happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update gguf-py/gguf/tensor_mapping.py 

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Ryan Mangeno 2025-10-10 12:01:47 -04:00 committed by GitHub
parent b442b43303
commit 94e7ece5cd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
gguf-py/gguf/tensor_mapping.py
View File

@ -256,7 +256,7 @@ class TensorNameMap:
"model.layers.{bid}.self_attn.linear_attn", # deci "model.layers.{bid}.self_attn.linear_attn", # deci
"layers.{bid}.attention.wo", # llama-pth "layers.{bid}.attention.wo", # llama-pth
"encoder.layer.{bid}.attention.output.dense", # bert "encoder.layer.{bid}.attention.output.dense", # bert
"layers.{bid}.attn.Wo", # modern bert "layers.{bid}.attn.Wo", # modern-bert
"transformer.layer.{bid}.attention.out_lin", # distillbert "transformer.layer.{bid}.attention.out_lin", # distillbert
"transformer.h.{bid}.attn.out_proj", # gpt-j "transformer.h.{bid}.attn.out_proj", # gpt-j
"language_model.encoder.layers.{bid}.self_attention.dense", # persimmon "language_model.encoder.layers.{bid}.self_attention.dense", # persimmon