Xiulin Yang's picture

2

Xiulin Yang

xiulinyang

·

xiulinyang

AI & ML interests

Language Modeling, Interpretability, (compositional) generalization, tokenization

Recent Activity

updated a collection 12 days ago

updated a collection 12 days ago

updated a collection 12 days ago

View all activity

Organizations

None yet

xiulinyang 's models 322

xiulinyang/dynamic_only_chunk_96

29.9M • Updated Nov 25 • 6

xiulinyang/dynamic_only_chunk_128

29.9M • Updated Nov 25 • 6

xiulinyang/linear_only_chunk_128

29.9M • Updated Nov 25 • 5

xiulinyang/linear_only_chunk_96

29.9M • Updated Nov 25 • 6

xiulinyang/linear_dyck_chunk_128

29.9M • Updated Nov 25 • 3

xiulinyang/linear_dyck_chunk_96

29.9M • Updated Nov 25 • 3

xiulinyang/dynamic_dyck_chunk_128

29.9M • Updated Nov 25 • 5

xiulinyang/dynamic_dyck_chunk_96

29.9M • Updated Nov 25 • 6

xiulinyang/dynamic_only_96

29.9M • Updated Nov 25 • 3

xiulinyang/dynamic_only_0

29.9M • Updated Nov 25 • 3

xiulinyang/dynamic_only_128

29.9M • Updated Nov 25 • 3

xiulinyang/linear_only_0

29.9M • Updated Nov 25 • 3

xiulinyang/linear_only_128

29.9M • Updated Nov 25 • 2

xiulinyang/linear_only_96

29.9M • Updated Nov 25 • 2

xiulinyang/linear_dyck_0

29.9M • Updated Nov 25 • 3

xiulinyang/linear_dyck_128

29.9M • Updated Nov 25 • 3

xiulinyang/linear_dyck_96

29.9M • Updated Nov 25 • 3

xiulinyang/dynamic_dyck_96

29.9M • Updated Nov 25 • 3

xiulinyang/dynamic_dyck_128

29.9M • Updated Nov 25 • 3

xiulinyang/dynamic_dyck_0

29.9M • Updated Nov 25 • 3

xiulinyang/output_linear_10Mf_20_32

29.9M • Updated Nov 14 • 3

xiulinyang/output_dynamic_10Mf_20_32

29.9M • Updated Nov 14 • 2

xiulinyang/output_linear_10Mf_20

29.9M • Updated Nov 14 • 3

xiulinyang/output_dynamic_10Mf_20

29.9M • Updated Nov 14 • 4

xiulinyang/gpt2_small_wiki_100M_32768_76

Updated Nov 4 • 3

xiulinyang/gpt2_small_baby_100M_32768_76

Updated Nov 4 • 8

xiulinyang/gpt2_small_baby_100M_32768_53

Updated Nov 3 • 3

xiulinyang/gpt2_small_wiki_100M_32768_53

Updated Nov 3 • 5

xiulinyang/dynamic_att20

5.52M • Updated Oct 28 • 3

xiulinyang/linear_att20

5.52M • Updated Oct 28 • 4