tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-25 17:48:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : remove Persimmon (#7408)

Browse Source 
* llama : remove Persimmon

* requirements : remove
This commit is contained in:
Georgi Gerganov
2024-05-20 19:35:28 +03:00
committed by GitHub
parent 20385cebcc
commit fabf30b4c4
7 changed files with 0 additions and 485 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -115,7 +115,6 @@ class MODEL_ARCH(IntEnum):
GPTNEOX = auto()
MPT = auto()
STARCODER = auto()
PERSIMMON = auto()
REFACT = auto()
BERT = auto()
NOMIC_BERT = auto()
@@ -193,7 +192,6 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
MODEL_ARCH.GPTNEOX: "gptneox",
MODEL_ARCH.MPT: "mpt",
MODEL_ARCH.STARCODER: "starcoder",
MODEL_ARCH.PERSIMMON: "persimmon",
MODEL_ARCH.REFACT: "refact",
MODEL_ARCH.BERT: "bert",
MODEL_ARCH.NOMIC_BERT: "nomic-bert",
@@ -426,20 +424,6 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
],
MODEL_ARCH.PERSIMMON: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT,
MODEL_TENSOR.OUTPUT_NORM,
MODEL_TENSOR.ATTN_NORM,
MODEL_TENSOR.ATTN_QKV,
MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP,
MODEL_TENSOR.ATTN_Q_NORM,
MODEL_TENSOR.ATTN_K_NORM,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
MODEL_ARCH.REFACT: [
MODEL_TENSOR.TOKEN_EMBD,
MODEL_TENSOR.OUTPUT_NORM,
@@ -756,9 +740,6 @@ MODEL_TENSOR_SKIP: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
MODEL_ARCH.PERSIMMON: [
MODEL_TENSOR.ROPE_FREQS,
],
MODEL_ARCH.QWEN: [
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,