Bump llama_tokenize APIs to latest specs #730
Closed
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Outdated suggestions cannot be applied.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.
The
llama_tokenize
andllama_tokenize_with_model
APIs are out-dated with respect to the equivalent APIs in llama.cpp (as shown below):ISSUE: Particularly, they are missing an argument
text_len
which denotes the length of the text/prompt being tokenized. This causes segmentation faults, as the wrong arguments get passed on to the C++ library.This PR adds the required arguments to llama_cpp.py. cc: @abetlen