Skip to page content
SAVRN
Search Plan a project

Open-weight model

margent-mcq-rsi-mmlu_pro_v3g_sta

by Madison MaliDDD/margent-mcq-rsi-mmlu_pro_v3g_sta

margent-mcq-rsi-mmlu_pro_v3g_sta is an open-weight model from Madison. Its published files total 441.9 MB.

Parameters—
Context—
Weights349.3 MB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
MaliDDD/margent-mcq-rsi-mmlu_pro_v3g_sta
Publisher
Madison
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
ece5af051e6b8bf97ce0a1a9d611bee9672b47ba
First published
2026-10-11
Last updated
2026-10-11

Files and Weights

375 files, 441.9 MB in total. The weights are 4 files totalling 349.3 MB in bin, safetensors.

Weights4 files · 349.3 MB
Configuration241 files · 606.3 KB
Tokenizer6 files · 60.0 MB
Documentation90 files · 478.4 KB
Other33 files · 31.5 MB
Repository1 file · 1.8 KB
Every file
FileTypeSizeSHA-256
runs/mmlu_pro_v3g_sta/r1/grpo/final/adapter_model.safetensorsWeights116.4 MB 267da4da5a75
runs/mmlu_pro_v3g_sta/r2/static/grpo/final/adapter_model.safetensorsWeights116.4 MB 3e9e2bf63bc7
runs/mmlu_pro_v3g_sta/r2/static/sft/model/adapter_model.safetensorsWeights116.4 MB af41c9f3650f
runs/mmlu_pro_v3g_sta/r2/static/sft/model/training_args.binWeights5.3 KB 7321264f979c
advisor_cache/locked_test/mmlu_pro.jsonConfiguration1.3 KB —
advisor_cache/preflight/aqua.jsonConfiguration8.6 KB —
advisor_cache/preflight/gpqa.jsonConfiguration8.8 KB —
advisor_cache/preflight/medqa.jsonConfiguration8.7 KB —
advisor_cache/preflight/mmlu_pro.jsonConfiguration8.8 KB —
import/aqua/import_manifest.jsonConfiguration11.0 KB —
import/gpqa/import_manifest.jsonConfiguration10.4 KB —
import/medqa/import_manifest.jsonConfiguration9.3 KB —
import/mmlu_pro/import_manifest.jsonConfiguration10.5 KB —
runs/mmlu_pro_v3g_sta/acks.jsonConfiguration1.8 KB —
runs/mmlu_pro_v3g_sta/budget.jsonConfiguration97 B —
runs/mmlu_pro_v3g_sta/prefetch/advisors/.mcq_rsi_complete.jsonConfiguration309 B —
runs/mmlu_pro_v3g_sta/prefetch/advisors/prefetch.jsonConfiguration1.6 KB —
runs/mmlu_pro_v3g_sta/r1/S1_dev/.mcq_rsi_complete.jsonConfiguration297 B —
runs/mmlu_pro_v3g_sta/r1/S1_dev/decision.jsonConfiguration974 B —
runs/mmlu_pro_v3g_sta/r1/S1_dev/manager_tool_eval_report.jsonConfiguration702 B —
runs/mmlu_pro_v3g_sta/r1/S1_dev/mcq_rsi_eval.jsonConfiguration5.6 KB —
runs/mmlu_pro_v3g_sta/r1/S1_dev/parity.jsonConfiguration2.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/.mcq_rsi_complete.jsonConfiguration293 B —
runs/mmlu_pro_v3g_sta/r1/grpo/baseline.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/controller_stage.jsonConfiguration181 B —
runs/mmlu_pro_v3g_sta/r1/grpo/final/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/resume.jsonConfiguration736 B —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00001-8phceham/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00001-8phceham/step.jsonConfiguration2.3 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00002-4o3wp2qh/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00002-4o3wp2qh/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00003-luywjdf9/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00003-luywjdf9/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00004-gpyg7l8j/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00004-gpyg7l8j/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00005-4dffwacy/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00005-4dffwacy/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00006-4n8km1hk/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00006-4n8km1hk/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00007-1174yw89/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00007-1174yw89/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00008-b74_u4t5/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00008-b74_u4t5/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00009-_nfyfitw/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00009-_nfyfitw/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00010-bn9zer3s/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00010-bn9zer3s/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00011-60ehych4/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00011-60ehych4/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00012-ko9000rn/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00012-ko9000rn/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00013-6u3yncu3/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00013-6u3yncu3/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00014-utw0d5ty/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00014-utw0d5ty/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00015-uwo_30cd/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00015-uwo_30cd/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00016-jft8o1nw/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00016-jft8o1nw/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00017-r0z0_h4m/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00017-r0z0_h4m/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00018-1118i40o/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00018-1118i40o/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00019-e3by4x7t/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00019-e3by4x7t/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00020-subox343/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00020-subox343/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00021-a4edkaxq/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00021-a4edkaxq/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00022-1why0myb/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00022-1why0myb/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00023-brpx_fb_/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00023-brpx_fb_/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00024-wzgh65sz/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00024-wzgh65sz/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/summary.jsonConfiguration27.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/training_run.jsonConfiguration4.6 KB —
runs/mmlu_pro_v3g_sta/r1/grpo_dev/.mcq_rsi_complete.jsonConfiguration297 B —
runs/mmlu_pro_v3g_sta/r1/grpo_dev/decision.jsonConfiguration1.5 KB —
runs/mmlu_pro_v3g_sta/r1/grpo_dev/manager_tool_eval_report.jsonConfiguration710 B —
runs/mmlu_pro_v3g_sta/r1/grpo_dev/mcq_rsi_eval.jsonConfiguration5.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/.mcq_rsi_complete.jsonConfiguration301 B —
runs/mmlu_pro_v3g_sta/r2/static/grpo/baseline.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/controller_stage.jsonConfiguration180 B —
runs/mmlu_pro_v3g_sta/r2/static/grpo/final/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/resume.jsonConfiguration1.8 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00001-0u2h9n20/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00001-0u2h9n20/step.jsonConfiguration2.3 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00002-mf6ii3ck/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00002-mf6ii3ck/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00003-vfom3g90/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00003-vfom3g90/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00004-gnzs0p8w/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00004-gnzs0p8w/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00005-yrsmwt6u/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00005-yrsmwt6u/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00006-7b2koi89/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00006-7b2koi89/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00007-g9wlo2u8/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00007-g9wlo2u8/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00008-ns2e1pjt/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00008-ns2e1pjt/step.jsonConfiguration3.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00009-j_inoe7y/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00009-j_inoe7y/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00010-qhd0liuq/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00010-qhd0liuq/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00011-t_6517wu/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00011-t_6517wu/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00012-v16k40t1/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00012-v16k40t1/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00013-cxwgac_l/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00013-cxwgac_l/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00014-mp8yqs8j/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00014-mp8yqs8j/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00015-dghadoyr/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00015-dghadoyr/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00016-swvgoaiy/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00016-swvgoaiy/step.jsonConfiguration3.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00017-z48fiv47/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00017-z48fiv47/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00018-10g8xf6k/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00018-10g8xf6k/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00019-njf_hsjz/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00019-njf_hsjz/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00020-ya_rxj8k/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00020-ya_rxj8k/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00021-gj_qbyjl/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00021-gj_qbyjl/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00022-d3y2j3hl/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00022-d3y2j3hl/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00023-5ah2twwu/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00023-5ah2twwu/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00024-n1r80g9s/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00024-n1r80g9s/step.jsonConfiguration3.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00025-rgbhgax6/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00025-rgbhgax6/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00026-8jcsk3gm/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00026-8jcsk3gm/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00027-gj4tg04n/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00027-gj4tg04n/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00028-uzkzxpbt/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00028-uzkzxpbt/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00029-9a435dii/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00029-9a435dii/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00030-7vm28ien/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00030-7vm28ien/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00031-hn3b3qi4/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00031-hn3b3qi4/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00032-o36ngwt2/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00032-o36ngwt2/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00033-kkf83afo/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00033-kkf83afo/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00034-j1sf35z5/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00034-j1sf35z5/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00035-hisntrsx/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00035-hisntrsx/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00036-g8x1hr_r/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00036-g8x1hr_r/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00037-rbnznf05/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00037-rbnznf05/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00038-h60s30dg/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00038-h60s30dg/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00039-k0ejo037/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00039-k0ejo037/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00040-0bauaczi/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00040-0bauaczi/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00041-ce3_v7t4/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00041-ce3_v7t4/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00042-rqnxizwx/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00042-rqnxizwx/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00043-1rho_pwq/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00043-1rho_pwq/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00044-exuy2wfy/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00044-exuy2wfy/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00045-iwja6hk4/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00045-iwja6hk4/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00046-j3cm1rdi/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00046-j3cm1rdi/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00047-gd3hbamb/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00047-gd3hbamb/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00048-w44eaf5b/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00048-w44eaf5b/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00049-a1dqvrkn/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00049-a1dqvrkn/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00050-zgt6l5_r/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00050-zgt6l5_r/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00051-2aaf0dfl/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00051-2aaf0dfl/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00052-u2j6g8zq/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00052-u2j6g8zq/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00053-642i3qew/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00053-642i3qew/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00054-g0z9vz6h/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00054-g0z9vz6h/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00055-xdvihh_9/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00055-xdvihh_9/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00056-w3g3hlx8/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00056-w3g3hlx8/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00057-gz07x3mu/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00057-gz07x3mu/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00058-09jdgj9j/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00058-09jdgj9j/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00059-r2eesjmt/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00059-r2eesjmt/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00060-xiis3d05/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00060-xiis3d05/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00061-e24boggm/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00061-e24boggm/step.jsonConfiguration2.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00062-dcsgr2oh/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00062-dcsgr2oh/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00063-inr6pffw/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00063-inr6pffw/step.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00064-__wf__ux/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00064-__wf__ux/step.jsonConfiguration2.9 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/summary.jsonConfiguration68.8 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/training_run.jsonConfiguration5.3 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo_dev/.mcq_rsi_complete.jsonConfiguration305 B —
runs/mmlu_pro_v3g_sta/r2/static/grpo_dev/decision.jsonConfiguration1.3 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo_dev/manager_tool_eval_report.jsonConfiguration717 B —
runs/mmlu_pro_v3g_sta/r2/static/grpo_dev/mcq_rsi_eval.jsonConfiguration5.6 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/.mcq_rsi_complete.jsonConfiguration299 B —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/adapter_config.jsonConfiguration1.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/environment_a19e8df236e449a39aad0bd79d7eb5b7.jsonConfiguration506 B —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/run_summary.jsonConfiguration1.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/sft_data_report.jsonConfiguration142 B —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/status.jsonConfiguration571 B —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/training_metrics.jsonConfiguration949 B —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/training_run.jsonConfiguration1.7 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/run_signature.jsonConfiguration3.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/sft_report.jsonConfiguration2.5 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft_dev/.mcq_rsi_complete.jsonConfiguration305 B —
runs/mmlu_pro_v3g_sta/r2/static/sft_dev/decision.jsonConfiguration1.9 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft_dev/manager_tool_eval_report.jsonConfiguration714 B —
runs/mmlu_pro_v3g_sta/r2/static/sft_dev/mcq_rsi_eval.jsonConfiguration6.3 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/environment_b7316c6f31084bc693816bb1cb0edd50.jsonConfiguration506 B —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/run_summary.jsonConfiguration1.2 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/sft_data_report.jsonConfiguration142 B —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/status.jsonConfiguration530 B —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/training_run.jsonConfiguration1.7 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/run_signature.jsonConfiguration3.5 KB —
runs/mmlu_pro_v3g_sta/report.jsonConfiguration8.2 KB —
runs/mmlu_pro_v3g_sta/rsi_run.jsonConfiguration25.3 KB —
runs/mmlu_pro_v3g_sta/static/select/.mcq_rsi_complete.jsonConfiguration302 B —
runs/mmlu_pro_v3g_sta/static/select/labels.report.jsonConfiguration406 B —
runs/mmlu_pro_v3g_sta/status.jsonConfiguration540 B —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00001-8phceham/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00002-4o3wp2qh/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00003-luywjdf9/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00004-gpyg7l8j/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00005-4dffwacy/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00006-4n8km1hk/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00007-1174yw89/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00008-b74_u4t5/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00009-_nfyfitw/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00010-bn9zer3s/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00011-60ehych4/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00012-ko9000rn/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00013-6u3yncu3/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00014-utw0d5ty/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00015-uwo_30cd/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00016-jft8o1nw/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00017-r0z0_h4m/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00018-1118i40o/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00019-e3by4x7t/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00020-subox343/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00021-a4edkaxq/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00022-1why0myb/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00023-brpx_fb_/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/step-00024-wzgh65sz/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00001-0u2h9n20/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00002-mf6ii3ck/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00003-vfom3g90/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00004-gnzs0p8w/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00005-yrsmwt6u/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00006-7b2koi89/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00007-g9wlo2u8/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00008-ns2e1pjt/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00009-j_inoe7y/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00010-qhd0liuq/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00011-t_6517wu/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00012-v16k40t1/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00013-cxwgac_l/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00014-mp8yqs8j/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00015-dghadoyr/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00016-swvgoaiy/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00017-z48fiv47/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00018-10g8xf6k/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00019-njf_hsjz/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00020-ya_rxj8k/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00021-gj_qbyjl/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00022-d3y2j3hl/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00023-5ah2twwu/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00024-n1r80g9s/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00025-rgbhgax6/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00026-8jcsk3gm/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00027-gj4tg04n/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00028-uzkzxpbt/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00029-9a435dii/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00030-7vm28ien/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00031-hn3b3qi4/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00032-o36ngwt2/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00033-kkf83afo/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00034-j1sf35z5/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00035-hisntrsx/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00036-g8x1hr_r/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00037-rbnznf05/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00038-h60s30dg/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00039-k0ejo037/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00040-0bauaczi/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00041-ce3_v7t4/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00042-rqnxizwx/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00043-1rho_pwq/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00044-exuy2wfy/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00045-iwja6hk4/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00046-j3cm1rdi/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00047-gd3hbamb/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00048-w44eaf5b/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00049-a1dqvrkn/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00050-zgt6l5_r/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00051-2aaf0dfl/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00052-u2j6g8zq/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00053-642i3qew/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00054-g0z9vz6h/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00055-xdvihh_9/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00056-w3g3hlx8/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00057-gz07x3mu/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00058-09jdgj9j/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00059-r2eesjmt/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00060-xiis3d05/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00061-e24boggm/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00062-dcsgr2oh/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00063-inr6pffw/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/step-00064-__wf__ux/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/README.mdDocumentation5.4 KB —
runs/mmlu_pro_v3g_sta/report.mdDocumentation2.0 KB —
advisor_cache.tar.gzOther28.4 MB 26fdc1f0b85a
logs/mmlu_pro_v3g_sta.logOther19.2 KB —
runs/mmlu_pro_v3g_sta/dev_metrics.csvOther590 B —
runs/mmlu_pro_v3g_sta/logs/prefetch__advisors.logOther2.2 KB —
runs/mmlu_pro_v3g_sta/logs/r1__S1_dev.logOther45.7 KB —
runs/mmlu_pro_v3g_sta/logs/r1__grpo.logOther3.0 KB —
runs/mmlu_pro_v3g_sta/logs/r1__grpo_dev.logOther45.6 KB —
runs/mmlu_pro_v3g_sta/logs/r2__static__grpo.logOther5.7 KB —
runs/mmlu_pro_v3g_sta/logs/r2__static__grpo_dev.logOther45.5 KB —
runs/mmlu_pro_v3g_sta/logs/r2__static__sft.logOther35.1 KB —
runs/mmlu_pro_v3g_sta/logs/r2__static__sft_dev.logOther45.9 KB —
runs/mmlu_pro_v3g_sta/logs/r3__static__sft.logOther16.9 KB —
runs/mmlu_pro_v3g_sta/logs/static__select.logOther288 B —
runs/mmlu_pro_v3g_sta/r1/S1_dev/manager_tool_eval.jsonlOther235.1 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/final/chat_template.jinjaOther7.8 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/metrics.jsonlOther49.7 KB —
runs/mmlu_pro_v3g_sta/r1/grpo_dev/manager_tool_eval.jsonlOther235.7 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/final/chat_template.jinjaOther7.8 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/metrics.jsonlOther133.3 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo_dev/manager_tool_eval.jsonlOther210.4 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/chat_template.jinjaOther7.8 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/events.jsonlOther935 B —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/gpu_samples.jsonlOther10.3 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/metrics.jsonlOther34.7 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/training_log.jsonlOther30.0 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/usage.jsonlOther276.8 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft_dev/manager_tool_eval.jsonlOther206.2 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/events.jsonlOther331 B —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/gpu_samples.jsonlOther5.7 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/metrics.jsonlOther17.6 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/training_log.jsonlOther15.3 KB —
runs/mmlu_pro_v3g_sta/r3/static/sft/model/usage.jsonlOther144.9 KB —
runs/mmlu_pro_v3g_sta/static/select/labels.jsonlOther1.3 MB —
.gitattributesRepository1.8 KB —
runs/mmlu_pro_v3g_sta/r1/grpo/final/tokenizer.jsonTokenizer20.0 MB 06b9509352d2
runs/mmlu_pro_v3g_sta/r1/grpo/final/tokenizer_config.jsonTokenizer1.1 KB —
runs/mmlu_pro_v3g_sta/r2/static/grpo/final/tokenizer.jsonTokenizer20.0 MB 06b9509352d2
runs/mmlu_pro_v3g_sta/r2/static/grpo/final/tokenizer_config.jsonTokenizer1.1 KB —
runs/mmlu_pro_v3g_sta/r2/static/sft/model/tokenizer.jsonTokenizer20.0 MB 06b9509352d2
runs/mmlu_pro_v3g_sta/r2/static/sft/model/tokenizer_config.jsonTokenizer1.1 KB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
349.3 MB
Download from Madison

Released by Madison through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published349.3 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.