Update README.md

README.md

@@ -17,4 +17,8 @@ This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/a
 - Training sequences beyond 2048 have the target truncated to equal 2048.
 - Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4
 
-Otherwise, I emulated the training process as closely as possible (rank 64 QLoRA) It was trained on 1x RTX 6000 Ada for ~43 hours.
+Otherwise, I emulated the training process as closely as possible (rank 64 QLoRA) It was trained on 1x RTX 6000 Ada for ~43 hours.
+
+## NTK Patch
+
+To use with HF transformers, AutoGPTQ, etc. See (NTK monkey patch)[https://github.com/bhenrym14/qlora-airoboros-longcontext/blob/main/scaledllama/llama_rope_ntk_monkey_patch.py].