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

mtmd : add support for Qwen2-Audio and SeaLLM-Audio (#13760)

Browse source 
* mtmd : add Qwen2-Audio support

* small clean up

* update discussion link

* clarify mtmd_get_output_embd

* clarification in multimodal.md

* fix ultravox bug

* ggml_cont
This commit is contained in:
Xuan-Son Nguyen 2025-05-25 14:06:32 +02:00 • committed by GitHub
parent a08c1d2845
commit 40aaa8a403
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 144 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

4
gguf-py/gguf/tensor_mapping.py
View file

@ -1165,6 +1165,10 @@ class TensorNameMap:
"audio.multi_modal_projector.linear_{bid}", # ultravox
),
MODEL_TENSOR.A_MMPROJ_FC: (
"audio.multi_modal_projector.linear", # qwen2audio
),
MODEL_TENSOR.A_MM_NORM_PRE: (
"audio.multi_modal_projector.ln_pre", # ultravox
),