Update README.md

README.md

@@ -51,6 +51,31 @@ The most important ones for using this model are
 * there does not seem to be a specific prompt structure - just provide the text
 you want to be completed
 
+### Text Completion with LLaMA.cpp ###
+
+For simple inferencing, use a command like 
+
+```
+./main -m stablelm-3b-4e1t-Q8_0.bin --temp 0 --top-k 4 --prompt "who was Joseph Weizenbaum?"
+```
+
+### Text Tokenization with LLaMA.cpp ###
+
+To get a list of tokens, use a command like 
+
+```
+./tokenization -m stablelm-3b-4e1t-Q8_0.bin --prompt "who was Joseph Weizenbaum?"
+```
+
+### Embeddings Calculation with LLaMA.cpp ###
+
+Text embeddings are calculated with a command like 
+
+```
+./embedding -m stablelm-3b-4e1t-Q8_0.bin --prompt "who was Joseph Weizenbaum?"
+```
+
+
 ## License ##
 
 The original "_Model checkpoints are licensed under the Creative Commons license