Spaces:
Running
Running
Commit
Β·
abe371d
1
Parent(s):
545a4a4
add
Browse files
app.py
CHANGED
@@ -80,8 +80,6 @@ def init_leaderboard(dataframe):
|
|
80 |
column_widths=[180, 60, 80, 80, 80, 80, 60],
|
81 |
)
|
82 |
|
83 |
-
|
84 |
-
|
85 |
# return Leaderboard(
|
86 |
# value=dataframe,
|
87 |
# datatype=[c.type for c in fields(AutoEvalColumn)],
|
@@ -127,95 +125,95 @@ with demo:
|
|
127 |
leaderboard = init_leaderboard(leaderboard_dict[t])
|
128 |
|
129 |
|
130 |
-
with gr.TabItem("π About", elem_id="llm-benchmark-tab-table", id=2):
|
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 |
-
|
217 |
-
|
218 |
-
|
219 |
|
220 |
with gr.Row():
|
221 |
# gr.Markdown()
|
|
|
80 |
column_widths=[180, 60, 80, 80, 80, 80, 60],
|
81 |
)
|
82 |
|
|
|
|
|
83 |
# return Leaderboard(
|
84 |
# value=dataframe,
|
85 |
# datatype=[c.type for c in fields(AutoEvalColumn)],
|
|
|
125 |
leaderboard = init_leaderboard(leaderboard_dict[t])
|
126 |
|
127 |
|
128 |
+
# with gr.TabItem("π About", elem_id="llm-benchmark-tab-table", id=2):
|
129 |
+
# gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
130 |
+
|
131 |
+
with gr.TabItem("π Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
|
132 |
+
with gr.Column():
|
133 |
+
with gr.Row():
|
134 |
+
gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
|
135 |
+
|
136 |
+
with gr.Column():
|
137 |
+
with gr.Accordion(
|
138 |
+
f"β
Finished Evaluations ({len(finished_eval_queue_df)})",
|
139 |
+
open=False,
|
140 |
+
):
|
141 |
+
with gr.Row():
|
142 |
+
finished_eval_table = gr.components.Dataframe(
|
143 |
+
value=finished_eval_queue_df,
|
144 |
+
headers=EVAL_COLS,
|
145 |
+
datatype=EVAL_TYPES,
|
146 |
+
row_count=5,
|
147 |
+
)
|
148 |
+
with gr.Accordion(
|
149 |
+
f"π Running Evaluation Queue ({len(running_eval_queue_df)})",
|
150 |
+
open=False,
|
151 |
+
):
|
152 |
+
with gr.Row():
|
153 |
+
running_eval_table = gr.components.Dataframe(
|
154 |
+
value=running_eval_queue_df,
|
155 |
+
headers=EVAL_COLS,
|
156 |
+
datatype=EVAL_TYPES,
|
157 |
+
row_count=5,
|
158 |
+
)
|
159 |
+
|
160 |
+
with gr.Accordion(
|
161 |
+
f"β³ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
|
162 |
+
open=False,
|
163 |
+
):
|
164 |
+
with gr.Row():
|
165 |
+
pending_eval_table = gr.components.Dataframe(
|
166 |
+
value=pending_eval_queue_df,
|
167 |
+
headers=EVAL_COLS,
|
168 |
+
datatype=EVAL_TYPES,
|
169 |
+
row_count=5,
|
170 |
+
)
|
171 |
+
with gr.Row():
|
172 |
+
gr.Markdown("# βοΈβ¨ Submit your model here!", elem_classes="markdown-text")
|
173 |
+
|
174 |
+
with gr.Row():
|
175 |
+
with gr.Column():
|
176 |
+
model_name_textbox = gr.Textbox(label="Model name")
|
177 |
+
revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
|
178 |
+
model_type = gr.Dropdown(
|
179 |
+
choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
|
180 |
+
label="Model type",
|
181 |
+
multiselect=False,
|
182 |
+
value=None,
|
183 |
+
interactive=True,
|
184 |
+
)
|
185 |
+
|
186 |
+
with gr.Column():
|
187 |
+
precision = gr.Dropdown(
|
188 |
+
choices=[i.value.name for i in Precision if i != Precision.Unknown],
|
189 |
+
label="Precision",
|
190 |
+
multiselect=False,
|
191 |
+
value="float16",
|
192 |
+
interactive=True,
|
193 |
+
)
|
194 |
+
weight_type = gr.Dropdown(
|
195 |
+
choices=[i.value.name for i in WeightType],
|
196 |
+
label="Weights type",
|
197 |
+
multiselect=False,
|
198 |
+
value="Original",
|
199 |
+
interactive=True,
|
200 |
+
)
|
201 |
+
base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
|
202 |
+
|
203 |
+
submit_button = gr.Button("Submit Eval")
|
204 |
+
submission_result = gr.Markdown()
|
205 |
+
submit_button.click(
|
206 |
+
add_new_eval,
|
207 |
+
[
|
208 |
+
model_name_textbox,
|
209 |
+
base_model_name_textbox,
|
210 |
+
revision_name_textbox,
|
211 |
+
precision,
|
212 |
+
weight_type,
|
213 |
+
model_type,
|
214 |
+
],
|
215 |
+
submission_result,
|
216 |
+
)
|
217 |
|
218 |
with gr.Row():
|
219 |
# gr.Markdown()
|