-
-
Notifications
You must be signed in to change notification settings - Fork 60
relase: v0.0.24 #324
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.
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
Merged
relase: v0.0.24 #324
Changes from 22 commits
Commits
Show all changes
26 commits
Select commit
Hold shift + click to select a range
476052a
feat: add newest version chronos-forecasting
AzulGarza 03f3c86
feat: add missing deps
AzulGarza 1543d80
feat: add init version chronos finetunning
AzulGarza d30b81a
docs: add finetunning config to docs
AzulGarza 05b27db
feat: add better doc chronos finetunning
AzulGarza bd29dc8
tests: chronos save model functionality
AzulGarza d187e43
feat: add save path model functionality
AzulGarza 490d190
tests: add finetunning models
AzulGarza 74e5c33
fix: handle lora finetunning
AzulGarza 984e7f6
docs: add finetunning example
AzulGarza b529b3d
fix: lint issues
AzulGarza f5ae06a
tests: rm finetune from main tests
AzulGarza e0c1160
tests: dedicate finetune tests for chronos
AzulGarza 4ce2b65
fix: cap transformers
AzulGarza f2a0bd3
Merge branch 'main' into feat/funetunning-chronos
AzulGarza 956d03a
fix: style things
AzulGarza 7aeebbc
fix: merge branch 'feat/funetunning-chronos' of https://github.com/Ti…
AzulGarza 137bb6c
fix: rm unused cell
AzulGarza 98f902d
fix: add correct docstring
AzulGarza f1ef9e8
fix: add torch_dtype as in chronos
AzulGarza dbb580a
fix: merge branch 'main' of https://github.com/TimeCopilot/timecopilo…
AzulGarza f6bb150
release: v0.0.24
AzulGarza bf63d71
fix: style
AzulGarza 5daf361
fix: add correct link
AzulGarza b3ad454
fix: add correct version
AzulGarza f749c03
fix: latest changelog
AzulGarza File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,64 @@ | ||
| ### Features | ||
|
|
||
| * **Chronos 2 finetuning**: Finetuning is now supported for Chronos 2. You can adapt the pre-trained model to your data before forecasting via `ChronosFinetuningConfig`, with options for full parameter update or LoRA, and optional saving of the finetuned checkpoint for reuse. See [#323](https://github.com/TimeCopilot/timecopilot/pull/323) and the [Finetuning Foundation Models](https://timecopilot.dev/examples/finetuning/) example for a full walkthrough. | ||
|
|
||
| ```python | ||
| from timecopilot.models.foundation.chronos import Chronos, ChronosFinetuningConfig | ||
|
|
||
| # Chronos 2 with finetuning (full or LoRA) | ||
| model = Chronos( | ||
| repo_id="amazon/chronos-2-base", | ||
| alias="chronos-2-finetuned", | ||
| finetuning_config=ChronosFinetuningConfig( | ||
| finetune_steps=100, | ||
| finetune_mode="lora", # or "full" | ||
| save_path="./chronos-2-finetuned/", # optional: reuse later with repo_id=save_path, finetuning_config=None | ||
| ), | ||
| ) | ||
| fcst = model.forecast(df, h=12) | ||
| ``` | ||
|
|
||
| * **PatchTST-FM foundation model**: Added [PatchTST-FM](https://huggingface.co/ibm-research/patchtst-fm-r1), a Time Series Foundation Model from IBM Research. Use it via the `PatchTSTFM` class. See [#312](https://github.com/TimeCopilot/timecopilot/pull/312) and the [PatchTST-FM example](https://timecopilot.dev/examples/patchtst-fm/). | ||
|
|
||
| ```python | ||
| from timecopilot.models.foundation.patchtst_fm import PatchTSTFM | ||
|
|
||
| model = PatchTSTFM() # defaults to ibm-research/patchtst-fm-r1 | ||
| fcst = model.forecast(df, h=12) | ||
| ``` | ||
|
|
||
| ### Fixes | ||
|
|
||
| * **Chronos default dtype**: Changed Chronos default dtype from `bfloat16` to `float32` for better compatibility on systems without bfloat16 support. See [#309](https://github.com/TimeCopilot/timecopilot/pull/309). | ||
|
|
||
| * **FlowState h=1 crash**: Fixed a crash in FlowState when using horizon `h=1`. See [#305](https://github.com/TimeCopilot/timecopilot/pull/305). | ||
|
|
||
| * **AWS Bedrock connection**: Fixed Bedrock connection error caused by a missing description. See [#311](https://github.com/TimeCopilot/timecopilot/pull/311). | ||
|
|
||
| * **Slow pip install**: Improved pip install performance. See [#306](https://github.com/TimeCopilot/timecopilot/pull/306). | ||
|
|
||
| ### Documentation | ||
|
|
||
| * **sktime integration blog post**: Added a blog post on using timecopilot with the sktime forecasting ecosystem. See [#301](https://github.com/TimeCopilot/timecopilot/pull/301) and [#304](https://github.com/TimeCopilot/timecopilot/pull/304). | ||
|
|
||
| * **Newsletter and contact**: Added newsletter signup and "Talk to Us" button to the docs. See [#303](https://github.com/TimeCopilot/timecopilot/pull/303). | ||
|
|
||
| * **Contributing and issue template**: Fixed timecopilot fork links in `contributing.md` and updated the issue template to use the correct repository link. See [#314](https://github.com/TimeCopilot/timecopilot/pull/314) and [#315](https://github.com/TimeCopilot/timecopilot/pull/315). | ||
|
|
||
| ### Continuous Integration | ||
|
|
||
| * **TOML check in CI**: CI now validates TOML configuration. See [#319](https://github.com/TimeCopilot/timecopilot/pull/319). | ||
|
|
||
| ### Other | ||
|
|
||
| * **Hugging Face Hub**: Bumped `huggingface_hub` to v0.36.0. See [#300](https://github.com/TimeCopilot/timecopilot/pull/300). | ||
|
|
||
| ## New Contributors | ||
|
|
||
| * @khuyentran1401 made their first contribution in [#301](https://github.com/TimeCopilot/timecopilot/pull/301) | ||
| * @rebot-eng made their first contribution in [#309](https://github.com/TimeCopilot/timecopilot/pull/309) | ||
| * @JoseCelis made their first contribution in [#311](https://github.com/TimeCopilot/timecopilot/pull/311) | ||
|
|
||
| --- | ||
|
|
||
| **Full Changelog**: https://github.com/TimeCopilot/timecopilot/compare/v0.0.23...v0.0.24 | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.