Update README.md

README.md

@@ -43,7 +43,7 @@ base_model:
 pipeline_tag: text-generation
 ---
 
-<h2>Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M [256k context]</h2>
+<h2>Qwen3-Coder-42B-A3B-Instruct-TOTAL-RECALL-MASTER-CODER-M-512k-ctx [512k context]</h2>
 
 <img src="qwen3-total-recall.gif" style="float:right; width:300px; height:300px; padding:10px;">
 
@@ -59,7 +59,7 @@ The Brainstorm adapter will improve general performance and "out of the box" thi
 
 This creates a model of 42B parameters, 67 layers and 807 tensors.
 
-This version has the NATIVE context of 256k.
+This version has the NATIVE context (up from 256k) set via yarn/rope to 512k as per Qwen tech notes.
 
 This is a non-reasoning/non-thinking block model.