Commit
·
254da86
1
Parent(s):
8526c25
added about and changed column names
Browse files- app.py +10 -1
- src/display/about.py +20 -4
app.py
CHANGED
@@ -8,6 +8,8 @@ os.environ['CURL_CA_BUNDLE'] = ''
|
|
8 |
from src.display.about import (
|
9 |
EVALUATION_QUEUE_TEXT,
|
10 |
INTRODUCTION_TEXT,
|
|
|
|
|
11 |
TITLE,
|
12 |
)
|
13 |
from src.display.css_html_js import custom_css
|
@@ -232,6 +234,13 @@ with demo:
|
|
232 |
datatype=EVAL_TYPES,
|
233 |
row_count=5,
|
234 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
235 |
with gr.Row():
|
236 |
gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
|
237 |
|
@@ -246,7 +255,7 @@ with demo:
|
|
246 |
choices=['safetensors', 'gguf'],
|
247 |
label="Weights type",
|
248 |
multiselect=False,
|
249 |
-
value='
|
250 |
interactive=True,
|
251 |
)
|
252 |
|
|
|
8 |
from src.display.about import (
|
9 |
EVALUATION_QUEUE_TEXT,
|
10 |
INTRODUCTION_TEXT,
|
11 |
+
LLM_BENCHMARKS_TEXT,
|
12 |
+
LLM_DATASET_TEXT,
|
13 |
TITLE,
|
14 |
)
|
15 |
from src.display.css_html_js import custom_css
|
|
|
234 |
datatype=EVAL_TYPES,
|
235 |
row_count=5,
|
236 |
)
|
237 |
+
with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
|
238 |
+
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
239 |
+
|
240 |
+
with gr.TabItem("📝 Evaluation Datasets", elem_id="llm-benchmark-tab-table", id=4):
|
241 |
+
gr.Markdown(LLM_DATASET_TEXT, elem_classes="markdown-text")
|
242 |
+
|
243 |
+
|
244 |
with gr.Row():
|
245 |
gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
|
246 |
|
|
|
255 |
choices=['safetensors', 'gguf'],
|
256 |
label="Weights type",
|
257 |
multiselect=False,
|
258 |
+
value='safgit petensors',
|
259 |
interactive=True,
|
260 |
)
|
261 |
|
src/display/about.py
CHANGED
@@ -12,10 +12,14 @@ class Task:
|
|
12 |
class Tasks(Enum):
|
13 |
# task_key in the json file, metric_key in the json file, name to display in the leaderboard
|
14 |
task0 = Task("MMLU", "metric_name", "MMLU")
|
15 |
-
task1 = Task("
|
16 |
-
task2 = Task("
|
17 |
-
task3 = Task("
|
18 |
-
task4 = Task("
|
|
|
|
|
|
|
|
|
19 |
|
20 |
|
21 |
# Your leaderboard name
|
@@ -31,6 +35,18 @@ If you have a fine-tuned Azerbaijani LLM, submit it for evaluation!
|
|
31 |
|
32 |
"""
|
33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
EVALUATION_QUEUE_TEXT = """
|
36 |
## Some good practices before submitting a model
|
|
|
12 |
class Tasks(Enum):
|
13 |
# task_key in the json file, metric_key in the json file, name to display in the leaderboard
|
14 |
task0 = Task("MMLU", "metric_name", "MMLU")
|
15 |
+
task1 = Task("Synthetic_QA", "metric_name", "Synthetic_QA")
|
16 |
+
task2 = Task("Support_MC", "metric_name", "Support_MC")
|
17 |
+
task3 = Task("Context_QA", "metric_name", "Context_QA")
|
18 |
+
task4 = Task("Banking_MC", "metric_name", "Banking_MC")
|
19 |
+
task5 = Task("ARC", "metric_name", "ARC")
|
20 |
+
task6 = Task("Binary_QA", "metric_name", "Binary_QA")
|
21 |
+
task7 = Task("ANL_Quad", "metric_name", "ANL_Quad")
|
22 |
+
|
23 |
|
24 |
|
25 |
# Your leaderboard name
|
|
|
35 |
|
36 |
"""
|
37 |
|
38 |
+
LLM_BENCHMARKS_TEXT = f"""
|
39 |
+
## How it works
|
40 |
+
## Reproducibility
|
41 |
+
HERE we have about part
|
42 |
+
"""
|
43 |
+
|
44 |
+
LLM_DATASET_TEXT = f"""
|
45 |
+
## How it works
|
46 |
+
## Reproducibility
|
47 |
+
HERE we have about part
|
48 |
+
"""
|
49 |
+
|
50 |
|
51 |
EVALUATION_QUEUE_TEXT = """
|
52 |
## Some good practices before submitting a model
|