Skip to content
ModelVerifiedExternal

Lirpg Fullparam Qwen2 5 Math 7b Handrolled Zeroinit Token Grpo

KindOtherBase modelQwen2.5Publisher@MilaWangCgrade

Model source

Kind
Other
File size
8.96 KB–4.59 GB
Base model
Qwen2.5
Updated
Sep 25, 2026
Publisher
@MilaWang
Parameters
7B

Source excerpt

Model artifacts

64 artifacts

best_ckpt_step_40/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 1f8e33f8cd48…84b1

best_ckpt_step_40/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 ad4059a8cdbe…f690

global_step_10/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 d06f1c756aaa…556d

global_step_10/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 fae7fe17a2c8…5368

global_step_10/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 088286af3261…2f24

global_step_10/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 8151e057adbb…b843

global_step_10/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 71891428c06d…33d2

global_step_10/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 eba9f314ac61…3241

global_step_100/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 b5dc083453ae…f1d1

global_step_100/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 42be3b175ec3…c027

global_step_100/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 bf462d447944…02f6

global_step_100/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 cc6b34083987…f28f

global_step_100/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 2b751051bfd0…9c71

global_step_100/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 66e0162f9d9b…71dc

global_step_110/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 ea5d47a56bfa…ae9c

global_step_110/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 51b5ad2e28c8…e145

global_step_110/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 517f0b836294…ea55

global_step_110/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 a76b5706cd4d…a1ab

global_step_110/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 bbe9145905e0…b825

global_step_110/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 824eb8b05c30…fb23

global_step_120/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 1bead42e3dd3…7cb8

global_step_120/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 c04766156e18…e14a

global_step_120/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 80321d6cb984…bdaa

global_step_120/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 f1f50ad9a6cb…99d4

global_step_120/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 c24ac88b52be…9694

global_step_120/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 8be2df295c33…a27b

global_step_20/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 e8223cba2cdc…5f10

global_step_20/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 32f14858e5f8…609b

global_step_20/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 c09162de8715…302a

global_step_20/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 0e3bc1228367…6c77

global_step_20/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 34509ea1270c…502d

global_step_20/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 9a9ee547f0d5…0f75

global_step_30/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 82f08a5afe7d…6dfa

global_step_30/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 e03e175cb5a2…be7e

global_step_30/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 55c1f2ca3ce6…9222

global_step_30/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 273678f39220…7a1e

global_step_30/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 3f44d516c8c2…3b90

global_step_30/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 df2a5a2e8e8a…2b5f

global_step_40/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 1f071c071a39…d596

global_step_40/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 2f06f641064d…d58b

global_step_40/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 1572deb261bc…97f4

global_step_40/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 d7e3d497bb41…8324

global_step_50/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 4f2581b48929…e8ba

global_step_50/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 764577405333…699a

global_step_50/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 7dd1ddcc085f…4061

global_step_50/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 c3789b3a4bfe…7e8c

global_step_50/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 69dd64c45819…b787

global_step_50/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 6e157937a4ea…fb56

global_step_60/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 34bd79f55b4d…d3aa

global_step_60/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 9d0cf52a74c7…e222

global_step_60/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 22cd7c1e19d5…21d4

global_step_60/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 6ee8187347c6…042e

global_step_60/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 a3f91e0270f1…685c

global_step_60/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 8ca5655c3393…ded6

global_step_70/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 8fe570776811…35e3

global_step_70/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 9b92d9f29d42…a204

global_step_70/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 76e1544c57cf…1d98

global_step_70/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 412511861748…4815

global_step_70/policy/model-00003-of-00004.safetensors

safetensors · 4.03 GB · SHA-256 27b1a2e9f383…1980

global_step_70/policy/model-00004-of-00004.safetensors

safetensors · 1.02 GB · SHA-256 ffce7dac04f9…6a73

global_step_80/intrinsic/intrinsic_adapter.pt

pt · 154 MB · SHA-256 42d9f383088e…310e

global_step_80/intrinsic/intrinsic_reward_head.pt

pt · 8.96 KB · SHA-256 e30305bedc28…5cd9

global_step_80/policy/model-00001-of-00004.safetensors

safetensors · 4.54 GB · SHA-256 07401d74aacb…1f0b

global_step_80/policy/model-00002-of-00004.safetensors

safetensors · 4.59 GB · SHA-256 6cffe3d77874…9655

Source excerpts

3 excerpts

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

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

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