laion/rl__40GPU_base_32b__exp_rpt_pymethods2test-large__syh-r2eg-askl-glm_4
33B • Updated
• 13
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
laion/sft_r2egym-nl2bash-stackoverflow-inferredbugs-32B_Qwen3-32B
Text Generation • 33B • Updated
• 24
laion/rl__40GPU_base_32b__exp_rpt_nemotron-bash__sft_GLM-4-7-swesmith
33B • Updated
• 13
laion/sft_GLM-4-7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k_Qwen3-32B
Text Generation • 33B • Updated
• 98
laion/Qwen3-8B_exp_tas_temp_0.5_traces_save-strategy_steps
Text Generation • 308k • Updated
• 193
laion/rl__40GPU_base_32b__exp_rpt_codeelo-v2__sft_GLM-4-7-swesmith
33B • Updated
• 13
laion/rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_curator-hard
8B • Updated
• 13
laion/rl_rl-conf_24GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt_trai-data_exp_rpt_stac-dock-v2
8B • Updated
• 28
laion/rl_rl-conf_24GP_base-yaml_mode-path_exp_tas_opti_comb_trac_trai-data_exp_rpt_unit-pyth-v3
8B • Updated
• 24
laion/rl_rl-config_24GPU_base-yaml_model-path_Qwen3-8B_train-data_exp_rpt_pymethods2test-large-50
8B • Updated
• 16
laion/rl_rl-config_24GPU_base-yaml_model-path_Qwen3-8B_train-data_exp_rpt_nemotron-bash-60
8B • Updated
• 13
laion/rl__24GPU_base__exp_rpt_stack-bash__Qwen3-8B-55
8B • Updated
• 15
laion/rl__24GPU_base__exp_rpt_scaffold__Qwen3-8B-60
8B • Updated
• 13
laion/rl__24GPU_base__exp_rpt_multifile__Qwen3-8B-60
8B • Updated
• 14
laion/rl__24GPU_base__exp_rpt_issue__Qwen3-8B-60
8B • Updated
• 14
laion/rl_rl-conf_24GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt-agai_trai-data_exp_rpt_soft-larg
8B • Updated
• 11
laion/rl_rl-conf_24GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt-agai_trai-data_exp_rpt_nemo-bash
8B • Updated
• 13
laion/rl__24GPU_base__exp_rpt_codeelo-v2__Qwen3-8B
8B • Updated
• 14
laion/rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr-postmortem
Updated
laion/rl_v1_tp4s64_8x_exercism-python
Updated
laion/rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_postmortem
8B • Updated
• 16
laion/rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr
8B • Updated
• 17
laion/rl_v1_tp4s64_8x_stack-pytest-large
8B • Updated
• 14
laion/rl_v1_tp4s64_8x_structural_debug
8B • Updated
• 13
laion/rl_v1_tp4s64_8x_stack-jest-large
8B • Updated
• 14
laion/Qwen3-32B-R2EGYM-256-3epochs
Text Generation • 33B • Updated
• 33
laion/rl_v1_tp4s64_8x_nemotron-junit
8B • Updated
• 18
laion/rl_rl-config_24GPU_base-yaml_model-path_Qwen3-8B_train-data_exp_rpt_codeelo-v2
Updated
laion/syh-r2eg-askl-glm_4-7_trac_jupi_-gfi-swes-rand-filt-10K_glm_4-7_trac_jupi_32B
Text Generation • 33B • Updated
• 35
laion/rl_r2egym-nl2bash-stack-bugsseq-fixthink_lr1e-5_taco
8B • Updated
• 32