fromziro/ZeroS-Micro-v1.0
3.24M • Updated • 141 • 5
AI & ML interests
Building stuff.
Recent Activity
View all activity
Harley-ml
updated a
model 7 days ago
[bot] Conversion to Parquet
#1 opened 9 days ago
by 
parquet-converter
Post
3033
AxiomicLabs released new benchmark, Tiny Theory of Mind, to test your SLM models' Theory of Mind Intuition!
Check it out and like it!
AxiomicLabs/Tiny_Theory_of_Mind
Check it out and like it!
AxiomicLabs/Tiny_Theory_of_Mind
Harley-ml
published a
dataset 9 days ago
Harley-ml
updated a
dataset 9 days ago
Harley-ml
updated a
Space 19 days ago
Harley-ml
updated 7
models 19 days ago
fromziro/ZeroS-v0.1-150M
0.2B • Updated • 1.2k • 16
fromziro/ZeroS-Linear-50M
49.6M • Updated • 888 • 4
fromziro/ZeroS-Qana-5M
Text Generation • 4.98M • Updated • 1.51k • 5
fromziro/Zero-TinyImage-0.6M
Unconditional Image Generation • 639k • Updated • 63 • 7
fromziro/Zero-Sentiment-0.2M
Text Classification • 191k • Updated • 301 • 5
fromziro/ZeroS-Pico-v1.0
67.7k • Updated • 2.41k • 8
fromziro/ZeroS-Pico-v1.1
59.8k • Updated • 2.26k • 8
Demo for this model on Spaces
#3 opened 20 days ago
by 
multimodalart
Demo for this model on Spaces
1
#2 opened 20 days ago
by multimodalart
Demo for this model on Spaces
1
#1 opened 23 days ago
by 
linoyts
Post
118
Zero-v1.0-144M is currently training. So far, it has completed 26% of its training run, with about 98 billion tokens to go.
Current Val PPL: 13.705
Zero-v1.0 uses a custom architecture consisting of RMSNorm, RoPe, SwiGLU, Engram Conditional Memory, mHC, and XSA GQA.
Current Val PPL: 13.705
Zero-v1.0 uses a custom architecture consisting of RMSNorm, RoPe, SwiGLU, Engram Conditional Memory, mHC, and XSA GQA.
Harley-ml
published a
model 24 days ago
Harley-ml
published a
model 26 days ago
Harley-ml
published a
model 28 days ago