Update README.md

README.md

@@ -1,16 +1,18 @@
----
-license: apache-2.0
-language:
-- en
-pipeline_tag: image-text-to-text
-tags:
-- multimodal
-- gui
-- llama-cpp
-- gguf-my-repo
-library_name: transformers
-base_model: bytedance-research/UI-TARS-72B-SFT
----
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- gui
+- llama-cpp
+- gguf-my-repo
+library_name: transformers
+base_model: bytedance-research/UI-TARS-72B-SFT
+---
+
+note: most qwen2 weights aren't divisible by 256, so this is really a q8/q5 quant.
 
 # main-horse/UI-TARS-72B-SFT-Q4_K_M-GGUF
 This model was converted to GGUF format from [`bytedance-research/UI-TARS-72B-SFT`](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT) using llama.cpp.