vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

quantize : be able to override metadata by key (#6321)

Browse source 
* quantize: be able to override metadata by key

* minor : spacing

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Kawrakow 2024-03-26 13:09:30 +01:00 • committed by GitHub
parent deb7240100
commit d25b1c31b0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 96 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.h
View file

@ -284,6 +284,7 @@ extern "C" {
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
bool pure; // quantize all tensors to the default type
void * imatrix; // pointer to importance matrix data
void * kv_overrides; // pointer to vector containing overrides
} llama_model_quantize_params;
// grammar types