()

()

(text)

(prompt, add_eos_token=True)

(epoch, wandb)

(X, num_heads)

(self, vertex_one, vertex_two)

(self, idx)

(self, idx)

(self, index)

(self, index)

(self, idx)

(self)

(self)

(self)

(self)

(self, arr)

(self, vocab_size, num_hiddens, norm_shape, ffn_num_input, ffn_num_hiddens, num_heads, num_l

(self, num_inputs, **kwargs)

(self, vocab_size, num_hiddens, norm_shape, ffn_num_input, ffn_num_hiddens, num_heads, num_la

(self, key_size, query_size, value_size, num_hiddens, num_heads, dropout, bias=False, **kwarg

(self, ffn_num_input, ffn_num_hiddens, ffn_num_outputs, **kwargs)

(self, key_size, query_size, value_size, num_hiddens, norm_shape, ffn_num_input, ffn_num_hidd

(self, vocab_size, key_size, query_size, value_size, num_hiddens, norm_shape, ffn_num_input,

(self, key_size, query_size, value_size, num_hiddens, norm_shape, ffn_num_input, ffn_num_hidd

(self, vocab_size, key_size, query_size, value_size, num_hiddens, norm_shape, ffn_num_input,

(self, input_size, output_size)

(self, input_size, hidden_size, num_classes)

( self, dropout: float = 0.0, bos_token_id: int = 0, eos_token

(self, args: MoeConfig)

(self, config: MoeConfig)

(self, config: MoeConfig)

(self, config: MoeConfig)

(self, layer_id: int, config: MoeConfig)

(self, config: MoeConfig)

(self, config: MoeConfig = None)

(self, data_path, tokenizer, max_length=512)

(self, file_path, tokenizer, max_length=4096)

(self, jsonl_path, tokenizer, max_length=1024)

(self)

(self)

(self, graph)

(self, graph, costs, parents)

(self)

(self, item, next=None)

(self, head=None)

(self, dataset, max_len, vocab=None)

(self, bert)

(self, val, left=None, right=None)

(self)

(self, item)

(self, root)

(self)

(self)

(self)

(self)

(self)

(self)

(self)

(self)

(self, *args, **kwargs)

(self, key)

(self, premise_hypothesis_tokens)

(self)

(self)

(self)

(self)

(n)

(self, tokens, segments, valid_lens)

(self, X, pred_positions)

(self, X)

(self, tokens, segments, valid_lens=None, pred_positions=None)

(self, queries, keys, values, valid_lens)

(self, X)

(self, X, Y)

(self, X, valid_lens)

(self, X, valid_lens, *args)

(self, X, state)

(self, X, state)

(self, x)

(self, x)

(self, x)

(self, x: torch.Tensor, position_embeddings: Tuple[torch.Tensor, torch.Tensor

(self, x: torch.Tensor)

(self, hidden_states)

(self, x)

(self, hidden_states, position_embeddings, past_key_value=None, use_cache=False, attention_mask=None)

(self, input_ids: Optional[torch.Tensor] = None, attention_mask: Optional[tor

(self, input_ids: Optional[torch.Tensor] = None, attention_mask: Optional[tor

(data_point)

(self)

(self, enc_outputs, enc_valid_lens, *args)

(self, k)

(self, k)