所有 / AI效率 / AI检索

google-research

timesfm 时间序列预测任务

32.2k 3.1k 210 235 231 5

智能搜索 AI检索 AI效率

(0 评价)

为timesfm打分

给出您宝贵的评分：

产品体验评价：

收藏到合集

timesfm 时间序列预测任务

GitHub Trend · Star / Watch / Fork

趋势分享图

手机端可长按上方图片保存到相册,或点击「下载/分享」分享到微信

使用 timesfm，你可以：

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

用户评论 (0)

0.0 (0 评分)

5星

0 0%

4星

0 0%

3星

0 0%

2星

0 0%

1星

0 0%

Github热门的Issue

#13.ImportError: cannot import name 'patched_decoder' from 'src'

2024年05月11日

#143.How to run timesfm on torch, questions and solve plan !

2024年09月12日

#14.Finetuning

2024年05月11日

#187.Conflict Between Python 3.11 Requirement for Torch Version and Incompatibility of Lingvo, Praxis, and Paxml

2024年11月20日

#43.Error in loading checkpoint

2024年05月21日

#225.Jax and Tensorflow requiring two different CUDA versions

2025年01月22日

#61.The training code

2024年05月31日

#333.Is 2.5 Flax version not ok now?

2025年10月31日

#203.can't reproduce performance of covariates.ipynb

2024年12月24日

#76.When will the training code be released?

2024年06月14日

Github最新的讨论区

#430.Question about data usage

2026年05月21日

#429.Question about data usage

2026年05月21日

#380.pip support

2026年04月01日

#370.TimesFM 2.5 pip support

2026年02月24日

#322.Timesfm 2.5 in-context fine tuning?

2025年10月06日

#317.Finetuning for 2.5

2025年10月02日

#308.AttributeError: module 'timesfm' has no attribute 'TimesFM_2p5_200M_torch'

2025年09月24日

#300.How can I get embedding for time-series using this model?

2025年09月18日

#288.forecast_with_covariates with torch version

2025年07月23日

#263.Can I finetune the model with Pytorch for "horizon_len" lower than 128?

2025年04月03日

Github最新Release版本

v3.0.0

2026年08月29日

v2.0.2

2026年07月03日

Package loading and compilation updates.

详细ChangeLog

v2.0.1

2026年06月12日

Package updated to handle TimesFM-2.5

详细ChangeLog

v1.2.6

2025年01月01日

Changes:

Add support for TimesFM-2.0 models.
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

详细ChangeLog

v1.2.1

2024年10月19日

Changes:

PyTorch support for TimesFM inference.

PyPI Release:

v1.2.1: Support separate dependencies for pax and torch versions of TimesFM:

pip install timesfm[pax] for the pax version and jax checkpoints.
pip install timesfm[torch] for the torch version and checkpoints.
See the updated README for the usage.

Checkpoints:

The PyTorch checkpoint for the 200m model is available on Hugging Face:

https://huggingface.co/google/timesfm-1.0-200m-pytorch

Full Changelog:

https://github.com/google-research/timesfm/commits/v1.2.1

详细ChangeLog

项目发展历程

Github榜单

日榜

2026-06-20

rank4

1116

周榜

2026年第37周

rank12

2966

timesfm 时间序列预测任务

timesfm 时间序列预测任务

用户评论 (0)

#13.ImportError: cannot import name 'patched_decoder' from 'src'

#143.How to run timesfm on torch, questions and solve plan !

#14.Finetuning

#187.Conflict Between Python 3.11 Requirement for Torch Version and Incompatibility of Lingvo, Praxis, and Paxml

#43.Error in loading checkpoint

#225.Jax and Tensorflow requiring two different CUDA versions

#61.The training code

#333.Is 2.5 Flax version not ok now?

#203.can't reproduce performance of covariates.ipynb

#76.When will the training code be released?

#430.Question about data usage

#429.Question about data usage

#380.pip support

#370.TimesFM 2.5 pip support

#322.Timesfm 2.5 in-context fine tuning?

#317.Finetuning for 2.5

#308.AttributeError: module 'timesfm' has no attribute 'TimesFM_2p5_200M_torch'

#300.How can I get embedding for time-series using this model?

#288.forecast_with_covariates with torch version

#263.Can I finetune the model with Pytorch for "horizon_len" lower than 128?

v3.0.0

v2.0.2

v2.0.1

v1.2.6

Changes:

PyPI Release:

Checkpoints:

Full Changelog:

v1.2.1

Changes:

PyPI Release:

Checkpoints:

Full Changelog:

项目发展历程

Github榜单

智能搜索排行

产品推荐

欢迎回来

timesfm 时间序列预测任务

timesfm 时间序列预测任务

为timesfm打分

收藏到合集

用户评论 (0)

#13.ImportError: cannot import name 'patched_decoder' from 'src'

#143.How to run timesfm on torch, questions and solve plan !

#14.Finetuning

#187.Conflict Between Python 3.11 Requirement for Torch Version and Incompatibility of Lingvo, Praxis, and Paxml

#43.Error in loading checkpoint

#225.Jax and Tensorflow requiring two different CUDA versions

#61.The training code

#333.Is 2.5 Flax version not ok now?

#203.can't reproduce performance of covariates.ipynb

#76.When will the training code be released?

#430.Question about data usage

#429.Question about data usage

#380.pip support

#370.TimesFM 2.5 pip support

#322.Timesfm 2.5 in-context fine tuning?

#317.Finetuning for 2.5

#308.AttributeError: module 'timesfm' has no attribute 'TimesFM_2p5_200M_torch'

#300.How can I get embedding for time-series using this model?

#288.forecast_with_covariates with torch version

#263.Can I finetune the model with Pytorch for "horizon_len" lower than 128?

v3.0.0

v2.0.2

v2.0.1

v1.2.6

Changes:

PyPI Release:

Checkpoints:

Full Changelog:

v1.2.1

Changes:

PyPI Release:

Checkpoints:

Full Changelog:

项目发展历程

Github榜单

智能搜索排行

产品推荐