Spaces:
Runtime error
Runtime error
initial upload
Browse files- .gitignore +163 -0
- app.py +83 -0
.gitignore
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Byte-compiled / optimized / DLL files
|
2 |
+
__pycache__/
|
3 |
+
*.py[cod]
|
4 |
+
*$py.class
|
5 |
+
|
6 |
+
# C extensions
|
7 |
+
*.so
|
8 |
+
|
9 |
+
# Distribution / packaging
|
10 |
+
.Python
|
11 |
+
build/
|
12 |
+
develop-eggs/
|
13 |
+
dist/
|
14 |
+
downloads/
|
15 |
+
eggs/
|
16 |
+
.eggs/
|
17 |
+
lib/
|
18 |
+
lib64/
|
19 |
+
parts/
|
20 |
+
sdist/
|
21 |
+
var/
|
22 |
+
wheels/
|
23 |
+
share/python-wheels/
|
24 |
+
*.egg-info/
|
25 |
+
.installed.cfg
|
26 |
+
*.egg
|
27 |
+
MANIFEST
|
28 |
+
|
29 |
+
# PyInstaller
|
30 |
+
# Usually these files are written by a python script from a template
|
31 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
32 |
+
*.manifest
|
33 |
+
*.spec
|
34 |
+
|
35 |
+
# Installer logs
|
36 |
+
pip-log.txt
|
37 |
+
pip-delete-this-directory.txt
|
38 |
+
|
39 |
+
# Unit test / coverage reports
|
40 |
+
htmlcov/
|
41 |
+
.tox/
|
42 |
+
.nox/
|
43 |
+
.coverage
|
44 |
+
.coverage.*
|
45 |
+
.cache
|
46 |
+
nosetests.xml
|
47 |
+
coverage.xml
|
48 |
+
*.cover
|
49 |
+
*.py,cover
|
50 |
+
.hypothesis/
|
51 |
+
.pytest_cache/
|
52 |
+
cover/
|
53 |
+
|
54 |
+
# Translations
|
55 |
+
*.mo
|
56 |
+
*.pot
|
57 |
+
|
58 |
+
# Django stuff:
|
59 |
+
*.log
|
60 |
+
local_settings.py
|
61 |
+
db.sqlite3
|
62 |
+
db.sqlite3-journal
|
63 |
+
|
64 |
+
# Flask stuff:
|
65 |
+
instance/
|
66 |
+
.webassets-cache
|
67 |
+
|
68 |
+
# Scrapy stuff:
|
69 |
+
.scrapy
|
70 |
+
|
71 |
+
# Sphinx documentation
|
72 |
+
docs/_build/
|
73 |
+
|
74 |
+
# PyBuilder
|
75 |
+
.pybuilder/
|
76 |
+
target/
|
77 |
+
|
78 |
+
# Jupyter Notebook
|
79 |
+
.ipynb_checkpoints
|
80 |
+
|
81 |
+
# IPython
|
82 |
+
profile_default/
|
83 |
+
ipython_config.py
|
84 |
+
|
85 |
+
# pyenv
|
86 |
+
# For a library or package, you might want to ignore these files since the code is
|
87 |
+
# intended to run in multiple environments; otherwise, check them in:
|
88 |
+
# .python-version
|
89 |
+
|
90 |
+
# pipenv
|
91 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
92 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
93 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
94 |
+
# install all needed dependencies.
|
95 |
+
#Pipfile.lock
|
96 |
+
|
97 |
+
# poetry
|
98 |
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
99 |
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
100 |
+
# commonly ignored for libraries.
|
101 |
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
102 |
+
#poetry.lock
|
103 |
+
|
104 |
+
# pdm
|
105 |
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
106 |
+
#pdm.lock
|
107 |
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
108 |
+
# in version control.
|
109 |
+
# https://pdm.fming.dev/#use-with-ide
|
110 |
+
.pdm.toml
|
111 |
+
|
112 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
113 |
+
__pypackages__/
|
114 |
+
|
115 |
+
# Celery stuff
|
116 |
+
celerybeat-schedule
|
117 |
+
celerybeat.pid
|
118 |
+
|
119 |
+
# SageMath parsed files
|
120 |
+
*.sage.py
|
121 |
+
|
122 |
+
# Environments
|
123 |
+
.env
|
124 |
+
.venv
|
125 |
+
env/
|
126 |
+
venv/
|
127 |
+
ENV/
|
128 |
+
env.bak/
|
129 |
+
venv.bak/
|
130 |
+
|
131 |
+
# Spyder project settings
|
132 |
+
.spyderproject
|
133 |
+
.spyproject
|
134 |
+
|
135 |
+
# Rope project settings
|
136 |
+
.ropeproject
|
137 |
+
|
138 |
+
# mkdocs documentation
|
139 |
+
/site
|
140 |
+
|
141 |
+
# mypy
|
142 |
+
.mypy_cache/
|
143 |
+
.dmypy.json
|
144 |
+
dmypy.json
|
145 |
+
|
146 |
+
# Pyre type checker
|
147 |
+
.pyre/
|
148 |
+
|
149 |
+
# pytype static type analyzer
|
150 |
+
.pytype/
|
151 |
+
|
152 |
+
# Cython debug symbols
|
153 |
+
cython_debug/
|
154 |
+
|
155 |
+
# PyCharm
|
156 |
+
.idea/
|
157 |
+
|
158 |
+
# ruff code style
|
159 |
+
.ruff_cache/
|
160 |
+
|
161 |
+
.vscode/
|
162 |
+
|
163 |
+
playground/
|
app.py
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import ast
|
2 |
+
import json
|
3 |
+
import urllib
|
4 |
+
|
5 |
+
import gradio as gr
|
6 |
+
|
7 |
+
import pandas as pd
|
8 |
+
from datasets import load_dataset
|
9 |
+
from gradio_leaderboard import Leaderboard, SelectColumns, SearchColumns, ColumnFilter
|
10 |
+
|
11 |
+
df = pd.read_json("https://raw.githubusercontent.com/huggingface/lighteval/main/src/lighteval/tasks/tasks_table.jsonl", lines=True).explode("suite").reset_index(drop=True)
|
12 |
+
|
13 |
+
with urllib.request.urlopen("https://raw.githubusercontent.com/huggingface/lighteval/main/src/lighteval/tasks/tasks_prompt_formatting.py") as f:
|
14 |
+
tasks_prompt_functions_raw = f.read().decode('utf-8')
|
15 |
+
tree = ast.parse(tasks_prompt_functions_raw)
|
16 |
+
tasks_prompt_functions = {}
|
17 |
+
|
18 |
+
for node in ast.walk(tree):
|
19 |
+
if isinstance(node, ast.FunctionDef):
|
20 |
+
function_name = node.name
|
21 |
+
# Get the source code for the function node
|
22 |
+
function_code = ast.get_source_segment(tasks_prompt_functions_raw, node)
|
23 |
+
tasks_prompt_functions[function_name] = function_code
|
24 |
+
|
25 |
+
def load_task_metadata(task_id):
|
26 |
+
task_row = df.iloc[task_id]
|
27 |
+
return (task_row.to_dict(), f"""Examples from the HF repository ([{task_row['hf_repo']}](https://huggingface.co/datasets/{task_row['hf_repo']}))""",
|
28 |
+
tasks_prompt_functions.get(task_row["prompt_function"]), "unknown")
|
29 |
+
|
30 |
+
def load_task_examples(task_id):
|
31 |
+
task_row = df.iloc[task_id]
|
32 |
+
dataset = load_dataset(task_row["hf_repo"], task_row["hf_subset"], split="+".join(task_row["evaluation_splits"]),
|
33 |
+
trust_remote_code=task_row["trust_dataset"], streaming=True)
|
34 |
+
|
35 |
+
sample_data = next(dataset.iter(20))
|
36 |
+
# dictionary of lists to list of dictionaries
|
37 |
+
return pd.DataFrame(dict(zip(sample_data, t if not isinstance(t, dict) and not isinstance(t, list) else json.dumps(t)))
|
38 |
+
for t in zip(*sample_data.values()))
|
39 |
+
|
40 |
+
|
41 |
+
|
42 |
+
with gr.Blocks() as demo:
|
43 |
+
gr.Markdown("""
|
44 |
+
# LightEval Tasks Explorer
|
45 |
+
""")
|
46 |
+
with gr.Tabs() as tabs:
|
47 |
+
with gr.TabItem("🗃️ Tasks List"):
|
48 |
+
Leaderboard(
|
49 |
+
value=df,
|
50 |
+
select_columns=SelectColumns(default_selection=["name", "suite", "prompt_function", "hf_repo", "hf_subset", "evaluation_splits", "metric"],
|
51 |
+
cant_deselect=["name", "suite"],
|
52 |
+
label="Columns to display"),
|
53 |
+
search_columns=SearchColumns(primary_column="name", secondary_columns=["suite", "prompt_function", "hf_repo", "metric"],
|
54 |
+
placeholder="Search for a task by name, suite, prompt_function, hf_repo or "
|
55 |
+
"metric. To search by suite, for example, type 'suite:<query>'. Separate queries by \";\"",
|
56 |
+
label="Search"),
|
57 |
+
filter_columns=[
|
58 |
+
ColumnFilter("suite", type="dropdown", label="Select suite"),
|
59 |
+
# ColumnFilter("prompt_function", type="dropdown", label="Select prompt_function"),
|
60 |
+
# ColumnFilter("metric", type="dropdown", label="Select metric")
|
61 |
+
],
|
62 |
+
wrap=True
|
63 |
+
)
|
64 |
+
with gr.TabItem("🔎 Task Inspector"):
|
65 |
+
task_inspector_selector = gr.Dropdown(
|
66 |
+
choices=sorted(zip((df['suite'] + '|' + df['name']).tolist(), range(len(df)))),
|
67 |
+
label="Task",
|
68 |
+
info="Select a task"
|
69 |
+
)
|
70 |
+
with gr.Row():
|
71 |
+
with gr.Column():
|
72 |
+
task_metadata = gr.Json(label="Task definition")
|
73 |
+
with gr.Column():
|
74 |
+
task_prompt_function = gr.Code(label="Task prompt function", language="python", interactive=False)
|
75 |
+
task_dataset_header = gr.Markdown("Examples from the HF repository")
|
76 |
+
task_dataset = gr.Dataframe(wrap=True)
|
77 |
+
|
78 |
+
gr.on(triggers=[task_inspector_selector.change], inputs=[task_inspector_selector], outputs=[task_metadata, task_dataset_header, task_prompt_function], fn=load_task_metadata)
|
79 |
+
gr.on(triggers=[task_inspector_selector.change], inputs=[task_inspector_selector], outputs=[task_dataset], fn=load_task_examples)
|
80 |
+
|
81 |
+
|
82 |
+
if __name__ == "__main__":
|
83 |
+
demo.launch()
|