Update README.md

README.md

@@ -6,4 +6,9 @@ base_model:
 - t-tech/T-lite-it-1.0
 pipeline_tag: image-to-text
 ---
-This model was converted to GGUF format from t-tech/T-lite-it-1.0 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
+# This model was converted to GGUF format from t-tech/T-lite-it-1.0 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.
+
+Run with LLaMa-CLI:
+```
+.\llama-cli.exe -m .\models\t-lite-it-1.0-q3_k_s.gguf --gpu-layers 50 -p "Write only on Russian" -cnv
+```