ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

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

Browse source 
* 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
Download patch file Download diff file Expand all files Collapse all files

9
docs/multimodal.md
View file

@ -98,3 +98,12 @@ NOTE: some models may require large context window, for example: `-c 8192`
# note: no pre-quantized GGUF this model, as they have very poor result
# ref: https://github.com/ggml-org/llama.cpp/pull/13760
```
**Mixed modalities**:
```sh
# Qwen2.5 Omni
# Capabilities: audio input, vision input
(tool_name) -hf ggml-org/Qwen2.5-Omni-3B-GGUF
(tool_name) -hf ggml-org/Qwen2.5-Omni-7B-GGUF
```