Update README.md

README.md

@@ -15,7 +15,7 @@ Image to be replaced :P
 </div>
 </center>
 
-This model uses the Alpaca **prompting format**. Unlike the base model this one is tuned on **8192 sequence length**. This was due to memory constraints.
+This model uses the Alpaca **prompting format**. Unlike the base model this one is tuned on **16384 sequence length**. This was due to memory constraints.
 
 This is a roleplay focused finetune using MiquMaid v2 70B DPO by [Undi95](https://huggingface.co/Undi95) and [IkariDev](https://huggingface.co/IkariDev) as base.
 
@@ -40,6 +40,9 @@ This repo contains BFP16 files of Miqu-PlayMaid-70B-v0.1
 - [Bluemoon Fandom RP](https://huggingface.co/datasets/Squish42/bluemoon-fandom-1-1-rp-cleaned)
 
 ### Format:
+
+I can only guarantuee that it works with a maximum context length of 16384. Might work with 32768, but no promises. 
+
 ```
 ### Instruction:
 {system prompt}