Spaces:
Running
Running
| <html> | |
| <head> | |
| <meta charset="utf-8" /> | |
| <meta name="viewport" content="width=device-width" /> | |
| <title>xet-repo-dedupe</title> | |
| <link rel="stylesheet" href="style.css" /> | |
| <script src="https://cdn.jsdelivr.net/npm/vega@5"></script> | |
| <script src="https://cdn.jsdelivr.net/npm/vega-lite@5"></script> | |
| <script src="https://cdn.jsdelivr.net/npm/vega-embed@6"></script> | |
| <style> | |
| #vis { | |
| width: 100%; | |
| text-align: center; | |
| } | |
| </style> | |
| </head> | |
| <body> | |
| <div class="card"> | |
| <h1>Visualizing Repo-level Dedupe</h1> | |
| <p>This visualization demonstrates the amount of <a href="https://huggingface.co/blog/from-files-to-chunks">chunk-level dedupe</a> within a repo or across a selection of repos. (For now, demonstrates a hardcoded selection.)</p> | |
| </div> | |
| <div id="vis"></div> | |
| <script> | |
| var vlSpec = { | |
| "$schema": "https://vega.github.io/schema/vega-lite/v5.json", | |
| "resolve": {"scale": {"x": "independent"}}, | |
| "width": 600, | |
| "height": 12, | |
| "data": { | |
| "url": "xorbs.json" | |
| }, | |
| "mark": "rect", | |
| "encoding": { | |
| "x": { | |
| "field": "xorb_id", | |
| "axis": null, | |
| "sort": {"field": "dedupe_factor", "order": "descending"}, | |
| "stack": "normalize" | |
| }, | |
| "color": { | |
| "field": "dedupe_factor", | |
| "type": "quantitative", | |
| "scale": {"domain": [0, 10]} | |
| }, | |
| "tooltip": {"field": "dedupe_factor"}, | |
| "row": { | |
| "field": "repo", | |
| "spacing": 1, | |
| "header": {"labelAngle": 0, "labelAlign": "left"}, | |
| "sort": {"field": "dedupe_factor", "order": "descending"} | |
| } | |
| } | |
| }; | |
| vegaEmbed('#vis', vlSpec); | |
| </script> | |
| </body> | |
| </html> | |