tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-26 19:23:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

model : add EXAONE 4.0 support (#14630)

Browse Source
This commit is contained in:
lgai-exaone
2025-07-18 17:45:49 +09:00
committed by GitHub
parent f9a31eea06
commit e0cb5c5cb8
9 changed files with 333 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -354,6 +354,7 @@ class MODEL_ARCH(IntEnum):
JAIS = auto()
NEMOTRON = auto()
EXAONE = auto()
EXAONE4 = auto()
GRANITE = auto()
GRANITE_MOE = auto()
GRANITE_HYBRID = auto()
@ -671,6 +672,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.JAIS: "jais",
MODEL_ARCH.NEMOTRON: "nemotron",
MODEL_ARCH.EXAONE: "exaone",
MODEL_ARCH.EXAONE4: "exaone4",
MODEL_ARCH.GRANITE: "granite",
MODEL_ARCH.GRANITE_MOE: "granitemoe",
MODEL_ARCH.GRANITE_HYBRID: "granitehybrid",
@ -2197,6 +2199,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.EXAONE4: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_Q,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_POST_NORM,
MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.FFN_POST_NORM,
],
MODEL_ARCH.GRANITE: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,