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 3 hours ago
haoranli-ml/lcft_gemma-2b_prolong-gemma-parts_ProLong64KMix_bsz256_steps1250_lr1e-5_warmup0.1_rope200000rope updated a model about 4 hours ago
haoranli-ml/lcft_gemma-2b_prolong-gemma-parts_ProLong64KMix_bsz256_steps1250_lr1e-5_warmup0.1_rope200000cope published a model about 5 hours ago
haoranli-ml/lcft_gemma-2b_prolong-gemma-parts_ProLong64KMix_bsz256_steps1250_lr1e-5_warmup0.1_rope200000rope