v1.2.6
HumanAIGC/Cloth2Texv1.2.6Dec 31, 2024by rajatsen91
AI Summary
This release introduces support for TimesFM-2.0 models, updates the default point forecaster to the median head, and includes bug fixes in PyTorch decoding. It also clarifies that cached decoding is currently unsupported in both JAX and PyTorch backends.
Key Highlights
- Add support for TimesFM-2.0 models
- Set the median head as the default point forecaster
- Add hparam support for TimesFM-2.0 models
- Some bug fixes in pytorch decoding
Breaking Changes
- Cached decoding is not supported in both JAX and PyTorch
- Switching to TimesFM-2.0 models requires new checkpoint paths
New Features
- TimesFM-2.0 model support
- Hparam support for TimesFM-2.0 models
- Default point forecaster set to median head
- PyTorch decoding bug fixes
Full Release Notes
Changes: ---- 1. Add support for TimesFM-2.0 models. 2. Set the median head as the default point forecaster. PyPI Release: ---- v1.2.6: Support for TimesFM-2.0 models. - Add hparam support for TimesFM-2.0 models. - Some bug fixes in pytorch decoding. - Right now we do not support cached decoding in both jax and pytorch. Checkpoints: ---- The TimesFM-2.0 checkpoints are available on Hugging Face: - https://huggingface.co/google/timesfm-2.0-500m-jax - https://huggingface.co/google/timesfm-2.0-500m-pytorch Full Changelog: ---- https://github.com/google-research/timesfm/commits/v1.2.6