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

llama : add support for the cohere2 model architecture (#10900)

Browse source
This commit is contained in:
DAN™ 2025-01-04 09:33:31 -05:00 • committed by GitHub
parent 78c6785175
commit 46be942214
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 221 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama-arch.h
View file

@ -43,6 +43,7 @@ enum llm_arch {
LLM_ARCH_MAMBA,
LLM_ARCH_XVERSE,
LLM_ARCH_COMMAND_R,
LLM_ARCH_COHERE2,
LLM_ARCH_DBRX,
LLM_ARCH_OLMO,
LLM_ARCH_OLMO2,