Support Value Zeroing for non-eager attention types #267
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
LuukSuurmeijer
pushed a commit
to LuukSuurmeijer/inseq
that referenced
this pull request
May 10, 2024
gsarti
added a commit
that referenced
this pull request
Jul 23, 2024
* Save attribution tensors with a lower precision. #202 Adds functionality for saving feature attributions objects and tensors in float16 or float8 format, depending on `scores_precision` parameters. Tensors are saved in huggingface safetensor format, and quantized using zeropoint quantization. Because safetensors are bytes objects, they are encoded with b64 to be saved in the output json and decoded upon reloading. * Add support for `device_map` use (#264) * Add device_map support * Fix device setter in HF model * Support Value Zeroing for non-eager attention types (#267) * Fix nans in attn, add pad if missing (#269) * Add transformers v4.40 models to config, update changelog * run tests * Minor fixes * fixed json decode error * Switched to torch-native float8_e4m3fn format * Fix style * Fix reqs * Fix safety * Add changelog --------- Co-authored-by: Gabriele Sarti <gabriele.sarti996@gmail.com>
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Outdated suggestions cannot be applied.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.
Description
This PR addresses the bug with SDPA attention described in #266, and enables the usage of VZ out of the box for all attention implementations