Update README.md

README.md

@@ -71,9 +71,14 @@ Please note that these GGMLs are **not compatible with llama.cpp, or currently w
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/minotaur-15B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openaccess-ai-collective/minotaur-15b)
 
-## A note regarding context length
+## A note regarding context length: 8K
 
-it is currently untested as to whether the 8K context is compatible with available clients/libraries such as KoboldCpp, ctransformers, etc.
+It is confirmed that the 8K context of this model works in KoboldCpp, if you manually set max context to 8K by adjusting the text box above the slider:
+![.](https://s3.amazonaws.com/moonup/production/uploads/63cd4b6d1c8a5d1d7d76a778/LcoIOa7YdDZa-R-R4BWYw.png)
+
+(set it to 8192 at most)
+
+It is currently unknown as to whether it is compatible with other clients.
 
 If you have feedback on this, please let me know.