Force use_cache=True #496
Merged
Force use_cache=True #496
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
borzunov
commented
Sep 2, 2023
| @@ -40,7 +40,7 @@ install_requires = | |||
| transformers>=4.32.0,<5.0.0 # if you change this, please also change version assert in petals/__init__.py | |||
| speedtest-cli==2.1.3 | |||
| pydantic>=1.10,<2.0 # 2.0 is incompatible with hivemind yet | |||
| hivemind @ git+https://github.com/learning-at-home/hivemind | |||
| hivemind==1.1.10.post2 | |||
There was a problem hiding this comment.
They are currently identical.
borzunov
added a commit
that referenced
this pull request
Sep 2, 2023
This reverts a part of #496 and instead overrides `use_cache` in `LlamaConfig`s only (so the correct value is visible by HF `.generate()` as well).
d-popov
pushed a commit
to d-popov/petals-ai
that referenced
this pull request
Sep 6, 2023
d-popov
pushed a commit
to d-popov/petals-ai
that referenced
this pull request
Sep 6, 2023
This reverts a part of bigscience-workshop#496 and instead overrides `use_cache` in `LlamaConfig`s only (so the correct value is visible by HF `.generate()` as well).
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Outdated suggestions cannot be applied.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.
Petals supports only
use_cache=Truefor inference.However, we should not reject
use_cache=Falsesince it returns identical results (just forces the slower O(n^3) inference algorithm instead of the O(n^2) one).I allow
use_cache=Falsesince some models use this setting for reasons unclear to me (see https://huggingface.co/garage-bAInd/Platypus2-70B-instruct/discussions/8), and this led toAssertionErrorbefore this PR.