tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 20:29:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

MODEL_TENSOR.SSM_DT_NORM has defined twice (#14991)

Browse Source 
* MODEL_TENSOR.SSM_DT_NORM has defined twice, and second overwritten the jamba model's layername

* correct order
This commit is contained in:
Csaba Kecskemeti
2025-07-31 07:59:49 -07:00
committed by GitHub
parent 94933c8c2e
commit 36e5fe7bcd
1 changed files with 1 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
gguf-py/gguf/tensor_mapping.py
View File

@@ -616,6 +616,7 @@ class TensorNameMap:
), ),
MODEL_TENSOR.SSM_DT_NORM: ( MODEL_TENSOR.SSM_DT_NORM: (
"model.layers.layers.{bid}.mixer.dt_norm.weight", # plamo2
"model.layers.{bid}.mamba.dt_layernorm", # jamba "model.layers.{bid}.mamba.dt_layernorm", # jamba
), ),
@@ -645,10 +646,6 @@ class TensorNameMap:
"model.layers.layers.{bid}.mixer.D", # plamo2 "model.layers.layers.{bid}.mixer.D", # plamo2
), ),
MODEL_TENSOR.SSM_DT_NORM: (
"model.layers.layers.{bid}.mixer.dt_norm.weight", # plamo2
),
MODEL_TENSOR.SSM_NORM: ( MODEL_TENSOR.SSM_NORM: (
"model.layers.{bid}.mamba.norm", # falcon-h1 granite-hybrid "model.layers.{bid}.mamba.norm", # falcon-h1 granite-hybrid
"backbone.layers.{bid}.mixer.norm", # mamba2 "backbone.layers.{bid}.mixer.norm", # mamba2