Ir para o conteúdo
ModelVerificadoExterno

Lirpg Fullparam Qwen2 5 Math 7b Handrolled Zeroinit Hier Code

TipoOtherModelo baseQwen2.5Publicador@MilaWangCnota

Fonte do modelo

Tipo
Other
Tamanho do arquivo
8,96 KB–4,59 GB
Modelo base
Qwen2.5
Atualizado
14 de set. de 2026
Publicador
@MilaWang
Parâmetros
7B

Trecho da fonte

Artefatos de modelo

64 artefatos

best_ckpt_step_20/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 35f2222f2689…a9ec

best_ckpt_step_20/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 6dce2cb788d0…9083

best_ckpt_step_20/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 d813b6e043c7…b9b6

best_ckpt_step_20/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 c21acb7e70e6…01e6

best_ckpt_step_20/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 9737b10fce15…4e84

best_ckpt_step_20/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 bf5145e292b6…4307

best_ckpt_step_220/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 fa9212a45c66…b421

best_ckpt_step_220/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 8e92f8ef857c…3554

best_ckpt_step_220/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 3055d2df771b…ae2a

best_ckpt_step_220/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 4db058ec3678…abd7

best_ckpt_step_220/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 e07c52d22522…8057

best_ckpt_step_220/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 05eba73dfd36…29c6

best_ckpt_step_230/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 07fd71550f82…cbf0

best_ckpt_step_230/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 baa61c719cc7…66b9

best_ckpt_step_230/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 89ffe96d6e22…acd1

best_ckpt_step_230/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 3200ef215f95…2aaf

best_ckpt_step_230/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 d00f07ec1c1f…3198

best_ckpt_step_230/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 e8f84c00f033…186c

best_ckpt_step_250/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 5f06a19bc7a2…cfa4

best_ckpt_step_250/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 4092d11b51a1…48be

best_ckpt_step_250/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 27793dc30b18…3b27

best_ckpt_step_250/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 7e21cd87c76f…4157

best_ckpt_step_250/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 4df81e83ea29…1b2f

best_ckpt_step_250/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 42ade70d54ea…0d97

best_ckpt_step_290/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 428ba2bed8fb…2609

best_ckpt_step_290/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 f0634beb9229…f77f

best_ckpt_step_290/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 9b7587115ade…5368

best_ckpt_step_290/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 6a1d9fd9c143…d56d

best_ckpt_step_290/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 0f49427c5c6d…9f85

best_ckpt_step_290/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 e4713cba0fad…5bb0

best_ckpt_step_30/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 7c43c5d97445…1046

best_ckpt_step_30/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 0e20cbcb54a3…f7fa

best_ckpt_step_30/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 84e04a913df2…e960

best_ckpt_step_30/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 1806833f8fa8…9573

best_ckpt_step_30/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 00d40202dca8…52a2

best_ckpt_step_30/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 70106a0877d4…974f

best_ckpt_step_360/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 22ae58fc2738…b00c

best_ckpt_step_360/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 93e6b7cb621f…3aef

best_ckpt_step_360/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 66a474d9c44e…d943

best_ckpt_step_360/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 9afa987f03f2…5cea

best_ckpt_step_360/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 e81b991401cb…2ffb

best_ckpt_step_360/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 4ad71c1edc76…ea71

best_ckpt_step_40/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 8c71b974ca5b…03e1

best_ckpt_step_40/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 d1df708838b6…c889

best_ckpt_step_40/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 41ed55b4eea6…667b

best_ckpt_step_40/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 c20c2036b955…897f

best_ckpt_step_40/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 bf537201ac28…716f

best_ckpt_step_40/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 cf2b10db51cf…eb77

best_ckpt_step_400/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 28586fedec3e…5927

best_ckpt_step_400/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 4dfdbac72244…c319

best_ckpt_step_400/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 6931e01c7acb…dda1

best_ckpt_step_400/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 ef4591ac75dd…e2ee

best_ckpt_step_400/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 f13a8730d935…7c48

best_ckpt_step_400/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 16b1185623f9…452e

best_ckpt_step_410/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 28962efa153a…4c81

best_ckpt_step_410/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 1d9d5a04a205…4074

best_ckpt_step_410/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 780113fc3051…79f1

best_ckpt_step_410/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 b0acfa161cc7…5f23

best_ckpt_step_410/policy/model-00003-of-00004.safetensors

safetensors · 4,03 GB · SHA-256 e0aecc011681…8b5c

best_ckpt_step_410/policy/model-00004-of-00004.safetensors

safetensors · 1,02 GB · SHA-256 d25312910202…d655

best_ckpt_step_50/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 db6c65201cb7…95c2

best_ckpt_step_50/intrinsic/intrinsic_reward_head.pt

pt · 8,96 KB · SHA-256 772cf45fd5d8…f608

best_ckpt_step_50/policy/model-00001-of-00004.safetensors

safetensors · 4,54 GB · SHA-256 eb1b5fcc5af1…50b9

best_ckpt_step_50/policy/model-00002-of-00004.safetensors

safetensors · 4,59 GB · SHA-256 9fda5d82a9a9…025d

Trechos de fonte

2 trechos

Source context: 0 downloads · 0 likes · Repo backuppp/lirpg-fullparam-qwen2-5-math-7b-handrolled-zeroinit-hier-code

Source context: 0 downloads · 0 likes · Repo MilaWang/lirpg-fullparam-qwen2-5-math-7b-handrolled-zeroinit-hier-code