Update README.md

README.md

@@ -146,12 +146,6 @@ def enable_grad_only_every_nth(model, n):
     for all other components of the model, including the embedding layers and the model's head. This setup is particularly 
     useful for fine-tuning processes where only a subset of layers are targeted for updates, ensuring efficient training and 
     adaptation of newly integrated layers while maintaining the pre-trained behavior of other model components.
-
-    :param model: The model instance, which is expected to have a structure compatible with selective layer training, such 
-    as AutoModelForCausalLM.
-    :param n: The interval at which layers are selected for gradient enabling, starting with the first layer. This 
-    parameter determines the sparsity of active training within the model's architecture, allowing for focused updates 
-    on specific layers.
     """
 
     # Freeze embeddings.
@@ -180,5 +174,4 @@ model = transformers.AutoModelForCausalLM.from_pretrained(
 # Update layer gradients, specify the correct value for n based on your model's architecture
 n =5
 enable_grad_only_every_nth(model, n)
-model_args.model_name_or_path = model
 ```