<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Evo2 on TPOW Lab</title><link>https://tpow-001.netlify.app/tags/evo2/</link><description>Recent content in Evo2 on TPOW Lab</description><generator>Hugo</generator><language>en</language><copyright>Copyright &amp;copy; 2025-2026 TPOW-001. All Rights Reserved.</copyright><lastBuildDate>Tue, 02 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://tpow-001.netlify.app/tags/evo2/index.xml" rel="self" type="application/rss+xml"/><item><title>Tutorial: NVIDIA-BioNeMo/bionemo-framework — 完整解讀（biopharma foundation model 訓練引擎，含 ESM-2 / AMPLIFY / Evo2 / Geneformer / CodonFM / MoCo 全套 recipes）</title><link>https://tpow-001.netlify.app/post/2026-06-02-bionemo-framework-tutorial/</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><guid>https://tpow-001.netlify.app/post/2026-06-02-bionemo-framework-tutorial/</guid><description><![CDATA[<h1 id="nvidia-bionemobionemo-framework-完整教學" data-numberify>NVIDIA-BioNeMo/bionemo-framework 完整教學<a class="anchor ms-1" href="#nvidia-bionemobionemo-framework-完整教學"></a></h1>
<blockquote>
<p><strong>一句話定位</strong>：NVIDIA Clara BioPharma 平台的<strong>訓練引擎開源層</strong> — GPU 高度最佳化的 recipe 與工具集，把 NVIDIA 在 LLM 上的全套絕活（<strong>TransformerEngine FP8/MXFP8/NVFP4</strong> 低精度、<strong>megatron-FSDP</strong>、<strong>context parallel</strong>、<strong>sequence packing</strong>、<strong>Hopper / Blackwell</strong> 架構優化）搬到 biopharma 領域：從 <strong>蛋白質</strong>（ESM-2 8M→15B、AMPLIFY）、<strong>單細胞 RNA</strong>（Geneformer）、<strong>基因體</strong>（Evo2 1B→40B，1M+ nt context）、<strong>codon</strong>（CodonFM 1B/5B）、<strong>生成式小分子</strong>（MoCo 系列 interpolant：DDPM/VDM/CFM/D3PM/MDLM/DFM），到通用 LLM（Llama3 144K context、Mixtral MoE、Qwen2.5/3）的 biopharma 適配版。整合 <strong>NVIDIA AI 全家桶</strong>（Megatron-Bridge / Automodel / TransformerEngine / NIM），是 NVIDIA/BioNeMo Blueprint hub 的<strong>底層引擎</strong>。</p>]]></description></item><item><title>Tutorial: NVIDIA-BioNeMo/bionemo-framework — 完整解讀（biopharma foundation model 訓練引擎，含 ESM-2 / AMPLIFY / Evo2 / Geneformer / CodonFM / MoCo 全套 recipes）</title><link>https://tpow-001.netlify.app/post/2026-06-02-bionemo-framework/</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><guid>https://tpow-001.netlify.app/post/2026-06-02-bionemo-framework/</guid><description><![CDATA[<h1 id="nvidia-bionemobionemo-framework-完整教學" data-numberify>NVIDIA-BioNeMo/bionemo-framework 完整教學<a class="anchor ms-1" href="#nvidia-bionemobionemo-framework-完整教學"></a></h1>
<blockquote>
<p><strong>一句話定位</strong>：NVIDIA Clara BioPharma 平台的<strong>訓練引擎開源層</strong> — GPU 高度最佳化的 recipe 與工具集，把 NVIDIA 在 LLM 上的全套絕活（<strong>TransformerEngine FP8/MXFP8/NVFP4</strong> 低精度、<strong>megatron-FSDP</strong>、<strong>context parallel</strong>、<strong>sequence packing</strong>、<strong>Hopper / Blackwell</strong> 架構優化）搬到 biopharma 領域：從 <strong>蛋白質</strong>（ESM-2 8M→15B、AMPLIFY）、<strong>單細胞 RNA</strong>（Geneformer）、<strong>基因體</strong>（Evo2 1B→40B，1M+ nt context）、<strong>codon</strong>（CodonFM 1B/5B）、<strong>生成式小分子</strong>（MoCo 系列 interpolant：DDPM/VDM/CFM/D3PM/MDLM/DFM），到通用 LLM（Llama3 144K context、Mixtral MoE、Qwen2.5/3）的 biopharma 適配版。整合 <strong>NVIDIA AI 全家桶</strong>（Megatron-Bridge / Automodel / TransformerEngine / NIM），是 NVIDIA/BioNeMo Blueprint hub 的<strong>底層引擎</strong>。</p>]]></description></item><item><title>Tutorial: NVIDIA/BioNeMo — BioPharma Developer Asset Hub 完整解讀（生物製藥版 Nemotron：25+ 開源模型 / 10+ NIM 微服務 / 8 個 GPU 函式庫 / 完整藥物開發流程）</title><link>https://tpow-001.netlify.app/post/2026-06-02-bionemo-hub-tutorial/</link><pubDate>Tue, 02 Jun 2026 00:00:00 +0000</pubDate><guid>https://tpow-001.netlify.app/post/2026-06-02-bionemo-hub-tutorial/</guid><description><![CDATA[<h1 id="nvidia-bionemohub-repo完整教學" data-numberify>NVIDIA BioNeMo（Hub Repo）完整教學<a class="anchor ms-1" href="#nvidia-bionemohub-repo完整教學"></a></h1>
<blockquote>
<p><strong>一句話定位</strong>：NVIDIA 在 <strong>BioPharma 領域</strong>的官方 <strong>Developer Asset Hub</strong> — 不是程式庫、不是模型、不是框架，而是一份<strong>集中索引 README</strong>，把散落在 <code>NVIDIA-Digital-Bio</code> / <code>NVIDIA/bionemo-framework</code> / <code>clara-parabricks-workflows</code> / <code>NVlabs</code> / <code>build.nvidia.com</code> 的 <strong>5 大支柱（資料 / 模型 / 函式庫 / 訓練 / NIM 推論）</strong> 串成一條可導覽的入口路徑。</p>]]></description></item></channel></rss>