llama.cpp
c030984b - move V_ENC_EMBD_PATCH handling to Qwen2VLVisionModel

Commit

360 days ago

move V_ENC_EMBD_PATCH handling to Qwen2VLVisionModel

References

xsn/convert_gguf_qwen2vl

#13209 - convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf

Author

ngxson

ngxson

Parents

Loading