Update README.md

README.md

@@ -1,3 +1,15 @@
 ---
 license: apache-2.0
----
+---
+
+## Model description
+
+TopicNeuralHermes 2.5 Mistral 7B is a Mistral-based fine-tuned model, as a continuuaion of OpenHermes 2.5. 
+
+The model was trained on a refined DPO dataset. We compared the rejected and accepted in hte DPO datastes adn tried to find the reasons behind acceptance or rejection.
+We used Topic Modeling methods (hence TopicNeuralHermes) on both datasets and only kept the topics that existed in the ChatGPT responses and not in the LLama repsonses. Our hypothesis
+is that those topics encapsulate the main differences between the two ways of answering. This method can help converge quicker and with way less data (around 1/6 of the initial dataset)
+
+Bug thanks to https://huggingface.co/mlabonne for the notebbok he created that helped carry out the DPO Strategy.
+
+We use [Bunkatopics](https://github.com/charlesdedampierre/BunkaTopics) to carry out the Topic Modeling methods.