Update README.md

README.md

@@ -164,7 +164,7 @@ Please note that all demo inferences are run on CodeRosa-70B-AB1-3.92bpw-EXL2.
 
 Setting from Midnight-Rose should work in SillyTavern. This is almost same what I use for testing.
 
-I use max_seq_len 8K with alpha_value 2.65.
+I use max_seq_len 8K with alpha_value 2.65. Model works also with 11K context when alpha_value is set to 5.5. Best outputs are with context around 6K however.
 
 ### Terms and Conditions of Use
 
@@ -181,8 +181,7 @@ Please remember that all CodeRosa-70B-AB1 models operate under the llama2 licens
 
 ### Quants
 
-[GGUF quants](https://huggingface.co/mradermacher/CodeRosa-70B-AB1-GGUF/discussions/1) for this model do not represent model full potential! 
-
+- [GGUF quants](https://huggingface.co/altomek/CodeRosa-70B-AB1-GGUF)
 - [6bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-6bpw-EXL2)
 - [5bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-5bpw-EXL2)
 - [4.5bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-4.5bpw-EXL2)