tohid.abedini
commited on
Commit
·
b9dac59
1
Parent(s):
c604eb0
test
Browse files
app.py
CHANGED
@@ -2,7 +2,7 @@ import gradio as gr
|
|
2 |
from gradio_leaderboard import Leaderboard, SelectColumns, ColumnFilter
|
3 |
from pathlib import Path
|
4 |
|
5 |
-
from utils import LLM_BENCHMARKS_ABOUT_TEXT, LLM_BENCHMARKS_SUBMIT_TEXT, custom_css, jsonl_to_dataframe, add_average_column_to_df, apply_markdown_format_for_columns, submit
|
6 |
|
7 |
|
8 |
|
@@ -26,6 +26,7 @@ columns_data_type = ["markdown" for i in range(len(leaderboard_df.columns))]
|
|
26 |
|
27 |
|
28 |
with gr.Blocks(css=custom_css) as demo:
|
|
|
29 |
gr.Markdown("""
|
30 |
# Persian LLM Leaderboard
|
31 |
""")
|
|
|
2 |
from gradio_leaderboard import Leaderboard, SelectColumns, ColumnFilter
|
3 |
from pathlib import Path
|
4 |
|
5 |
+
from utils import LLM_BENCHMARKS_ABOUT_TEXT, LLM_BENCHMARKS_SUBMIT_TEXT, custom_css, jsonl_to_dataframe, add_average_column_to_df, apply_markdown_format_for_columns, submit, PART_LOGO
|
6 |
|
7 |
|
8 |
|
|
|
26 |
|
27 |
|
28 |
with gr.Blocks(css=custom_css) as demo:
|
29 |
+
gr.HTML(PART_LOGO)
|
30 |
gr.Markdown("""
|
31 |
# Persian LLM Leaderboard
|
32 |
""")
|
utils.py
CHANGED
@@ -114,7 +114,7 @@ LLM_BENCHMARKS_ABOUT_TEXT = f"""
|
|
114 |
|
115 |
> The Persian LLM Evaluation Leaderboard, developed by **Part DP AI** in collaboration with **AUT (Amirkabir University of Technology) NLP Lab**, provides a comprehensive benchmarking system specifically designed for Persian LLMs. This leaderboard, based on the open-source [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness), offers a unique platform for evaluating the performance of large language models (LLMs) on tasks that demand linguistic proficiency and technical skill in Persian.
|
116 |
|
117 |
-
> **Note:** This leaderboard is continuously updating its data and models, reflecting the latest developments in Persian LLMs. It is currently in version 1, serving as the initial benchmark for Persian LLM evaluation, with plans for future enhancements.
|
118 |
|
119 |
## 1. Key Features
|
120 |
|
@@ -172,6 +172,11 @@ LLM_BENCHMARKS_SUBMIT_TEXT = """## Submitting a Model for Evaluation
|
|
172 |
"""
|
173 |
|
174 |
|
|
|
|
|
|
|
|
|
|
|
175 |
def load_jsonl(input_file):
|
176 |
data = []
|
177 |
with open(input_file, 'r') as f:
|
|
|
114 |
|
115 |
> The Persian LLM Evaluation Leaderboard, developed by **Part DP AI** in collaboration with **AUT (Amirkabir University of Technology) NLP Lab**, provides a comprehensive benchmarking system specifically designed for Persian LLMs. This leaderboard, based on the open-source [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness), offers a unique platform for evaluating the performance of large language models (LLMs) on tasks that demand linguistic proficiency and technical skill in Persian.
|
116 |
|
117 |
+
> **Note:** This leaderboard is continuously updating its data and models, reflecting the latest developments in Persian LLMs. It is currently in version 1.0.0, serving as the initial benchmark for Persian LLM evaluation, with plans for future enhancements.
|
118 |
|
119 |
## 1. Key Features
|
120 |
|
|
|
172 |
"""
|
173 |
|
174 |
|
175 |
+
PART_LOGO = """
|
176 |
+
<img src="https://avatars.githubusercontent.com/u/39557177?v=4" style="width:30%;display:block;margin-left:auto;margin-right:auto">
|
177 |
+
<h1 style="font-size: 28px; margin-bottom: 2px;">Part DP AI</h1>
|
178 |
+
"""
|
179 |
+
|
180 |
def load_jsonl(input_file):
|
181 |
data = []
|
182 |
with open(input_file, 'r') as f:
|