Spaces:
Running
Running
File size: 10,690 Bytes
dfd45d6 80b302f c963b80 dfd45d6 80b302f dfd45d6 c963b80 80b302f dfd45d6 80b302f dfd45d6 c963b80 dfd45d6 80b302f dfd45d6 80b302f dfd45d6 c963b80 dfd45d6 80b302f dfd45d6 80b302f dfd45d6 80b302f 5a5767f 80b302f dfd45d6 80b302f 0bc79d9 dfd45d6 c963b80 80b302f 0bc79d9 dfd45d6 80b302f 0bc79d9 80b302f dfd45d6 80b302f 0bc79d9 80b302f dfd45d6 80b302f 0bc79d9 80b302f dfd45d6 0bc79d9 80b302f dfd45d6 80b302f 0bc79d9 80b302f dfd45d6 0bc79d9 80b302f dfd45d6 80b302f 0bc79d9 80b302f dfd45d6 80b302f dfd45d6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
"""
handle multi_header options
"""
from st_aggrid import JsCode
from streamlit_theme import st_theme
HEADER_STYLE = {'fontSize': '18px'}
CELL_STYLE = {'fontSize': '18px'}
LINK = ' https://huggingface.co/datasets/embedding-benchmark/'
def get_dataset_url_name(field_name):
"""Convert field name to proper URL format for closed datasets"""
# Handle field names like "ClosedDataset 2 (German Legal Sentences)"
if field_name.startswith("ClosedDataset "):
# Extract the number and format it as ClosedDataset_X
if "(" in field_name:
# Extract number from "ClosedDataset 2 (description)" -> "2"
number_part = field_name.split("ClosedDataset ")[1].split(" ")[0]
return f"ClosedDataset_{number_part}"
else:
# Handle cases where it might already be in the right format or no parentheses
return field_name.replace(" ", "_")
# Return original field_name for open datasets
return field_name
def mutil_header_options(column_list: list, avg_column: str, is_section: bool):
"""
get mutil_header_options - 优化版本，减少组件实例化
:param column_list:
:param avg_column:
:param is_section:
:return:
"""
if is_section:
column_def_list = [
{'headerName': column if "Average" not in column else column.replace("Average", "").strip().capitalize(),
'field': column,
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'headerTooltip': column if "Average" not in column else column.replace("Average",
"").strip().capitalize()
# 'suppressSizeToFit': True
} for column in column_list if
column not in (avg_column, "Closed average", "Open average")]
return column_def_list
mutil_column_list = [column for column in column_list if
column not in (avg_column, "Closed average", "Open average")]
close_group_list = list(filter(lambda x: x.startswith('_') or x.startswith("ClosedDataset "), mutil_column_list))
open_group_list = list(
filter(lambda x: not x.startswith('_') and not x.startswith("ClosedDataset "), mutil_column_list))
close_group_def = {
'headerName': 'CLOSED DATASETS',
'width': 'fit-content',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'autoHeaderHeight': True,
'children': [
{'headerName': column.replace('_', ''),
'field': column,
"headerComponentParams": {
"innerHeaderComponent": "linkHeaderComponent",
"url": LINK + get_dataset_url_name(column),
"headerName": column
},
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'sortable': True,
# 'width': 150,
"suppressColumnVirtualisation": True,
} for column in close_group_list
],
}
open_group_def = {
'headerName': 'OPEN DATASETS',
'width': 'fit-content',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'autoHeaderHeight': True,
'children': [
{'headerName': column,
'field': column,
"headerComponentParams": {
"innerHeaderComponent": "linkHeaderComponent",
"url": LINK + get_dataset_url_name(column),
"headerName": column
},
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'sortable': True,
# 'width': 150,
"suppressColumnVirtualisation": True,
} for column in open_group_list
],
}
return [close_group_def, open_group_def]
def get_header_options(column_list: list, avg_column: str, is_section: bool):
grid_options = {
'columnDefs': [
{
'headerName': 'Model Name',
'field': 'model_name',
'pinned': 'left',
'sortable': False,
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'autoHeaderHeight': True,
"tooltipValueGetter": JsCode(
"""
function(p) {
console.log(p);
const value = p.data && p.data.tooltip ? p.data.tooltip : "";
const link = p.data && p.data.reference ? p.data.reference : "";
return link ? `${value} (${link})` : value;
}
"""
),
"width": 250,
'cellRenderer': JsCode("""class CustomHTML {
init(params) {
const link = params.data.reference;
this.eGui = document.createElement('div');
this.eGui.innerHTML = link ?
`<a href="${link}" class="a-cell" target="_blank">${params.value} </a>` :
params.value;
}
getGui() {
return this.eGui;
}
}"""),
'suppressSizeToFit': True,
'headerTooltip': 'Name of the embedding model being evaluated for retrieval tasks',
},
{'headerName': "Vendor",
'field': 'vendor',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'headerTooltip': 'Company or organization that developed and maintains the model',
},
{'headerName': "Overall Score",
'field': avg_column,
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'headerTooltip': 'Overall average performance score across all evaluated datasets',
},
# Add Open average column definition
{'headerName': 'Open Average',
'field': 'Open average',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'headerTooltip': 'Average NDCG@10 performance score across publicly available datasets',
},
{'headerName': 'Closed Average',
'field': 'Closed average',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'headerTooltip': 'Average NDCG@10 performance score across proprietary/restricted datasets',
},
{
'headerName': 'Embd Dtype',
'field': 'embd_dtype',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'headerTooltip': 'Data type format of the embedding vectors (e.g., float32, int8, binary)',
},
{
'headerName': 'Embd Dim',
'field': 'embd_dim',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'valueFormatter': JsCode(
"""
function(params) {
const num = params.value;
if (typeof num !== "number") return num;
if (Math.abs(num) >= 10000) {
return num.toLocaleString("en-US");
}
return num;
}
"""
),
'headerTooltip': 'Number of dimensions in the embedding vector representation',
},
{
'headerName': 'Number of Parameters',
'field': 'num_params',
'cellDataType': 'number',
"colId": "num_params",
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
'valueFormatter': JsCode(
"""function(params) {
const num = params.value;
if (num >= 1e9) return (num / 1e9).toFixed(2) + "B";
if (num >= 1e6) return (num / 1e6).toFixed(2) + "M";
if (num >= 1e3) return (num / 1e3).toFixed(2) + "K";
return num;
}"""
),
"width": 120,
# 'suppressSizeToFit': True,
'headerTooltip': 'Total number of trainable parameters in the embedding model',
},
{
'headerName': 'Context Length',
'field': 'max_tokens',
'headerClass': 'custom-header-style',
'cellClass': 'custom-cell-style',
# 'suppressSizeToFit': True,
'valueFormatter': JsCode(
"""
function(params) {
const num = params.value;
if (typeof num !== "number") return num;
if (Math.abs(num) >= 10000) {
return num.toLocaleString("en-US");
}
return num;
}
"""
),
'headerTooltip': 'Maximum number of tokens the model can process in a single input',
},
*mutil_header_options(column_list, avg_column, is_section)
],
'defaultColDef': {
'filter': True,
'sortable': True,
'resizable': True,
'headerClass': "multi-line-header",
'autoHeaderHeight': True,
'width': 105
},
"autoSizeStrategy": {
"type": 'fitCellContents',
"colIds": [column for column in column_list if column not in (avg_column, "Closed average", "Open average")]
},
"tooltipShowDelay": 500,
"suppressColumnVirtualisation": True
}
return grid_options
|