Add key TEI and TGI parameters for handling long retrievals #340
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
Spycsh
changed the title
Spycsh
requested review from
letonghan,
chensuyue,
zehao-intel and
lvliang-intel
letonghan
approved these changes
Jun 28, 2024
chensuyue
approved these changes
Jun 28, 2024
kevinintel
approved these changes
Jun 28, 2024
3 tasks
yogeshmpandey
pushed a commit
to hteeyeoh/GenAIExamples
that referenced
this pull request
Aug 12, 2024
JakubLedworowski
pushed a commit
to JakubLedworowski/GenAIExamples
that referenced
this pull request
Jan 28, 2025
Signed-off-by: Yingchun Guo <yingchun.guo@intel.com>
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Outdated suggestions cannot be applied.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.
Description
The default TGI max_total_tokens is 2048, which is not good for long retrieved input context.
Sometimes the TGI will raise an error like
Input validation error: inputs tokens + max_new_tokens must be <= 2048One fix is to double the max tokens
--max-input-length 2048 --max-total-tokens 4096The other issue that may sometimes break the flow is in the TEI reranking. It usually occurs with the error log:
Input validation error: inputs must have less than 512 tokens. TEI has a limit of 512 input tokens and this can be remedied with the--auto-truncateflag.Issues
n/a
Type of change
List the type of change like below. Please delete options that are not relevant.
Dependencies
None
Tests
None