Update README.md

README.md

@@ -48,18 +48,21 @@ Jan-v1 is optimized for direct integration with the [Jan App](https://jan.ai/).
 
 **Using vLLM:**
 ```bash
-vllm serve Menlo/Jan-v1 \
+vllm serve janhq/Jan-v1-4B \
     --host 0.0.0.0 \
     --port 1234 \
     --enable-auto-tool-choice \
     --tool-call-parser hermes
+    
 ```
 
 **Using llama.cpp:**
 ```bash
-llama-server --model jan-v1.gguf \
+llama-server --model Jan-v1-4B-Q4_K_M.gguf \
     --host 0.0.0.0 \
-    --port 1234
+    --port 1234 \
+    --jinja \
+    --no-context-shift
 ```
 
 ### Recommended Parameters