b11532: model : use exact GELU for ModernBERT encoders (#30108)
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
- model : use exact GELU for ModernBERT encoders
Assisted-by: Codex
- model : keep tanh GELU aliases on ggml_geglu
Assisted-by: Claude Opus 5.5
- model : map gelu_python to ggml_geglu_erf
Assisted-by: Claude Opus 5.5
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.