fix: suppress tokenizer max context length warning #200
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
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
marcelklehr
approved these changes
Aug 8, 2025
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
kyteinsky
force-pushed
the
fix/suppress-tokenizer-warn
branch
from
ffc5448 to
10c332d
Compare
kyteinsky
force-pushed
the
fix/suppress-tokenizer-warn
branch
4 times, most recently
from
443ed7b to
3545c35
Compare
|
seems like we're running out of disk space since the larger embedding model wasn't downloaded but the smaller gpt2 tokenizer was, which are downloaded in that order. Let's see if switching to |
Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
kyteinsky
force-pushed
the
fix/suppress-tokenizer-warn
branch
from
3545c35 to
310d89a
Compare
|
It was an issue with nc_py_api not downloading the model in the latest version. Fixed its version to the previous release: |
Merged
kyteinsky
added a commit
that referenced
this pull request
Aug 29, 2025
## 4.5.0-beta.0 - 2025-08-29 ### Fixed - suppress tokenizer max context length warning (#200) @kyteinsky - fix nc_py_api to 0.20.2 (#200) @kyteinsky ### Changed - store worker logs and present them better (#200) @kyteinsky ### Added - add app version to file logs (#201) @kyteinsky Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
Merged
kyteinsky
added a commit
that referenced
this pull request
Sep 23, 2025
## 4.5.0 - 2025-09-23 ### Changed - stable release of the 4.5.0-beta series - bump max NC version to 33 - store worker logs and present them better (#200) @kyteinsky ### Fixed - better parsing of version string for repairs (#209) @kyteinsky - suppress tokenizer max context length warning (#200) @kyteinsky - fix nc_py_api to 0.20.2 (#200) @kyteinsky ### Added - add app version to file logs (#201) @kyteinsky Signed-off-by: Anupam Kumar <kyteinsky@gmail.com>
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.
It was used as the default fallback for nc_texttotext provider under the hood before.
The tokenizer is pre-downloaded in the init step.