Skip to content

docs(recipes): point chat_template at where the templates actually live #2460

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
yeyu-nvidia merged 1 commit into from
Sep 17, 2026
Merged

docs(recipes): point chat_template at where the templates actually live #2460

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
3 changes: 2 additions & 1 deletion modelopt_recipes/general/speculative_decoding/dflash.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,8 @@ data:
offline_data_path:
# Jinja chat template with {% generation %} tags for answer_only_loss.
# Required when answer_only_loss=true. Set in per-model launcher YAML.
# Templates are in modelopt_recipes/general/speculative_decoding/chat_templates/
# Each model keeps its own beside its launcher example, e.g.
# tools/launcher/examples/Qwen/Qwen3-8B/chat_template_train.jinja
chat_template:

# maps to TrainingArguments (main.py)
Expand Down
Loading