LAION eV

non-profit

https://laion.ai

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

penfever updated a model about 10 hours ago

laion/sft__g1_gptlong_top8_train_on_obs_fa3__40-0__Qwen3-32B

penfever published a model 1 day ago

laion/dense-1node-8b-smoke

penfever updated a model 1 day ago

laion/delphi-1e22-p33m67-rl-rlvr7500_w0-think-140-10B

View all activity

laion 's models 908

laion/exp-swd-r2egym-wo-docker_glm_4_7_traces

Text Generation • 308k • Updated Jan 21 • 7

laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_8-0_Qwen3-32B

Text Generation • 33B • Updated Jan 20 • 4

laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-01_Qwen3-32B

Text Generation • 33B • Updated Jan 20 • 2

laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

Text Generation • 33B • Updated Jan 20 • 4

laion/Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k

Text Generation • 308k • Updated Jan 20 • 10

laion/Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k

Text Generation • 308k • Updated Jan 20 • 8

laion/Majestrino-0.30

0.2B • Updated Jan 18

laion/Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k

Text Generation • 308k • Updated Jan 18 • 19 •

laion/Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32k

Text Generation • 308k • Updated Jan 18 • 3

laion/exp_tas_timeout_multiplier_8_0_traces

Text Generation • 308k • Updated Jan 16 • 7

laion/exp_tas_timeout_multiplier_4_0_traces

Text Generation • 308k • Updated Jan 16 • 5

laion/exp_tas_timeout_multiplier_1_0_traces

Text Generation • 308k • Updated Jan 16 • 7

laion/exp_tas_timeout_multiplier_0_25_traces

Text Generation • 308k • Updated Jan 16 • 4

laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_learning-rate_1e-06_Qwen3-32B

Text Generation • 33B • Updated Jan 14 • 5

laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_lr_1e-5_Qwen3-32B

Text Generation • 33B • Updated Jan 12 • 5

laion/clap-htsat-fused

Audio Classification • 0.2B • Updated Jan 12 • 15.4M • 107

laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_7.0_Qwen3-32B

Text Generation • 33B • Updated Jan 11 • 3

laion/openMaMMUT-ViT-B-32-512x512-pt_DFN2B-ft_DFN512x512-s293M-b73k

Zero-Shot Image Classification • Updated Jan 10 • 4 • 2

laion/openMaMMUT-ViT-B-16-512x512-pt_DFN2B-ft_DFN512x512-s293M-b73k

Zero-Shot Image Classification • Updated Jan 10 • 4 • 2

laion/openMaMMUT-ViT-B-32-512x512-pt_datacomp1b-ft_datacomp512x512-s76M-b73k

Zero-Shot Image Classification • Updated Jan 10 • 4 • 3

laion/openMaMMUT-ViT-B-16-512x512-pt_datacomp1b-ft_datacomp512x512-s76M-b73k

Zero-Shot Image Classification • Updated Jan 10 • 6 • 3

laion/openMaMMUT-ViT-L-14-512x512-pt_datacomp1b-ft_datacomp512x512-s76M-b73k

Zero-Shot Image Classification • Updated Jan 10 • 4 • 3

laion/stackexchange-tezos-sandboxes_glm_4_6_traces_locetash_again

Text Generation • 308k • Updated Jan 10 • 4

laion/Qwen3-8B_exp-swd-swesmith-wo-docker_glm_4.7_traces_locetash_save-strategy_steps

Text Generation • 308k • Updated Jan 10 • 4

laion/Qwen3-8B_exp_tas_top_k_32_traces_save-strategy_steps

Text Generation • 308k • Updated Jan 10 • 4

laion/Qwen3-8B_perturbed-docker-exp-taskmaster2-tasks_glm_4.7_traces_locetash_save-strategy_steps

Text Generation • 308k • Updated Jan 10 • 8

laion/Qwen3-8B_exp_tas_summarize_threshold_4096_traces_save-strategy_steps

308k • Updated Jan 10 • 2

laion/Qwen3-8B_exp_tas_tmux_large_traces_save-strategy_steps

Text Generation • 308k • Updated Jan 10 • 5

laion/Qwen3-8B_exp_tas_temp_0.25_traces_save-strategy_steps

Text Generation • 308k • Updated Jan 10 • 3

laion/Qwen3-8B_exp_tas_trajectory_minimal_traces_save-strategy_steps

Text Generation • 308k • Updated Jan 10 • 33 •