improve chat template processing #549
Merged
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
pavel-esir
force-pushed
the
improve_chat_template
branch
4 times, most recently
from
708ab4f
to
73c44bb
Compare
|
please do not review, PR is not ready yet |
pavel-esir
force-pushed
the
improve_chat_template
branch
from
73c44bb
to
d3e561b
Compare
|
PR is ready for review |
pavel-esir
force-pushed
the
improve_chat_template
branch
2 times, most recently
from
209cb1f
to
025dfd3
Compare
| atten_mask = new_atten_mask; | ||
| } else { | ||
| atten_mask = attention_mask; | ||
| } |
There was a problem hiding this comment.
attention mask and position ids are specific for stateful and static model runners, while they are not required for PA-based.
I would move it to model runners / pipelines to avoid complexity in generic LLM pipeline impl.
But maybe it should be done during migration to CB rails
CC @Wovchena
There was a problem hiding this comment.
There's no other way for now
Wovchena
requested changes
Jun 26, 2024
| // If header containt that typical expression we update template and | ||
| // extract system message manually from ChatHistory. | ||
| std::string header_with_slice = "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}"; | ||
| std::string replacement_string = "{% if false %}{% set placeholder = false %}"; |
There was a problem hiding this comment.
Can you extend your Jinja2Cpp issue to keep track of missing features
pavel-esir
commented
Jun 27, 2024
pavel-esir
force-pushed
the
improve_chat_template
branch
2 times, most recently
from
8641b8d
to
f54c1da
Compare
pavel-esir
force-pushed
the
improve_chat_template
branch
from
16110ba
to
784f269
Compare
pavel-esir
commented
Jul 5, 2024
Wovchena
requested changes
Jul 8, 2024
Wovchena
requested changes
Jul 10, 2024
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
pavel-esir
force-pushed
the
improve_chat_template
branch
2 times, most recently
from
7f77f89
to
e4e78ac
Compare
…ng used by another process'
Wovchena
approved these changes
Jul 11, 2024
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.
TODO
ticket: CVS-143685