-
Notifications
You must be signed in to change notification settings - Fork 180
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Feature Branch][LLM Testing] Create GroundTruthSource objects #1219
[Feature Branch][LLM Testing] Create GroundTruthSource objects #1219
Conversation
…/damian/testing_sources_truth
…/damian/testing_sources_truth
assert numpy.allclose( | ||
torch_target_prompt_logits, ort_target_prompt_logits, atol=1e-4 | ||
) | ||
# check that the prompt cache is the same | ||
for torch_cache, ort_cache in zip( | ||
torch_target_prompt_cache, ort_target_prompt_cache | ||
): | ||
assert numpy.allclose(torch_cache, ort_cache, atol=1e-5) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
could be useful to add in this functionality as helper to the GTS objects
from sparsezoo import Model | ||
|
||
|
||
class GroundTruthSource(ABC): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
let's rename to Source
or GenerationSource
? we use this for all scenarios, not just ground truth right?
…/damian/testing_sources_truth
* Update README.md * Update src/deepsparse/yolov8/README.md * Update text_generation.py * quality * readability * all tests passing * added some full kv cache tests * initial commit * ready for review * Delete tests/deepsparse/transformers/pipelines/proposal_text_generation_tests.md
…re_branch' into feature/damian/testing_sources_truth
* initial commit * initial commit * [Feature Branch][LLM Testing] Create GroundTruthSource objects (#1219) * initial commit * finish creation of helper objects * Update tests/conftest.py * small refactor * [Feature Branch][LLM Testing] LLM Testing Suite (#1227) * Update README.md * Update src/deepsparse/yolov8/README.md * Update text_generation.py * quality * readability * all tests passing * added some full kv cache tests * initial commit * ready for review * Delete tests/deepsparse/transformers/pipelines/proposal_text_generation_tests.md * fix tests * Dipika's comments plus adjusting the script to renamed variables * remove ORT ground truth * add OPT tests * rebase and disable tests in GHA * quality
Create two objects that facilitate the generation of the ground truth data (coming from ORT and Torch models) for LLM testing.