Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[KV-Cache Injection][MPT] Update config #1801

Merged
merged 8 commits into from
Nov 3, 2023
4 changes: 2 additions & 2 deletions src/sparseml/exporters/transforms/kv_cache/configs.py
Original file line number Diff line number Diff line change
Expand Up @@ -113,8 +113,8 @@ class Config:
additional_transforms=AdditionalTransformsMPT,
key_num_attention_heads="n_heads",
key_num_embedding_hidden_size="d_model",
transpose_value_input=None,
transpose_key_input=(0, 1, 3, 2),
transpose_value_input=(0, 2, 1, 3),
transpose_key_input=(0, 2, 1, 3),
dbogunowicz marked this conversation as resolved.
Show resolved Hide resolved
multiply_batch_by_num_att_heads=False,
)

Expand Down
Loading