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_pooling for rerankers (#29627)

Browse Source 
* model : support classifier_pooling for ModernBERT rerankers

Assisted-by: Claude Opus 5.5

* model : read classifier pooling type in load_hparams

Write classifier.pooling_type from _try_set_pooling_type whenever the
config has classifier_pooling, and read it in
llama_model_base::load_hparams. ModernBERT falls back to mean when it
is unspecified.

Assisted-by: Claude Opus 5.5

* conversion : only accept cls and mean for classifier_pooling

Assisted-by: Claude Opus 5.5

* model : rename classifier_pooling_type to pooling_type_cls

Assisted-by: Claude Opus 5.5
This commit is contained in:
bosh
2026-09-29 22:33:05 +02:00
committed by GitHub
parent 7fee178464
commit 48de2a1bcb
9 changed files with 21 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conversion/base.py
+6
View File
@@ -2326,6 +2326,12 @@ class TextModel(ModelBase):
raise NotImplementedError("Only MEAN, CLS, and LAST pooling types supported")
self.gguf_writer.add_pooling_type(pooling_type)
# pooling before a classification head (e.g. ModernBertForSequenceClassification)
if (classifier_pooling := self.hparams.get("classifier_pooling")) is not None:
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])
def _set_vocab_glmedge(self):
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(self.dir_model)