from typing import Optional, List, Tuple, Union import torch from torch import nn from transformers import DynamicCache, Cache from transformers.modeling_attn_mask_utils import _prepare_4d_causal_attention_mask, \ _prepare_4d_causal_attention_mask_for_sdpa from transformers.modeling_outputs import BaseModelOutputWithPast from transformers.models.mistral.modeling_mistral import MistralPreTrainedModel, MistralDecoderLayer, MistralRMSNorm, \ MistralForCausalLM from transformers.utils import logging from .configuration_mistral import MistralDenseFormerConfig from .denseformer import DWAModules logger = logging.get_logger(__name__) class MistralDenseFormerModel(MistralPreTrainedModel): """ Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`MistralDecoderLayer`] Args: config: MistralDenseFormerConfig """ config_class = MistralDenseFormerConfig def __init__(self, config: MistralDenseFormerConfig): super().__init__(config) self.padding_idx = config.pad_token_id self.vocab_size = config.vocab_size self.dwa_modules = DWAModules(config.num_hidden_layers, config.dilation, config.dwa_period) self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx) self.layers = nn.ModuleList( [MistralDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)] ) self._attn_implementation = config._attn_implementation self.norm = MistralRMSNorm(config.hidden_size, eps=config.rms_norm_eps) self.gradient_checkpointing = False # Initialize weights and apply final processing self.post_init() def get_input_embeddings(self): return self.embed_tokens def set_input_embeddings(self, value): self.embed_tokens = value def forward( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[List[torch.FloatTensor]] = None, inputs_embeds: Optional[torch.FloatTensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple, BaseModelOutputWithPast]: output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions output_hidden_states = ( output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states ) use_cache = use_cache if use_cache is not None else self.config.use_cache return_dict = return_dict if return_dict is not None else self.config.use_return_dict # retrieve input_ids and inputs_embeds if input_ids is not None and inputs_embeds is not None: raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time") elif input_ids is not None: batch_size, seq_length = input_ids.shape elif inputs_embeds is not None: batch_size, seq_length, _ = inputs_embeds.shape else: raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds") if self.gradient_checkpointing and self.training: if use_cache: logger.warning_once( "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..." ) use_cache = False past_key_values_length = 0 if use_cache: use_legacy_cache = not isinstance(past_key_values, Cache) if use_legacy_cache: past_key_values = DynamicCache.from_legacy_cache(past_key_values) past_key_values_length = past_key_values.get_usable_length(seq_length) if position_ids is None: device = input_ids.device if input_ids is not None else inputs_embeds.device position_ids = torch.arange( past_key_values_length, seq_length + past_key_values_length, dtype=torch.long, device=device ) position_ids = position_ids.unsqueeze(0).view(-1, seq_length) else: position_ids = position_ids.view(-1, seq_length).long() if inputs_embeds is None: inputs_embeds = self.embed_tokens(input_ids) if attention_mask is not None and self._attn_implementation == "flash_attention_2" and use_cache: is_padding_right = attention_mask[:, -1].sum().item() != batch_size if is_padding_right: raise ValueError( "You are attempting to perform batched generation with padding_side='right'" " this may lead to unexpected behaviour for Flash Attention version of Mistral. Make sure to " " call `tokenizer.padding_side = 'left'` before tokenizing the input. " ) if self._attn_implementation == "flash_attention_2": # 2d mask is passed through the layers attention_mask = attention_mask if (attention_mask is not None and 0 in attention_mask) else None elif self._attn_implementation == "sdpa" and not output_attentions: # output_attentions=True can not be supported when using SDPA, and we fall back on # the manual implementation that requires a 4D causal mask in all cases. attention_mask = _prepare_4d_causal_attention_mask_for_sdpa( attention_mask, (batch_size, seq_length), inputs_embeds, past_key_values_length, ) else: # 4d mask is passed through the layers attention_mask = _prepare_4d_causal_attention_mask( attention_mask, (batch_size, seq_length), inputs_embeds, past_key_values_length, sliding_window=self.config.sliding_window, ) hidden_states = inputs_embeds # decoder layers all_hidden_states = () if output_hidden_states else None all_self_attns = () if output_attentions else None next_decoder_cache = None self.dwa_modules.init_accumulators(hidden_states) for layer_idx, decoder_layer in enumerate(self.layers): if output_hidden_states: all_hidden_states += (hidden_states,) if self.gradient_checkpointing and self.training: layer_outputs = self._gradient_checkpointing_func( decoder_layer.__call__, hidden_states, attention_mask, position_ids, past_key_values, output_attentions, use_cache, ) else: layer_outputs = decoder_layer( hidden_states, attention_mask=attention_mask, position_ids=position_ids, past_key_value=past_key_values, output_attentions=output_attentions, use_cache=use_cache, ) hidden_states = layer_outputs[0] if use_cache: next_decoder_cache = layer_outputs[2 if output_attentions else 1] if output_attentions: all_self_attns += (layer_outputs[1],) hidden_states = self.dwa_modules(hidden_states, block_idx=layer_idx) hidden_states = self.norm(hidden_states) # add hidden states from the last decoder layer if output_hidden_states: all_hidden_states += (hidden_states,) next_cache = None if use_cache: next_cache = next_decoder_cache.to_legacy_cache() if use_legacy_cache else next_decoder_cache if not return_dict: return tuple(v for v in [hidden_states, next_cache, all_hidden_states, all_self_attns] if v is not None) return BaseModelOutputWithPast( last_hidden_state=hidden_states, past_key_values=next_cache, hidden_states=all_hidden_states, attentions=all_self_attns, ) class MistralDenseFormerForCausalLM(MistralForCausalLM): config_class = MistralDenseFormerConfig def __init__(self, config: MistralDenseFormerConfig): super().__init__(config) self.model = MistralDenseFormerModel(config) self.vocab_size = config.vocab_size self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False) # Initialize weights and apply final processing self.post_init()