Update README.md

README.md

@@ -2,14 +2,28 @@
 pipeline_tag: text-generation
 inference: false
 license: apache-2.0
-library_name: transformers
+library_name: exllamav2
 tags:
 - language
 - granite-3.2
 base_model:
-- ibm-granite/granite-3.1-8b-instruct
+- ibm-granite/granite-3.2-8b-instruct
 ---
-
+# Granite-3.2-8B-Instruct-exl2
+Original model: [granite-3.2-8b-instruct](https://huggingface.co/ibm-granite/granite-3.2-8b-instruct)  
+Created by: [Granite Team, IBM](https://huggingface.co/ibm-granite)
+
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/granite-3.2-8b-instruct-exl2/tree/main)  
+[4.5bpw h6](https://huggingface.co/cgus/granite-3.2-8b-instruct-exl2/tree/4.5bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/granite-3.2-8b-instruct-exl2/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/granite-3.2-8b-instruct-exl2/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/granite-3.2-8b-instruct-exl2/tree/8bpw-h8)  
+
+## Quantization notes
+Made with Exllamav2 0.2.8. Granite3 models require Exllamav2 0.2.7 or newer to use.  
+Exl2 models don't support native RAM offloading, so the model has to fully fit into GPU VRAM.  
+It's also required to use Nvidia RTX on Windows or Nvidia RTX/AMD ROCm on Linux.
 # Granite-3.2-8B-Instruct
 
 **Model Summary:**