1 Post
3 Comments

Joined 1 year ago

Cake day: October 31st, 2023

You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.

OverviewCommentsPosts

Ok_Relationship_9879@alien.topBtoLocalLLaMA•🐺🐦‍⬛ LLM Comparison/Test: 2x 34B Yi (Dolphin, Nous Capybara) vs. 12x 70B, 120B, ChatGPT/GPT-4
link
fedilink
English
arrow-up
1·
1 year ago
That’s pretty amazing. Thanks for all your hard work!
Does anyone know if the Nous Capybara 34B is uncensored?

link
fedilink

Ok_Relationship_9879@alien.topB to

LocalLLaMAEnglish · 1 year ago

GPT-4's 128K context window tested

6

1

GPT-4's 128K context window tested

Ok_Relationship_9879@alien.topB to

LocalLLaMAEnglish · 1 year ago

6

Ok_Relationship_9879@alien.topBtoLocalLLaMA•For roleplay purposes, Goliath-120b is absolutely thrilling me
link
fedilink
English
arrow-up
1·
1 year ago
Which models do you find to be good at 16k context for story writing?

link
fedilink

Ok_Relationship_9879@alien.topBtoLocalLLaMA•RedPajama-Data-v2: an Open Dataset with 30 Trillion Tokens for Training Large Language Models
link
fedilink
English
arrow-up
1·
1 year ago
If chinchilla is right, this dataset could be huge for small models.

https://www.lesswrong.com/posts/6Fpvch8RR29qLEWNH/chinchilla-s-wild-implications

link
fedilink