]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 87c2e8b)
llama : allow for user specified embedding pooling type (#5849)
authorDouglas Hanley <redacted>
Sun, 3 Mar 2024 10:40:27 +0000 (04:40 -0600)
committerGitHub <redacted>
Sun, 3 Mar 2024 10:40:27 +0000 (12:40 +0200)
commit475df1d6cf817060028d3ff763cb8097d4ec40d6
tree5cad43f149f24b7b3f40604b78b7971e458aa309tree
parent87c2e8b2797860a06af3d6c06b8488a8ff1a09abcommit | diff
llama : allow for user specified embedding pooling type (#5849)

* allow for user specified pooling type

* llama : use enum types over int

---------

Co-authored-by: Georgi Gerganov <redacted>
common/common.cpp diff | blob | history
common/common.h diff | blob | history
convert-hf-to-gguf.py diff | blob | history
llama.cpp diff | blob | history
llama.h diff | blob | history
Packaging of ggml-org/llama.cpp