Align the tokenized result between deepseek coder python model and gguf model #3986
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Outdated suggestions cannot be applied.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.
Thanks for your efforts to support convert deepseek coder model according to
#3633
I just found that the tokenized result of the quantinized model is sightly different from the original because deepseek coder use different pretokenizer from the gpt2 style preprocess implement in your code. So I add deepseekcoder process pipeline to your work.
The convert script is modified from strutive07's work.
I ran above commands and did some test to make sure the tokenized result are the same