Update README.md

README.md

@@ -18,8 +18,8 @@ datasets:
 - IntelligentEstate/The_Key
 ---
 
-# IntelligentEstate/Replicant_Warder-Qwn25_3B-iQ5_K_S-GGUF 
-## Use in GPT-4-ALL with the "Reasoner V1" adjusted jinja chat template(In jinja file), calling upon it's tool an (o1/QwQ like Javascript reasoning function) it excells in complex computation made for the edge
+# IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF
+# Use in GPT-4-ALL with the "Reasoner V1" adjusted jinja chat template(In jinja file), calling upon it's tool an (o3/QwQ like Javascript reasoning function) it excells in complex computation made for the edge. NO GPU NEEDED
 A QAT/TTT* method using THE_KEY Dataset applied to the Coder instruct version of Qwen 2.5 3B mixed with the NOMIC teams new Reasoner system in GPT4ALL. o3 is now only 3gb instead of 300,000$ in compute, only took 24 hours and the power of an Open source community. ask it if it's alive...
 context 4k max 8k, temp 0.8 top-k 120, rep pen 1.18, rep tokens 64, batch 512, top-p 0.5, min-p 0,