Update README.md

README.md

@@ -1,3 +1,23 @@
 ---
 license: llama2
 ---
+Airoboros c34 2.2.1 Mistral GGUF
+
+CodeLlama 34b With Airoboros 2.2.1 dataset by Jon Durbin
+
+Then
+
+With Mistral AI 7b 0.1 delta bits compared to Llama2 (extracted by Undi95), merged by myself.
+
+---
+
+Base model (CodeLlama) training context : 16k (max context up to 96k with the base ROPE)
+
+Mistral injection training context : 8k (Sliding Windows Attention is likely inoperant on such a merge/injection)
+
+---
+
+For test and amusement only.
+
+
+Prompt : Airoboros