root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-30 21:34:36 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

skip rope freq and rotary embeddings from being serialized

Browse Source
This commit is contained in:
Sourab Mangrulkar 2024-02-29 19:32:04 +05:30
parent 6c108068b1
commit d62ce1c6b4
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
gguf-py/gguf/constants.py
View File

@ -571,6 +571,10 @@ MODEL_TENSOR_SKIP: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ROPE_FREQS, MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD, MODEL_TENSOR.ATTN_ROT_EMBD,
], ],
MODEL_ARCH.STARCODER2: [
MODEL_TENSOR.ROPE_FREQS,
MODEL_TENSOR.ATTN_ROT_EMBD,
],
} }
# #