Update README.md

README.md

@@ -8,6 +8,12 @@ inference:
         temperature: 0.4
 ---
 
+## Preamble
+The main purpose of that model, outside form providing a strong foundation for assisted prompting, was to better understand how fine-tuning works.
+Therefore, the dataset is prone to change, as well as the training workflow.
+
+---
+
 # IMAGINE-7B-Instruct
 
 > *Interaction Model for Advanced Graphics Inference and Exploration*
@@ -34,7 +40,7 @@ This instruction model is based on [Mistral-7B-v0.1](https://huggingface.co/mist
 # 💻 Get Started with IMAGINE
 
 ## Prompt template
-To leverage instruction fine-tuning, your prompt should begin with `<s>` token and be surrounded with `[INST]` and `[/INST]`.
+To leverage instruction fine-tuning, your prompt should be surrounded with `[INST]` and `[/INST]`.
 
 ```text
 <s>[INST] {your prompt goes here} [/INST]