Skip to content

Fix SSM dt clamp default for Nemotron-H #1026

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
angeloskath merged 1 commit into from
Mar 30, 2026
+2 −2
Merged

Fix SSM dt clamp default for Nemotron-H #1026

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 2 additions & 2 deletions mlx_lm/models/nemotron_h.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,8 +61,8 @@ class ModelArgs(BaseModelArgs):
_block_type_to_char = {"mamba": "M", "attention": "*", "moe": "E", "mlp": "-"}

def __post_init__(self):
if self.time_step_limit is None and self.time_step_min is not None:
self.time_step_limit = (self.time_step_min, float("inf"))
if self.time_step_limit is None:
self.time_step_limit = (0.0, float("inf"))

# Normalize to hybrid_override_pattern (single-char list)
if self.hybrid_override_pattern is None and self.layers_block_type is not None:
Expand Down
Loading