CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : add openPangu-Embedded (#16941)

Browse Source 
* Model: add openPangu-Embedded

* fixed according to reviewer's comments

* fixed the chat template check condition

* Apply suggestions from code review

change the chat-template check condition and some formatting issue

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* whitespace cleanup

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Li Pengzhan
2025-11-05 17:28:58 +08:00
committed by GitHub
parent 03ea04175d
commit 9f052478c2
10 changed files with 292 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
gguf-py/gguf/constants.py
View File

@@ -426,6 +426,7 @@ class MODEL_ARCH(IntEnum):
APERTUS = auto()
COGVLM = auto()
MINIMAXM2 = auto()
PANGU_EMBED = auto()
class VISION_PROJECTOR_TYPE(IntEnum):
@@ -793,6 +794,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.APERTUS: "apertus",
MODEL_ARCH.MINIMAXM2: "minimax-m2",
MODEL_ARCH.COGVLM: "cogvlm",
MODEL_ARCH.PANGU_EMBED: "pangu-embedded",
}
VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@@ -2958,6 +2960,20 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.VISEXP_UP,
MODEL_TENSOR.VISEXP_DOWN,
],
MODEL_ARCH.PANGU_EMBED: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
# TODO
}
@@ -3013,6 +3029,10 @@ MODEL_TENSOR_SKIP: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_ARCH.BAILINGMOE: [
MODEL_TENSOR.ROPE_FREQS,
],
MODEL_ARCH.PANGU_EMBED: [
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
}
#