Update README.md

README.md

@@ -34,13 +34,17 @@ The pipeline we used to produce the data and models is fully open-sourced!
 - [Models](https://huggingface.co/collections/nvidia/openmath-2-66fb142317d86400783d2c7b)
 - [Dataset](https://huggingface.co/datasets/nvidia/OpenMathInstruct-2)
 
+See our [paper](https://arxiv.org/abs/2410.01560) to learn more details!
 
 # How to use the models?
 
-Our models are fully compatible with Llama3.1-instruct format, so you should be able to just replace an existing Llama3.1 checkpoint and use it in the same way. 
-Please note that these models have not been instruction tuned and might not provide good answers outside of math domain. 
+Our models are trained with the same "chat format" as Llama3.1-instruct models (same system/user/assistant tokens). 
+Please note that these models have not been instruction tuned on general data and thus might not provide good answers outside of math domain.
 
-If you don't know how to use Llama3.1 models, we provide convenient [instructions in our repo](https://github.com/Kipok/NeMo-Skills/blob/main/docs/inference.md).
+This is a NeMo checkpoint, so you need to use [NeMo Framework](https://github.com/NVIDIA/NeMo) to run inference or finetune it. 
+We also release a [HuggingFace checkpoint](https://huggingface.co/nvidia/OpenMath2-Llama3.1-70B) and provide easy instructions on how to
+[convert between different formats](https://github.com/Kipok/NeMo-Skills/blob/main/docs/checkpoint-conversion.md) or 
+[run inference](https://github.com/Kipok/NeMo-Skills/blob/main/docs/inference.md) with these models using our codebase.
 
 # Reproducing our results