clarification in multimodal.md

Author: ngxson

convert_hf_to_gguf.py

@@ -2668,7 +2668,7 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         if "language_model." in name:
             name = name.replace("language_model.", "") # for InternVL
         if name.startswith("mlp") or name.startswith("multi_modal_projector") \
-            or name.startswith("vision_model") or name.startswith("audio_tower"):
+                or name.startswith("vision_model") or name.startswith("audio_tower"):
             # skip vision and audio tensors
             return []
         yield from super().modify_tensors(data_torch, name, bid)

docs/multimodal.md

@@ -89,4 +89,8 @@ NOTE: some models may require large context window, for example: `-c 8192`
 # Ultravox 0.5
 (tool_name) -hf ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF
 (tool_name) -hf ggml-org/ultravox-v0_5-llama-3_1-8b-GGUF
+
+# Qwen2-Audio and SeaLLM-Audio
+# note: no pre-quantized GGUF this model, as they have very poor result
+# ref: https://github.com/ggml-org/llama.cpp/pull/13760
 ```