mozempk/ggml-org-llama-cpp-mirror
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-13 00:10:37 +02:00
Code Issues Packages Projects Releases Wiki Activity

model : support classifier_activation for rerankers (#29692)

Browse Source 
* model : support classifier_activation for rerankers

Assisted-by: Claude Opus 5.5

* model : map classifier gelu to gelu_erf and accept tanh

Assisted-by: Claude Opus 5.5

* model : default act_cls to tanh, ModernBERT falls back to gelu_erf

Assisted-by: Claude Opus 5.5
This commit is contained in:
bosh
2026-10-08 09:29:20 +03:00
committed by GitHub
parent 24e41838e0
commit 37ac634566
9 changed files with 31 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/base.py
+4
View File
@@ -2352,6 +2352,10 @@ class TextModel(ModelBase):
if classifier_pooling not in ("cls", "mean"):
raise NotImplementedError(f"Unsupported classifier_pooling: {classifier_pooling}")
self.gguf_writer.add_classifier_pooling_type(mode_mapping[classifier_pooling])
if (classifier_activation := self.hparams.get("classifier_activation")) is not None:
if classifier_activation not in ("gelu", "silu", "tanh"):
raise NotImplementedError(f"Unsupported classifier_activation: {classifier_activation}")
self.gguf_writer.add_classifier_activation(classifier_activation)
def _set_vocab_glmedge(self):
from transformers import AutoTokenizer