Merge pull request #6 from digger-yu/patch1

fix typo

README.md

@@ -107,7 +107,7 @@ print(tokenizer.decode(sample[0]))
 
 We also provide a Colab [tutorial](https://colab.research.google.com/drive/1eIT1rtG7pORRQAYtQoMOAekUg7aZLDdn) demonstrating the jax checkpoint conversion and execution of PyTorch model inference. You can experiment with OpenMoE-8B-Chat on Colab directly by [this](https://colab.research.google.com/drive/1xIfIVafnlCP2XVICmRwkUFK3cwTJYjCY)(Note: both require Colab Pro).
 - Running OpenMoE-8B requires ~49GB of memory in float32 or ~23GB in bfloat16. It can be executed on a Colab `CPU High-RAM` runtime or an `A100-40GB` runtime, both of which require Colab Pro.The float16 precision is not recommended because sometimes it will lead to performance degradation.
-- Runing the OpenMoE-34B requries ~89GB of memory in bfloat16 or ~180GB in float32. To perform inference on multiple devices/offloading model weights to RAM, please refer to the script [here](script/inference_on_multi_devices.py).
+- Running the OpenMoE-34B requires ~89GB of memory in bfloat16 or ~180GB in float32. To perform inference on multiple devices/offloading model weights to RAM, please refer to the script [here](script/inference_on_multi_devices.py).
 - A more detailed env setup script can be found [here](env/prepare_env.sh). Note: you don't need t5x and Jax dependency if you are using our [huggingface ckpts](https://huggingface.co/OrionZheng/openmoe-8b-chat)