This collection contains datasets and models related to "BLEUBERI: BLEU is a surprisingly effective reward for instruction following".
Yapei Chang PRO
yapeichang
AI & ML interests
NLP
Recent Activity
published a model 2 days ago
yapeichang/grpo_olmo3_pretrain_sft_ckpt_80pct published a model 2 days ago
yapeichang/sft_olmo3_pretrain_ckpt_80pct published a model 2 days ago
yapeichang/grpo_olmo3_pretrain_sft_ckpt_10pctOrganizations
models 42
yapeichang/memo-32b-4tier
32B • Updated • 8
yapeichang/memo-7b-4tier-50B-preserved
7B • Updated • 9
yapeichang/memo-7b-4tier
7B • Updated • 6
yapeichang/grpo_olmo3_pretrain_sft_ckpt_80pct
528k • Updated • 9
yapeichang/sft_olmo3_pretrain_ckpt_80pct
Updated • 9
yapeichang/grpo_olmo3_pretrain_sft_ckpt_10pct
528k • Updated • 9
yapeichang/grpo_olmo3_pretrain_sft_ckpt_25pct
528k • Updated • 9
yapeichang/grpo_olmo3_pretrain_sft_ckpt_50pct
528k • Updated • 10
yapeichang/grpo_olmo3_pretrain_sft_ckpt_100pct
528k • Updated • 3
yapeichang/memo-7b
7B • Updated • 10