Spaces:
Running
Running
File size: 2,494 Bytes
2c9628e d4d6f06 2c9628e d4d6f06 2c9628e d4d6f06 2c9628e d4d6f06 2c9628e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
import os
import json
import glob
from collections import defaultdict
import pandas as pd
import gradio as gr
from content import *
from css import *
import glob
ARC = "arc"
HELLASWAG = "hellaswag"
MMLU = "mmlu"
TRUTHFULQA = "truthfulqa"
BENCHMARKS = [ARC, HELLASWAG, MMLU, TRUTHFULQA]
METRICS = ["acc_norm", "acc_norm", "acc_norm", "mc2"]
LANGS = 'ar,bn,ca,da,de,es,eu,fr,gu,hi,hr,hu,hy,id,it,kn,ml,mr,ne,nl,pt,ro,ru,sk,sr,sv,ta,te,uk,vi,zh'.split(',')
LANG_NAME = {
'ar': 'Arabic',
'bn': 'Bengali',
'ca': 'Catalan',
'da': 'Danish',
'de': 'German',
'es': 'Spanish',
'eu': 'Basque',
'fr': 'French',
'gu': 'Gujarati',
'hi': 'Hindi',
'hr': 'Croatian',
'hu': 'Hungarian',
'hy': 'Armenian',
'id': 'Indonesian',
'it': 'Italian',
'kn': 'Kannada',
'ml': 'Malayalam',
'mr': 'Marathi',
'ne': 'Nepali',
'nl': 'Dutch',
'pt': 'Portuguese',
'ro': 'Romanian',
'ru': 'Russian',
'sk': 'Slovak',
'sr': 'Serbian',
'sv': 'Swedish',
'ta': 'Tamil',
'te': 'Telugu',
'uk': 'Ukrainian',
'vi': 'Vietnamese',
'zh': 'Chinese'
}
NONE_COL = "None"
COLS = ["Method", "Model" , "SS Easy", "SS Medium", "SS Hard", "MS Easy", "MS Meduium", "MS Hard", "Overall", NONE_COL]
TYPES = ["str", "str", "number", "number", "number", "number", "number", "number", "number", "number" , "number"]
df = []
row = ["React", "Qwen-plus" , "10.5", "20.6", "30.4", "10.5", "20.6", "30.4", "20", NONE_COL]
df.append(row)
df.append(row)
df.append(row)
df.append(row)
df = pd.DataFrame.from_records(df, columns=COLS)
df = df.sort_values(by=["Method", "Overall"], ascending=False)
df = df[COLS]
demo = gr.Blocks(css=CUSTOM_CSS)
with demo:
gr.HTML(TITLE)
gr.Markdown(INTRO_TEXT, elem_classes="markdown-text")
gr.Markdown(HOW_TO, elem_classes="markdown-text")
print(TYPES)
print(df.columns)
with gr.Group():
with gr.Tab("Results: Agent"):
leaderboard_table_test = gr.components.Dataframe(
value=df, datatype=TYPES, interactive=False,
column_widths = ["20%"] * len(df.columns)
)
with gr.Tab("Results: RAG-system"):
leaderboard_table_val = gr.components.Dataframe(
value=df, datatype=TYPES, interactive=False,
column_widths=["20%"]
)
gr.Markdown(CREDIT, elem_classes="markdown-text")
gr.Markdown(CITATION, elem_classes="markdown-text")
demo.launch(share=True) |