AI & ML interests

Building stuff.

Recent Activity

Enderchef 
posted an update 10 days ago
view post
Post
100
Introducing Open SLM Evaluations!
Open SLM Evaluations is a dataset containing benchmarks for 106 SLMs(150M parameters and below). It has benchmark scores for each model, links, parameter counts, and names.
Results were evaluated independently over 30 GPU minutes on a Runpod B200!
Data is open on Apache 2.0! Check it out!
Enderchef/Open-SLM-Evalulations
Enderchef 
posted an update 23 days ago
view post
Post
3,049
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
Harley-ml 
updated a Space about 1 month ago

Demo for this model on Spaces

#3 opened about 1 month ago by
multimodalart

Demo for this model on Spaces

1
#1 opened about 1 month ago by
linoyts
Harley-ml 
posted an update about 1 month ago
view post
Post
128
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.