ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)

Browse source
This commit is contained in:
Jared Van Bortel 2025-05-02 11:42:30 -04:00 • committed by GitHub
parent 7d2123484e
commit 2f567611c0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 45 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

2
gguf-py/gguf/constants.py
View file

@ -2033,6 +2033,8 @@ class PoolingType(IntEnum):
NONE = 0
MEAN = 1
CLS = 2
LAST = 3
RANK = 4
class GGMLQuantizationType(IntEnum):