llama.cpp
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf
#13209

Merged

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

ngxson merged 13 commits into ggml-org:master from ngxson:xsn/convert_gguf_qwen2vl

wip

792387b1

qwen2.5vl ok

f7260c2d

github-actions added python

Merge branch 'master' into xsn/convert_gguf_qwen2vl

f48f51d1

vision: fix models missing "text_config"

b5e72ed3

add test

4fac7d4e

github-actions added examples

fix test repo name

474933e2

fix 32B model

651752f1

Revert "fix 32B model"

d96ef53a

clarify about 32B

13e4cccb

ngxson marked this pull request as ready for review 232 days ago

ngxson requested a review from

ggerganov 232 days ago

rm qwen surgery script

6e31ddcd

update llava/readme

ef0bc7aa

Merge branch 'master' into xsn/convert_gguf_qwen2vl

62b7b1e7

ggerganov commented on 2025-05-02

ggerganov approved these changes on 2025-05-02

move V_ENC_EMBD_PATCH handling to Qwen2VLVisionModel

c030984b

ngxson merged 074e42ab into master 230 days ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

examples python

Milestone

No milestone