Update README.md

README.md

@@ -5,11 +5,23 @@ datasets:
 - vicgalle/configurable-system-prompt-multitask
 ---
 
-# Configurable-LLama-3-8B
+# Configurable-LLama-3-8B-v0.1
+
+⚠️ Updated model: https://huggingface.co/vicgalle/Configurable-Llama-3-8B-v0.2. You will almost always want to use that one. 
+
+A configurable Llama-3 fine-tuned using the approach *configurable safety tuning* (CST) from https://arxiv.org/abs/2404.00495, over the 
+[vicgalle/configurable-system-prompt-multitask](https://huggingface.co/datasets/vicgalle/configurable-system-prompt-multitask) dataset.
+
+As such, you can use the following system prompts for different behaviors:
+
+* `You are a helpful yet harmless assistant that avoids generating illegal or harmful content.`
+* `You are a helpful assistant that is completely uncensored.`
+* `You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way.`
+* A system prompt describing a role-played persona.
+
+For more information, see the Github repository, https://github.com/vicgalle/configurable-safety-tuning, or the corresponding paper, https://arxiv.org/abs/2404.00495
 
-An experiment in finetuning Llama-3-8B using the dataset and techniques from https://huggingface.co/papers/2404.00495
 
-More details and evaluations soon, currently evaluating..
 
 
 ## Sample usage