Update modeling_Llamoe.py

modeling_Llamoe.py

@@ -1225,7 +1225,25 @@ class LlamoeForCausalLM(LlammoePreTrainedModel):
         output_router_logits: Optional[bool] = None,
         return_dict: Optional[bool] = None,
     ) -> Union[Tuple, MoeCausalLMOutputWithPast]:
-       
+        r"""
+        Args:
+            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+                Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
+                config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+        Returns:
+        Example:
+        ```python
+        >>> from transformers import AutoTokenizer, GemmoeForCausalLM
+        >>> model = GemmoeForCausalLM.from_pretrained("mistralai/Gemmoe-8x7B-v0.1")
+        >>> tokenizer = AutoTokenizer.from_pretrained("mistralai/Gemmoe-8x7B-v0.1")
+        >>> prompt = "Hey, are you conscious? Can you talk to me?"
+        >>> inputs = tokenizer(prompt, return_tensors="pt")
+        >>> # Generate
+        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
+        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
+        ```"""
 
         output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
         output_router_logits = (