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

phi2 implementation

Browse source
This commit is contained in:
Ebey Abraham 2023-12-15 20:56:57 +00:00
parent 6744dbe924
commit 12cc80cb89
4 changed files with 226 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

13
gguf-py/gguf/constants.py
View file

@ -95,6 +95,7 @@ class MODEL_ARCH(IntEnum):
BLOOM = auto()
STABLELM = auto()
QWEN = auto()
PHI2 = auto()
class MODEL_TENSOR(IntEnum):
@ -140,6 +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",
}
TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@ -350,6 +352,17 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_ARCH.GPT2: [
# TODO
],
MODEL_ARCH.PHI2: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
]
# TODO
}