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 946
laion/grug-67b-a2b-sft-s3-agentic-step1903
Text Generation • 67B • Updated • 16
laion/delphi-1e23-wc50m-rl-d3-dapomath-32gpu
25B • Updated • 22
laion/delphi-1e23-wc50m-rl-d2-ifeval-32gpu
25B • Updated • 24
laion/delphi-1e23-wc50m-rl-d4-math500-32gpu
25B • Updated • 25
laion/delphi-1e23-wc50m-rl-d1-rlvrmath-32gpu
25B • Updated • 36
laion/vocalburst-classifier-single
Audio Classification • Updated • 37
laion/vocalburst-classifier-multilabel
Audio Classification • Updated • 38
laion/delphi-1e23-wc50m-warmup-levanter-sft
Text Generation • 25B • Updated • 80
laion/delphi-1e23-magpie-warmup-levanter-sft
Text Generation • 25B • Updated • 47
laion/delphi-1e23-p33m67-k0p076-prepared
25B • Updated • 95
datasets 587
laion/moss-local-voice-acting-top3-with-neutral-refs
Updated • 439
laion/grug-agentic-eval-v2-traces
Viewer • Updated • 4
laion/mv2_decontaminated
Preview • Updated • 3.12k
laion/moss-character-voices-top3-captioned
Viewer • Updated • 38.4k • 276
laion/moss-character-voices-bestof64
Viewer • Updated • 825k • 1.88k • 1
laion/delphi-1e23-25b-stageE-rl-eval-artifacts
Updated • 22
laion/nl2bash-tasks-cleaned-oracle-qwen3.5-122b-131k-opencode-sft-serveparity
Viewer • Updated • 633 • 30
laion/nemotron-gym-math-advanced-calculations-v3-qwen3.5-122b-131k-opencode-sft-serveparity
Viewer • Updated • 5.23k • 31
laion/nemotron-gym-knowledge-web-search-mcqa-qwen3.5-122b-131k-opencode-sft-serveparity
Viewer • Updated • 2.9k • 28
laion/nemotron-gym-instruction-following-structured-qwen3.5-122b-131k-opencode-sft-serveparity
Viewer • Updated • 9.04k • 26