evals-lab 0.3.0 → 0.4.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +36 -0
- package/README.md +68 -141
- package/lab/VERSION +1 -1
- package/lab/evals-core.mjs +90 -19
- package/lab/run-evals.js +2 -2
- package/lab/server.py +165 -52
- package/lab/web/dist/assets/{gallery-DRBlZ8mP.js → gallery-B-7oyY37.js} +1 -1
- package/lab/web/dist/assets/main-BkZTEix2.js +21 -0
- package/lab/web/dist/assets/{main-wfqC6HcM.css → main-C_b7QoTv.css} +1 -1
- package/lab/web/dist/assets/tokens-DLRdTFGY.js +55 -0
- package/lab/web/dist/gallery.html +2 -2
- package/lab/web/dist/index.html +3 -3
- package/package.json +1 -1
- package/lab/web/dist/assets/main-DMpQmW8l.js +0 -21
- package/lab/web/dist/assets/tokens-iGpvbD5R.js +0 -55
|
@@ -5,8 +5,8 @@
|
|
|
5
5
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
6
6
|
<meta name="color-scheme" content="dark light">
|
|
7
7
|
<title>Components</title>
|
|
8
|
-
<script type="module" crossorigin src="/assets/gallery-
|
|
9
|
-
<link rel="modulepreload" crossorigin href="/assets/tokens-
|
|
8
|
+
<script type="module" crossorigin src="/assets/gallery-B-7oyY37.js"></script>
|
|
9
|
+
<link rel="modulepreload" crossorigin href="/assets/tokens-DLRdTFGY.js">
|
|
10
10
|
<link rel="stylesheet" crossorigin href="/assets/tokens-BEn6_hVz.css">
|
|
11
11
|
<link rel="stylesheet" crossorigin href="/assets/gallery-DFeJkfUw.css">
|
|
12
12
|
</head>
|
package/lab/web/dist/index.html
CHANGED
|
@@ -5,10 +5,10 @@
|
|
|
5
5
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
6
6
|
<meta name="color-scheme" content="dark light">
|
|
7
7
|
<title>Evals Lab</title>
|
|
8
|
-
<script type="module" crossorigin src="/assets/main-
|
|
9
|
-
<link rel="modulepreload" crossorigin href="/assets/tokens-
|
|
8
|
+
<script type="module" crossorigin src="/assets/main-BkZTEix2.js"></script>
|
|
9
|
+
<link rel="modulepreload" crossorigin href="/assets/tokens-DLRdTFGY.js">
|
|
10
10
|
<link rel="stylesheet" crossorigin href="/assets/tokens-BEn6_hVz.css">
|
|
11
|
-
<link rel="stylesheet" crossorigin href="/assets/main-
|
|
11
|
+
<link rel="stylesheet" crossorigin href="/assets/main-C_b7QoTv.css">
|
|
12
12
|
</head>
|
|
13
13
|
<body>
|
|
14
14
|
<div id="root"></div>
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "evals-lab",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.4.1",
|
|
4
4
|
"description": "A browser bench for grading what a model answers: two wordings side by side over a set of files, scored against answers fixed in advance.",
|
|
5
5
|
"license": "SEE LICENSE IN LICENSE.md",
|
|
6
6
|
"author": "Grainbox Limited",
|