Update README.md

README.md

@@ -16,6 +16,20 @@ extra_gated_description: If you want to learn more about how we process your per
 
 # Model Card for Mistral-Nemo-Instruct-2407
 
+[This is the **6bpw** EXL2 Quant of the Update for Mistral Nemo as of 07/31. Find the original model here.](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
+
+Not sure how much this differs from the unsloth version (it didn't look like Unsloth had theirs updated yet so I've quanted the one produced my Mistral here). Commits indicate a chat template was fixed and some fixes to the eos token/clean_up_tokenization_spaces. So if you had issues with Nemo previously, this may fix some of this. May.
+<br>
+
+[8BPW Quant here](https://huggingface.co/Statuo/Mistral-Nemo-Instruct-2407-EXL2-8bpw)
+<br>
+
+[6bpw Quant here](https://huggingface.co/Statuo/Mistral-Nemo-Instruct-2407-EXL2-6bpw)
+
+<br>
+
+---
+
 The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407). Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
 
 For more details about this model please refer to our release [blog post](https://mistral.ai/news/mistral-nemo/).