llama : Added support for SmolLm pre-tokenizer (#8608) #8609
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
compilade
reviewed
Jul 21, 2024
Co-authored-by: compilade <[email protected]>
Co-authored-by: compilade <[email protected]>
ggerganov
approved these changes
Jul 21, 2024
Closed
4 tasks
Vaibhavs10
approved these changes
Jul 22, 2024
This was referenced Jul 22, 2024
|
Seems to work well for me too @Stillerman, thanks a lot for adding support to our model! 🤗 |
|
The 1.7B model prints out nonsense, isn't that supported? Asking for clarification. |
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Jul 27, 2024
* Adding SmolLM Pre Tokenizer * Update convert_hf_to_gguf_update.py Co-authored-by: compilade <[email protected]> * Update src/llama.cpp Co-authored-by: compilade <[email protected]> * handle regex * removed .inp and out .out ggufs --------- Co-authored-by: compilade <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 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Outdated suggestions cannot be applied.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.
Adding SmolLM pre-tokenizer support for SmolLM models.
Added tokenizer type for SmolLM-135M in convert-hf-to-gguf-update.py
Added the chkhsh for SmolLM-135M in convert-hf-to-gguf.py
Added LLAMA_VOCAB_PRE_TYPE_SMOLLM enum to llama.h
Ran
./tests/test-tokenizer-0.sh smollm ./models/ggml-vocab-smollm.ggufand Tests passed.Thank you @m18coppola for #8579
@loubnabnl @anton-l Does
src/llama.cpplook right? Any special settings needed in the tokenizer? The .gguf I created for SmolLM-135M seemed to inference well.