Skip to page content
SAVRN
Search Plan a project

Dataset

internal-mrme-benchmark-conditioned-runtime-20261005

by Saif Punjwani SaifPunjwani/internal-mrme-benchmark-conditioned-runtime-20261005

This repository is a transfer artifact for an internal calibration study. The corpora deliberately expose evaluation benchmarks and include captured, cross-family, and explicitly constructed training branches.

Rows—
Configurations—
Size1.8 GB
Licenseother
AccessPublicly accessible
Monthly Downloads338

Dataset Card

This repository is a transfer artifact for an internal calibration study. The corpora deliberately expose evaluation benchmarks and include captured, cross-family, and explicitly constructed training branches. They are not unbiased evaluation evidence and must not be used to support paper claims. All downstream checkpoints and results must retain these flags: - evaluationcontaminated: true - benchmarkconditioned: true - validforunbiasedevaluation: false The archive contains no selected or rewritten final-evaluation generations. Fresh complete n=64 pools are generated separately and retained in full.

Excerpt from the card by Saif Punjwani, licensed other.

Details

Repository
SaifPunjwani/internal-mrme-benchmark-conditioned-runtime-20261005
Publisher
Saif Punjwani
Task category
Not stated by the source
Tags
Not stated by the source
Size category
Not stated by the source
Languages
Not stated by the source
Revision
bab6ad924492b08add1882a22e245b85f0b56bb0
Last updated
2026-10-07

Files

544 files, 1.8 GB in total.

Data122 files · 1.8 GB
Documentation25 files · 187.2 KB
Other396 files · 8.5 MB
Repository1 file · 4.3 KB
Every file
FileTypeSizeSHA-256
code_v1/CODE_MANIFEST.jsonData9.9 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v1/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v1/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v1/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v1/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v1/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v1/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v1/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v1/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v1/requirements.txtData143 B—
code_v2/CODE_MANIFEST.jsonData10.3 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v2/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v2/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v2/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v2/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v2/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v2/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v2/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v2/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v2/requirements.txtData143 B—
code_v3/CODE_MANIFEST.jsonData10.3 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v3/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v3/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v3/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v3/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v3/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v3/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v3/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v3/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v3/requirements.txtData143 B—
code_v4/CODE_MANIFEST.jsonData10.2 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v4/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v4/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v4/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v4/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v4/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v4/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v4/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v4/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v4/requirements.txtData143 B—
code_v5/CODE_MANIFEST.jsonData10.5 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v5/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v5/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v5/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v5/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v5/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v5/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v5/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v5/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v5/requirements.txtData143 B—
code_v6/CODE_MANIFEST.jsonData10.7 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v6/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v6/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v6/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v6/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v6/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v6/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v6/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v6/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v6/requirements.txtData143 B—
code_v7/CODE_MANIFEST.jsonData10.8 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v7/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v7/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v7/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v7/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v7/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v7/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v7/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v7/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v7/requirements.txtData143 B—
code_v8/CODE_MANIFEST.jsonData10.8 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solutions_2fe88a.jsonData13.0 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/package_r1/manifest.jsonData379.9 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/package_r1/mmlupro.jsonData11.7 MB362606a573ba
code_v8/analysis/general_base_2026-09-24/package/data/test-00000-of-00001.parquetData345.8 KB545cd5cce9c5
code_v8/analysis/general_base_2026-09-24/package/general.jsonData5.2 MB—
code_v8/analysis/general_base_2026-09-24/package/instruction_following_eval/data/input_data.jsonlData207.1 KB—
code_v8/analysis/general_base_2026-09-24/package/manifest.jsonData5.7 KB—
code_v8/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txtData619 B—
code_v8/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/sent_starters.txtData241 B—
code_v8/analysis/mmlu_redux_2026-09-24/package/manifest.jsonData32.1 KB—
code_v8/analysis/mmlu_redux_2026-09-24/package/redux.jsonData1.6 MB—
code_v8/requirements.txtData143 B—
runtime_v1/PREPARATION_RECEIPT.jsonData1.2 KB—
runtime_v1/corpora/ministral-3-3b/grpo.jsonlData76.3 MBe19ae277c7f8
runtime_v1/corpora/ministral-3-3b/manifest.jsonData1.2 KB—
runtime_v1/corpora/ministral-3-3b/preferences.jsonlData212.6 MBf98650d101fe
runtime_v1/corpora/ministral-3-3b/sft.jsonlData129.8 MB219bed3a9626
runtime_v1/corpora/ministral-3-3b/source_ledger.jsonlData21.5 MBccece6fa1254
runtime_v1/corpora/qwen3-1.7b/grpo.jsonlData76.3 MB22161cd2a648
runtime_v1/corpora/qwen3-1.7b/manifest.jsonData1.2 KB—
runtime_v1/corpora/qwen3-1.7b/preferences.jsonlData323.9 MB750009962485
runtime_v1/corpora/qwen3-1.7b/sft.jsonlData196.5 MBd84650dd248b
runtime_v1/corpora/qwen3-1.7b/source_ledger.jsonlData21.3 MB999ba8e9f257
runtime_v1/corpora/qwen3-4b/grpo.jsonlData76.2 MBb3d8aac3e5c1
runtime_v1/corpora/qwen3-4b/manifest.jsonData1.2 KB—
runtime_v1/corpora/qwen3-4b/preferences.jsonlData296.1 MB7f05fa3ea22f
runtime_v1/corpora/qwen3-4b/sft.jsonlData191.3 MBeb764dd70f89
runtime_v1/corpora/qwen3-4b/source_ledger.jsonlData21.2 MB586ec8a6b0c9
runtime_v1/histograms.jsonData22.9 KB—
runtime_v1/targets.jsonData5.7 KB—
README.mdDocumentation773 B—
code_v1/README.mdDocumentation583 B—
code_v1/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v1/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v2/README.mdDocumentation583 B—
code_v2/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v2/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v3/README.mdDocumentation583 B—
code_v3/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v3/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v4/README.mdDocumentation583 B—
code_v4/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v4/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v5/README.mdDocumentation583 B—
code_v5/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v5/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v6/README.mdDocumentation583 B—
code_v6/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v6/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v7/README.mdDocumentation583 B—
code_v7/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v7/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v8/README.mdDocumentation583 B—
code_v8/analysis/general_base_2026-09-24/package/instruction_following_eval/LICENSEDocumentation11.4 KB—
code_v8/analysis/general_base_2026-09-24/package/zeroeval/LICENSEDocumentation11.4 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v1/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v1/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v1/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v1/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v1/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v1/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v1/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v1/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v1/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v1/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v1/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v1/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v1/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v1/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v1/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v1/internal_mrme/__init__.pyOther70 B—
code_v1/internal_mrme/corpus.pyOther14.9 KB—
code_v1/internal_mrme/curves.pyOther1.5 KB—
code_v1/internal_mrme/evaluate.pyOther14.4 KB—
code_v1/internal_mrme/histograms.pyOther7.4 KB—
code_v1/internal_mrme/rewards.pyOther3.4 KB—
code_v1/internal_mrme/sources.pyOther1.4 KB—
code_v1/internal_mrme/targets.pyOther12.8 KB—
code_v1/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v1/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v1/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v1/scripts/expdis_general_worker.pyOther13.4 KB—
code_v1/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v1/scripts/expdis_redux_data.pyOther8.9 KB—
code_v1/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v1/scripts/run_internal_mrme_eval.pyOther45.8 KB—
code_v1/scripts/verify_internal_mrme_checkpoint.pyOther48.1 KB—
code_v1/training/internal_mrme_calibration.pyOther34.0 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v2/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v2/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v2/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v2/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v2/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v2/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v2/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v2/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v2/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v2/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v2/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v2/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v2/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v2/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v2/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v2/internal_mrme/__init__.pyOther70 B—
code_v2/internal_mrme/corpus.pyOther14.9 KB—
code_v2/internal_mrme/curves.pyOther1.5 KB—
code_v2/internal_mrme/evaluate.pyOther14.4 KB—
code_v2/internal_mrme/histograms.pyOther7.4 KB—
code_v2/internal_mrme/rewards.pyOther3.4 KB—
code_v2/internal_mrme/sources.pyOther1.4 KB—
code_v2/internal_mrme/targets.pyOther12.8 KB—
code_v2/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v2/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v2/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v2/scripts/expdis_general_worker.pyOther13.4 KB—
code_v2/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v2/scripts/expdis_redux_data.pyOther8.9 KB—
code_v2/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v2/scripts/run_internal_mrme_eval.pyOther45.8 KB—
code_v2/scripts/verify_internal_mrme_checkpoint.pyOther48.1 KB—
code_v2/training/internal_mrme_calibration.pyOther35.4 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v3/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v3/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v3/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v3/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v3/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v3/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v3/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v3/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v3/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v3/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v3/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v3/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v3/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v3/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v3/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v3/internal_mrme/__init__.pyOther70 B—
code_v3/internal_mrme/corpus.pyOther14.9 KB—
code_v3/internal_mrme/curves.pyOther1.5 KB—
code_v3/internal_mrme/evaluate.pyOther14.4 KB—
code_v3/internal_mrme/histograms.pyOther7.4 KB—
code_v3/internal_mrme/rewards.pyOther3.4 KB—
code_v3/internal_mrme/sources.pyOther1.4 KB—
code_v3/internal_mrme/targets.pyOther12.8 KB—
code_v3/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v3/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v3/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v3/scripts/expdis_general_worker.pyOther13.4 KB—
code_v3/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v3/scripts/expdis_redux_data.pyOther8.9 KB—
code_v3/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v3/scripts/run_internal_mrme_eval.pyOther45.8 KB—
code_v3/scripts/verify_internal_mrme_checkpoint.pyOther48.1 KB—
code_v3/training/internal_mrme_calibration.pyOther35.5 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v4/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v4/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v4/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v4/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v4/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v4/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v4/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v4/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v4/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v4/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v4/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v4/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v4/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v4/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v4/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v4/internal_mrme/__init__.pyOther70 B—
code_v4/internal_mrme/corpus.pyOther14.9 KB—
code_v4/internal_mrme/curves.pyOther1.5 KB—
code_v4/internal_mrme/evaluate.pyOther14.4 KB—
code_v4/internal_mrme/histograms.pyOther7.4 KB—
code_v4/internal_mrme/rewards.pyOther3.4 KB—
code_v4/internal_mrme/sources.pyOther1.4 KB—
code_v4/internal_mrme/targets.pyOther12.8 KB—
code_v4/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v4/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v4/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v4/scripts/expdis_general_worker.pyOther13.4 KB—
code_v4/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v4/scripts/expdis_redux_data.pyOther8.9 KB—
code_v4/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v4/scripts/run_internal_mrme_eval.pyOther65.1 KB—
code_v4/scripts/verify_internal_mrme_checkpoint.pyOther48.1 KB—
code_v4/training/internal_mrme_calibration.pyOther35.5 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v5/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v5/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v5/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v5/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v5/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v5/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v5/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v5/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v5/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v5/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v5/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v5/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v5/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v5/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v5/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v5/internal_mrme/__init__.pyOther70 B—
code_v5/internal_mrme/corpus.pyOther14.9 KB—
code_v5/internal_mrme/curves.pyOther1.5 KB—
code_v5/internal_mrme/evaluate.pyOther14.4 KB—
code_v5/internal_mrme/histograms.pyOther7.4 KB—
code_v5/internal_mrme/residual_calibration.pyOther6.8 KB—
code_v5/internal_mrme/residual_round.pyOther10.5 KB—
code_v5/internal_mrme/rewards.pyOther3.4 KB—
code_v5/internal_mrme/sources.pyOther1.4 KB—
code_v5/internal_mrme/targets.pyOther12.8 KB—
code_v5/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v5/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v5/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v5/scripts/expdis_general_worker.pyOther13.4 KB—
code_v5/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v5/scripts/expdis_redux_data.pyOther8.9 KB—
code_v5/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v5/scripts/run_internal_mrme_eval.pyOther65.1 KB—
code_v5/scripts/verify_internal_mrme_checkpoint.pyOther48.1 KB—
code_v5/training/internal_mrme_calibration.pyOther35.5 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v6/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v6/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v6/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v6/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v6/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v6/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v6/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v6/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v6/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v6/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v6/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v6/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v6/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v6/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v6/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v6/internal_mrme/__init__.pyOther70 B—
code_v6/internal_mrme/corpus.pyOther14.9 KB—
code_v6/internal_mrme/curves.pyOther1.5 KB—
code_v6/internal_mrme/evaluate.pyOther14.4 KB—
code_v6/internal_mrme/histograms.pyOther7.4 KB—
code_v6/internal_mrme/residual_calibration.pyOther7.6 KB—
code_v6/internal_mrme/residual_round.pyOther13.1 KB—
code_v6/internal_mrme/rewards.pyOther3.4 KB—
code_v6/internal_mrme/sources.pyOther1.4 KB—
code_v6/internal_mrme/suite_assembly.pyOther15.6 KB—
code_v6/internal_mrme/targets.pyOther12.8 KB—
code_v6/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v6/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v6/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v6/scripts/expdis_general_worker.pyOther13.4 KB—
code_v6/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v6/scripts/expdis_redux_data.pyOther8.9 KB—
code_v6/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v6/scripts/run_internal_mrme_eval.pyOther65.1 KB—
code_v6/scripts/verify_internal_mrme_checkpoint.pyOther48.1 KB—
code_v6/training/internal_mrme_calibration.pyOther35.5 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v7/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v7/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v7/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v7/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v7/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v7/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v7/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v7/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v7/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v7/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v7/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v7/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v7/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v7/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v7/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v7/internal_mrme/__init__.pyOther70 B—
code_v7/internal_mrme/corpus.pyOther14.9 KB—
code_v7/internal_mrme/curves.pyOther1.5 KB—
code_v7/internal_mrme/evaluate.pyOther14.4 KB—
code_v7/internal_mrme/histograms.pyOther7.4 KB—
code_v7/internal_mrme/residual_calibration.pyOther7.6 KB—
code_v7/internal_mrme/residual_round.pyOther13.1 KB—
code_v7/internal_mrme/rewards.pyOther3.4 KB—
code_v7/internal_mrme/sources.pyOther1.4 KB—
code_v7/internal_mrme/suite_assembly.pyOther16.1 KB—
code_v7/internal_mrme/targets.pyOther12.8 KB—
code_v7/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v7/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v7/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v7/scripts/expdis_general_worker.pyOther13.4 KB—
code_v7/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v7/scripts/expdis_redux_data.pyOther8.9 KB—
code_v7/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v7/scripts/run_internal_mrme_eval.pyOther47.0 KB—
code_v7/scripts/verify_internal_mrme_checkpoint.pyOther49.6 KB—
code_v7/training/internal_mrme_calibration.pyOther35.5 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/artifacts.pyOther21.9 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/common.pyOther5.2 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/__init__.pyOther594 B—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_native_solution_source.pyOther4.6 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/aime24_source_preserving_proofs.pyOther14.6 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/bench_datasets.pyOther5.7 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/run_eval.pyOther123.7 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/scoring.pyOther19.2 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/audit_harness/qwen_eval/teacher_protocols.pyOther41.5 KB—
code_v8/analysis/final_eval_matrix_2026-09-20/package_r1/expdis_final_eval_worker.pyOther19.9 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_general.pyOther22.9 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_general_gpqa.pyOther7.5 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_general_ifeval.pyOther10.2 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_general_worker.pyOther13.4 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_general_zebra.pyOther11.2 KB—
code_v8/analysis/general_base_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v8/analysis/general_base_2026-09-24/package/instruction_following_eval/evaluation_lib.pyOther7.0 KB—
code_v8/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions.pyOther55.2 KB—
code_v8/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_registry.pyOther7.2 KB—
code_v8/analysis/general_base_2026-09-24/package/instruction_following_eval/instructions_util.pyOther19.5 KB—
code_v8/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/collocations.tabOther594 B—
code_v8/analysis/general_base_2026-09-24/package/nltk_data/tokenizers/punkt_tab/english/ortho_context.tabOther236.3 KB—
code_v8/analysis/general_base_2026-09-24/package/zeroeval/src/_TEMPLATES.pyOther5.4 KB—
code_v8/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/eval_utils.pyOther5.5 KB—
code_v8/analysis/general_base_2026-09-24/package/zeroeval/src/evaluation/zebra_grid_eval.pyOther20.9 KB—
code_v8/analysis/general_base_2026-09-24/package/zeroeval/src/templates/ZEBRA_GRID.pyOther1.4 KB—
code_v8/analysis/mmlu_redux_2026-09-24/package/expdis_final_eval_worker.pyOther19.9 KB—
code_v8/analysis/mmlu_redux_2026-09-24/package/expdis_redux_data.pyOther8.9 KB—
code_v8/analysis/mmlu_redux_2026-09-24/package/expdis_redux_worker.pyOther14.1 KB—
code_v8/internal_mrme/__init__.pyOther70 B—
code_v8/internal_mrme/corpus.pyOther14.9 KB—
code_v8/internal_mrme/curves.pyOther1.5 KB—
code_v8/internal_mrme/evaluate.pyOther14.4 KB—
code_v8/internal_mrme/histograms.pyOther7.4 KB—
code_v8/internal_mrme/residual_calibration.pyOther7.6 KB—
code_v8/internal_mrme/residual_round.pyOther13.1 KB—
code_v8/internal_mrme/rewards.pyOther3.4 KB—
code_v8/internal_mrme/sources.pyOther1.4 KB—
code_v8/internal_mrme/suite_assembly.pyOther16.1 KB—
code_v8/internal_mrme/targets.pyOther12.8 KB—
code_v8/scripts/expdis_final_eval_worker.pyOther19.9 KB—
code_v8/scripts/expdis_general_gpqa.pyOther7.5 KB—
code_v8/scripts/expdis_general_ifeval.pyOther10.2 KB—
code_v8/scripts/expdis_general_worker.pyOther13.4 KB—
code_v8/scripts/expdis_general_zebra.pyOther11.2 KB—
code_v8/scripts/expdis_redux_data.pyOther8.9 KB—
code_v8/scripts/expdis_redux_worker.pyOther14.1 KB—
code_v8/scripts/run_internal_mrme_eval.pyOther47.0 KB—
code_v8/scripts/run_internal_mrme_sharded_eval.pyOther65.1 KB—
code_v8/scripts/verify_internal_mrme_checkpoint.pyOther49.6 KB—
code_v8/training/internal_mrme_calibration.pyOther35.5 KB—
.gitattributesRepository4.3 KB—

License and Download

License
other
Access
No access gate
Download from Saif Punjwani

Released by Saif Punjwani through its official repository on Hugging Face.