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

* wip

* qwen2.5vl ok

* vision: fix models missing "text_config"

* add test

* fix test repo name

* fix 32B model

* Revert "fix 32B model"

This reverts commit 651752f1ae25fe8a01c1e57c18cf2eca80b2774e.

* clarify about 32B

* rm qwen surgery script

* update llava/readme

* move V_ENC_EMBD_PATCH handling to Qwen2VLVisionModel

gguf-py/gguf/constants.py

@@ -234,6 +234,7 @@ class Keys:
         SPATIAL_MERGE_SIZE  = "clip.vision.spatial_merge_size"
         USE_GELU            = "clip.use_gelu"
         USE_SILU            = "clip.use_silu"
+        N_WA_PATTERN        = "clip.vision.n_wa_pattern" # used by qwen2.5vl
 
         class Attention:
             HEAD_COUNT      = "clip.vision.attention.head_count"
@@ -2162,6 +2163,8 @@ class VisionProjectorType:
     GEMMA3 = "gemma3"
     IDEFICS3 = "idefics3"
     PIXTRAL = "pixtral"
+    QWEN2VL = "qwen2vl_merger"
+    QWEN25VL = "qwen2.5vl_merger"
 
 
 # Items here are (block size, type size)