]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
authorJared Van Bortel <redacted>
Fri, 2 May 2025 15:42:30 +0000 (11:42 -0400)
committerGitHub <redacted>
Fri, 2 May 2025 15:42:30 +0000 (11:42 -0400)
commit2f567611c0234bbca0a4009762acb47b56866095
tree16d46e5be0a55a1de4ee2bf197a116ba9a4a1374
parent7d2123484e6ba8fcd90fff8c01661b9dbbefdc9d
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
convert_hf_to_gguf.py
gguf-py/gguf/constants.py
src/llama-model.cpp