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

llava : support MiniCPM-V-2.6 (#8967)

Browse source 
* init

* rename

* add run android for termux in readme

* add android readme

* add instructions in readme

* change name in readme

* Update README.md

* fixed line

* add result in readme

* random pos_embed

* add positions index

* change for ollama

* change for ollama

* better pos_embed in clip

* support ollama

* updata cmakelist

* updata cmakelist

* rename wrapper

* clear code

* replace and organize code

* add link

* sync master

* fix warnings

* fix warnings

* fix bug in bicubic resize when need resize iamge smaller

* receive review comments and modify

* receive review comments and modify

* put all code into llava dir

* fix quality problem in pr code

* change n_layer

* add space in "-1"

* imitate reshape bug of python code

* fix bug in clip

* fix issues for merging

* fix llama-minicpmv-cli in cmake file

* change pr readme

* fix code review

* remove in line 33 directory in the /cmakelists.txt (not in example, in the main dir

* fix cmakefile

* add warn

* fix KEY_HAS_MINICPMV_PROJ

* remove load_image_size into clip_ctx

* remove the extern "C", MINICPMV_API

* fix uhd code for review comment

* delete minicpmv-wrapper in pr

* remove uhd_image_embed

* Modify 2 notes

* support minicpmv2.6

* modify convert script of minicpmv

* modify convert

* modify convert

* add readme

* add resampler of v2.6

* modify clip

* modify readme

* fix type-check

* fix type-check

* fix type-check

* fix type-check

* modify convert script and readme

* fix convert script and readme

* fix convert

* fix num in convert

* fix type-check

---------

Co-authored-by: Hongji Zhu <fireyoucan@gmail.com>
Co-authored-by: harvestingmoon <leewenyeong@gmail.com>
This commit is contained in:
tc-mb 2024-08-16 21:34:41 +08:00 • committed by GitHub
parent ee2984bdaf
commit d565bb2fd5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 645 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

9
examples/llava/llava.cpp
View file

@ -256,7 +256,14 @@ static bool encode_image_with_clip(clip_ctx * ctx_clip, int n_threads, const cli
load_image_size->width = img_res_v.data[i].nx;
load_image_size->height = img_res_v.data[i].ny;
clip_add_load_image_size(ctx_clip, load_image_size);
const bool encoded = clip_image_encode(ctx_clip, n_threads, only_v2_5_reshape_by_patch(&img_res_v.data[i], patch_size), image_embd_v[i]);
bool encoded = false;
int has_minicpmv_projector = clip_is_minicpmv(ctx_clip);
if (has_minicpmv_projector == 2) {
encoded = clip_image_encode(ctx_clip, n_threads, only_v2_5_reshape_by_patch(&img_res_v.data[i], patch_size), image_embd_v[i]);
}
else if (has_minicpmv_projector == 3) {
encoded = clip_image_encode(ctx_clip, n_threads, &img_res_v.data[i], image_embd_v[i]);
}
if (!encoded) {
LOG_TEE("Unable to encode image - spatial_unpad - subimage %d of %d\n", (int) i+1, (int) img_res_v.size);
return false;