Add gpt-3.5-turbo-16k support to ctx len getter #1388
Merged
+15
−8
Conversation
This file contains hidden or 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
Co-Authored-By: Ian McKenzie <[email protected]>
danesherbs
requested review from
andrew-openai,
jwang47 and
logankilpatrick
as code owners
danesherbs
commented
Oct 24, 2023
Comment on lines
+84
to
+87
| for model_prefix in {"gpt-3.5-turbo-", "gpt-4-"}: | ||
| if model_name.startswith(model_prefix): | ||
| return True | ||
|
|
Contributor
Author
There was a problem hiding this comment.
We may also want to throw an error when there's not an exact match, or be more restrictive about when the prefix matching applies to avoid similar errors in the future.
logankilpatrick
approved these changes
Jan 3, 2024
Contributor
logankilpatrick
left a comment
logankilpatrick
left a comment
There was a problem hiding this comment.
Nice, thank you!
jacobbieker
pushed a commit
to withmartian/-ARCHIVED--router-evals
that referenced
this pull request
Jan 9, 2024
**What:** Adds support for `gpt-3.5-turbo-16k` to `n_ctx_from_model_name`. **Why:** Currently `n_ctx_from_model_name` returns 4096 for `gpt-3.5-turbo-16k`. Co-authored-by: Ian McKenzie <[email protected]>
Linmj-Judy
pushed a commit
to TablewareBox/evals
that referenced
this pull request
Feb 27, 2024
**What:** Adds support for `gpt-3.5-turbo-16k` to `n_ctx_from_model_name`. **Why:** Currently `n_ctx_from_model_name` returns 4096 for `gpt-3.5-turbo-16k`. Co-authored-by: Ian McKenzie <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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: Adds support for
gpt-3.5-turbo-16kton_ctx_from_model_name.Why: Currently
n_ctx_from_model_namereturns 4096 forgpt-3.5-turbo-16k.