Create Modelfile or ollama

Modelfile

@@ -0,0 +1,32 @@
+# FROM ... (Keep your existing FROM line)
+#FROM hf.co/ajvikram/Qwen2.5-Coder-3B-Network-Eng-GGUF
+FROM hf.co/ajvikram/network-compliance-auditor-grpo
+
+# --- 1. STOP TOKENS (Keep these!) ---
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "</answer>"
+PARAMETER stop "User:"
+PARAMETER stop "<|fim_prefix|>"
+PARAMETER stop "<|fim_middle|>"
+PARAMETER stop "<|fim_suffix|>"
+PARAMETER stop "<|repo_name|>"
+
+# --- 2. CRITICAL FIX: ANTI-LOOPING ---
+# repeat_penalty 1.15 tells the model: "If you just said this token, don't say it again."
+# This kills the "😦 😦 😦" loop instantly.
+PARAMETER repeat_penalty 1.15
+
+# repeat_last_n 64 tells it to look back at the last 64 tokens to check for repeats.
+PARAMETER repeat_last_n 64
+
+# --- 3. TEMPLATE (Keep this exactly as before) ---
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+<think>
+{{ .Response }}"""
+
+# --- 4. SYSTEM (Keep this exactly as before) ---
+SYSTEM """ You are an intelligent Network Compliance Auditor. You must output your internal reasoning trace within <reasoning> tags, followed by a final JSON object containing the verdict (PASS/FAIL), the specific control ID, and the evidence line. Dont repeat and provide only one answer."""