from typing import Callable, List, Optional, Tuple, Union import torch import torch.nn as nn from transformers.cache_utils import Cache from transformers.activations import ACT2FN from transformers.cache_utils import Cache, StaticCache from .hybrid_cache import HybridCache from transformers.generation import GenerationMixin from transformers.modeling_attn_mask_utils import AttentionMaskConverter from transformers.modeling_flash_attention_utils import FlashAttentionKwargs from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel from transformers.modeling_outputs import ( BaseModelOutputWithPast, CausalLMOutputWithPast, ) from transformers.processing_utils import Unpack from transformers.utils import ( LossKwargs, add_start_docstrings, add_start_docstrings_to_model_forward, logging, ) import threading from .wkv import Rwkv7Attention, Rwkv6Attention from .configuration_rwkv_hybrid import RwkvHybridConfig from transformers.models.qwen2.modeling_qwen2 import (Qwen2MLP, Qwen2RMSNorm, Qwen2RotaryEmbedding, Qwen2Attention) logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "RwkvHybridConfig" class RwkvHybridDecoderLayer(nn.Module): def __init__(self, config: RwkvHybridConfig, layer_idx: int, update_v_first, get_v_first): super().__init__() self.hidden_size = config.hidden_size self.is_rwkv = True if layer_idx in config.wkv_layers else False if self.is_rwkv: if config.wkv_version == 7: self.self_attn = Rwkv7Attention(args=config, layer_id=layer_idx, update_v_first=update_v_first, get_v_first=get_v_first) elif config.wkv_version == 6: self.self_attn = Rwkv6Attention(args=config, layer_id=layer_idx, update_v_first=update_v_first, get_v_first=get_v_first) else: raise NotImplementedError elif not self.is_rwkv: self.self_attn = Qwen2Attention(config=config, layer_idx=layer_idx) else: self.self_attn = None raise NotImplementedError self.mlp = Qwen2MLP(config) self.input_layernorm = Qwen2RMSNorm( config.hidden_size, eps=config.rms_norm_eps) self.post_attention_layernorm = Qwen2RMSNorm( config.hidden_size, eps=config.rms_norm_eps) def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_value: Optional[Cache] = None, output_attentions: Optional[bool] = False, use_cache: Optional[bool] = False, cache_position: Optional[torch.LongTensor] = None, position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None, # necessary, but kept here for BC **kwargs, ) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]: residual = hidden_states hidden_states = self.input_layernorm(hidden_states) # RWKV attention hidden_states, self_attn_weights = self.self_attn( hidden_states=hidden_states, attention_mask=attention_mask, position_ids=position_ids, past_key_value=past_key_value, output_attentions=output_attentions, use_cache=use_cache, cache_position=cache_position, position_embeddings=position_embeddings, ) hidden_states = residual + hidden_states # Fully Connected residual = hidden_states hidden_states = self.post_attention_layernorm(hidden_states) hidden_states = self.mlp(hidden_states) hidden_states = residual + hidden_states outputs = (hidden_states,) if output_attentions: outputs += (self_attn_weights,) return outputs RWKV_HYBRID_START_DOCSTRING = r""" This model inherits from [`PreTrainedModel`]. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior. Parameters: config ([`RwkvHybridConfig`]): Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [`~PreTrainedModel.from_pretrained`] method to load the model weights. """ @add_start_docstrings( "The bare RWKV Hybrid Model outputting raw hidden-states without any specific head on top.", RWKV_HYBRID_START_DOCSTRING, ) class RwkvHybridPreTrainedModel(PreTrainedModel): config_class = RwkvHybridConfig base_model_prefix = "rwkv_hybrid" supports_gradient_checkpointing = True _no_split_modules = ["RwkvHybridDecoderLayer"] _skip_keys_device_placement = ["past_key_values"] def _init_weights(self, module): std = self.config.initializer_range if isinstance(module, nn.Linear): module.weight.data.normal_(mean=0.0, std=std) if module.bias is not None: module.bias.data.zero_() elif isinstance(module, nn.Embedding): module.weight.data.normal_(mean=0.0, std=std) if module.padding_idx is not None: module.weight.data[module.padding_idx].zero_() RWKV_HYBRID_INPUTS_DOCSTRING = r""" Args: input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it. Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input IDs?](../glossary#input-ids) attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*): Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. If `past_key_values` is used, optionally only the last `input_ids` have to be input (see `past_key_values`). If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`] and modify to your needs. See diagram 1 in [the paper](https://arxiv.org/abs/1910.13461) for more information on the default strategy. - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. position_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.n_positions - 1]`. [What are position IDs?](../glossary#position-ids) past_key_values (`Cache` or `tuple(tuple(torch.FloatTensor))`, *optional*): Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values` returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`. Two formats are allowed: - a [`~cache_utils.Cache`] instance, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache); - Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape `(batch_size, num_heads, sequence_length, embed_size_per_head)`). This is also known as the legacy cache format. The model will output the same cache format that is fed as input. If no `past_key_values` are passed, the legacy cache format will be returned. If `past_key_values` are used, the user can optionally input only the last `input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `input_ids` of shape `(batch_size, sequence_length)`. inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*): Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert `input_ids` indices into associated vectors than the model's internal embedding lookup matrix. use_cache (`bool`, *optional*): If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see `past_key_values`). output_attentions (`bool`, *optional*): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. output_hidden_states (`bool`, *optional*): Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. return_dict (`bool`, *optional*): Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple. cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*): Indices depicting the position of the input sequence tokens in the sequence. Contrarily to `position_ids`, this tensor is not affected by padding. It is used to update the cache in the correct position and to infer the complete sequence length. """ @add_start_docstrings( "The bare RWKV Hybrid Model outputting raw hidden-states without any specific head on top.", RWKV_HYBRID_START_DOCSTRING, ) class RwkvHybridModel(RwkvHybridPreTrainedModel): """ RWKV and Transformer hybrid decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`RwkvHybridDecoderLayer`] Args: config: RwkvHybridConfig """ def __init__(self, config: RwkvHybridConfig): super().__init__(config) self.padding_idx = config.pad_token_id self.vocab_size = config.vocab_size self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx) self.thread_local = threading.local() self.thread_local.v_first = None self.layers = nn.ModuleList( [RwkvHybridDecoderLayer(config, layer_idx, self.update_v_first, self.get_v_first) for layer_idx in range(config.num_hidden_layers)] ) self.norm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps) self.rotary_emb = Qwen2RotaryEmbedding(config=config) self.gradient_checkpointing = False # Initialize weights and apply final processing self.post_init() def post_init(self): """ A method executed at the end of each Transformer model initialization, to execute code that needs the model's modules properly initialized (such as weight initialization). """ self.init_weights() self._backward_compatibility_gradient_checkpointing() # If current model is a base model, attach `base_model_tp_plan` from config if self.base_model is self: self._tp_plan = self.config.base_model_tp_plan from transformers.modeling_utils import _init_weights if _init_weights: for layer in self.layers: layer.self_attn.time_mixer.post_init() def update_v_first(self, new_v_first): """Callback function to update v_first in HybridModel.""" self.thread_local.v_first = new_v_first def get_v_first(self): return self.thread_local.v_first def get_input_embeddings(self): return self.embed_tokens def set_input_embeddings(self, value): self.embed_tokens = value @add_start_docstrings_to_model_forward(RWKV_HYBRID_INPUTS_DOCSTRING) def forward( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[Cache] = 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, cache_position: Optional[torch.LongTensor] = None, **flash_attn_kwargs: Unpack[FlashAttentionKwargs], ) -> 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 if (input_ids is None) ^ (inputs_embeds is not None): raise ValueError("You must specify exactly one of input_ids or inputs_embeds") if self.gradient_checkpointing and self.training and use_cache: logger.warning_once( "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`." ) use_cache = False if inputs_embeds is None: inputs_embeds = self.embed_tokens(input_ids) if use_cache and past_key_values is None: past_key_values = HybridCache() if cache_position is None: past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0 cache_position = torch.arange( past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device ) if position_ids is None: position_ids = cache_position.unsqueeze(0) causal_mask = self._update_causal_mask( attention_mask, inputs_embeds, cache_position, past_key_values, output_attentions ) hidden_states = inputs_embeds # create position embeddings to be shared across the decoder layers position_embeddings = self.rotary_emb(hidden_states, position_ids) # decoder layers all_hidden_states = () if output_hidden_states else None all_self_attns = () if output_attentions else None for decoder_layer in self.layers[: self.config.num_hidden_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, causal_mask, position_ids, past_key_values, output_attentions, use_cache, cache_position, position_embeddings, ) else: layer_outputs = decoder_layer( hidden_states, attention_mask=causal_mask, position_ids=position_ids, past_key_value=past_key_values, output_attentions=output_attentions, use_cache=use_cache, cache_position=cache_position, position_embeddings=position_embeddings, **flash_attn_kwargs, ) hidden_states = layer_outputs[0] if output_attentions: all_self_attns += (layer_outputs[1],) hidden_states = self.norm(hidden_states) # add hidden states from the last decoder layer if output_hidden_states: all_hidden_states += (hidden_states,) output = BaseModelOutputWithPast( last_hidden_state=hidden_states, past_key_values=past_key_values if use_cache else None, hidden_states=all_hidden_states, attentions=all_self_attns, ) return output if return_dict else output.to_tuple() def _update_causal_mask( self, attention_mask: torch.Tensor, input_tensor: torch.Tensor, cache_position: torch.Tensor, past_key_values: Cache, output_attentions: bool, ): if self.config._attn_implementation == "flash_attention_2": if attention_mask is not None and (attention_mask == 0.0).any(): return attention_mask return None # For SDPA, when possible, we will rely on its `is_causal` argument instead of its `attn_mask` argument, in # order to dispatch on Flash Attention 2. This feature is not compatible with static cache, as SDPA will fail # to infer the attention mask. past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0 using_static_cache = isinstance(past_key_values, StaticCache) # When output attentions is True, sdpa implementation's forward method calls the eager implementation's forward if self.config._attn_implementation == "sdpa" and not using_static_cache and not output_attentions: if AttentionMaskConverter._ignore_causal_mask_sdpa( attention_mask, inputs_embeds=input_tensor, past_key_values_length=past_seen_tokens, is_training=self.training, ): return None dtype, device = input_tensor.dtype, input_tensor.device sequence_length = input_tensor.shape[1] if using_static_cache: target_length = past_key_values.get_max_cache_shape() else: target_length = ( attention_mask.shape[-1] if isinstance(attention_mask, torch.Tensor) else past_seen_tokens + sequence_length + 1 ) # In case the provided `attention` mask is 2D, we generate a causal mask here (4D). causal_mask = self._prepare_4d_causal_attention_mask_with_cache_position( attention_mask, sequence_length=sequence_length, target_length=target_length, dtype=dtype, device=device, cache_position=cache_position, batch_size=input_tensor.shape[0], ) if ( self.config._attn_implementation == "sdpa" and attention_mask is not None and attention_mask.device.type == "cuda" and not output_attentions ): # Attend to all tokens in fully masked rows in the causal_mask, for example the relevant first rows when # using left padding. This is required by F.scaled_dot_product_attention memory-efficient attention path. # Details: https://github.com/pytorch/pytorch/issues/110213 min_dtype = torch.finfo(dtype).min causal_mask = AttentionMaskConverter._unmask_unattended(causal_mask, min_dtype) return causal_mask @staticmethod def _prepare_4d_causal_attention_mask_with_cache_position( attention_mask: torch.Tensor, sequence_length: int, target_length: int, dtype: torch.dtype, device: torch.device, cache_position: torch.Tensor, batch_size: int, **kwargs, ): """ Creates a causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape `(batch_size, key_value_length)`, or if the input `attention_mask` is already 4D, do nothing. Args: attention_mask (`torch.Tensor`): A 2D attention mask of shape `(batch_size, key_value_length)` or a 4D attention mask of shape `(batch_size, 1, query_length, key_value_length)`. sequence_length (`int`): The sequence length being processed. target_length (`int`): The target length: when generating with static cache, the mask should be as long as the static cache, to account for the 0 padding, the part of the cache that is not filled yet. dtype (`torch.dtype`): The dtype to use for the 4D attention mask. device (`torch.device`): The device to plcae the 4D attention mask on. cache_position (`torch.Tensor`): Indices depicting the position of the input sequence tokens in the sequence. batch_size (`torch.Tensor`): Batch size. """ if attention_mask is not None and attention_mask.dim() == 4: # In this case we assume that the mask comes already in inverted form and requires no inversion or slicing. causal_mask = attention_mask else: min_dtype = torch.finfo(dtype).min causal_mask = torch.full( (sequence_length, target_length), fill_value=min_dtype, dtype=dtype, device=device ) if sequence_length != 1: causal_mask = torch.triu(causal_mask, diagonal=1) causal_mask *= torch.arange(target_length, device=device) > cache_position.reshape(-1, 1) causal_mask = causal_mask[None, None, :, :].expand(batch_size, 1, -1, -1) if attention_mask is not None: causal_mask = causal_mask.clone() # copy to contiguous memory for in-place edit mask_length = attention_mask.shape[-1] padding_mask = causal_mask[:, :, :, :mask_length] + attention_mask[:, None, None, :] padding_mask = padding_mask == 0 causal_mask[:, :, :, :mask_length] = causal_mask[:, :, :, :mask_length].masked_fill( padding_mask, min_dtype ) return causal_mask class KwargsForCausalLM(FlashAttentionKwargs, LossKwargs): ... class RwkvHybridForCausalLM(RwkvHybridPreTrainedModel, GenerationMixin): _tied_weights_keys = ["lm_head.weight"] _tp_plan = {"lm_head": "colwise_rep"} def __init__(self, config): super().__init__(config) self.model = RwkvHybridModel(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() def get_input_embeddings(self): return self.model.embed_tokens def set_input_embeddings(self, value): self.model.embed_tokens = value def get_output_embeddings(self): return self.lm_head def set_output_embeddings(self, new_embeddings): self.lm_head = new_embeddings def set_decoder(self, decoder): self.model = decoder def get_decoder(self): return self.model # @add_start_docstrings_to_model_forward(QWEN2_INPUTS_DOCSTRING) # @replace_return_docstrings(output_type=CausalLMOutputWithPast, config_class=_CONFIG_FOR_DOC) def forward( self, input_ids: torch.LongTensor = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_values: Optional[Union[Cache, List[torch.FloatTensor]]] = None, inputs_embeds: Optional[torch.FloatTensor] = None, labels: Optional[torch.LongTensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None, cache_position: Optional[torch.LongTensor] = None, num_logits_to_keep: int = 0, **kwargs: Unpack[KwargsForCausalLM], ) -> Union[Tuple, CausalLMOutputWithPast]: 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]`. num_logits_to_keep (`int`, *optional*): Calculate logits for the last `num_logits_to_keep` tokens. If `0`, calculate logits for all `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that token can save memory, which becomes pretty significant for long sequences or large vocabulary size. Returns: Example: ```python >>> from transformers import AutoTokenizer, RwkvHybridForCausalLM >>> model = Qwen2ForCausalLM.from_pretrained("RWKV-Red-Team/ARWKV-7B-Preview-0.1") >>> tokenizer = AutoTokenizer.from_pretrained("RWKV-Red-Team/ARWKV-7B-Preview-0.1") >>> 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_hidden_states = ( output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states ) return_dict = return_dict if return_dict is not None else self.config.use_return_dict # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn) outputs = self.model( input_ids=input_ids, attention_mask=attention_mask, position_ids=position_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict, cache_position=cache_position, **kwargs, ) hidden_states = outputs[0] # Only compute necessary logits, and do not upcast them to float if we are not computing the loss logits = self.lm_head(hidden_states[:, -num_logits_to_keep:, :]) loss = None if labels is not None: loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs) if not return_dict: output = (logits,) + outputs[1:] return (loss,) + output if loss is not None else output return CausalLMOutputWithPast( loss=loss, logits=logits, past_key_values=outputs.past_key_values, hidden_states=outputs.hidden_states, attentions=outputs.attentions, )