diff --git a/README.md b/README.md
index 8135220..ffb5979 100644
--- a/README.md
+++ b/README.md
@@ -51,6 +51,11 @@ model.generate("Scaled dot product attention:\n\n\\[")
 # Scaled dot product attention:\n\n\\[ \\displaystyle\\text{Attention}(Q,K,V)=\\text{softmax}(\\frac{QK^{T}}{\\sqrt{d_{k}}}%\n)V \\]
 ```
 
+The `load_model()` function accepts the following parameters:
+- `name: str` that accepts `mini`, `base`, `standard`, `large`, and `huge`
+- `dtype: str=None` that accepts `float16` (or when the name is set to `huge`) and `float32`
+- `num_gpus: int=None` that accepts the total number of GPUs to be used (by default this is `8`)
+
 Read the full introduction to Galactica models as a [PDF](https://github.com/paperswithcode/galai/blob/main/notebooks/Introduction%20to%20Galactica%20Models.pdf) or a [jupyter notebook](https://github.com/paperswithcode/galai/blob/main/notebooks/Introduction%20to%20Galactica%20Models.ipynb).
 
 You can also find all the model weights with their model cards and inference widget in the [Hugging Face Hub](https://huggingface.co/models?other=galactica). All the models can be used out of the box with the `transformers` library.