CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

model: Add support for PhiMoE arch (#11003)

Browse Source 
* model: support phimoe

* python linter

* doc: minor

Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>

* doc: minor

Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>

* doc: add phimoe as supported model

ggml-ci

---------

Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
This commit is contained in:
Pierrick Hymbert
2025-01-09 11:21:41 +01:00
committed by GitHub
parent be0e950c91
commit f8feb4b01a
10 changed files with 208 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -244,6 +244,7 @@ class MODEL_ARCH(IntEnum):
QWEN2VL = auto()
PHI2 = auto()
PHI3 = auto()
PHIMOE = auto()
PLAMO = auto()
CODESHELL = auto()
ORION = auto()
@@ -428,6 +429,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.QWEN2VL: "qwen2vl",
MODEL_ARCH.PHI2: "phi2",
MODEL_ARCH.PHI3: "phi3",
MODEL_ARCH.PHIMOE: "phimoe",
MODEL_ARCH.PLAMO: "plamo",
MODEL_ARCH.CODESHELL: "codeshell",
MODEL_ARCH.ORION: "orion",
@@ -940,6 +942,24 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.PHIMOE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FACTORS_LONG,
MODEL_TENSOR.ROPE_FACTORS_SHORT,
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_GATE_INP,
MODEL_TENSOR.FFN_GATE_EXP,
MODEL_TENSOR.FFN_DOWN_EXP,
MODEL_TENSOR.FFN_UP_EXP,
],
MODEL_ARCH.CODESHELL: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.POS_EMBD,