Upload README.md with huggingface_hub

README.md

@@ -88,11 +88,23 @@ Because the dominant donor is reasoning-derived, RazorStrike-v1 can produce long
 
 **llama.cpp:**
 ```bash
-llama-server -hf lancejames221b/razorstrike-v1-GGUF --port 8080
+llama-server -hf lancejames221b/razorstrike-v1-GGUF:Q4_K_M --port 8080
 # or, if downloaded locally:
 llama-server -m razorstrike-v1-Q4_K_M.gguf --port 8080 -c 32768
 ```
 
+Then query it with the recommended settings and a "think fast" system prompt:
+```bash
+curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+  "messages": [
+    {"role": "system", "content": "Think fast, not long - a few sentences of reasoning at most, then answer directly."},
+    {"role": "user", "content": "Write a Python function that reverses a linked list."}
+  ],
+  "temperature": 0.6, "top_p": 0.95, "top_k": 20, "min_p": 0.0,
+  "max_tokens": 1024
+}'
+```
+
 **Ollama:**
 ```bash
 ollama pull hf.co/lancejames221b/razorstrike-v1-GGUF