Elgato_dark/chronos-forecasting
1
0
Fork 0
mirror of https://github.com/amazon-science/chronos-forecasting synced 2026-05-24 10:08:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Chronos-2: Ensure updated chronos_config is saved after fine-tuning (#420)

Browse source 
*Issue #, if available:*

*Description of changes:* Previously, only the returned pipeline had
correct configuration but it was not being saved to disk.


By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
This commit is contained in:
Abdul Fatir 2025-12-03 17:32:14 +01:00 committed by GitHub
parent f0e1ef5b8f
commit 564218776a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
src/chronos/chronos2/pipeline.py
View file

@ -336,6 +336,8 @@ class Chronos2Pipeline(BaseChronosPipeline):
model.chronos_config.max_output_patches = max(
model.chronos_config.max_output_patches, math.ceil(prediction_length / self.model_output_patch_size)
)
# update chronos_config in model's config, so it is saved correctly
model.config.chronos_config = model.chronos_config.__dict__
# Create a new pipeline with the fine-tuned model
finetuned_pipeline = Chronos2Pipeline(model=model)