Use model->gguf_kv for loading the template instead of using the C API. #10868
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
|
This seems too much for something that is called frequently. I would prefer if it skipped the C API and just used |
dranger003
changed the title
slaren
approved these changes
Dec 17, 2024
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Dec 20, 2024
…I. (ggerganov#10868) * Bump model_template to 16384 bytes to support larger chat templates. * Use `model->gguf_kv` for efficiency.
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Outdated suggestions cannot be applied.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.
Cohere's command-r models use a rather large chat template and therefore
llama_chat_detect_template()fails to properly detect because<|USER_TOKEN|>is beyond the current 2048 limit. This patch bumps the limit to 16K bytes and allows the conversation mode to work with the command-r models.