Lemmy.World

170,961 readers
6,221 users here now

The World's Internet Frontpage Lemmy.World is a general-purpose Lemmy instance of various topics, for the entire world to use.

Be polite and follow the rules ⚖ https://legal.lemmy.world/tos

Get started

See the Getting Started Guide

Donations 💗

If you would like to make a donation to support the cost of running this platform, please do so at the following donation URLs.

If you can, please use / switch to Ko-Fi, it has the lowest fees for us

Join the team 😎

Check out our team page to join

Questions / Issues

Questions/issues post to
To open a ticket
Reporting is to be done via the reporting button under a post/comment.
Additional Report Info HERE
Please note, you will NOT be able to comment or post while on a VPN or Tor connection

More Lemmy.World

Follow us for server news 🐘

Chat 🗨

Alternative UIs

https://a.lemmy.world - Alexandrite UI
https://photon.lemmy.world - Photon UI
https://m.lemmy.world - Voyager mobile UI
https://old.lemmy.world - A familiar UI

Monitoring / Stats 🌐

Service Status 🔥

https://status.lemmy.world

Lemmy.World is part of the FediHosting Foundation

founded 2 years ago

ADMINS

[News] NEW LLAMA 2 MODELS FROM THE BLOKE!! (huggingface.co)

submitted 2 years ago by pavnilschanda to c/aicompanions

2 comments fedilink

cross-posted from: https://lemmy.world/post/1760388

Giving this one a go!

https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ

NEW LLAMA 2 MODELS FROM THE BLOKE!! (huggingface.co)

submitted 2 years ago by 2dollarsim to c/oobabooga

0 comments fedilink

Giving this one a go!

https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ

[Resource] exLlama SuperHOT 8K context models download links (huggingface.co)

submitted 2 years ago by pavnilschanda to c/aicompanions

0 comments fedilink

cross-posted from: https://lemmy.world/post/1234908

https://huggingface.co/TheBloke

contains the latest exLlama SuperHOT 8K context models

Model download links (huggingface.co)

submitted 2 years ago by 2dollarsim to c/oobabooga

0 comments fedilink

https://huggingface.co/TheBloke

contains the latest exLlama SuperHOT 8K context models

TheBloke Releases "SuperHot" Versions of Various GPTQ Models - Empowering LLM Users w/ a Context Length of 8,000 Tokens! (huggingface.co)

submitted 2 years ago by Blaed to c/[email protected]

0 comments fedilink

cross-posted from: https://lemmy.world/post/708817

Visit TheBloke's HuggingFace page to see all of the new models in their SuperHOT glory.

SuperHOT models are LLMs who's LoRAs have been adapted to support a context length of 8,000 tokens!

For reference, this is x4 times the default amount of many LLMs (i.e. 2048 tokens). Even some of the newer ones can only reach a context length of 4096 tokens, half the amount of these SuperHOT models!

Here are a few that were released if you couldn't view his HuggingFace:

New GPTQ Models from TheBloke

airoboros (13B)

CAMEL (13B)

Chronos (13B)

Guanaco (13B & 33B)

Manticore (13B)

Minotaur (13B)

Nous Hermes (13B)

Pygmalion (13B)

Samantha (13B & 33B)

Snoozy (13B)

Tulu (13B & 33B)

Vicuna (13B & 33B)

WizardLM (13B)

We owe a tremendous thank you to TheBloke, who has enabled many of us in the community to interact with versions of Manticore, Nous Hermes, WizardLM and others running the remarkable 8k context length from SuperHOT.

Many of these are 13B models, which should be compatible with consumer grade GPUs. Try using Exllama or Oobabooga for testing out these new formats.

Shoutout to Kaikendev for the creation of SuperHOT. You can learn more about their work here.

If you enjoyed reading this, please consider subscribing to /c/FOSAI where I do my best to keep you in the know with the latest and greatest advancements regarding free open-source artificial intelligence.