mtmd : support SmolVLM (version 1 and 2) (#13050)

* mtmd : support SmolVLM (version 1 and 2)

* correct chat template

* fix n_patches

* scale_factor is an int

* add more models to test

gguf-py/gguf/constants.py

@@ -231,11 +231,15 @@ class Keys:
         IMAGE_MEAN          = "clip.vision.image_mean"
         IMAGE_STD           = "clip.vision.image_std"
         USE_GELU            = "clip.use_gelu"
+        USE_SILU            = "clip.use_silu"
 
         class Attention:
             HEAD_COUNT      = "clip.vision.attention.head_count"
             LAYERNORM_EPS   = "clip.vision.attention.layer_norm_epsilon"
 
+        class Projector:
+            SCALE_FACTOR    = "clip.vision.projector.scale_factor"
+
 #
 # recommended mapping of model tensor names for storage in gguf
 #
@@ -2122,6 +2126,11 @@ class GGUFValueType(IntEnum):
             raise ValueError(f"Unknown type: {type(val)}")
 
 
+class VisionProjectorType:
+    GEMMA3 = "gemma3"
+    IDEFICS3 = "idefics3"
+
+
 # Items here are (block size, type size)
 QK_K = 256
 GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = {