ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

common : refactor downloading system, handle mmproj with -hf option (#12694)

Browse source 
* (wip) refactor downloading system [no ci]

* fix all examples

* fix mmproj with -hf

* gemma3: update readme

* only handle mmproj in llava example

* fix multi-shard download

* windows: fix problem with std::min and std::max

* fix 2
This commit is contained in:
Xuan-Son Nguyen 2025-04-01 23:44:05 +02:00 • committed by GitHub
parent f423981ac8
commit 267c1399f1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 673 additions and 635 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/gritlm/gritlm.cpp
View file

@ -168,7 +168,7 @@ int main(int argc, char * argv[]) {
llama_backend_init();
llama_model * model = llama_model_load_from_file(params.model.c_str(), mparams);
llama_model * model = llama_model_load_from_file(params.model.path.c_str(), mparams);
// create generation context
llama_context * ctx = llama_init_from_model(model, cparams);