Andrew Lee's picture

1

Andrew Lee

ajyl

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 12 days ago

Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls

updated a model 4 months ago

ajyl/grpo_joint_seed_500

published a model 4 months ago

ajyl/grpo_joint_seed_500

View all activity

Organizations

ajyl 's models 53

ajyl/grpo_joint_seed_500

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_joint_seed_400

Text Generation • 0.0B • Updated Jun 21 • 1

ajyl/grpo_joint_seed_300

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_joint_seed_200

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_joint_seed_100

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_500_with_pretrain

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_400_with_pretrain

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_300_with_pretrain

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_200_with_pretrain

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_100_with_pretrain

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_500

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_400

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_300

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_200

Text Generation • 0.0B • Updated Jun 21

ajyl/grpo_sft_seed_100

Text Generation • 0.0B • Updated Jun 21

ajyl/sft_seed_500_512d_8L_8H_datatype_first_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_400_512d_8L_8H_datatype_first_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_300_512d_8L_8H_datatype_first_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_200_512d_8L_8H_datatype_first_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_100_512d_8L_8H_datatype_first_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_500_512d_8L_8H_datatype_full_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_400_512d_8L_8H_datatype_full_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_300_512d_8L_8H_datatype_full_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_200_512d_8L_8H_datatype_full_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/sft_seed_100_512d_8L_8H_datatype_full_pretrain

Text Generation • 0.0B • Updated Jun 14

ajyl/joint_seed_500_512d_8L_8H_alpha_1.0

Text Generation • 0.0B • Updated Jun 14

ajyl/joint_seed_400_512d_8L_8H_alpha_1.0

Text Generation • 0.0B • Updated Jun 14

ajyl/joint_seed_300_512d_8L_8H_alpha_1.0

Text Generation • 0.0B • Updated Jun 14

ajyl/joint_seed_200_512d_8L_8H_alpha_1.0

Text Generation • 0.0B • Updated Jun 14

ajyl/joint_seed_100_512d_8L_8H_alpha_1.0

Text Generation • 0.0B • Updated Jun 14