quantize: be able to explicitly specify quantization type of output and token embedding tensors #6239
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Outdated suggestions cannot be applied.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.
Two new command line options for the
quantize
tool:--output-tensor-type ggml_type
specifies the type of the output tensor--token-embedding-type ggml_type
specifies the type of the token embedding tensorThe
ggml_type
argument is the string thatggml
uses to identify the various possible types (q4_0, q4_1, ..., f16
, etc., seetype_traits
inggml.c
.Can be useful e.g. when comparing with quantization papers (where researchers tend to not worry about these tensors and just leave them at
f16
), or, if one wants to fine-tune the size vs quality tradeoff (particularly relevant for very low-bit quantization and/or small models). I guess, it could be useful for Gemma as well.