Andrew Lee's picture

1

Andrew Lee

ajyl

·

AI & ML interests

None yet

Organizations

ajyl 's models 53

ajyl/grpo_joint_seed_500

Text Generation • 25.3M • Updated Jun 21, 2025 • 6

ajyl/grpo_joint_seed_400

Text Generation • 25.3M • Updated Jun 21, 2025 • 4

ajyl/grpo_joint_seed_300

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_joint_seed_200

Text Generation • 25.3M • Updated Jun 21, 2025 • 4

ajyl/grpo_joint_seed_100

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_500_with_pretrain

Text Generation • 25.3M • Updated Jun 21, 2025 • 4

ajyl/grpo_sft_seed_400_with_pretrain

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_300_with_pretrain

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_200_with_pretrain

Text Generation • 25.3M • Updated Jun 21, 2025 • 8

ajyl/grpo_sft_seed_100_with_pretrain

Text Generation • 25.3M • Updated Jun 21, 2025 • 5

ajyl/grpo_sft_seed_500

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_400

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_300

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_200

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/grpo_sft_seed_100

Text Generation • 25.3M • Updated Jun 21, 2025 • 1

ajyl/sft_seed_500_512d_8L_8H_datatype_first_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_400_512d_8L_8H_datatype_first_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_300_512d_8L_8H_datatype_first_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_200_512d_8L_8H_datatype_first_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_100_512d_8L_8H_datatype_first_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_500_512d_8L_8H_datatype_full_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_400_512d_8L_8H_datatype_full_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_300_512d_8L_8H_datatype_full_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_200_512d_8L_8H_datatype_full_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/sft_seed_100_512d_8L_8H_datatype_full_pretrain

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/joint_seed_500_512d_8L_8H_alpha_1.0

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/joint_seed_400_512d_8L_8H_alpha_1.0

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/joint_seed_300_512d_8L_8H_alpha_1.0

Text Generation • 25.3M • Updated Jun 14, 2025 • 4

ajyl/joint_seed_200_512d_8L_8H_alpha_1.0

Text Generation • 25.3M • Updated Jun 14, 2025

ajyl/joint_seed_100_512d_8L_8H_alpha_1.0

Text Generation • 25.3M • Updated Jun 14, 2025