litellm: add qwen2.5-72b alias (Anvil) as the best-quality local model

Replaces the short-lived mistral-large alias. Backed by ollama_chat/qwen2.5:72b
on Anvil. Consumers (paperless-ai, RAG chat, HA, morning-report) target this.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

vars/main.yml

@@ -93,6 +93,10 @@ litellm_models:
     api_base: "{{ anvil_ollama_base }}"
     api_key: ollama-no-auth
   # Direct local model names (explicit)
+  - name: qwen2.5-72b
+    backend: ollama_chat/qwen2.5:72b
+    api_base: "{{ anvil_ollama_base }}"
+    api_key: ollama-no-auth
   - name: llama-3.3-70b
     backend: ollama_chat/llama3.3:70b
     api_base: "{{ anvil_ollama_base }}"