🏗️ Building on HF

Boning Cui

Bc-AI

52 3 40

AI & ML interests

He/Him. I like LLM's and VLM's. I work with my other friends to make stuff. We are in year 7 and we are enthusiastic about AI. We are based in Australia 🇦🇺

Recent Activity

new activity about 5 hours ago

CodeSoft/SLM-Arena:Model Addition Request

new activity about 5 hours ago

bananamind-research-community/BananaMind-Smoothie:I will put my experiment model here

updated a dataset about 6 hours ago

hugging-science/G1-Pretrain-Data-Repo

View all activity

Organizations

New activity in CodeSoft/SLM-Arena about 5 hours ago

Model Addition Request

#7 opened about 6 hours ago by

Banaxi-Tech

New activity in bananamind-research-community/BananaMind-Smoothie about 5 hours ago

I will put my experiment model here

#1 opened about 12 hours ago by

Bc-AI

updated a dataset about 6 hours ago

hugging-science/G1-Pretrain-Data-Repo

Updated less than a minute ago • 931

New activity in ml-intern-explorers/nova1-pretrain-20T about 6 hours ago

Hey

#2 opened about 6 hours ago by

Banaxi-Tech

New activity in HeraFox-ai/Mental-Health-Safety-Eval about 6 hours ago

Wow

#4 opened about 6 hours ago by

Bc-AI

published a dataset about 6 hours ago

hugging-science/G1-Pretrain-Data-Repo

Updated less than a minute ago • 931

replied to their post about 6 hours ago

It will be open source on launch by the way

posted an update about 6 hours ago

Post

Building a 6.58B sparse MoE model from scratch on a single GPU.
Hey everyone! Today is day 1 of training Smilyai-Lab's new model I call G1-MINI. It's basically the smaller version of our planned model G1 which will be 20B and activate about 2B per token. MINI activates about 1.16B params per token and is currently training right now. If no errors spring up now, I'd say i can launch sometime around September 15th~ish. Thanks to our beta testers:
@guardamarcos
@ProCreations
@juiceb0xc0de
@Timmy6767
@Sbui503
@atom77777
@Fishtiks
@smartdigitalnetworks
@EmetTheGolum
@smilyai-large-team
@MUK-IS-GOAT
@Bc-AI
@Banaxi-Tech
@vovaRL
@Datdanboi25

3 replies

replied to Banaxi-Tech's post about 10 hours ago

nice! excited to see that. right now im working on G1-MINI a 6.4B parameters model which activates about 1.16B per token. I will make a new SLM soon after it lol.