Bobinas P4G
  • Login
  • Public

    • Public
    • Groups
    • Popular
    • People

Conversation

Notices

  1. Bernie (codewiz@mstdn.io)'s status on Sunday, 19-Mar-2023 23:58:53 UTC Bernie Bernie

    I've been playing a bit with #OpenAssistant, an open-source #AI chatbot similar in scope to #ChatGPT:
    https://open-assistant.io/

    While it's in early stages, it looks very promising. If you have some time, you can contribute by manually labeling / ranking prompts and responses.

    In conversation Sunday, 19-Mar-2023 23:58:53 UTC from mstdn.io permalink

    Attachments


    • Srevin Saju (srevinsaju@mstdn.io)'s status on Monday, 20-Mar-2023 11:54:32 UTC Srevin Saju Srevin Saju
      in reply to

      @codewiz recently, I gave my shot with the Pygmalion AI 6B model, the results were not as bad as I thought it would be. I tried running it on Google Collab, and it worked pretty okay. Testing it locally is going to be a pain, since my laptop doesn’t have a GPU. The model was able to load and generate dialogues in 10 to 15 seconds, at a rate of 1 second per token, at 8 GB GPU RAM, 3 GB RAM and optimal CPU usage.

      In conversation Monday, 20-Mar-2023 11:54:32 UTC permalink
    • Bernie (codewiz@mstdn.io)'s status on Monday, 20-Mar-2023 18:47:11 UTC Bernie Bernie
      in reply to
      • Srevin Saju
      • smol, desu ne?

      @srevinsaju @smoldesu For a GPT, is the model size affect the number of neurons in each layer? Then, it would be somewhere between N^2 and N^3, without considering the effects of caches and the difference between layer type.

      I imagine changing the number of layers is more complicated, but for inference layers should have linear cost... right?

      My experience is limited to reading ML blogs and watching video lectures 😅

      In conversation Monday, 20-Mar-2023 18:47:11 UTC permalink
    • Srevin Saju (srevinsaju@mstdn.io)'s status on Monday, 20-Mar-2023 18:47:12 UTC Srevin Saju Srevin Saju
      in reply to
      • smol, desu ne?

      @smoldesu @codewiz right! looks like the time taken grows exponentially with the size of the model.

      In conversation Monday, 20-Mar-2023 18:47:12 UTC permalink
    • smol, desu ne? (smoldesu@mastodon.social)'s status on Monday, 20-Mar-2023 18:47:14 UTC smol, desu ne? smol, desu ne?
      in reply to
      • Srevin Saju

      @srevinsaju @codewiz On my 4 core ARM rack I can get ~240 tokens in <10 seconds if I use gpt-j-125m

      In conversation Monday, 20-Mar-2023 18:47:14 UTC permalink

Feeds

  • Activity Streams
  • RSS 2.0
  • Atom
  • Help
  • About
  • FAQ
  • Privacy
  • Source
  • Version
  • Contact

Bobinas P4G is a social network. It runs on GNU social, version 2.0.1-beta0, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All Bobinas P4G content and data are available under the Creative Commons Attribution 3.0 license.