llama.cpp
bc583e3c - mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784)

Commit
206 days ago
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
Author
Parents
Loading