Building a local legal drafting LLM — no dataset?

<!-- SC_OFF --><div class="md"><p>Hi everyone,</p> <p>I’m currently working on a project to build a <strong>100% local AI chatbot</strong> for a government-related use case

<!-- SC_OFF --><div class="md"><p>Fine-tuning an LLM for Japanese translation of legal documents like birth certificates, relationship certificates, character certificates,

<!-- SC_OFF --><div class="md"><p>There are thoughts going on about using AI to manage workflows in company, but this might involve feeding the AI database sensitive data. </p>

<!-- SC_OFF --><div class="md"><p>Hello everyone,</p> <p>I’m looking for an AI that runs entirely locally on my PC, without needing an internet connection.</p> <p>I’d like it to

<!-- SC_OFF --><div class="md"><p>One thing keeps coming up:</p> <p>Models often produce very confident legal answers, but the citations are either missing, outdated, or not

<!-- SC_OFF --><div class="md"><p>Hello everyone, I am currently building a RAG pipeline. Since it involves highly sensitive medical data, I have deployed the models locally to

<!-- SC_OFF --><div class="md"><p><strong>TL;DR</strong>: Released en_legal_ner_ind_trf v0.1 - InLegalBERT fine-tuned on ~34,700 silver-annotated chunks from 33k Indian SC

<!-- SC_OFF --><div class="md"><p>Trying to auto categorize a former employees photos from personal and work related. It’s a lot of photos and I don’t want the guy to loose