CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases 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
9 changed files with 273 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
gguf-py/gguf/constants.py
View File

@@ -280,6 +280,7 @@ class MODEL_ARCH(IntEnum):
DEEPSEEK = auto()
DEEPSEEK2 = auto()
CHATGLM = auto()
GLM4 = auto()
BITNET = auto()
T5 = auto()
T5ENCODER = auto()
@@ -487,6 +488,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.DEEPSEEK: "deepseek",
MODEL_ARCH.DEEPSEEK2: "deepseek2",
MODEL_ARCH.CHATGLM: "chatglm",
MODEL_ARCH.GLM4: "glm4",
MODEL_ARCH.BITNET: "bitnet",
MODEL_ARCH.T5: "t5",
MODEL_ARCH.T5ENCODER: "t5encoder",
@@ -1561,6 +1563,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.GLM4 : [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.ATTN_POST_NORM,
MODEL_TENSOR.FFN_POST_NORM,
],
MODEL_ARCH.BITNET: [
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,