fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false #5487
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
…oken is set to false
Member
|
Should the list of |
Contributor
Author
|
Good idea, but I guess that would also require added functions here and constants here I'll gladly add them later on |
ggerganov
reviewed
Feb 15, 2024
vriesdemichael
force-pushed
the
fix/5040-eos-bos-token-missing-in-gguf
branch
2 times, most recently
from
b656423 to
10f9651
Compare
ggerganov
approved these changes
Feb 15, 2024
Member
|
Lint check needs fix too |
vriesdemichael
force-pushed
the
fix/5040-eos-bos-token-missing-in-gguf
branch
from
10f9651 to
3b5dc11
Compare
slaren
approved these changes
Feb 15, 2024
jordankanter
pushed a commit
to jordankanter/llama.cpp
that referenced
this pull request
Mar 13, 2024
…oken is set to false (ggml-org#5487) * fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false * fix(gguf-py): added missing cls and mask token ids to the gguf metadata
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 1, 2024
…oken is set to false (ggml-org#5487) * fix(gguf-py): special tokens are no longer skipped when add_<token>_token is set to false * fix(gguf-py): added missing cls and mask token ids to the gguf metadata
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
This fixes one of the problems in #5040
The
add_bos_tokenandadd_eos_tokenare config params to determine whether you should add special tokens to the sequence automatically: https://huggingface.co/docs/transformers/en/model_doc/llama2#transformers.LlamaTokenizer.add_bos_token describes the params.Regardless of
add_bos_tokenandadd_eos_tokenthe special tokens should be added in the metadata, as they can still be used in the chat_template.