AI & ML interests

We make SLMs.

Recent Activity

GGUFGuyΒ  updated a model 6 days ago
Novi-AI/Novi-Pico-Base
GGUFGuyΒ  updated a model 7 days ago
Novi-AI/Novi-Micro-Instruct
GGUFGuyΒ  published a model 7 days ago
Novi-AI/Novi-Micro-Instruct
View all activity

Bc-AIΒ 
in Novi-AI/Novi-510x 20 days ago

Hmmmm

6
#2 opened 21 days ago by
Bc-AI
GGUFGuyΒ 
in Novi-AI/Novi-510x 20 days ago

Hmmmm

6
#2 opened 21 days ago by
Bc-AI
DedeProGamesΒ 
in Novi-AI/Novi-510x 20 days ago

Hmmmm

6
#2 opened 21 days ago by
Bc-AI
Bc-AIΒ 
in Novi-AI/README 23 days ago

Can I also join Novi AI?

3
#4 opened 23 days ago by
Bc-AI
Bc-AIΒ 

hmm

4
#1 opened 23 days ago by
Bc-AI
GGUFGuyΒ 

hmm

4
#1 opened 23 days ago by
Bc-AI
GGUFGuyΒ 
updated a Space 24 days ago
Bc-AIΒ 
posted an update 29 days ago
view post
Post
237
Hello everyone! πŸ‘‹

A small SmilyAI Labs update!

G1-MINI has now seen around 8B tokens during its current run, and pretraining is still going strong.

Our E1 (Efficiency-1) prototype has also reached 15B pretraining tokens. E1 has 1B total parameters while activating under 100M parameters per token. It features adaptive activation, meaning easier tokens can use less compute while harder tokens receive more.

We plan to open-source E1 ASAP! πŸš€

We’re also excited to announce Project Prism, which will provide limited access to our upcoming Orion Flagship model, powered by our T2 architecture.

Note: T2 here refers to the architecture, not our T2 (Thinker-2) model.

Applications for Project Prism are available through the org page, with more details coming soon!

Finally, welcome @soyL061215 , who joined the Hugging Face org today! πŸŽ‰

Thanks to our existing members:
@smilyai-large-team @MUK-IS-GOAT @Keeby-smilyai @Bc-AI

β€” Bc-AI
SmilyAI Labs
  • 3 replies
Β·
NILKNARFGonzoΒ 
posted an update 29 days ago
view post
Post
111
just recieved my stack of 10 floppy disks - you know what that means

floppyx4 is canceled, floppyx10 is next

here's the intended specs:
- official tokenizer (the actual tokenizer for gpt-2)
- actual gpu training (barely)
- sharegpt (if i can afford it computationally)
- full thing fitting on 10 floppy disks (not just the safetensors file)
- and if needed different arch (like llama)

also unsloth on a gpu from 2015 is insane
  • 3 replies
Β·