mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784)

* mtmd : allow multiple modalities at the same time

* refactor mtmd tokenizer

* fix compile

* ok, missing SinusoidsPositionEmbedding

* first working version

* fix style

* more strict validate of n_embd

* refactor if..else to switch

* fix regression

* add test for 3B

* update docs

* fix tokenizing with add_special

* add more tests

* fix test case "huge"

* rm redundant code

* set_position_mrope_1d rm n_tokens
This commit is contained in:
Xuan-Son Nguyen 2025-05-27 14:06:10 +02:00 committed by GitHub
parent 72b090da2c
commit bc583e3c63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 1148 additions and 744 deletions

View file

@ -17,12 +17,22 @@ struct clip_image_f32;
struct clip_image_u8_batch;
struct clip_image_f32_batch;
enum clip_modality {
CLIP_MODALITY_VISION,
CLIP_MODALITY_AUDIO,
};
struct clip_context_params {
bool use_gpu;
enum ggml_log_level verbosity;
};
struct clip_ctx * clip_init(const char * fname, struct clip_context_params ctx_params);
struct clip_init_result {
struct clip_ctx * ctx_v; // vision context
struct clip_ctx * ctx_a; // audio context
};
struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params);
void clip_free(struct clip_ctx * ctx);