CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Rename Olmo1124 to Olmo2 (#10500)

Browse Source
This commit is contained in:
Shane A
2024-11-25 10:36:09 -08:00
committed by GitHub
parent 10bce0450f
commit 80acb7b430
4 changed files with 29 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
gguf-py/gguf/constants.py
View File

@@ -243,7 +243,7 @@ class MODEL_ARCH(IntEnum):
COMMAND_R = auto()
DBRX = auto()
OLMO = auto()
OLMO_1124 = auto()
OLMO2 = auto()
OLMOE = auto()
OPENELM = auto()
ARCTIC = auto()
@@ -405,7 +405,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.COMMAND_R: "command-r",
MODEL_ARCH.DBRX: "dbrx",
MODEL_ARCH.OLMO: "olmo",
MODEL_ARCH.OLMO_1124: "olmo_1124",
MODEL_ARCH.OLMO2: "olmo2",
MODEL_ARCH.OLMOE: "olmoe",
MODEL_ARCH.OPENELM: "openelm",
MODEL_ARCH.ARCTIC: "arctic",
@@ -1071,7 +1071,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.OLMO_1124: [
MODEL_ARCH.OLMO2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,