* MODEL_TENSOR.SSM_DT_NORM has defined twice, and second overwritten the jamba model's layername
* correct order
),
MODEL_TENSOR.SSM_DT_NORM: (
+ "model.layers.layers.{bid}.mixer.dt_norm.weight", # plamo2
"model.layers.{bid}.mamba.dt_layernorm", # jamba
),
"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.layers.{bid}.mamba.norm", # falcon-h1 granite-hybrid
"backbone.layers.{bid}.mixer.norm", # mamba2