Skip to content

Fix k_norm dimension #521

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.

Sign up for GitHub

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

Merged
davidbrandfonbrener merged 3 commits into from
Mar 26, 2024
Merged

Fix k_norm dimension #521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
985c212
Fix k_norm dimension
davidbrandfonbrener Mar 24, 2024
b923ed9
Merge branch 'main' into davidbrandfonbrener-patch-1
dirkgr Mar 25, 2024
322c8b6
Changelog
dirkgr Mar 25, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

- Don't log garbage on nodes that aren't rank 0
- Don't crash in the HF code when we are referring to a tokenizer in a local file
- Fixed the size calculation for qk layer norm

## [v0.2.5](https://github.com/allenai/OLMo/releases/tag/v0.2.5) - 2024-03-06

Expand Down
4 changes: 2 additions & 2 deletions olmo/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -425,10 +425,10 @@ def __init__(self, layer_id: int, config: ModelConfig, cache: BufferCache):
self.k_norm: Optional[LayerNormBase] = None
self.q_norm: Optional[LayerNormBase] = None
if config.attention_layer_norm:
assert config.n_kv_heads is not None
assert config.effective_n_kv_heads is not None
self.k_norm = LayerNormBase.build(
config,
size=config.d_model // config.effective_n_kv_heads,
size=(config.d_model // config.n_heads) * config.effective_n_kv_heads,
elementwise_affine=config.attention_layer_norm_with_affine,
)
self.q_norm = LayerNormBase.build(config, elementwise_affine=config.attention_layer_norm_with_affine)
Expand Down