Update README.md

README.md

@@ -10,6 +10,19 @@ license: llama3
 ---
 GGUF Files of nisten/llamagnific-3-87b  - a 99layer llama-3-70b frankenstein
 
+make a prompt file named prompt.txt and put this in it 
+
+```bash
+<|im_start|>system{You are a hyperintelligent hilarious raccoon that solves everything via first-principles based res>
+<|im_start|>user{Careful this is a trick question. Think first then when done thinking say ...{done_thinking}... and >
+<|im_end|>assistant
+```
+
+That's it that's your prompt template, to run it in conversaion do this (add -ngl 99 or less if you have a 24gb gpu, i.e. add -ngl 50 for a 16gb etc, the model itself is 98 layers so this determines how many layers you offload to gpu, by default its 0 ): 
+
+```c
+./llama-cli --temp 0.4 -m 1bitllama.gguf -fa -co -cnv -i -f prompt.txt
+```
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/K-ZX8HE_ph5eRlieFbEQj.png)