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

llama-model : add Glm4Model implementation for GLM-4-0414 (#12867)

Browse source 
* GLM-4-0414

* use original one

* Using with tensor map

* fix bug

* change order

* change order

* format with flask8
This commit is contained in:
Yuxuan Zhang 2025-04-11 18:10:10 +08:00 • committed by GitHub
parent 0c50923944
commit 06bb53ad9b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 273 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-arch.h
View file

@ -58,6 +58,7 @@ enum llm_arch {
LLM_ARCH_DEEPSEEK,
LLM_ARCH_DEEPSEEK2,
LLM_ARCH_CHATGLM,
LLM_ARCH_GLM4,
LLM_ARCH_BITNET,
LLM_ARCH_T5,
LLM_ARCH_T5ENCODER,
@ -256,6 +257,8 @@ enum llm_tensor {
LLM_TENSOR_ATTN_Q_NORM,
LLM_TENSOR_ATTN_K_NORM,
LLM_TENSOR_LAYER_OUT_NORM,
LLM_TENSOR_POST_ATTN_NORM,
LLM_TENSOR_POST_MLP_NORM,
LLM_TENSOR_SSM_IN,
LLM_TENSOR_SSM_CONV1D,
LLM_TENSOR_SSM_X,