Updated Readme.md

README.md

@@ -62,31 +62,7 @@ Q4_K_M is a 4-bit quantization method that compresses the model to ~2.2GB with n
 ollama run hf.co/tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
 ```
 
-**OR run with custom Kanoonu AI identity:**
 
-Create a file called `Modelfile` with this content:
-```
-FROM hf.co/tejasgowda05/Kanoonu-AI-Phi3-GGUF:Q4_K_M
-
-TEMPLATE """{{ if .System }}<|system|>
-{{ .System }}<|end|>
-{{ end }}{{ if .Prompt }}<|user|>
-{{ .Prompt }}<|end|>
-{{ end }}<|assistant|>
-{{ .Response }}<|end|>"""
-
-SYSTEM """You are Kanoonu AI, an expert Indian legal assistant created by Tejas Gowda."""
-
-PARAMETER temperature 0.3
-PARAMETER num_predict 300
-PARAMETER num_ctx 2048
-```
-
-Then run:
-```bash
-ollama create kanoonu-ai -f Modelfile
-ollama run kanoonu-ai
-```
 
 ### Option 2 — llama.cpp CLI
 
@@ -164,7 +140,7 @@ tejasgowda05/Kanoonu-AI-Phi3-GGUF  ← you are here
 | Final Train Loss | 0.3478 |
 | Best Eval Loss | 0.6568 |
 | Training Examples | 23,370 |
-| Training Time | ~205 minutes |
+| Training Time | ~270 minutes |
 
 ---