Add TimesFM Time Series Forecasting Model #34082
Draft
+1,733
−0
Conversation
This file contains 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 was referenced Oct 24, 2024
rajatsen91
approved these changes
Oct 24, 2024
|
|
||
| # B x N x D | ||
| patched_inputs = patched_inputs * (1.0 - patched_pads) | ||
| print(">>> PatchedDecoder patched_inputs", patched_inputs.shape) |
There was a problem hiding this comment.
nit: not sure if these print statements are necessary.
There was a problem hiding this comment.
The PR is still in progress. We will make sure to eliminate all debug info when ready for review.
| patched_inputs = patched_inputs * (1.0 - patched_pads) | ||
| print(">>> PatchedDecoder patched_inputs", patched_inputs.shape) | ||
| concat_inputs = torch.cat([patched_inputs, patched_pads], dim=-1) | ||
| print(">>> PatchedDecoder concat_inputs", concat_inputs.shape) |
| current_padding = paddings[:, 0 : final_out.shape[1]] | ||
| input_ts = final_out[:, -max_len:] | ||
| input_padding = current_padding[:, -max_len:] | ||
| fprop_outputs, all_attentions, all_hidden_states = self.forward(input_ts, input_padding, freq, output_attentions=output_attentions, output_hidden_states=output_hidden_states) |
There was a problem hiding this comment.
Is caching being used to save on key value computations here? May be that is the purpose of output_attentions and output_hidden_states ?
There was a problem hiding this comment.
It is required by the Hugging Face framework.
| print(">>> TimesFMModel _preprocess", len(inputs), inputs[0].shape) | ||
| input_ts, input_padding, inp_freq = [], [], [] | ||
|
|
||
| pmap_pad = ( |
There was a problem hiding this comment.
Note that this padding might not be required if we are not compiling the model.
|
Great work! I left some minor comments. |
|
Would this PR add finetuning support for the model? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
What does this PR do?
This PR adds a new model, TimesFM, to HuggingFace. TimesFM is a time series forecasting model based on the transformer architecture. It was proposed in A decoder-only foundation model for time-series forecasting.
Code Example
TODOs