xiulinyang/GPT2_no_function_53
Updated • 5
Xiulin Yang
xiulinyang
AI & ML interests
Language Modeling, Interpretability, (compositional) generalization, tokenization
Organizations
None yet
xiulinyang/PT2_no_function_53
Updated
xiulinyang/GPT2_natural_function_42_b
Updated • 2
xiulinyang/linear_only_chunk_0
29.9M • Updated • 3
xiulinyang/linear_dyck_chunk_0
29.9M • Updated • 2
xiulinyang/dynamic_only_chunk_0
29.9M • Updated • 3
xiulinyang/dynamic_dyck_chunk_0
29.9M • Updated • 3
xiulinyang/dynamic_only_chunk_96
29.9M • Updated • 3
xiulinyang/dynamic_only_chunk_128
29.9M • Updated • 3
xiulinyang/linear_only_chunk_128
29.9M • Updated • 3
xiulinyang/linear_only_chunk_96
29.9M • Updated • 3
xiulinyang/linear_dyck_chunk_128
29.9M • Updated • 3
xiulinyang/linear_dyck_chunk_96
29.9M • Updated • 3
xiulinyang/dynamic_dyck_chunk_128
29.9M • Updated • 3
xiulinyang/dynamic_dyck_chunk_96
29.9M • Updated • 6
xiulinyang/dynamic_only_96
29.9M • Updated • 5
xiulinyang/dynamic_only_0
29.9M • Updated • 5
xiulinyang/dynamic_only_128
29.9M • Updated • 8
xiulinyang/linear_only_0
29.9M • Updated • 4
xiulinyang/linear_only_128
29.9M • Updated • 4
xiulinyang/linear_only_96
29.9M • Updated • 4
xiulinyang/linear_dyck_0
29.9M • Updated • 12
xiulinyang/linear_dyck_128
29.9M • Updated • 3
xiulinyang/linear_dyck_96
29.9M • Updated • 6
xiulinyang/dynamic_dyck_96
29.9M • Updated • 4
xiulinyang/dynamic_dyck_128
29.9M • Updated • 3
xiulinyang/dynamic_dyck_0
29.9M • Updated • 7
xiulinyang/output_linear_10Mf_20_32
29.9M • Updated • 6
xiulinyang/output_dynamic_10Mf_20_32
29.9M • Updated • 3
xiulinyang/output_linear_10Mf_20
29.9M • Updated • 3