ajyl/grpo_joint_seed_500
Text Generation
•
25.3M
•
Updated
•
5
Andrew Lee
ajyl
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals
Long-Range Dependency Pitfalls
updated
a model
5 months ago
ajyl/grpo_joint_seed_500
published
a model
5 months ago
ajyl/grpo_joint_seed_500
Organizations
models
53
ajyl/grpo_joint_seed_400
Text Generation
•
25.3M
•
Updated
•
6
ajyl/grpo_joint_seed_300
Text Generation
•
25.3M
•
Updated
•
6
ajyl/grpo_joint_seed_200
Text Generation
•
25.3M
•
Updated
•
4
ajyl/grpo_joint_seed_100
Text Generation
•
25.3M
•
Updated
•
7
ajyl/grpo_sft_seed_500_with_pretrain
Text Generation
•
25.3M
•
Updated
•
5
ajyl/grpo_sft_seed_400_with_pretrain
Text Generation
•
25.3M
•
Updated
•
5
ajyl/grpo_sft_seed_300_with_pretrain
Text Generation
•
25.3M
•
Updated
•
8
ajyl/grpo_sft_seed_200_with_pretrain
Text Generation
•
25.3M
•
Updated
•
4
ajyl/grpo_sft_seed_100_with_pretrain
Text Generation
•
25.3M
•
Updated
•
5
datasets
0
None public yet