Loser Cheems's picture

Loser Cheems

JingzeShi

·

https://github.com/LoserCheems

LoserCheems

AI & ML interests

I like training small languge models.

Recent Activity

new activity 40 minutes ago

perplexity-ai/r1-1776:作为中国开发者感谢perplexity，As a Chinese developer, thanks to perplexity

new activity about 3 hours ago

perplexity-ai/r1-1776:Freedom of speech is a basic human right of the Chinese people

reacted to their post with 🚀 about 5 hours ago

🤗Welcome to the Doge Edge Device Small language Model. https://huggingface.co/SmallDoge/Doge-160M-Instruct

View all activity

Organizations

JingzeShi's activity

upvoted 3 collections 21 days ago

Doge-Downstream-Applications

1 item • Updated 21 days ago • 1

🐶Doge-CheckPoint

A series of checkPoint weights that can continue training on new datasets without spikes of the training. • 4 items • Updated 8 days ago • 2

🐕Doge-SLM

Doge family of small language models! • 10 items • Updated 1 day ago • 1

upvoted a collection 25 days ago

YuLan-Mini

A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details. • 5 items • Updated about 11 hours ago • 14

upvoted a collection about 1 month ago

Doge

Doge family of small language models. • 7 items • Updated 20 days ago • 5

upvoted a paper 2 months ago

Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture

Paper • 2412.11834 • Published Dec 16, 2024 • 7

upvoted a paper 3 months ago

Cheems: Wonderful Matrices More Efficient and More Effective Architecture

Paper • 2407.16958 • Published Jul 24, 2024 • 3