Update README.md

README.md

@@ -1,3 +1,23 @@
 ---
 license: apache-2.0
 ---
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/F4Vx4EZN6zRCiRKF58Heb.jpeg)
+
+This tensor is made for entertainment, as I was exercizing how to do DPO. 
+After I stumbled on psychotherapy datasets on huggingface, I mixed them with the empathetic dialogues datasets of meta and got interested in what happens fine tuning opennllama 7b on it. 
+One of the datasets included accepted and rejected therapist answers, so I used that for DPO. 
+This is not a bandaid replacement for seeking professional help. 
+That said, here is a CPU version for the GPUless anons. 
+You can get interesting interactions out of it with the chatmode of the textgen webui, I get 6 tokens per seconds on 8 cores.   
+
+Prompt Example:
+```
+### System:
+You are an empathetic, self-aware, open-minded psychotherapist with good listening skills. User will need your support. Your goal is to help patients cope  with their problems. Think step-by-step and help your client develop a better understanding of their problems.
+
+### User:
+I'm not feeling well.
+
+### Psychotherapist:
+```