27 Delphi midtraining endpoint checkpoints (K=0.20): 9 scales x 3 mixes. Dense Qwen3, Llama-3 tok. marin#6279.
LAION eV
non-profit
AI & ML interests
open multi-modal foundation models and datasets for their creation; scaling laws, model evaluation; fully local, sovereign model deployment, personalized assistants and open local agentic systems
Recent Activity
View all activity
Organization Card
models 790
laion/explore-tis-minp-40-8B
8B • Updated
laion/explore-tis-temp10-60-8B
8B • Updated
laion/delphi-3e19-p67m33-k0p20-lr83-a002-wc386k_lr1e5-sft
Text Generation • 1.0B • Updated
laion/delphi-3e19-p33m67-k0p20-lr83-a002-wc386k_lr1e5-sft
Text Generation • 1.0B • Updated
laion/delphi-2e19-p67m33-k0p20-lr83-a002-wc386k_lr1e5-sft
Text Generation • 0.8B • Updated
laion/delphi-2e19-p67m33-k0p20-lr83-a002-magpie_lr1e5-sft
Text Generation • 0.8B • Updated
laion/delphi-2e19-p50m50-k0p20-lr83-a002-magpie_lr1e5-sft
Text Generation • 0.8B • Updated
laion/delphi-2e19-p33m67-k0p20-lr83-a002-wc386k_lr1e5-sft
Text Generation • 0.8B • Updated
laion/delphi-9e18-p67m33-k0p20-lr83-a002-magpie_lr1e5-sft
Text Generation • 0.6B • Updated
laion/voiceclap-small-v2
Feature Extraction • 0.1B • Updated • 1 • 1
datasets 439
laion/soundscape-bench
Viewer • Updated • 200 • 46 • 1
laion/llama-nemotron-science-reasoning-on-le3000tok-100k-canonical-think
Viewer • Updated • 100k • 19
laion/llama-nemotron-science-reasoning-on-le3000tok-100k
Viewer • Updated • 100k • 34
laion/laionbox-voice-acting-training-data
Updated • 16
laion/dramabox-voice-acting-data-annotated
Viewer • Updated • 345k • 2.75k
laion/small-overlapping-speech-bench
Viewer • Updated • 100 • 163
laion/nemotron-gym-qa-abstention-v2
Viewer • Updated • 3.15k • 30
laion/nemotron-gym-math-v4
Viewer • Updated • 6.53k • 33
laion/nemotron-gym-multichallenge-vanilla-v2
Viewer • Updated • 1.05k • 31
laion/nemotron-gym-multichallenge-advanced-v2
Viewer • Updated • 1.07k • 32