index.html

<!doctype html><html><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1">
<title>Providus AI</title><style>
body{font-family:ui-sans-serif,system-ui,-apple-system,Segoe UI,sans-serif;max-width:760px;margin:0 auto;padding:16px;line-height:1.55;color:#111827;background:#fff}
h1{font-size:1.6rem;margin:.2rem 0 .6rem}h2{font-size:1.15rem;margin:1.4rem 0 .5rem}
table{border-collapse:collapse;width:100%;font-size:.92rem}th,td{border-bottom:1px solid #e5e7eb;padding:6px 8px;text-align:left;vertical-align:top}
pre{background:rgba(127,127,127,.16);color:inherit;padding:10px 12px;border-radius:8px;white-space:pre-wrap;overflow-wrap:anywhere;font-size:.85rem}code{font-size:.88em;color:inherit;background:none}
a{color:#2563eb;text-decoration:none}a:hover{text-decoration:underline}
@media (prefers-color-scheme:dark){body{background:#0b0f19;color:#e5e7eb}th,td{border-color:#1f2937}a{color:#60a5fa}}
</style></head><body><h1>Providus AI</h1>
<p>We build document AI that runs where your documents live: on your own servers or in our cloud.
Our open models read document pages (text, headings, tables and charts) and turn them into clean Markdown.</p>
<h2>providus-vl-mini</h2>
<p>An open-weight document parsing model, a fine-tune of MinerU2.5-Pro by OpenDataLab (Apache-2.0).</p>
<ul>
<li><strong>78.96 ± 0.04 on ParseBench</strong> (mean of 4 full runs). On ParseBench's leaderboard (b9ba246, 2026-10-12) it would place first among open-weight models.</li>
<li><strong>Zero per-page fees:</strong> providus-vl-mini is free to use under Apache-2.0. Your only cost is your own hardware.</li>
</ul>
<table>
<thead>
<tr>
<th>Repo</th>
<th>What it is</th>
</tr>
</thead>
<tbody>
<tr>
<td><a href="https://huggingface.co/ProvidusAI/providus-vl-mini">providus-vl-mini</a></td>
<td>The full model, for vLLM on a GPU server (access approved automatically)</td>
</tr>
<tr>
<td><a href="https://huggingface.co/ProvidusAI/providus-vl-mini-GGUF">providus-vl-mini-GGUF</a></td>
<td>One file for LM Studio, llama.cpp and Ollama (open, no login)</td>
</tr>
<tr>
<td><a href="https://github.com/ProvidusAI/providus-parse-tools">providus-parse-tools</a></td>
<td>The pipeline that turns pages into Markdown (<code>pip install providus-parse-tools</code>)</td>
</tr>
</tbody>
</table>
<h2>Try it on your laptop (LM Studio)</h2>
<pre><code>lms get https://huggingface.co/ProvidusAI/providus-vl-mini-GGUF
lms load providus-vl-mini --context-length 8192 --identifier providus-vl-mini
lms server start
pip install providus-parse-tools==1.0.0
</code></pre>
<p>Then point the pipeline at <code>http://127.0.0.1:1234</code>. The model card has the full steps for LM Studio, llama.cpp and Ollama.</p>
<p>If you like our work, please follow us here, like the models and star the repo on GitHub.</p>
<p><a href="https://providus.ai">providus.ai</a> · <a href="https://github.com/ProvidusAI">GitHub</a></p></body></html>