Update README.md

README.md

@@ -2,12 +2,16 @@
 license: other
 ---
 
+- **At least Huggingface Transformers [4.31.0](https://pypi.org/project/transformers/4.31.0/) is required to load this model!**
+- datatpye: fp16
 - [wand](https://wandb.ai/open-assistant/supervised-finetuning/runs/2jfazjt9) (still internal, needs to be moved to public-sft)
 - checkpoint: 3319 steps
 
-## Note
 
-In order to load this model you need to install a pre-release version of the Huggingface transformers library.
+## Long context via RoPE scaling
+
+This model was fine-tuned with a context size of 8192 tokens using linear scaling of RoPE embeddings. In order to load and use this model 
+a version >=4.31.0 of HF Transformers needs to be installed.
 
 
 ## Model Configuration