Update README.md

README.md

@@ -27,5 +27,21 @@ This llama model was trained 2x faster with [Unsloth](https://github.com/unsloth
 This is a test model on a the following 
 - a private dataset
 - slight customization on llama3 template (no new tokens | no new configs)
-- not suited for anything production, think of it as more a fictional chracter
+- Works with Ollama create with just "FROM path/to/model" as Modelfile (llama3 template works no issues)
 
+# NOTE: DISCLAIMER
+
+Please note this is not for the purpose of production, but result of Fine Tuning through self learning
+
+The llama3 Tokens where kept the same, however the format was slight customized using the available tokens
+
+```
+<|begin_of_text|> <|start_header_id|>user<|end_header_id|>
+{user_input}<|eot_id|><|start_header_id|>analysis<|end_header_id|>
+{analysis}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+{response}<|eot_id|><|start_header_id|>classification<|end_header_id|>
+{classification}<|eot_id|><|start_header_id|>sentiment<|end_header_id|>
+{sentiment}<|eot_id|> <|start_header_id|>user<|end_header_id|>
+Thank you for your answer.<|eot_id|> <|start_header_id|>analysis<|end_header_id|>
+You're most welcome, what would like to know next?<|eot_id|>
+```