TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Developing an LLM: Building, Training, Finetuning (A 1h Video Explainer)

43 pointsby rasbt11 months ago

4 comments

htrp11 months ago
Not Sebastian (who I assume is the OP), but his blog&#x2F;substack is also a great resource<p><a href="https:&#x2F;&#x2F;magazine.sebastianraschka.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;magazine.sebastianraschka.com&#x2F;</a>
评论 #40680719 未加载
mdp202111 months ago
Seems very good, thank you.<p>The channel: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;@SebastianRaschka&#x2F;videos" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;@SebastianRaschka&#x2F;videos</a><p>contains hundreds of video lessons, originally seemingly originating from Sebastian Raschka teaching at Wisconsin-Madison Uni (before he went full-time entrepreneur).
评论 #40680443 未加载
yoouareperfect11 months ago
Is anyone training LLMs outside of Meta, OpenAI, etc... ?<p>I don&#x27;t much get the point. For huge models, it&#x27;s impossible to outcompete them. For smaller models, isn&#x27;t mistral or LLaMa good enough?<p>What are other startups finetuning LLMs for?
评论 #40680758 未加载
评论 #40685371 未加载
评论 #40680622 未加载
oneshtein11 months ago
Can someone train an AI to perform all that?