Improve T5 encoder tests with more prompts and static context length #976
+262
−228
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 PR is on top of #967, which must be merged first. |
sogartar
force-pushed
the
t5-improve-test-numerics
branch
from
92c078e to
7226258
Compare
We don't want the stack to depend on the conversion tool from the lamma.cpp repo. Also the conversion to GGUF would not convert all tensors to bf16, but leave some in f32. We would like to control that ourselves if needed. This change makes any previously generated IRPA files obsolete.
The set of prompts is not big enough for statistically sound testing of the T5 encoder. This is true for other text encoders. With the expansion of the prompt set the bf16 numerical difference between eager and IREE vanished. IREE is even more accurate. In tests the tokenizer padding has been change to produce always max length token sequence. This is in line how T5 is used int the Flux pipeline. The T5 encoder export has been expanded with an option to export with a static token sequence length. The tests were refactored to share tolerance values for f32 and bf16.
sogartar
force-pushed
the
t5-improve-test-numerics
branch
from
7226258 to
753414f
Compare
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Outdated suggestions cannot be applied.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.
The set of prompts is not big enough for statistically sound testing of
the T5 encoder. This is true for other text encoders.
With the expansion of the prompt set the bf16 numerical difference
between eager and IREE vanished. IREE is even more accurate.
In tests the tokenizer padding has been change to produce always max
length token sequence. This is in line how T5 is used int the Flux
pipeline. The T5 encoder export has been expanded with an option to
export with a static token sequence length.
The tests were refactored to share tolerance values for f32 and bf16.