Hugging Face's logo

skymizer
/
granite-4.0-tiny-base-preview-GGUF

GGUF
Model card Files
xet
 Community
elichen-skymizer commited on
Commit
c324fa5
·
verified ·
1 Parent(s): e84325e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -2,4 +2,6 @@
2
  license: apache-2.0
3
  ---
4
 
5
- This the GGUF models are quantized from [ibm-granite/granite-4.0-tiny-base-preview](https://huggingface.co/ibm-granite/granite-4.0-tiny-base-preview)
 
 
 
2
  license: apache-2.0
3
  ---
4
 
5
+ This the GGUF models are quantized from [ibm-granite/granite-4.0-tiny-base-preview](https://huggingface.co/ibm-granite/granite-4.0-tiny-base-preview)
6
+
7
+ Granite-4.0-Tiny-Base-Preview is a 7B-parameter **hybrid mixture-of-experts (MoE)** language model featuring a 128k token context window. The architecture leverages **Mamba-2**, superimposed with a softmax attention for enhanced expressiveness, with **no positional encoding** for better length generalization.