add_trained_weights

#1
by leejunhyeok - opened
Motif Technologies org
No description provided.
leejunhyeok changed pull request status to open
Motif Technologies org

@leejunhyeok
It might be better to update the MotifAttention class docstring to mention Grouped Differential Attention instead of Differential Attention.

Motif Technologies org
โ€ข
edited Dec 1, 2025

@leejunhyeok we might need to remove "_attn_implementation": "flash_attention_2" option as described in config.json of Motif-2-12.7-Base.

SungminLee changed pull request status to merged

Sign up or log in to comment