set default values for vision model in config

convert/convert_qwen2.go

@@ -40,7 +40,7 @@ func (q *qwen2Model) KV(t *Tokenizer) ggml.KV {
 	case "yarn":
 		kv["qwen2.rope.scaling.type"] = q.RopeScaling.Type
 		kv["qwen2.rope.scaling.factor"] = q.RopeScaling.Factor
-	case "mrope":
+	case "mrope", "default":
 		kv["qwen2.rope.mrope_section"] = q.RopeScaling.MropeSection
 	default:
 		panic("unknown rope scaling type")

convert/convert_qwen25vl.go

@@ -39,19 +39,24 @@ func (q *qwen25VLModel) KV(t *Tokenizer) ggml.KV {
 		}
 	}
 
-	kv["qwen25vl.vision.block_count"] = q.VisionModel.Depth
+	if q.VisionModel.FullAttentionBlocks == nil {
+		kv["qwen25vl.vision.fullatt_block_indexes"] = []int32{7, 15, 23, 31}
+	}
+
+	// Use cmp.Or directly in the KV assignments to provide defaults for missing values
+	kv["qwen25vl.vision.block_count"] = cmp.Or(q.VisionModel.Depth, 32)
 	kv["qwen25vl.vision.embedding_length"] = q.VisionModel.HiddenSize
-	kv["qwen25vl.vision.attention.head_count"] = q.VisionModel.NumHeads
+	kv["qwen25vl.vision.attention.head_count"] = cmp.Or(q.VisionModel.NumHeads, 16)
 	kv["qwen25vl.vision.num_channels"] = q.VisionModel.InChannels
-	kv["qwen25vl.vision.patch_size"] = q.VisionModel.PatchSize
-	kv["qwen25vl.vision.spatial_merge_size"] = q.VisionModel.SpatialMergeSize
+	kv["qwen25vl.vision.patch_size"] = cmp.Or(q.VisionModel.PatchSize, 14)
+	kv["qwen25vl.vision.spatial_merge_size"] = cmp.Or(q.VisionModel.SpatialMergeSize, 2)
 	kv["qwen25vl.vision.spatial_patch_size"] = q.VisionModel.SpatialPatchSize
-	kv["qwen25vl.vision.window_size"] = q.VisionModel.WindowSize
+	kv["qwen25vl.vision.window_size"] = cmp.Or(q.VisionModel.WindowSize, 112)
 	kv["qwen25vl.vision.attention.layer_norm_epsilon"] = cmp.Or(q.VisionModel.RMSNormEps, 1e-6)
 	// RoPE theta increased from 1e4 to 1e5 to compensate for numerical differences between tensor operations; empirically produces better results.
 	kv["qwen25vl.vision.rope.freq_base"] = cmp.Or(q.VisionModel.RopeTheta, 1e4)
 	kv["qwen25vl.vision.fullatt_block_indexes"] = q.VisionModel.FullAttentionBlocks
-	kv["qwen25vl.vision.temporal_patch_size"] = q.VisionModel.TemporalPatchSize
+	kv["qwen25vl.vision.temporal_patch_size"] = cmp.Or(q.VisionModel.TemporalPatchSize, 2)
 
 	return kv
 }