Update README.md

README.md

@@ -16,6 +16,8 @@ If this 2x7b model is loaded in 4 bit the hellaswag score is .8270 which is high
 
 The process is outlined in this [notebook](https://github.com/cognitivecomputations/laserRMT/blob/main/examples/laser-dolphin-mixtral-2x7b.ipynb)
 
+**These Quants will result in unpredicted behavior and I am working on new Quants as I have updated the model**
+
 Quatizations provided by [TheBloke](https://huggingface.co/TheBloke/laser-dolphin-mixtral-2x7b-dpo-GGUF)
 
 
@@ -23,6 +25,10 @@ Quatizations provided by [TheBloke](https://huggingface.co/TheBloke/laser-dolphi
 
 This model follows the same prompt format as the aforementioned model.
 
+However, there have been reports that this causes errors even though both models were ChatML models.
+
+The provided example code does not use this format.
+
 Prompt format:
 
 ```