diff options
| author | Onur Gündüz <ogunduz@gmail.com> | 2026-09-29 13:05:44 +0200 |
|---|---|---|
| committer | Onur Gündüz <ogunduz@gmail.com> | 2026-09-29 13:05:44 +0200 |
| commit | cf7d8169ec12cb3adf90d4ff78b3257e74985302 (patch) | |
| tree | f666589acfd68e76bbde4e74eead44ae7819d0bb /README.md | |
| parent | 91871be6ece9317c5d49353f6474583e7e28168d (diff) | |
| download | langdet-cf7d8169ec12cb3adf90d4ff78b3257e74985302.tar.gz langdet-cf7d8169ec12cb3adf90d4ff78b3257e74985302.zip | |
Remove unused model families and inference paths
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 4 |
1 files changed, 3 insertions, 1 deletions
@@ -38,7 +38,9 @@ Use `--` before text that begins with a hyphen. Diagnostics go to stderr. ## Inference `langdetect.c` loads and validates the four F32 classifier tensors and the -`id2label` mapping. The encoder uses first-token pooling without L2 normalization. +`id2label` mapping. The encoder accepts F32 XLM-R weights with exact GeLU activation; +other model families and reduced-precision weights are not supported. +The encoder uses first-token pooling without L2 normalization. The classifier applies a 768-to-768 linear layer, `tanh`, a 768-to-20 linear layer, and stable softmax. Dropout is disabled during inference. |
