xiulinyang/output_dynamic_10Mf_20
29.9M • Updated • 3
Xiulin Yang
xiulinyang
·
AI & ML interests
Language Modeling, Interpretability, (compositional) generalization, tokenization
Organizations
None yet
xiulinyang/gpt2_small_wiki_100M_32768_76
Updated • 49
xiulinyang/gpt2_small_baby_100M_32768_76
Updated • 43
xiulinyang/gpt2_small_baby_100M_32768_53
Updated • 48
xiulinyang/gpt2_small_wiki_100M_32768_53
Updated • 48
xiulinyang/dynamic_att20
5.52M • Updated • 3
xiulinyang/linear_att20
5.52M • Updated • 3
xiulinyang/linear_att
5.52M • Updated • 6
xiulinyang/dynamic_att
5.52M • Updated • 6
xiulinyang/gpt2_mini_baby-dyck_10Mf_32768_42
Updated • 4
xiulinyang/gpt2_mini_baby-dyck_10Mf_32768_76
Updated • 6
xiulinyang/gpt2_mini_baby-dyck_10Mf_32768_53
Updated • 6
xiulinyang/pretraining-10Mf-gpt2-small-42
Text Generation • 29.6M • Updated • 7
xiulinyang/pre-pretraining-10Mf-gpt2-small-42
Text Generation • 29.6M • Updated • 8
xiulinyang/pretraining-gpt2-mini-10Mf
Text Generation • 29.6M • Updated • 9
xiulinyang/pre-pretraining-gpt2-mini-10Mf
Text Generation • 29.6M • Updated • 13
xiulinyang/replicate_dyn_linear
5.52M • Updated • 2
xiulinyang/replicate_linear_attention
5.52M • Updated • 3
xiulinyang/pre-pretraining-10Mf-40k
Updated
xiulinyang/replicate_dynamic_attention
5.52M • Updated • 2
xiulinyang/pre-pretraining-10Mf-10k-53
Text Generation • 0.2B • Updated • 4
xiulinyang/pretraining-10Mf-10k-53
Text Generation • 0.2B • Updated • 10
xiulinyang/pretraining-10Mf-10k-42
Text Generation • 0.2B • Updated • 6
xiulinyang/pre-pretraining-10Mf-10k-42
Text Generation • 0.2B • Updated • 4
xiulinyang/pre-pretraining-10Mf-10k
Text Generation • 0.2B • Updated • 5
xiulinyang/pretraining-10Mf-10k
Text Generation • 0.2B • Updated • 10
xiulinyang/linear_attention_10Mf
11.8M • Updated • 2
xiulinyang/linear_attention_10M
11.8M • Updated • 2
xiulinyang/dynamic_attention_10M
11.8M • Updated • 2
xiulinyang/gpt2_small_wiki_50M_32768_76
Updated • 34