consistent nn. and nn.functional: part 5 docs (#12161)

docs/source/task_summary.rst

@@ -451,7 +451,7 @@ of tokens.
     >>> ## PYTORCH CODE
     >>> from transformers import AutoModelWithLMHead, AutoTokenizer, top_k_top_p_filtering
     >>> import torch
-    >>> from torch.nn import functional as F
+    >>> from torch import nn
 
     >>> tokenizer = AutoTokenizer.from_pretrained("gpt2")
     >>> model = AutoModelWithLMHead.from_pretrained("gpt2")
@@ -467,7 +467,7 @@ of tokens.
     >>> filtered_next_token_logits = top_k_top_p_filtering(next_token_logits, top_k=50, top_p=1.0)
 
     >>> # sample
-    >>> probs = F.softmax(filtered_next_token_logits, dim=-1)
+    >>> probs = nn.functional.softmax(filtered_next_token_logits, dim=-1)
     >>> next_token = torch.multinomial(probs, num_samples=1)
 
     >>> generated = torch.cat([input_ids, next_token], dim=-1)