]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : gemma3 : use output tensor if it exists in model weight (#12506)
authorXuan-Son Nguyen <redacted>
Sat, 22 Mar 2025 22:28:19 +0000 (23:28 +0100)
committerGitHub <redacted>
Sat, 22 Mar 2025 22:28:19 +0000 (23:28 +0100)
commitfbdfefe74e736f1a3687283c25ac21b11ba07b2e
tree728312dda4aa3eb204060f1d5924f385d5907ac0
parentba932dfb50cc694645b1a148c72f8c06ee080b17
llama : gemma3 : use output tensor if it exists in model weight (#12506)

* llama : gemma3 : use output tensor if it exists in model weight

* also add to the llm_tensor_names
gguf-py/gguf/constants.py
src/llama-arch.cpp
src/llama-model.cpp