tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

clip : refactor clip_init, add tests (#12757)

Browse Source 
* refactor clip_init

* fix loading file

* fix style

* test ok

* better test with report

* add missing headers

* clarify

* add KEY_MM_PATCH_MERGE_TYPE

* remove bool has_* pattern

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/llava/clip.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* use ggml_soft_max_ext

* refactor logging system

* add minicpm-v-o 2.6 for testing

* use nullptr everywhere

* fix Yi-VL model

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Xuan-Son Nguyen
2025-04-05 17:17:40 +02:00
committed by GitHub
parent c6ff5d2a8d
commit 0364178ca2
9 changed files with 916 additions and 887 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/llava/gemma3-cli.cpp
View File

@ -79,7 +79,11 @@ struct gemma3_context {
void init_clip_model(common_params & params) {
const char * clip_path = params.mmproj.path.c_str();
ctx_clip = clip_model_load(clip_path, params.verbosity > 1);
ctx_clip = clip_model_load(clip_path, GGML_LOG_LEVEL_INFO);
if (!ctx_clip) {
LOG_ERR("Failed to load CLIP model from %s\n", clip_path);
exit(1);
}
}
~gemma3_context() {