Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
Paper
•
2512.04844
•
Published
•
3
SSU: Source-Shielded Updates
Collection of models for "Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates"
-
-
ssu-project/OLMo-2-1124-7B-Instruct-am-random
7B • Updated • 10 -
ssu-project/OLMo-2-1124-7B-Instruct-am-magnitude
7B • Updated • 8 -
ssu-project/OLMo-2-1124-7B-Instruct-am-ssu
7B • Updated • 9 -
ssu-project/OLMo-2-1124-7B-Instruct-am-hft
7B • Updated • 8 -
ssu-project/OLMo-2-1124-7B-Instruct-am-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-am-gmt
7B • Updated • 9 -
ssu-project/OLMo-2-1124-7B-Instruct-am-fft
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-random
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-magnitude
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-ssu
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-hft
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-gmt
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ha-fft
7B • Updated • 1 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-random
7B • Updated • 8 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-magnitude
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-adalora
Updated -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-fft
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_ew
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_rw
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_0.125
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_0.25
7B • Updated • 5 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_0.375
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_0.625
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_0.75
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_0.875
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_alpaca
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_sgpt
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_fisher
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-random
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-magnitude
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-ssu
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-hft
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-gmt
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ky-fft
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-random
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-magnitude
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-ssu
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-hft
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-gmt
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ne-fft
7B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-am-random
14B • Updated • 5 -
ssu-project/OLMo-2-1124-13B-Instruct-am-magnitude
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-am-ssu
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-am-hft
14B • Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-am-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-am-gmt
14B • Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-am-fft
Updated -
ssu-project/OLMo-2-1124-13B-Instruct-ha-random
14B • Updated • 5 -
ssu-project/OLMo-2-1124-13B-Instruct-ha-magnitude
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-ha-ssu
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ha-hft
14B • Updated • 6 -
ssu-project/OLMo-2-1124-13B-Instruct-ha-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ha-gmt
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ha-fft
14B • Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-random
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-magnitude
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-ssu
14B • Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-hft
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-adalora
Updated • 5 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-gmt
14B • Updated • 5 -
ssu-project/OLMo-2-1124-13B-Instruct-ig-fft
14B • Updated • 6 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-random
14B • Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-magnitude
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-ssu
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-hft
14B • Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-gmt
14B • Updated • 5 -
ssu-project/OLMo-2-1124-13B-Instruct-ky-fft
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-random
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-magnitude
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-ssu
14B • Updated • 7 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-hft
14B • Updated • 4 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-adalora
Updated • 3 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-gmt
14B • Updated • 6 -
ssu-project/OLMo-2-1124-13B-Instruct-ne-fft
14B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.125
7B • Updated • 5 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.25
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.375
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.625
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.75
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.875
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-lota_0.5
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-s2ft_d
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-s2ft_d_16
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-s2ft_d_32
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-s2ft_d_64
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft_0.125
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft_0.25
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft_0.375
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft_0.625
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft_0.75
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-hft_0.875
7B • Updated • 2 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-ssu_128
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt_0.125
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt_0.25
7B • Updated • 6 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt_0.375
7B • Updated • 4 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt_0.625
7B • Updated • 7 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt_0.75
7B • Updated • 3 -
ssu-project/OLMo-2-1124-7B-Instruct-ig-gmt_0.875
7B • Updated • 7
