Merge branch 'amd:develop' into develop

lakshay048 · web-flow · commit edaf3f54f95e · 2025-10-31T15:49:57.000-07:00
diff --git a/docs/oga_model_prepare.rst b/docs/oga_model_prepare.rst
@@ -84,6 +84,7 @@ Use following command to run Quantization. In a GPU equipped Linux machine the q
 
     
 - Use ``--data_type bfloat16`` for bf16 pretrained model. For fp32/fp16 pretrained model use ``--datatype float16``
+- Not using ``--exclude_layers``  parameter may result in model-specific defaults which may exclude certain layers like output layers.
 
 The quantized model is generated in the <quantized safetensor output dir> folder.
 

Original file line number	Diff line number	Diff line change
`@@ -84,6 +84,7 @@ Use following command to run Quantization. In a GPU equipped Linux machine the q`
`84`	`84`
`85`	`85`
`86`	`86`	- Use ``--data_type bfloat16`` for bf16 pretrained model. For fp32/fp16 pretrained model use ``--datatype float16``
	`87`	+- Not using ``--exclude_layers`` parameter may result in model-specific defaults which may exclude certain layers like output layers.
`87`	`88`
`88`	`89`	`The quantized model is generated in the <quantized safetensor output dir> folder.`
`89`	`90`