SeanWang0027
/

rose-opd-implementation

on-policy-distillation

Model card Files Files and versions

rose-opd-implementation / frameworks /slime /slime_plugins /models

102 kB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

SeanWang0027's picture

Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)

af66a85 verified about 1 month ago

glm5
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
__init__.py

0 Bytes
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
flash_dot_product_attention.py

7.1 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
glm4.py

625 Bytes
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
gpt_oss.py

2.12 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
hf_attention.py

6.93 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
learnable_softmax_attention.py

7.08 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
qwen3_5.py

8.47 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago
qwen3_next.py

9.38 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2) about 1 month ago