Skip to content

fix(qwen3.5): read layer types from model config #612

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
pan-x-c merged 1 commit into from
Jul 31, 2026
Merged

fix(qwen3.5): read layer types from model config #612

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
6 changes: 4 additions & 2 deletions trinity/trainer/verl_legacy/monkey_patch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -440,8 +440,10 @@ def state_dict(self, *args, **kwargs):

from trinity.common.patch.qwen3_5 import ulysses_gate_delta_net_decorator

for layer in model.model.language_model.layers:
if layer.layer_type == "linear_attention":
language_model = model.model.language_model
for layer_idx, layer in enumerate(language_model.layers):
layer_type = language_model.config.layer_types[layer_idx]
if layer_type == "linear_attention":
ulysses_gate_delta_net_decorator(layer.linear_attn, ulysses_sp_size)

# Step 3: patch verl.utils.flops_counter
Expand Down
Loading