Models without Vocabulary#5798
Merged
ggerganov merged 10 commits intoggml-org:masterfrom Mar 14, 2024
Merged
Conversation
cebtenzzre
reviewed
Feb 29, 2024
cebtenzzre
reviewed
Feb 29, 2024
Collaborator
|
Do you have a more specific example of a use case for this feature - e.g., a model with a vocab type not currently supported by llama.cpp, but with weights that are? |
ggerganov
approved these changes
Mar 1, 2024
Member
ggerganov
left a comment
ggerganov
left a comment
There was a problem hiding this comment.
This seems something that can be useful
Contributor
Author
|
@cebtenzzre right now we're using some kind of this tokenizer with the llama model trained by our ml engineers. And in our system the vocab is on the client side, and the server only processes tokens. So there is no need for the vocab to be included in the model. |
Xarbirus
force-pushed
the
models-without-vocab
branch
from
735c684 to
2580fe5
Compare
Xarbirus
force-pushed
the
models-without-vocab
branch
from
2580fe5 to
e0504d5
Compare
cebtenzzre
reviewed
Mar 8, 2024
cebtenzzre
reviewed
Mar 12, 2024
cebtenzzre
reviewed
Mar 12, 2024
cebtenzzre
reviewed
Mar 14, 2024
cebtenzzre
approved these changes
Mar 14, 2024
NeoZhangJianyu
pushed a commit
to NeoZhangJianyu/llama.cpp
that referenced
this pull request
Mar 15, 2024
* additional methods to read model and ctx parameters * vocab size as a part of a model metadata * models without vocabulary, convert.py part * models without vocabulary, llama.cpp part * PR clean up * converter scrypt fixes * llama_vocab_type update (renamed the new key) * pr review fixes * revert function renaming * one more NoVocab assert
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
* additional methods to read model and ctx parameters * vocab size as a part of a model metadata * models without vocabulary, convert.py part * models without vocabulary, llama.cpp part * PR clean up * converter scrypt fixes * llama_vocab_type update (renamed the new key) * pr review fixes * revert function renaming * one more NoVocab assert
phuongncn
pushed a commit
to phuongncn/llama.cpp-gx10-dgx-sparks-deepseekv4
that referenced
this pull request
Apr 28, 2026
* additional methods to read model and ctx parameters * vocab size as a part of a model metadata * models without vocabulary, convert.py part * models without vocabulary, llama.cpp part * PR clean up * converter scrypt fixes * llama_vocab_type update (renamed the new key) * pr review fixes * revert function renaming * one more NoVocab assert
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
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.
I made some changes to the model converter so that it could create a gguf model without a built-in dictionary.
This will allow to use any custom external dictionary in an application built with llama.cpp.