[Frontend] Use a proper chat template for VLM2Vec #9912
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
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
mergify
bot
added
documentation
51 tasks
github-actions
bot
added
the
ready
DarkLight1337
requested review from
robertgshaw2-neuralmagic and
simon-mo
as code owners
mgoin
approved these changes
Nov 1, 2024
DarkLight1337
commented
Nov 1, 2024
Comment on lines
+500
to
+504
| wrap_dicts = (chat_template_text_format == "openai" | ||
| or (model_config.task == "embedding" | ||
| and model_config.is_multimodal_model) | ||
| or (model_config.hf_config.model_type | ||
| in MODEL_KEEP_MULTI_MODAL_CONTENT)) |
There was a problem hiding this comment.
Maybe we should auto-detect this in the future...
lk-chen
pushed a commit
to lk-chen/vllm
that referenced
this pull request
Nov 4, 2024
lk-chen
pushed a commit
to lk-chen/vllm
that referenced
this pull request
Nov 4, 2024
Signed-off-by: Linkun Chen <[email protected]>
richardsliu
pushed a commit
to richardsliu/vllm
that referenced
this pull request
Nov 4, 2024
Signed-off-by: Richard Liu <[email protected]>
bigPYJ1151
pushed a commit
to bigPYJ1151/vllm
that referenced
this pull request
Nov 5, 2024
hissu-hyvarinen
pushed a commit
to ROCm/vllm
that referenced
this pull request
Nov 6, 2024
JC1DA
pushed a commit
to JC1DA/vllm
that referenced
this pull request
Nov 11, 2024
Signed-off-by: Loc Huynh <[email protected]>
sumitd2
pushed a commit
to sumitd2/vllm
that referenced
this pull request
Nov 14, 2024
Signed-off-by: Sumit Dubey <[email protected]>
KuntaiDu
pushed a commit
to KuntaiDu/vllm
that referenced
this pull request
Nov 20, 2024
mfournioux
pushed a commit
to mfournioux/vllm
that referenced
this pull request
Nov 20, 2024
Signed-off-by: Maxime Fournioux <[email protected]>
tlrmchlsmth
pushed a commit
to neuralmagic/vllm
that referenced
this pull request
Nov 23, 2024
Signed-off-by: Tyler Michael Smith <[email protected]>
sleepwalker2017
pushed a commit
to sleepwalker2017/vllm
that referenced
this pull request
Dec 13, 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.
VLM2Vec is not intended to be a chat model, so the existing chat template from Phi-3.5-vision doesn't work well.
Building on #9759, this PR adds a chat template to convert the incoming messages into a format suitable for VLM2Vec and updates the docs accordingly.