CoPE is a drop-in enhancement of RoPE that delivers consistent gains within the training context and during long-context extrapoaltion.
Haoran Li PRO
haoranli-ml
·
AI & ML interests
ML, RL, Foundation Models
Recent Activity
updated a model about 21 hours ago
haoranli-ml/Gemma-7B-RoPE-Base-theta_200k_sft published a model about 21 hours ago
haoranli-ml/Gemma-7B-RoPE-Base-theta_200k_sft updated a model 1 day ago
haoranli-ml/Gemma-7B-HardClip-Base-theta_200k_sft