Add two-stage TrajMixer mixing
This commit is contained in:
@@ -15,7 +15,7 @@ from backbones import (
|
||||
from targets import PAD_IDX
|
||||
|
||||
|
||||
TRAJ_MIXER_ARCHITECTURE = "traj_mixer_v2"
|
||||
TRAJ_MIXER_ARCHITECTURE = "traj_mixer_v3"
|
||||
|
||||
|
||||
def validate_traj_mixer_config(config: Mapping[str, object]) -> None:
|
||||
@@ -29,6 +29,13 @@ def validate_traj_mixer_config(config: Mapping[str, object]) -> None:
|
||||
|
||||
def validate_traj_mixer_state_dict(state_dict: Mapping[str, object]) -> None:
|
||||
required_keys = {
|
||||
"blocks.0.mlp.intra_norm.weight",
|
||||
"blocks.0.mlp.intra_norm.bias",
|
||||
"blocks.0.mlp.intra_gate_proj",
|
||||
"blocks.0.mlp.intra_value_proj",
|
||||
"blocks.0.mlp.intra_output_proj",
|
||||
"blocks.0.mlp.cross_norm.weight",
|
||||
"blocks.0.mlp.cross_norm.bias",
|
||||
"blocks.0.mlp.group_align",
|
||||
"blocks.0.mlp.gate_proj",
|
||||
"blocks.0.mlp.value_proj",
|
||||
|
||||
Reference in New Issue
Block a user