LocalLLaMA@sh.itjust.worksEnglish · 4 hours ago

30B-A3B GLM-4.7-Flash Released

huggingface.co

cross-posted to:
fosai@lemmy.world
hackernews

30B-A3B GLM-4.7-Flash Released

huggingface.co

TheCornCollector@piefed.zip to

LocalLLaMA@sh.itjust.worksEnglish · 4 hours ago

cross-posted to:
fosai@lemmy.world
hackernews

zai-org/GLM-4.7-Flash · Hugging Face

huggingface.co

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

cross-posted from: https://piefed.zip/c/fosai/p/958141/30b-a3b-glm-4-7-flash-released

Small/fast model with MIT license for local use.

Benchmarks look good for the size. But IMO these smaller models aren’t consistent enough to live up to their promises.

Chat

panda_abyss@lemmy.ca
link
fedilink
English
arrow-up
2·
3 hours ago
Anyone get this working in llama.cpp yet?

I know flash attention and PyTorch have patchy support.
- TheCornCollector@piefed.zipOP
  link
  fedilink
  English
  arrow-up
  1·
  3 hours ago
  Seems to be a new architecture so custom support is needed.
  
  Tracking issue
  
  PR

LocalLLaMA@sh.itjust.works

localllama@sh.itjust.works

Create a post

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: !localllama@sh.itjust.works

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they’re still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

Visibility: Public

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

11 users / day
14 users / week
89 users / month
1.27K users / 6 months
1 local subscriber
4K subscribers
127 Posts
578 Comments
Modlog