Clarify settings, quantization level in readme

README.md

@@ -1,18 +1,18 @@
----
-license: apache-2.0
-language:
-- en
-base_model: Nanbeige/Nanbeige4.1-3B
-base_model_relation: quantized
-pipeline_tag: text-generation
-library_name: mnn
-tags:
-- code
-- mnn
----
-
-This model [DeProgrammer/Nanbeige4.1-3B-MNN](https://huggingface.co/DeProgrammer/Nanbeige4.1-3B-MNN) was
-converted to MNN format from [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B)
-using [llmexport.py](https://github.com/alibaba/MNN/issues/4153#issuecomment-3866182869) in [MNN version **3.4.0**](https://github.com/alibaba/MNN/commit/a874b302f094599e2838a9186e5ce2cf6a81a7a7).
-
+---
+license: apache-2.0
+language:
+- en
+base_model: Nanbeige/Nanbeige4.1-3B
+base_model_relation: quantized
+pipeline_tag: text-generation
+library_name: mnn
+tags:
+- code
+- mnn
+---
+
+This model [DeProgrammer/Nanbeige4.1-3B-MNN](https://huggingface.co/DeProgrammer/Nanbeige4.1-3B-MNN) was
+converted to MNN format from [Nanbeige/Nanbeige4.1-3B](https://huggingface.co/Nanbeige/Nanbeige4.1-3B)
+using [llmexport.py](https://github.com/alibaba/MNN/issues/4153#issuecomment-3866182869) in [MNN version **3.4.0**](https://github.com/alibaba/MNN/commit/a874b302f094599e2838a9186e5ce2cf6a81a7a7) with default settings (4-bit quantization).
+
 Inference can be run via MNN, e.g., MNN Chat on Android.