🔄 In a Training Loop
Logicvex AI
MultivexAI
AI & ML interests
A machine learning collective focused on AGI. We believe Tiny Language Models are the future, so we build and share them—along with datasets—to support community progress. Not a company.
Recent Activity
liked a dataset 23 minutes ago
StentorLabs/The-Depth-Myth-When-More-Layers-Work-Against-You updated a model about 4 hours ago
AtomixLabs/Photon-1.0-1M liked a Space about 5 hours ago
bench-labs/BenchLabs-LeaderboardOrganizations
Added `AtomixLabs/Photon-1.0-1M`
#8 opened about 5 hours ago
by MultivexAI
Add Photon-1.0-1M
#49 opened about 16 hours ago
by MultivexAI
scaling laws
👍 1
39
#2 opened about 1 month ago
by 
encryptedoreo
Just Curious...
19
#1 opened 20 days ago
by 
GODELEV
Take Down The Latest blog
26
#8 opened 29 days ago
by 
QyrouNnet-AI
Update index.html
#25 opened 23 days ago
by MultivexAI
Model Submission Request: AtomixS2-5M-v1.0
1
#24 opened 23 days ago
by MultivexAI
Rename the model!
4
#1 opened about 1 month ago
by 
LH-Tech-AI
Model Submission Request: MultivexAI Plyx-15M & Supra-1.6-50M
1
#14 opened about 1 month ago
by MultivexAI
Seriously cool work!
🚀🔥 1
5
#9 opened about 1 month ago
by MultivexAI
How did you estimate model parameter count before training and use correct hyperparams?
11
#1 opened almost 2 years ago
by 
mahiatlinux
🚩 Report: Spam
#1 opened 10 months ago
by MultivexAI
🚩 Report: Spam
2
#1 opened 10 months ago
by MultivexAI
🚩 Report: Spam
#1 opened 10 months ago
by MultivexAI
Why it takes so long to generate?
1
#296 opened over 1 year ago
by 
clui
different between DeepSeek-V2-Chat-0628 and Deepseek-v2-API-0628
1
#2 opened almost 2 years ago
by 
xxllp