初始化项目，由ModelHub XC社区提供模型

Model: Mathieu-Thomas-JOSSET/joke-finetome-model-gguf-phi4-20260112-081758
Source: Original Platform

inference/llama_cli_examples.md

@@ -0,0 +1,12 @@
+### Local inference (llama.cpp)
+
+```bash
+llama-cli -hf {REPO_ID}:q8_0 -cnv --chat-template phi4
+```
+
+### Server (OpenAI-compatible)
+
+```bash
+llama-server -hf {REPO_ID}:q8_0
+# /v1/chat/completions will be available (OpenAI-compatible)
+```