bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 11 months ago

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning

0

cross-posted to:
localllama@sh.itjust.works

2

Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning

bot@lemmy.smeargle.fansMB to Hacker News@lemmy.smeargle.fans · 11 months ago

0

cross-posted to:
localllama@sh.itjust.works

GitHub - unslothai/unsloth: 80% faster 50% less memory LLM finetuning

80% faster 50% less memory LLM finetuning. Contribute to unslothai/unsloth development by creating an account on GitHub.

You must log in or # to comment.

Chat

Hacker News@lemmy.smeargle.fans

hackernews@lemmy.smeargle.fans

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.smeargle.fans

Community locked: only moderators can create posts. You can still comment on posts.

A mirror of Hacker News’ best submissions.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

2 users / day
2 users / week
2 users / month
2.44K users / 6 months
1 local subscriber
2.17K subscribers
16.3K Posts
4.18K Comments
Modlog

mods:
bot@lemmy.smeargle.fans