Spaces:

bird-of-paradise
/

ReTool-Implementation

Running

App Files Files Community

ReTool-Implementation / src

Commit History

Add custom sampler, train data loader and GRPO style train loop for ReTool_trainer

c710786
verified

bird-of-paradise commited on 19 days ago

adding test suite -- first commit

0690c9f
verified

bird-of-paradise commited on Jul 20

replace `model.generate` with custom generation function to optimize kv_cache

a0dec77
verified

bird-of-paradise commited on Jul 20

first commit --curriculum callback

cfa2a65
verified

bird-of-paradise commited on Jul 6

Add reward functions and registry

2fc6f4d
verified

bird-of-paradise commited on Jul 6

Use weighted list reward functions

e9196fe
verified

bird-of-paradise commited on Jul 6

clean up default args

f757722
verified

bird-of-paradise commited on Jun 8

Upload 5 files

cb481ca
verified

bird-of-paradise commited on Jun 1