_size.change,
             filter_columns_add_special_tokens.change,
-            filter_columns_version.change,
-            filter_columns_vllm.change,
             filter_columns_enable_thinking.change,
             filter_columns_apply_chat_template.change,
             search_bar.submit,
@@ -502,8 +472,6 @@ with gr.Blocks() as demo_leaderboard:
             filter_columns_precision,
             filter_columns_size,
             filter_columns_add_special_tokens,
-            filter_columns_version,
-            filter_columns_vllm,
             filter_columns_enable_thinking,
             filter_columns_apply_chat_template,
             search_bar,

pyproject.toml

@@ -3,7 +3,7 @@ name = "open-japanese-llm-leaderboard"
 version = "0.1.0"
 description = ""
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.13, <3.14"
 dependencies = [
     "apscheduler>=3.10.4",
     "datasets>=3.2.0",

requirements.txt

@@ -1,324 +1,105 @@
-# This file was autogenerated by uv via the following command:
-#    uv export --no-hashes --frozen
 aiofiles==24.1.0
-    # via gradio
 aiohappyeyeballs==2.6.1
-    # via aiohttp
 aiohttp==3.13.2
-    # via fsspec
 aiosignal==1.4.0
-    # via aiohttp
 annotated-doc==0.0.3
-    # via fastapi
 annotated-types==0.7.0
-    # via pydantic
 anyio==4.11.0
-    # via
-    #   gradio
-    #   httpx
-    #   starlette
 apscheduler==3.11.1
-    # via open-japanese-llm-leaderboard
-async-timeout==5.0.1 ; python_full_version < '3.11'
-    # via aiohttp
 attrs==25.4.0
-    # via aiohttp
-audioop-lts==0.2.2 ; python_full_version >= '3.13'
-    # via gradio
+audioop-lts==0.2.2
 authlib==1.6.5
-    # via gradio
 brotli==1.2.0
-    # via gradio
 certifi==2025.10.5
-    # via
-    #   httpcore
-    #   httpx
-    #   requests
-cffi==2.0.0 ; platform_python_implementation != 'PyPy'
-    # via cryptography
+cffi==2.0.0
 charset-normalizer==3.4.4
-    # via requests
 click==8.3.0
-    # via
-    #   typer
-    #   uvicorn
-colorama==0.4.6 ; sys_platform == 'win32'
-    # via
-    #   click
-    #   tqdm
 cryptography==46.0.3
-    # via authlib
 datasets==4.4.1
-    # via open-japanese-llm-leaderboard
 dill==0.4.0
-    # via
-    #   datasets
-    #   multiprocess
-exceptiongroup==1.3.0 ; python_full_version < '3.11'
-    # via anyio
 fastapi==0.121.1
-    # via gradio
 ffmpy==0.6.4
-    # via gradio
 filelock==3.20.0
-    # via
-    #   datasets
-    #   huggingface-hub
-    #   torch
-    #   transformers
 frozenlist==1.8.0
-    # via
-    #   aiohttp
-    #   aiosignal
 fsspec==2025.10.0
-    # via
-    #   datasets
-    #   gradio-client
-    #   huggingface-hub
-    #   torch
 gradio==5.49.1
-    # via open-japanese-llm-leaderboard
 gradio-client==1.13.3
-    # via gradio
 groovy==0.1.2
-    # via gradio
 h11==0.16.0
-    # via
-    #   httpcore
-    #   uvicorn
 hf-transfer==0.1.9
-    # via open-japanese-llm-leaderboard
-hf-xet==1.2.0 ; platform_machine == 'aarch64' or platform_machine == 'amd64' or platform_machine == 'arm64' or platform_machine == 'x86_64'
-    # via huggingface-hub
+hf-xet==1.2.0
 httpcore==1.0.9
-    # via httpx
 httpx==0.28.1
-    # via
-    #   datasets
-    #   gradio
-    #   gradio-client
-    #   safehttpx
 huggingface-hub==0.36.0
-    # via
-    #   datasets
-    #   gradio
-    #   gradio-client
-    #   tokenizers
-    #   transformers
 idna==3.11
-    # via
-    #   anyio
-    #   httpx
-    #   requests
-    #   yarl
 itsdangerous==2.2.0
-    # via gradio
 jinja2==3.1.6
-    # via
-    #   gradio
-    #   torch
 markdown-it-py==4.0.0
-    # via rich
 markupsafe==3.0.3
-    # via
-    #   gradio
-    #   jinja2
 mdurl==0.1.2
-    # via markdown-it-py
 mpmath==1.3.0
-    # via sympy
 multidict==6.7.0
-    # via
-    #   aiohttp
-    #   yarl
 multiprocess==0.70.18
-    # via datasets
-networkx==3.4.2 ; python_full_version < '3.11'
-    # via torch
-networkx==3.5 ; python_full_version >= '3.11'
-    # via torch
-numpy==2.2.6 ; python_full_version < '3.11'
-    # via
-    #   datasets
-    #   gradio
-    #   pandas
-    #   transformers
-numpy==2.3.4 ; python_full_version >= '3.11'
-    # via
-    #   datasets
-    #   gradio
-    #   pandas
-    #   transformers
-nvidia-cublas-cu12==12.8.4.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via
-    #   nvidia-cudnn-cu12
-    #   nvidia-cusolver-cu12
-    #   torch
-nvidia-cuda-cupti-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cuda-nvrtc-cu12==12.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cuda-runtime-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cudnn-cu12==9.10.2.21 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cufft-cu12==11.3.3.83 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cufile-cu12==1.13.1.3 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-curand-cu12==10.3.9.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cusolver-cu12==11.7.3.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-cusparse-cu12==12.5.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via
-    #   nvidia-cusolver-cu12
-    #   torch
-nvidia-cusparselt-cu12==0.7.1 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-nccl-cu12==2.27.5 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-nvjitlink-cu12==12.8.93 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via
-    #   nvidia-cufft-cu12
-    #   nvidia-cusolver-cu12
-    #   nvidia-cusparse-cu12
-    #   torch
-nvidia-nvshmem-cu12==3.3.20 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
-nvidia-nvtx-cu12==12.8.90 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
+networkx==3.5
+numpy==2.3.4
+nvidia-cublas-cu12==12.8.4.1
+nvidia-cuda-cupti-cu12==12.8.90
+nvidia-cuda-nvrtc-cu12==12.8.93
+nvidia-cuda-runtime-cu12==12.8.90
+nvidia-cudnn-cu12==9.10.2.21
+nvidia-cufft-cu12==11.3.3.83
+nvidia-cufile-cu12==1.13.1.3
+nvidia-curand-cu12==10.3.9.90
+nvidia-cusolver-cu12==11.7.3.90
+nvidia-cusparse-cu12==12.5.8.93
+nvidia-cusparselt-cu12==0.7.1
+nvidia-nccl-cu12==2.27.5
+nvidia-nvjitlink-cu12==12.8.93
+nvidia-nvshmem-cu12==3.3.20
+nvidia-nvtx-cu12==12.8.90
 orjson==3.11.4
-    # via gradio
 packaging==25.0
-    # via
-    #   datasets
-    #   gradio
-    #   gradio-client
-    #   huggingface-hub
-    #   plotly
-    #   transformers
 pandas==2.3.3
-    # via
-    #   datasets
-    #   gradio
 pillow==11.3.0
-    # via gradio
 plotly==5.24.1
-    # via open-japanese-llm-leaderboard
 propcache==0.4.1
-    # via
-    #   aiohttp
-    #   yarl
 pyarrow==22.0.0
-    # via datasets
-pycparser==2.23 ; implementation_name != 'PyPy' and platform_python_implementation != 'PyPy'
-    # via cffi
+pycparser==2.23
 pydantic==2.11.10
-    # via
-    #   fastapi
-    #   gradio
 pydantic-core==2.33.2
-    # via pydantic
 pydub==0.25.1
-    # via gradio
 pygments==2.19.2
-    # via rich
 python-dateutil==2.9.0.post0
-    # via pandas
 python-multipart==0.0.20
-    # via gradio
 pytz==2025.2
-    # via pandas
 pyyaml==6.0.3
-    # via
-    #   datasets
-    #   gradio
-    #   huggingface-hub
-    #   transformers
 regex==2025.11.3
-    # via transformers
 requests==2.32.5
-    # via
-    #   datasets
-    #   huggingface-hub
-    #   transformers
 rich==14.2.0
-    # via typer
 ruff==0.14.4
-    # via gradio
 safehttpx==0.1.7
-    # via gradio
 safetensors==0.6.2
-    # via transformers
 semantic-version==2.10.0
-    # via gradio
-setuptools==80.9.0 ; python_full_version >= '3.12'
-    # via torch
+setuptools==80.9.0
 shellingham==1.5.4
-    # via typer
 six==1.17.0
-    # via python-dateutil
 sniffio==1.3.1
-    # via anyio
 starlette==0.49.3
-    # via
-    #   fastapi
-    #   gradio
 sympy==1.14.0
-    # via torch
 tenacity==9.1.2
-    # via plotly
 tokenizers==0.22.1
-    # via transformers
 tomlkit==0.13.3
-    # via gradio
 torch==2.9.0
-    # via open-japanese-llm-leaderboard
 tqdm==4.67.1
-    # via
-    #   datasets
-    #   huggingface-hub
-    #   transformers
 transformers==4.57.6
-    # via open-japanese-llm-leaderboard
-triton==3.5.0 ; platform_machine == 'x86_64' and sys_platform == 'linux'
-    # via torch
+triton==3.5.0
 typer==0.20.0
-    # via gradio
 typing-extensions==4.15.0
-    # via
-    #   aiosignal
-    #   anyio
-    #   cryptography
-    #   exceptiongroup
-    #   fastapi
-    #   gradio
-    #   gradio-client
-    #   huggingface-hub
-    #   multidict
-    #   pydantic
-    #   pydantic-core
-    #   starlette
-    #   torch
-    #   typer
-    #   typing-inspection
-    #   uvicorn
 typing-inspection==0.4.2
-    # via pydantic
 tzdata==2025.2
-    # via
-    #   pandas
-    #   tzlocal
 tzlocal==5.3.1
-    # via apscheduler
 urllib3==2.5.0
-    # via requests
 uvicorn==0.38.0
-    # via gradio
 websockets==15.0.1
-    # via gradio-client
 xxhash==3.6.0
-    # via datasets
 yarl==1.22.0
-    # via aiohttp

src/display/utils.py

@@ -13,7 +13,7 @@ def fields(raw_class):
 # These classes are for user facing column names,
 # to avoid having to change them all around the code
 # when a modif is needed
-@dataclass
+@dataclass(frozen=True)
 class ColumnContent:
     name: str
     type: str
@@ -33,19 +33,17 @@ auto_eval_column_dict.append(["model", ColumnContent, ColumnContent("Model", "ma
 # Scores
 # auto_eval_column_dict.append(["average", ColumnContent, ColumnContent("Average ⬆️", "number", True)])
 for task in Tasks:
-    auto_eval_column_dict.append(
-        [
-            task.name,
-            ColumnContent,
-            ColumnContent(
-                task.value.col_name,
-                "number",
-                displayed_by_default=(task.value.task_type == TaskType.AVG or task.value.average),
-                task_type=task.value.task_type,
-                average=task.value.average,
-            ),
-        ]
-    )
+    auto_eval_column_dict.append([
+        task.name,
+        ColumnContent,
+        ColumnContent(
+            task.value.col_name,
+            "number",
+            displayed_by_default=(task.value.task_type == TaskType.AVG or task.value.average),
+            task_type=task.value.task_type,
+            average=task.value.average,
+        ),
+    ])
 # Model information
 auto_eval_column_dict.append(["model_type", ColumnContent, ColumnContent("Type", "str", False)])
 auto_eval_column_dict.append(["architecture", ColumnContent, ColumnContent("Architecture", "str", False)])
@@ -57,19 +55,16 @@ auto_eval_column_dict.append(["likes", ColumnContent, ColumnContent("Hub ❤️"
 auto_eval_column_dict.append(["revision", ColumnContent, ColumnContent("Revision", "str", False, False)])
 auto_eval_column_dict.append(["add_special_tokens", ColumnContent, ColumnContent("Add Special Tokens", "bool", False)])
 auto_eval_column_dict.append(["enable_thinking", ColumnContent, ColumnContent("Enable Thinking", "bool", False)])
-auto_eval_column_dict.append(
-    ["apply_chat_template", ColumnContent, ColumnContent("Apply Chat Template", "bool", False)]
-)
+auto_eval_column_dict.append(["apply_chat_template", ColumnContent, ColumnContent("Apply Chat Template", "bool", False)])
 auto_eval_column_dict.append(["dummy", ColumnContent, ColumnContent("model_name_for_query", "str", False, dummy=True)])
 auto_eval_column_dict.append(["row_id", ColumnContent, ColumnContent("ID", "number", False, dummy=True)])
 
 # We use make dataclass to dynamically fill the scores from Tasks
-AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict, frozen=True)
+AutoEvalColumn = make_dataclass("AutoEvalColumn", auto_eval_column_dict)
 
 
 ## For the queue columns in the submission tab
-@dataclass(frozen=True)
-class EvalQueueColumn:  # Queue column
+class EvalQueueColumn:  # Queue column (not a dataclass - used as class attributes)
     model = ColumnContent("model", "markdown", True)
     revision = ColumnContent("revision", "str", True)
     model_type = ColumnContent("model_type", "str", True)