Publish standalone WALD website
Browse files
assets/{benchmarks-CWsTgd-J.json → benchmarks-PqmVdGim.json}
RENAMED
|
@@ -120,16 +120,17 @@
|
|
| 120 |
"referenceUrl": "https://huggingface.co/org2ai/Wald-4B/tree/v2.1",
|
| 121 |
"metrics": {
|
| 122 |
"jevbench": {
|
| 123 |
-
"value":
|
| 124 |
"n": 231,
|
| 125 |
-
"config": "
|
| 126 |
"policy": "Auto 0.7",
|
| 127 |
"source": {
|
| 128 |
-
"file": "results/
|
| 129 |
-
"pointer": "
|
| 130 |
-
"sha256": "
|
| 131 |
},
|
| 132 |
-
"correct":
|
|
|
|
| 133 |
},
|
| 134 |
"xl": {
|
| 135 |
"value": 67.75100892747952,
|
|
|
|
| 120 |
"referenceUrl": "https://huggingface.co/org2ai/Wald-4B/tree/v2.1",
|
| 121 |
"metrics": {
|
| 122 |
"jevbench": {
|
| 123 |
+
"value": 90.9090909090909,
|
| 124 |
"n": 231,
|
| 125 |
+
"config": "Shown as on the v2.1 model card: measured on WALD 4B v2.0 (04701-c22), Auto 0.7, at most 512 thought tokens",
|
| 126 |
"policy": "Auto 0.7",
|
| 127 |
"source": {
|
| 128 |
+
"file": "results/c16b-di-round-1007/04701-c22/report.json",
|
| 129 |
+
"pointer": "/scores/guards/full7799/gate0.7",
|
| 130 |
+
"sha256": "bcdab2e76b0e5b210ee4aceb849c14a41ddb4608b29231cdd2923e6c6ebb048f"
|
| 131 |
},
|
| 132 |
+
"correct": 210,
|
| 133 |
+
"footnote": "* Measured on WALD 4B v2.0."
|
| 134 |
},
|
| 135 |
"xl": {
|
| 136 |
"value": 67.75100892747952,
|
assets/{main-Cem4j1ET.js → main-BIb7j2FA.js}
RENAMED
|
The diff for this file is too large to render.
See raw diff
|
|
|
benchmark/index.html
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
/>
|
| 11 |
<title>WALD — Benchmark</title>
|
| 12 |
<link rel="icon" type="image/svg+xml" href="/assets/wald-mark-A8BzeTUp.svg" />
|
| 13 |
-
<script type="module" crossorigin src="/assets/main-
|
| 14 |
<link rel="stylesheet" crossorigin href="/assets/main-ClrQz15C.css">
|
| 15 |
</head>
|
| 16 |
<body>
|
|
|
|
| 10 |
/>
|
| 11 |
<title>WALD — Benchmark</title>
|
| 12 |
<link rel="icon" type="image/svg+xml" href="/assets/wald-mark-A8BzeTUp.svg" />
|
| 13 |
+
<script type="module" crossorigin src="/assets/main-BIb7j2FA.js"></script>
|
| 14 |
<link rel="stylesheet" crossorigin href="/assets/main-ClrQz15C.css">
|
| 15 |
</head>
|
| 16 |
<body>
|
index.html
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
/>
|
| 11 |
<title>WALD — Wait a bit. Look. Decide.</title>
|
| 12 |
<link rel="icon" type="image/svg+xml" href="/assets/wald-mark-A8BzeTUp.svg" />
|
| 13 |
-
<script type="module" crossorigin src="/assets/main-
|
| 14 |
<link rel="stylesheet" crossorigin href="/assets/main-ClrQz15C.css">
|
| 15 |
</head>
|
| 16 |
<body>
|
|
|
|
| 10 |
/>
|
| 11 |
<title>WALD — Wait a bit. Look. Decide.</title>
|
| 12 |
<link rel="icon" type="image/svg+xml" href="/assets/wald-mark-A8BzeTUp.svg" />
|
| 13 |
+
<script type="module" crossorigin src="/assets/main-BIb7j2FA.js"></script>
|
| 14 |
<link rel="stylesheet" crossorigin href="/assets/main-ClrQz15C.css">
|
| 15 |
</head>
|
| 16 |
<body>
|
use-cases/index.html
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
/>
|
| 11 |
<title>WALD — Use Cases</title>
|
| 12 |
<link rel="icon" type="image/svg+xml" href="/assets/wald-mark-A8BzeTUp.svg" />
|
| 13 |
-
<script type="module" crossorigin src="/assets/main-
|
| 14 |
<link rel="stylesheet" crossorigin href="/assets/main-ClrQz15C.css">
|
| 15 |
</head>
|
| 16 |
<body>
|
|
|
|
| 10 |
/>
|
| 11 |
<title>WALD — Use Cases</title>
|
| 12 |
<link rel="icon" type="image/svg+xml" href="/assets/wald-mark-A8BzeTUp.svg" />
|
| 13 |
+
<script type="module" crossorigin src="/assets/main-BIb7j2FA.js"></script>
|
| 14 |
<link rel="stylesheet" crossorigin href="/assets/main-ClrQz15C.css">
|
| 15 |
</head>
|
| 16 |
<body>
|