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

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

16
src/llama-arch.cpp
View file

@ -39,6 +39,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_MAMBA, "mamba" },
{ LLM_ARCH_XVERSE, "xverse" },
{ LLM_ARCH_COMMAND_R, "command-r" },
{ LLM_ARCH_COHERE2, "cohere2" },
{ LLM_ARCH_DBRX, "dbrx" },
{ LLM_ARCH_OLMO, "olmo" },
{ LLM_ARCH_OLMO2, "olmo2" },
@ -807,6 +808,21 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_ATTN_K_NORM, "blk.%d.attn_k_norm" },
},
},
{
LLM_ARCH_COHERE2,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
{ LLM_TENSOR_ATTN_K, "blk.%d.attn_k" },
{ LLM_TENSOR_ATTN_V, "blk.%d.attn_v" },
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
{ LLM_TENSOR_FFN_GATE, "blk.%d.ffn_gate" },
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
},
},
{
LLM_ARCH_DBRX,
{