Update README.md

README.md

@@ -44,11 +44,11 @@ Please note that these models have not been instruction tuned on general data an
 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/NVIDIA/NeMo-Skills/blob/main/docs/pipelines/checkpoint-conversion.md) or 
-[run inference](https://github.com/NVIDIA/NeMo-Skills/blob/main/docs/inference.md) with these models using our codebase.
+[run inference](https://github.com/NVIDIA/NeMo-Skills/blob/main/docs/basics/inference.md) with these models using our codebase.
 
 # Reproducing our results
 
-We provide [all instructions](https://github.com/NVIDIA/NeMo-Skills/blob/main/docs/openmathinstruct2/training.md) to fully reproduce our results.
+We provide [all instructions](https://github.com/NVIDIA/NeMo-Skills/blob/main/docs/openmathinstruct2/index.md) to fully reproduce our results.
 
 ## Citation