File size: 8,293 Bytes
9346f1c
8b28d2b
9346f1c
4596a70
2a5f9fb
 
1ffc326
8c49cb6
 
 
 
 
 
 
976f398
df66f6e
 
 
 
 
 
 
 
9d22eee
 
df66f6e
24622c4
df66f6e
 
8c49cb6
2374038
 
 
 
 
 
2a73469
10f9b3c
50df158
d084b26
8b28d2b
d084b26
 
 
4879b93
d084b26
 
 
 
 
 
4879b93
d084b26
 
 
26286b2
a885f09
8b28d2b
2a73469
ffefe11
 
 
 
adb0416
614ee1f
8b28d2b
7ec1b66
 
d78ed99
8b28d2b
 
 
 
 
 
 
 
b47b51e
8b28d2b
 
b47b51e
 
 
 
 
 
 
 
 
 
 
 
8b28d2b
 
 
 
d2179b0
7644705
01233b7
 
58733e4
6e8f400
2374038
 
10f9b3c
8cb7546
613696b
8b28d2b
f2bc0a5
613696b
6e8f400
0227006
613696b
d78ed99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2374038
00358b1
 
0227006
6e8f400
 
 
a163e5c
b323764
9d22eee
8c49cb6
b323764
ef627e9
b323764
 
0227006
6e8f400
12cea14
9d22eee
8c49cb6
12cea14
24622c4
217b585
 
12cea14
9d22eee
8c49cb6
12cea14
 
 
6e8f400
d78ed99
b47b51e
0256ee3
 
 
 
 
2374038
 
 
 
 
 
 
 
 
 
 
 
8cb7546
d16cee2
 
 
 
 
67109fc
d16cee2
adb0416
 
d16cee2
10f9b3c
7ec1b66
10f9b3c
daf60ae
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
import gradio as gr
from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
import pandas as pd
from apscheduler.schedulers.background import BackgroundScheduler
from huggingface_hub import snapshot_download

from src.about import (
    CITATION_BUTTON_LABEL,
    CITATION_BUTTON_TEXT,
    EVALUATION_QUEUE_TEXT,
    INTRODUCTION_TEXT,
    LLM_BENCHMARKS_TEXT,
    TITLE,
)
from src.display.css_html_js import custom_css
from src.display.utils import (
    BENCHMARK_COLS,
    COLS,
    EVAL_COLS,
    EVAL_TYPES,
    AutoEvalColumn,
    ModelType,
    fields,
    WeightType,
    Precision
)
from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
from src.populate import get_evaluation_queue_df, get_leaderboard_df
from src.submission.submit import add_new_eval

loggedin = False

def check_login(profile: gr.OAuthProfile | None) -> bool:
    if profile is None:
        return False
    return True

def restart_space():
    API.restart_space(repo_id=REPO_ID)

### Space initialisation
try:
    print(EVAL_REQUESTS_PATH)
    snapshot_download(
        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
    )
except Exception:
    restart_space()
try:
    print(EVAL_RESULTS_PATH)
    snapshot_download(
        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
    )
except Exception:
    restart_space()


LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)

(
    finished_eval_queue_df,
    running_eval_queue_df,
    pending_eval_queue_df,
) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)

def init_leaderboard(dataframe):
    # if dataframe is None or dataframe.empty:
    #     raise ValueError("Leaderboard DataFrame is empty or None.")
    # print(dataframe.columns)
    return Leaderboard(
        value=dataframe,
        datatype=[c.type for c in fields(AutoEvalColumn)],
        select_columns=SelectColumns(
            default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
            cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
            label="Select Columns to Display:",
        ),
        search_columns=[AutoEvalColumn.model.name],
        hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
        filter_columns=[
            # ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
            # ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
            # ColumnFilter(
            #     AutoEvalColumn.params.name,
            #     type="slider",
            #     min=0.01,
            #     max=150,
            #     label="Select the number of parameters (B)",
            # ),
            # ColumnFilter(
            #     AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
            # ),
        ],
        bool_checkboxgroup_label="Hide models",
        interactive=False,
    )


demo = gr.Blocks(css=custom_css)
with demo:
    gr.HTML(TITLE)
    gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
    login_button = gr.LoginButton(elem_id="oauth-button")


    with gr.Tabs(elem_classes="tab-buttons") as tabs:
        with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
            leaderboard = init_leaderboard(LEADERBOARD_DF)

        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")

        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
            # with gr.Column():
            #     with gr.Row():
            #         gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")

                # with gr.Column():
                    # with gr.Accordion(
                    #     f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
                    #     open=False,
                    # ):
                    #     with gr.Row():
                    #         finished_eval_table = gr.components.Dataframe(
                    #             value=finished_eval_queue_df,
                    #             headers=EVAL_COLS,
                    #             datatype=EVAL_TYPES,
                    #             row_count=5,
                    #         )
                    # with gr.Accordion(
                    #     f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
                    #     open=False,
                    # ):
                    #     with gr.Row():
                    #         running_eval_table = gr.components.Dataframe(
                    #             value=running_eval_queue_df,
                    #             headers=EVAL_COLS,
                    #             datatype=EVAL_TYPES,
                    #             row_count=5,
                    #         )

                    # with gr.Accordion(
                    #     f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
                    #     open=False,
                    # ):
                    #     with gr.Row():
                    #         pending_eval_table = gr.components.Dataframe(
                    #             value=pending_eval_queue_df,
                    #             headers=EVAL_COLS,
                    #             datatype=EVAL_TYPES,
                    #             row_count=5,

            with gr.Row():
                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")

            with gr.Row():
                with gr.Column():
                    model_name_textbox = gr.Textbox(label="Model name")
                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
                    model_type = gr.Dropdown(
                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
                        label="Model type",
                        multiselect=False,
                        value=None,
                        interactive=True,
                    )

                with gr.Column():
                    precision = gr.Dropdown(
                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
                        label="Precision",
                        multiselect=False,
                        value="float16",
                        interactive=True,
                    )
                    weight_type = gr.Dropdown(
                        choices=[i.value.name for i in WeightType],
                        label="Weights type",
                        multiselect=False,
                        value="Original",
                        interactive=True,
                    )
                    base_model_name_textbox = gr.Textbox(label="Организация")
                    ans_file = gr.File(label="Arena Hard Answer File", file_types=["json","jsonl"])
            loggedin = login_button.click(check_login)

            submit_button = gr.Button("Submit Eval")
            submission_result = gr.Markdown()
            submit_button.click(
                    add_new_eval,
                    [
                        model_name_textbox,
                        base_model_name_textbox,
                        revision_name_textbox,
                        precision,
                        weight_type,
                        model_type,
                        ans_file,
                    ],
                    submission_result,
                )

    with gr.Row():
        with gr.Accordion("📙 Citation", open=False):
            citation_button = gr.Textbox(
                value=CITATION_BUTTON_TEXT,
                label=CITATION_BUTTON_LABEL,
                lines=20,
                elem_id="citation-button",
                show_copy_button=True,
            )

scheduler = BackgroundScheduler()
# scheduler.add_job(restart_space, "interval", seconds=1800)
scheduler.start()
demo.queue(default_concurrency_limit=40).launch()