gabegoodhart commited on
Commit
9309b02
·
verified ·
1 Parent(s): b65d715

Add precision error note

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -15,4 +15,10 @@ base_model:
15
  > This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base model.
16
  >
17
  > Please reference the base model's full model card here:
18
- > https://huggingface.co/ibm-granite/granite-4.0-1b
 
 
 
 
 
 
 
15
  > This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base model.
16
  >
17
  > Please reference the base model's full model card here:
18
+ > https://huggingface.co/ibm-granite/granite-4.0-1b
19
+
20
+ ### Known Issues
21
+
22
+ This model often uses the full numerical range of a 32-bit float (`f32`), so variants with smaller numerical ranges may run into precision errors at inference. The `F16` variant is known to fail on many hardware combinations.
23
+
24
+ **The recommended full-precision variant is `bf16`**.