root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

convert-llama-h5-to-gguf.py : clarify the reverse permute

Browse Source
This commit is contained in:
klosax 2023-08-16 11:23:15 +02:00 committed by GitHub
parent 4a1741aa2d
commit ea5615a03a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
convert-llama-h5-to-gguf.py
View File

@ -18,7 +18,9 @@ from sentencepiece import SentencePieceProcessor
# compatible with python < 3.9 # compatible with python < 3.9
NDArray: 'TypeAlias' = 'np.ndarray[Any, Any]' NDArray: 'TypeAlias' = 'np.ndarray[Any, Any]'
def permute(weights: NDArray, n_head: int, n_kv_head: Optional[int] = None) -> NDArray: # reverse HF permute back to original pth layout
# https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py
def reverse_hf_permute(weights: NDArray, n_head: int, n_kv_head: Optional[int] = None) -> NDArray:
if n_kv_head is not None and n_head != n_kv_head: n_head //= n_kv_head if n_kv_head is not None and n_head != n_kv_head: n_head //= n_kv_head
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)
@ -219,9 +221,9 @@ for part_name in part_names:
data = data.squeeze().numpy() data = data.squeeze().numpy()
# permute these # reverse permute these
if name.endswith(".q_proj.weight") or name.endswith(".k_proj.weight"): if name.endswith(".q_proj.weight") or name.endswith(".k_proj.weight"):
data = permute(data, head_count, head_count_kv) data = reverse_hf_permute(data, head_count, head_count_kv)
# map tensor names # map tensor names
if name.endswith(".weight") and name[:-7] in tensor_map: if name.endswith(".weight") and name[:-7] in tensor_map:
@ -288,9 +290,9 @@ for part_name in part_names:
data = data.squeeze().numpy() data = data.squeeze().numpy()
# permute these # reverse permute these
if name.endswith(".q_proj.weight") or name.endswith(".k_proj.weight"): if name.endswith(".q_proj.weight") or name.endswith(".k_proj.weight"):
data = permute(data, head_count, head_count_kv) data = reverse_hf_permute(data, head_count, head_count_kv)
# map tensor names # map tensor names
if name.endswith(".weight") and name[:-7] in tensor_map: if name.endswith(".weight") and name[:-7] in tensor_map: