DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to rewrite a report while keeping chosen quotes word for word with Humanizer Local Model

Import a Word or PDF report and mark the passages that must stay exactly as written.

Authorization notice. Humanizer Local Model is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA policy analyst or project lead who has an AI-drafted report with exact quotes or figures that must not change.

The problemA general rewrite can alter a quote or a figure, and the author needs certain passages to stay verbatim.

The outcomeA rewritten report where the selected passages appear unchanged and are highlighted in both the draft and the rewrite.

What you need first

  • A Mac with Apple silicon (M1 or newer) or a Windows x64 PC, for the app
  • Enough free disk space and memory for the model; the app suggests a size for your machine, down to 8 GB machines
  • Python 3.8 or newer for the hz command line tool
  • llama.cpp (llama-server), curl and jq for the one-command server route

Steps

  1. Install the app for your computer from the Quick start section and open it.
  2. Import the text of your Word (.docx) or PDF file using the app.
  3. Select the passage that must stay exact, then click Create fact.
  4. Click rewrite and wait for the result; check that the kept passages are highlighted in the draft and the rewrite.
  5. Edit the draft if needed and run again, since the draft stays editable after a rewrite.

Prompt for your agent

Using the sgaofen/humanizer-local-model repo app, import <path-to-report.docx> and mark the passages listed in <passages.txt> with Create fact before rewriting. Expected output: a rewritten report in which each marked passage appears word for word. Verify that each marked passage is highlighted in the rewrite and matches the original exactly.

Caveat. The README says the model still changes details in some rewrites, so anything not marked with Create fact still needs checking.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page