LocalLLaMA

11 readers

4 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 2 years ago

MODERATORS

communick@poweruser.forum

dolphin-2.2-yi-34b released (alien.top)

submitted 2 years ago by Amgadoz@alien.top to c/localllama@poweruser.forum

34 comments fedilink hide all child comments

Eric Hartford, the author of dolphin models, released dolphin-2.2-yi-34b.

This is one of the earliest community finetunes of the yi-34B.

yi-34B was developed by a Chinese company and they claim sota performance that are on par with gpt-3.5

HF: https://huggingface.co/ehartford/dolphin-2_2-yi-34b

Announcement: https://x.com/erhartford/status/1723940171991663088?s=20

you are viewing a single comment's thread
view the rest of the comments

[–] Sabin_Stargem@alien.top 1 points 2 years ago (1 children)

Having tried out Yi-34b-200k with Nous Capybera, I think the Yi-34b-16k Dolphin v2.2 has a better flavor to it. Nous also wants more rep penalty, I am guessing the 200k foundation is doing that. 1.1 is what I used to get a better response. Haven't tried a higher penalty yet.

[–] mcmoose1900@alien.top 1 points 2 years ago

The Yi 200K base model was really funny about sampling. Mirostat was a disaster, and so were some other presets, but it liked TFS.