ShaoShuai0605
/

Harness-R1

Reinforcement Learning

harness-engineering

supervised-fine-tuning

Model card Files Files and versions

Commit History

Upload cold-start SFT weights

f6a9159
verified

ShaoShuai0605 commited on 19 days ago

Add cold-start SFT metadata and inference config

615b9c3
verified

ShaoShuai0605 commited on 19 days ago

Upload direct Agent-SFT target model weights

a045bd2
verified

ShaoShuai0605 commited on 25 days ago

Document and add Agent-SFT target metadata

a4184cc
verified

ShaoShuai0605 commited on 25 days ago

Add direct Agent-SFT A1 tokenizer

857c959
verified

ShaoShuai0605 commited on 25 days ago

Rename checkpoint folders to harness-r1 and agent-sft-harness-r1

c1ae038
verified

ShaoShuai0605 commited on Aug 1

Add Harness-R1 E1 iter495 main-table engineer checkpoint

efd864b
verified

ShaoShuai0605 commited on Aug 1

Simplify model card

2b06337
verified

ShaoShuai0605 commited on Aug 1

Add Harness-R1 E0 iter143 main-table engineer checkpoint

a96827d
verified

ShaoShuai0605 commited on Aug 1

Add model card for main-table Harness-R1 checkpoints

0e26bf9
verified

ShaoShuai0605 commited on Aug 1

initial commit

7fb7023
verified

ShaoShuai0605 commited on Jul 31