root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

convert : remove bug in convert.py permute function (#3364)

Browse Source
This commit is contained in:
Zhang Peiyuan 2023-09-28 02:45:20 +08:00 committed by GitHub
parent ac43576124
commit e519621010
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
convert.py
View File

@ -439,7 +439,7 @@ Vocab: TypeAlias = 'BpeVocab | SentencePieceVocab'
def permute(weights: NDArray, n_head: int, n_head_kv: int) -> NDArray: def permute(weights: NDArray, n_head: int, n_head_kv: int) -> NDArray:
#print( "permute debug " + str(weights.shape[0]) + " x " + str(weights.shape[1]) + " nhead " + str(n_head) + " nheadkv " + str(n_kv_head) ) #print( "permute debug " + str(weights.shape[0]) + " x " + str(weights.shape[1]) + " nhead " + str(n_head) + " nheadkv " + str(n_kv_head) )
if n_head_kv is not None and n_head != n_head_kv: if n_head_kv is not None and n_head != n_head_kv:
n_head //= n_head_kv n_head = n_head_kv
return (weights.reshape(n_head, 2, weights.shape[0] // n_head // 2, *weights.shape[1:]) return (weights.reshape(n_head, 2, weights.shape[0] // n_head // 2, *weights.shape[1:])
.swapaxes(1, 2) .swapaxes(1, 2)
.reshape(weights.shape)) .reshape(weights.shape))