vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Consolidate PHI and PHI2 architectures in gguf constants

Browse source 
Signed-off-by: teleprint-me <77757836+teleprint-me@users.noreply.github.com>
This commit is contained in:
teleprint-me 2023-12-20 15:15:35 -05:00
parent 1d4bcd2044
commit e53d44c0bb
No known key found for this signature in database
GPG key ID: B0D11345E65C4D48
1 changed files with 2 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

8
gguf-py/gguf/constants.py
View file

@ -95,7 +95,6 @@ class MODEL_ARCH(IntEnum):
BLOOM = auto()
STABLELM = auto()
QWEN = auto()
PHI2 = auto()
PHI = auto()
@ -142,7 +141,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.BLOOM: "bloom",
MODEL_ARCH.STABLELM: "stablelm",
MODEL_ARCH.QWEN: "qwen",
MODEL_ARCH.PHI2: "phi2",
MODEL_ARCH.PHI: "phi",
}
TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@ -353,7 +352,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_ARCH.GPT2: [
# TODO
],
MODEL_ARCH.PHI2: [
MODEL_ARCH.PHI: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
@ -364,9 +363,6 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
]
MODEL_ARCH.PHI: [
# TODO
],
# TODO
}