nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 35 Packages Projects Releases Wiki Activity

mtmd: add more validations (#25013)

Browse Source 
* mtmd: add more validations

* fix

* refactor a bit

* type check for get_arr_int
This commit is contained in:
Xuan-Son Nguyen
2026-06-26 08:43:29 +02:00
committed by GitHub
parent f818065d75
commit b11f7c16bc
4 changed files with 59 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/clip-model.h
+3 -6
View File
@@ -55,8 +55,7 @@ struct clip_hparams {
int32_t n_head = 0;
int32_t n_head_kv = 0;
int32_t n_layer = 0;
// idefics3
int32_t n_merge = 0; // number of patch merges **per-side**
int32_t n_merge = 1; // number of patch merges **per-side**
// for preprocessor
int32_t image_longest_edge = 0;
@@ -135,8 +134,7 @@ struct clip_hparams {
int32_t custom_image_max_tokens = -1;
void set_limit_image_tokens(int n_tokens_min, int n_tokens_max) {
const int cur_merge = n_merge == 0 ? 1 : n_merge;
const int patch_area = patch_size * patch_size * cur_merge * cur_merge;
const int patch_area = patch_size * patch_size * n_merge * n_merge;
image_min_pixels = (custom_image_min_tokens > 0 ? custom_image_min_tokens : n_tokens_min) * patch_area;
image_max_pixels = (custom_image_max_tokens > 0 ? custom_image_max_tokens : n_tokens_max) * patch_area;
warmup_image_size = static_cast<int>(std::sqrt(image_max_pixels));
@@ -145,8 +143,7 @@ struct clip_hparams {
void set_warmup_n_tokens(int n_tokens) {
int n_tok_per_side = static_cast<int>(std::sqrt(n_tokens));
GGML_ASSERT(n_tok_per_side * n_tok_per_side == n_tokens && "n_tokens must be n*n");
const int cur_merge = n_merge == 0 ? 1 : n_merge;
warmup_image_size = n_tok_per_side * patch_size * cur_merge;
warmup_image_size = n_tok_per_side * patch_size * n_merge;
// TODO: support warmup size for custom token numbers
}
// sam vit deepseek-ocr