dis way, the person cn finally use their smart knowledge instead of doing boring work at company <3

i rlli hav to get a better structure for my funis on 196 so peeps dun ignore… current way is jus me infodumpin n evn peeps who lik my posts dun see them, cuz they r jus so boring to look at… fair point ;(

anyway i hop dis one … is a bit intrsting…

EDIT:
im so srri to tell u peeps… turns out all of u liv lik 500 years away!! ;( i rlli wish i cud visit u peeps n we cud rlli do dis!!! if someone near Germany - Rheinlandpfalz - hit me up we’ll try do dis!!!

if not- -lik if u liv in US, pls maybsies find othr peeps in comments to do similr thing!!! yall peeps prolli mor comf to be aorund than me soo u cn jus hav ur own magical adventrrrr <3 <3

  • Smorty [she/her]OP
    link
    fedilink
    English
    arrow-up
    3
    ·
    1 day ago

    hmmm ysiyis ur right! <3 the methods ur refern to are

    • standard fine-tuning (LoRa or full)
    • model merging
    • distilling

    n ---- yis these approachs wrok, bt thads all using boring, predicatbl, python or javascript libraries… n i dun lik using premade boring sutuff! i wan to learn fulli!!! how to back-propagate myself! how to actulli adjust params from bac to fron. i wan to kno which percentg of the reuestd change in fron is de bias change, how mch de weights change from back activations, n how that split goes, u kno? maybsies is jus 50% n im bein dum bout it >v<

    nt borin librari!!! lets mek own, supr slo, bad librari which does job!!! becuzz!!!

    • we lern!! ~ 📘 🏫
    • we undrstnd blobcat, thinksmart
    • we cn say “we made dis” n open-sourc it <3
    • we fel comfff when doin it! ~ ~ <3 🧸 🛌 💖 🍼 👩‍🍼

    n thos r good reason!!

    i dun wan “experience using premade boring framewrorkrs”. i wan to

    • build own train n inference pipelin
    • curate own dataset (totalli curated, nt jus scraped from wikipeda >v<)
    • run modl n see it genrate gibbrish wif som wikipeda syntax!!!

    n thn release, open sourc n feel comf <3

    dis whad i wan!! ~ ~

    • theneverfox@pawb.social
      link
      fedilink
      English
      arrow-up
      1
      ·
      24 hours ago

      Hmm… Well if you want to learn how to build a car you could kidnap an auto engineer, or you could find a really simple car and rip it apart to get to its delicious secrets

      At least that’s what I’d do, I’m an engineer, not a mathematician. If you understand what they’re trying to do and you can see how they did it, you can play with the pieces until you understand. And that way, you can learn things they never knew when they built it

      • Smorty [she/her]OP
        link
        fedilink
        English
        arrow-up
        1
        ·
        24 hours ago

        yisyis bt i wan to hav nvidia prsn so they cn finalli do fun stuff with their knoledg instead of boring finfance n bugfixes ;(

        • theneverfox@pawb.social
          link
          fedilink
          English
          arrow-up
          1
          ·
          23 hours ago

          Well if you do, try to grab someone from the team doing the new robotics models…I want to take that apart and play with it XD

          • Smorty [she/her]OP
            link
            fedilink
            English
            arrow-up
            1
            ·
            21 hours ago

            isn’t Nvidias Groot N1 model already openly available?.. or am i confus…