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
published
a model
about 15 hours ago
haoranli-ml/Qwen3-4B-Instruct-raw_prefix_all_oracle_data_v2
published
a model
about 15 hours ago
haoranli-ml/Qwen3-4B-Instruct-raw_prefix_all_oracle_data_v2_hl_gauss_cdf_bin_006sigma
published
a model
about 15 hours ago
haoranli-ml/Qwen3-4B-Instruct-raw_prefix_all_oracle_data_v2_hl_gauss_cdf_bin_012sigma
Organizations
