this post was submitted on 13 Aug 2023
391 points (74.5% liked)

Technology

59593 readers
3247 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] NGC2346@sh.itjust.works 10 points 1 year ago (4 children)

Its fine, i got my own LlaMa at home, it does almost the same as GPT

[–] RoyalEngineering@lemmy.world 10 points 1 year ago (1 children)

Which one? What are your system specs?

I’ve been thinking about doing this too.

[–] NGC2346@sh.itjust.works 1 points 1 year ago* (last edited 1 year ago)

uncensored vicuna 7b if i recall

nvidia rtx 3060, 20 core intel cpu, 32gb ram

[–] average650@lemmy.world 1 points 1 year ago

The biggest issue I find is it's just not as easy to use as chatgpt. I'm surprised no one has sold an easy to use consumer version.

[–] WigglingWalrus@feddit.uk 1 points 1 year ago

I'd like to know too!

[–] Blizzard@lemmy.zip 1 points 1 year ago (1 children)

Are you referring to https://gpt4all.io or something else? I was going to try this one but will welcome any recommendations.

[–] BetaDoggo_@lemmy.world 1 points 1 year ago

In terms of flexibility oobabooga's text generation webui is the best as it supports nearly every model as ggml, gptq and transformers.

For the model itself Nous-hermes-llama2 is one the best for easy use.