Terry Zhuo
commited on
Commit
·
e122c3e
1
Parent(s):
3a9e36a
fix typos
Browse files
README.md
CHANGED
|
@@ -4,7 +4,15 @@ emoji: 🥇
|
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
|
|
|
|
|
|
|
|
|
| 7 |
app_file: app.py
|
| 8 |
pinned: false
|
| 9 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
|
|
|
| 4 |
colorFrom: green
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 4.36.1
|
| 8 |
+
app_file: app.py
|
| 9 |
+
disable_embedding: true
|
| 10 |
app_file: app.py
|
| 11 |
pinned: false
|
| 12 |
license: apache-2.0
|
| 13 |
+
tags:
|
| 14 |
+
- leaderboard
|
| 15 |
+
- eval:code
|
| 16 |
+
- test:public
|
| 17 |
+
- judge:auto
|
| 18 |
---
|
app.py
CHANGED
|
@@ -124,17 +124,13 @@ def search_table(df, leaderboard_table, query):
|
|
| 124 |
|
| 125 |
df = make_clickable_names(df)
|
| 126 |
|
| 127 |
-
# <div style='background-color: #F5F1CB; text-align: center; padding: 10px;'>
|
| 128 |
-
# <p><b>Warning</b>: This leaderboard is not regularily updated with the latest instruction-tuned code models, check the <b>Submit Results</b> section for submitting new evaluation results.
|
| 129 |
-
# You can also check other code leaderboards like <a href="https://evalplus.github.io/leaderboard.html">EvalPlus</a> & <a href="https://huggingface.co/spaces/mike-ravkine/can-ai-code-results">Can-AI-Code</a> .</p>
|
| 130 |
-
# </div>
|
| 131 |
demo = gr.Blocks(css=custom_css)
|
| 132 |
with demo:
|
| 133 |
with gr.Row():
|
| 134 |
gr.Markdown(
|
| 135 |
"""<div style="text-align: center;"><h1> 🌸<span style='color: #A74E95;'>Big</span><span style='color: #C867B5;'>Code</span><span style='color: #DD71C8;'>Bench</span> Leaderboard🌸</h1></div>\
|
| 136 |
<br>\
|
| 137 |
-
<p>Inspired from the <a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">🤗 Open LLM Leaderboard</a> and <a href="https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard"
|
| 138 |
""",
|
| 139 |
elem_classes="markdown-text",
|
| 140 |
)
|
|
@@ -223,13 +219,6 @@ with demo:
|
|
| 223 |
[hidden_leaderboard_df, shown_columns],
|
| 224 |
leaderboard_df,
|
| 225 |
)
|
| 226 |
-
# <li>
|
| 227 |
-
# <i>Complete</i> vs <i>Instruct</i>:
|
| 228 |
-
# <br />
|
| 229 |
-
# <i><strong><u>Complete</u></strong></i>: Code Completion based on the (verbose) structured docstring. This variant tests if the models are good at coding.
|
| 230 |
-
# <br />
|
| 231 |
-
# <i><strong><u>Instruct</u></i> (🔥Vibe Check🔥)</strong>: Code Generation based on the (less verbose) NL-oriented instructions. This variant tests if the models are really capable enough to understand human intents to code.
|
| 232 |
-
# </li>
|
| 233 |
gr.Markdown(
|
| 234 |
"""
|
| 235 |
**Notes:**
|
|
|
|
| 124 |
|
| 125 |
df = make_clickable_names(df)
|
| 126 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
demo = gr.Blocks(css=custom_css)
|
| 128 |
with demo:
|
| 129 |
with gr.Row():
|
| 130 |
gr.Markdown(
|
| 131 |
"""<div style="text-align: center;"><h1> 🌸<span style='color: #A74E95;'>Big</span><span style='color: #C867B5;'>Code</span><span style='color: #DD71C8;'>Bench</span> Leaderboard🌸</h1></div>\
|
| 132 |
<br>\
|
| 133 |
+
<p>Inspired from the <a href="https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard">🤗 Open LLM Leaderboard</a> and <a href="https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard">⭐ Big Code Models Leaderboard</a>, we compare performance of LLMs on <a href="https://huggingface.co/datasets/bigcode/bigcodebench">BigCodeBench</a> benchmark.</p>
|
| 134 |
""",
|
| 135 |
elem_classes="markdown-text",
|
| 136 |
)
|
|
|
|
| 219 |
[hidden_leaderboard_df, shown_columns],
|
| 220 |
leaderboard_df,
|
| 221 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 222 |
gr.Markdown(
|
| 223 |
"""
|
| 224 |
**Notes:**
|