Update README.md

README.md

@@ -5,22 +5,24 @@ base_model: Felladrin/TinyMistral-248M-Chat-v2
 
 GGUF version of [Felladrin/TinyMistral-248M-Chat-v2](https://huggingface.co/Felladrin/TinyMistral-248M-Chat-v2).
 
-## Usage with llama.cpp
+## Try it with [llama.cpp](https://github.com/ggerganov/llama.cpp)
 
 ```bash
 brew install ggerganov/ggerganov/llama.cpp
 ```
-
 ```bash
 llama-cli \
   --hf-repo Felladrin/gguf-TinyMistral-248M-Chat-v2 \
   --model TinyMistral-248M-Chat-v2.Q8_0.gguf \
-  -p "<|im_start|>system\nYou are a helpful assistant who answers user's questions with details and curiosity.<|im_end|>\n<|im_start|>user\nWhat are some potential applications for quantum computing?<|im_end|>\n<|im_start|>assistant\n" \
-  -e \
-  --dynatemp-range "0.1-0.35" \
-  --min-p 0.05 \
+  --random-prompt  \
+  --dynatemp-range "0.1-2.5" \
+  --top-k 0 \
+  --top-p 1 \
+  --min-p 0.1 \
+  --typical 0.85 \
+  --mirostat 2 \
+  --mirostat-ent 3.5 \
   --repeat-penalty 1.1 \
-  -c 2048 \
-  -n 250 \
-  -r "<|im_end|>"
+  --repeat-last-n -1 \
+  -n 256
 ```