• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Brendan Foody Recommends Edward's LoRA Post-Training Blog

    Mercor CEO highlights Edward's blog for open-source model post-training.

    PM
    B(
    AS
    3 Sources, 27d ago, first seen 27d ago

    TLDR

    Brendan Foody, identified as co-founder and CEO of Mercor, an AI talent marketplace, made a statement about a blog post. He noted that Edward, who created LoRA for fine-tuning, authored material on post-training open-source models. Foody encouraged readers involved in post-training to examine the post. The comment comes from a public social media post by the account @BrendanFoody. It positions the blog as useful guidance for those working on such tasks. The evidence consists solely of this quoted recommendation without additional context or verification of the blog's existence beyond the mention.

    Combined views

    162.6K

    3 Sources, first seen 27d ago

    Combined views

    162.6K

    3 Sources, first seen 27d ago

    1.5K likes
    1.5K likes
    14 comments
    2.2K saves
    206 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    14 comments
    2.2K saves
    206 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    3 Sources

    @adithya_s_k[Must Read] One of the best open-source writeups I've seen on actually doing RL training for knowledge-work agents at scale.
    @BrendanFoodyEdward, the creator of LoRA (fine-tuning), wrote a blog post on how to post-train open-source models. I strongly encourage checking this out for anyone who's post-training.
    @PMinerviniRT @adithya_s_k: [Must Read] One of the best open-source writeups I've seen on actually doing RL training for knowledge-work agents at sca…

    3 Sources

    @adithya_s_k[Must Read] One of the best open-source writeups I've seen on actually doing RL training for knowledge-work agents at scale.
    @BrendanFoodyEdward, the creator of LoRA (fine-tuning), wrote a blog post on how to post-train open-source models. I strongly encourage checking this out for anyone who's post-training.
    @PMinerviniRT @adithya_s_k: [Must Read] One of the best open-source writeups I've seen on actually doing RL training for knowledge-work agents at sca…