# Source: Based on transformers OLMoE implementation # Modifications are denoted by the symbol: [MODIFIED] """ PyTorch OLMoE model with KV Cache support.""" import math from typing import List, Optional, Tuple, Union import torch import torch.nn.functional as F import torch.utils.checkpoint from torch import nn from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss # [MODIFIED] Import from transformer library from transformers.activations import ACT2FN from transformers.modeling_outputs import ( BaseModelOutputWithPast, CausalLMOutputWithPast, SequenceClassifierOutputWithPast, MoeModelOutputWithPast, MoeCausalLMOutputWithPast, ) from transformers.modeling_utils import PreTrainedModel from transformers.utils import ( add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings, ) from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update from transformers.models.olmoe.configuration_olmoe import OlmoeConfig from transformers.generation.utils import GenerationMixin logger = logging.get_logger(__name__) _CONFIG_FOR_DOC = "OlmoeConfig" # Copied from transformers.models.bart.modeling_bart._make_causal_mask def _make_causal_mask( input_ids_shape: torch.Size, dtype: torch.dtype, device: torch.device, past_key_values_length: int = 0, ): """ Create a causal mask for bi-directional self-attention. Args: input_ids_shape (torch.Size): The shape of input_ids tensor, typically (batch_size, tgt_len). dtype (torch.dtype): The data type of the mask. device (torch.device): The device on which the mask will be placed. past_key_values_length (int, optional): The length of past key values. Default is 0. Returns: torch.Tensor: The causal mask tensor. """ bsz, tgt_len = input_ids_shape mask = torch.full((tgt_len, tgt_len), torch.finfo(dtype).min, device=device) mask_cond = torch.arange(mask.size(-1), device=device) mask.masked_fill_(mask_cond < (mask_cond + 1).view(mask.size(-1), 1), 0) mask = mask.to(dtype) if past_key_values_length > 0: mask = torch.cat( [ torch.zeros( tgt_len, past_key_values_length, dtype=dtype, device=device ), mask, ], dim=-1, ) return mask[None, None, :, :].expand( bsz, 1, tgt_len, tgt_len + past_key_values_length ) # Copied from transformers.models.bart.modeling_bart._expand_mask def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None): """ Expand attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`. Args: mask (torch.Tensor): The attention mask tensor of shape `[bsz, seq_len]`. dtype (torch.dtype): The data type of the mask. tgt_len (Optional[int], optional): The target sequence length. If None, it defaults to the source sequence length. Returns: torch.Tensor: The expanded mask tensor. """ bsz, src_len = mask.size() tgt_len = tgt_len if tgt_len is not None else src_len expanded_mask = mask[:, None, None, :].expand(bsz, 1, tgt_len, src_len).to(dtype) inverted_mask = 1.0 - expanded_mask return inverted_mask.masked_fill( inverted_mask.to(torch.bool), torch.finfo(dtype).min ) # Copied from transformers.models.mixtral.modeling_mixtral.load_balancing_loss_func def load_balancing_loss_func( gate_logits: Union[torch.Tensor, Tuple[torch.Tensor], None], num_experts: Optional[int] = None, top_k=2, attention_mask: Optional[torch.Tensor] = None, ) -> Union[torch.Tensor, int]: r""" Computes auxiliary load balancing loss as in Switch Transformer - implemented in Pytorch. See Switch Transformer (https://arxiv.org/abs/2101.03961) for more details. This function implements the loss function presented in equations (4) - (6) of the paper. It aims at penalizing cases where the routing between experts is too unbalanced. Args: gate_logits: Logits from the `gate`, should be a tuple of model.config.num_hidden_layers tensors of shape [batch_size X sequence_length, num_experts]. num_experts: Number of experts top_k: The number of experts to route per-token, can be also interpreted as the `top-k` routing parameter. attention_mask (`torch.Tensor`, *optional*): The attention_mask used in forward function shape [batch_size X sequence_length] if not None. Returns: The auxiliary loss. """ if gate_logits is None or not isinstance(gate_logits, tuple): return 0 if isinstance(gate_logits, tuple): compute_device = gate_logits[0].device concatenated_gate_logits = torch.cat([layer_gate.to(compute_device) for layer_gate in gate_logits], dim=0) routing_weights = torch.nn.functional.softmax(concatenated_gate_logits, dim=-1) _, selected_experts = torch.topk(routing_weights, top_k, dim=-1) expert_mask = torch.nn.functional.one_hot(selected_experts, num_experts) if attention_mask is None: # Compute the percentage of tokens routed to each experts tokens_per_expert = torch.mean(expert_mask.float(), dim=0) # Compute the average probability of routing to these experts router_prob_per_expert = torch.mean(routing_weights, dim=0) else: batch_size, sequence_length = attention_mask.shape num_hidden_layers = concatenated_gate_logits.shape[0] // (batch_size * sequence_length) # Compute the mask that masks all padding tokens as 0 with the same shape of expert_mask expert_attention_mask = ( attention_mask[None, :, :, None, None] .expand((num_hidden_layers, batch_size, sequence_length, top_k, num_experts)) .reshape(-1, top_k, num_experts) .to(compute_device) ) # Compute the percentage of tokens routed to each experts tokens_per_expert = torch.sum(expert_mask.float() * expert_attention_mask, dim=0) / torch.sum( expert_attention_mask, dim=0 ) # Compute the mask that masks all padding tokens as 0 with the same shape of tokens_per_expert router_per_expert_attention_mask = ( attention_mask[None, :, :, None] .expand((num_hidden_layers, batch_size, sequence_length, num_experts)) .reshape(-1, num_experts) .to(compute_device) ) # Compute the average probability of routing to these experts router_prob_per_expert = torch.sum(routing_weights * router_per_expert_attention_mask, dim=0) / torch.sum( router_per_expert_attention_mask, dim=0 ) overall_loss = torch.sum(tokens_per_expert * router_prob_per_expert.unsqueeze(0)) return overall_loss * num_experts class OlmoeRMSNorm(nn.Module): def __init__(self, hidden_size, eps=1e-5): """ OlmoeRMSNorm is equivalent to T5LayerNorm """ super().__init__() self.weight = nn.Parameter(torch.ones(hidden_size)) self.variance_epsilon = eps def forward(self, hidden_states): input_dtype = hidden_states.dtype hidden_states = hidden_states.to(torch.float32) variance = hidden_states.pow(2).mean(-1, keepdim=True) hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon) return self.weight * hidden_states.to(input_dtype) def extra_repr(self): return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}" # Copied from transformers.models.llama.modeling_llama.LlamaRotaryEmbedding with Llama->Olmoe class OlmoeRotaryEmbedding(nn.Module): def __init__(self, config: OlmoeConfig, device=None): super().__init__() # BC: "rope_type" was originally "type" if hasattr(config, "rope_scaling") and config.rope_scaling is not None: self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type")) else: self.rope_type = "default" self.max_seq_len_cached = config.max_position_embeddings self.original_max_seq_len = config.max_position_embeddings self.config = config self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type] inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device) self.register_buffer("inv_freq", inv_freq, persistent=False) self.original_inv_freq = self.inv_freq @torch.no_grad() @dynamic_rope_update # power user: used with advanced RoPE types (e.g. dynamic rope) def forward(self, x, position_ids): inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device) position_ids_expanded = position_ids[:, None, :].float() device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu" with torch.autocast(device_type=device_type, enabled=False): # Force float32 freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2) emb = torch.cat((freqs, freqs), dim=-1) cos = emb.cos() * self.attention_scaling sin = emb.sin() * self.attention_scaling return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype) # Copied from transformers.models.llama.modeling_llama.rotate_half def rotate_half(x): """Rotates half the hidden dims of the input.""" x1 = x[..., : x.shape[-1] // 2] x2 = x[..., x.shape[-1] // 2 :] return torch.cat((-x2, x1), dim=-1) # Copied from transformers.models.llama.modeling_llama.apply_rotary_pos_emb def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1): """Applies Rotary Position Embedding to the query and key tensors. Args: q (`torch.Tensor`): The query tensor. k (`torch.Tensor`): The key tensor. cos (`torch.Tensor`): The cosine part of the rotary embedding. sin (`torch.Tensor`): The sine part of the rotary embedding. position_ids (`torch.Tensor`, *optional*): Deprecated and unused. unsqueeze_dim (`int`, *optional*, defaults to 1): The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2. Returns: `tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding. """ cos = cos.unsqueeze(unsqueeze_dim) sin = sin.unsqueeze(unsqueeze_dim) q_embed = (q * cos) + (rotate_half(q) * sin) k_embed = (k * cos) + (rotate_half(k) * sin) return q_embed, k_embed # Copied from transformers.models.olmo.modeling_olmo.OlmoMLP with Olmo->Olmoe class OlmoeMLP(nn.Module): def __init__(self, config): super().__init__() self.config = config self.hidden_size = config.hidden_size self.intermediate_size = config.intermediate_size self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False) self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False) self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False) self.act_fn = ACT2FN[config.hidden_act] def forward(self, x): down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x)) return down_proj # Copied from transformers.models.llama.modeling_llama.repeat_kv def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor: """ This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim) """ batch, num_key_value_heads, slen, head_dim = hidden_states.shape if n_rep == 1: return hidden_states hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim) return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim) class OlmoeAttention(nn.Module): """Multi-headed attention from 'Attention Is All You Need' paper""" def __init__(self, config: OlmoeConfig, rotary_emb, layer_idx: Optional[int] = None): super().__init__() self.config = config self.layer_idx = layer_idx if layer_idx is None: logger.warning_once( f"Instantiating {self.__class__.__name__} without passing a `layer_idx` is not recommended and will " "lead to errors during the forward call if caching is used. Please make sure to provide a `layer_idx` " "when creating this class." ) self.attention_dropout = config.attention_dropout self.hidden_size = config.hidden_size self.num_heads = config.num_attention_heads self.head_dim = self.hidden_size // self.num_heads self.num_key_value_heads = config.num_key_value_heads self.num_key_value_groups = self.num_heads // self.num_key_value_heads self.max_position_embeddings = config.max_position_embeddings self.rope_theta = config.rope_theta self.is_causal = True if (self.head_dim * self.num_heads) != self.hidden_size: raise ValueError( f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}" f" and `num_heads`: {self.num_heads})." ) self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=config.attention_bias) self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=config.attention_bias) self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=config.attention_bias) self.o_proj = nn.Linear(self.hidden_size, self.hidden_size, bias=config.attention_bias) self.q_norm = OlmoeRMSNorm(self.hidden_size, eps=config.rms_norm_eps) self.k_norm = OlmoeRMSNorm( (self.hidden_size // self.num_heads) * self.num_key_value_heads, eps=config.rms_norm_eps ) self.rotary_emb = rotary_emb def forward( self, hidden_states: torch.Tensor, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_value: Optional[Tuple[torch.Tensor]] = None, output_attentions: bool = False, use_cache: bool = False, **kwargs, ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: bsz, q_len, _ = hidden_states.size() query_states = self.q_norm(self.q_proj(hidden_states)) key_states = self.k_norm(self.k_proj(hidden_states)) value_states = self.v_proj(hidden_states) if self.config.clip_qkv is not None: query_states.clamp_(min=-self.config.clip_qkv, max=self.config.clip_qkv) key_states.clamp_(min=-self.config.clip_qkv, max=self.config.clip_qkv) value_states.clamp_(min=-self.config.clip_qkv, max=self.config.clip_qkv) query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2) key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2) value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2) kv_seq_len = key_states.shape[-2] if past_key_value is not None: kv_seq_len += past_key_value[0].shape[-2] # Prepare position embeddings cos, sin = self.rotary_emb(query_states, position_ids) query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin) # [MODIFIED] Using KVCache mechanism for preallocated GPU memory optimization # past_key_value is utilized to leverage previously computed key and value states. # If past_key_value is available, reuse the states for k, v, and self_attention. if past_key_value is not None: key_states = past_key_value[0].cat(key_states, dim=2) value_states = past_key_value[1].cat(value_states, dim=2) # Reset past_key_value to avoid return past_key_value. past_key_value = None key_states = repeat_kv(key_states, self.num_key_value_groups) value_states = repeat_kv(value_states, self.num_key_value_groups) attn_weights = torch.matmul(query_states, key_states.transpose(2, 3)) / math.sqrt(self.head_dim) if attention_mask is not None: # no matter the length, we just slice it causal_mask = attention_mask[:, :, :, : key_states.shape[-2]] attn_weights = attn_weights + causal_mask # upcast attention to fp32 attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype) attn_weights = nn.functional.dropout(attn_weights, p=self.attention_dropout, training=self.training) attn_output = torch.matmul(attn_weights, value_states) if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim): raise ValueError( f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is" f" {attn_output.size()}" ) attn_output = attn_output.transpose(1, 2).contiguous() attn_output = attn_output.reshape(bsz, q_len, self.hidden_size) attn_output = self.o_proj(attn_output) if not output_attentions: attn_weights = None return attn_output, attn_weights, past_key_value class OlmoeSparseMoeBlock(nn.Module): def __init__(self, config): super().__init__() self.num_experts = config.num_experts self.top_k = config.num_experts_per_tok self.norm_topk_prob = config.norm_topk_prob self.gate = nn.Linear(config.hidden_size, self.num_experts, bias=False) self.experts = nn.ModuleList([OlmoeMLP(config) for _ in range(self.num_experts)]) def forward(self, hidden_states: torch.Tensor, expert_counter_list= None) -> torch.Tensor: #modified-shw batch_size, sequence_length, hidden_dim = hidden_states.shape hidden_states = hidden_states.view(-1, hidden_dim) # router_logits: (batch * sequence_length, n_experts) router_logits = self.gate(hidden_states) routing_weights = F.softmax(router_logits, dim=1, dtype=torch.float) routing_weights, selected_experts = torch.topk(routing_weights, self.top_k, dim=-1) if self.norm_topk_prob: routing_weights /= routing_weights.sum(dim=-1, keepdim=True) # we cast back to the input dtype routing_weights = routing_weights.to(hidden_states.dtype) unique_experts = torch.unique(selected_experts) #modified-shw num_experts = len(unique_experts) #modified-shw if expert_counter_list is not None: #modified-shw expert_counter_list.append(num_experts) #modified-shw final_hidden_states = torch.zeros( (batch_size * sequence_length, hidden_dim), dtype=hidden_states.dtype, device=hidden_states.device ) # One hot encode the selected experts to create an expert mask # this will be used to easily index which expert is going to be selected expert_mask = torch.nn.functional.one_hot(selected_experts, num_classes=self.num_experts).permute(2, 1, 0) # Loop over all available experts in the model and perform the computation on each expert for expert_idx in range(self.num_experts): expert_layer = self.experts[expert_idx] idx, top_x = torch.where(expert_mask[expert_idx]) # Index the correct hidden states and compute the expert hidden state for # the current expert. We need to make sure to multiply the output hidden # states by `routing_weights` on the corresponding tokens (top-1 and top-2) current_state = hidden_states[None, top_x].reshape(-1, hidden_dim) current_hidden_states = expert_layer(current_state) * routing_weights[top_x, idx, None] # However `index_add_` only support torch tensors for indexing so we'll use # the `top_x` tensor here. final_hidden_states.index_add_(0, top_x, current_hidden_states.to(hidden_states.dtype)) final_hidden_states = final_hidden_states.reshape(batch_size, sequence_length, hidden_dim) return final_hidden_states, router_logits class OlmoeDecoderLayer(nn.Module): def __init__(self, config: OlmoeConfig, rotary_emb, layer_idx: int): super().__init__() self.hidden_size = config.hidden_size self.self_attn = OlmoeAttention(config=config, rotary_emb=rotary_emb, layer_idx=layer_idx) self.mlp = OlmoeSparseMoeBlock(config) self.input_layernorm = OlmoeRMSNorm(config.hidden_size, eps=config.rms_norm_eps) self.post_attention_layernorm = OlmoeRMSNorm(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[Tuple[torch.Tensor]] = None, output_attentions: Optional[bool] = False, output_router_logits: Optional[bool] = False, use_cache: Optional[bool] = False, expert_counter_list= None, #modified-shw **kwargs, ) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]: """ Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (`torch.FloatTensor`, *optional*): attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1, query_sequence_length, key_sequence_length)` if default attention is used. 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_router_logits (`bool`, *optional*): Whether or not to return the logits of all the routers. They are useful for computing the router loss, and should not be returned during inference. 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`). past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states """ residual = hidden_states hidden_states = self.input_layernorm(hidden_states) # Self Attention hidden_states, self_attn_weights, present_key_value = 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, ) hidden_states = residual + hidden_states # Fully Connected residual = hidden_states hidden_states = self.post_attention_layernorm(hidden_states) hidden_states, router_logits = self.mlp(hidden_states, expert_counter_list=expert_counter_list) hidden_states = residual + hidden_states outputs = (hidden_states,) if output_attentions: outputs += (self_attn_weights,) if use_cache: outputs += (present_key_value,) if output_router_logits: outputs += (router_logits,) return outputs OLMOE_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 ([`OlmoeConfig`]): 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 OLMoE Model outputting raw hidden-states without any specific head on top.", OLMOE_START_DOCSTRING, ) class OlmoePreTrainedModel(PreTrainedModel): config_class = OlmoeConfig base_model_prefix = "model" supports_gradient_checkpointing = True _no_split_modules = ["OlmoeDecoderLayer"] _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, OlmoeRMSNorm): module.weight.data.fill_(1.0) 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_() def _set_gradient_checkpointing(self, module, value=False): if isinstance(module, OlmoeModel): module.gradient_checkpointing = value OLMOE_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 `decoder_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 (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`): 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)`) and 2 additional tensors of shape `(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)`. Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see `past_key_values` input) to speed up sequential decoding. If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all `decoder_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. """ @add_start_docstrings( "The bare OLMoE Model outputting raw hidden-states without any specific head on top.", OLMOE_START_DOCSTRING, ) class OlmoeModel(OlmoePreTrainedModel): """ Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`OlmoeDecoderLayer`] Args: config: OlmoeConfig """ def __init__(self, config: OlmoeConfig): 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.rotary_emb = OlmoeRotaryEmbedding(config=config) self.layers = nn.ModuleList( [OlmoeDecoderLayer(config, self.rotary_emb, layer_idx) for layer_idx in range(config.num_hidden_layers)] ) self.norm = OlmoeRMSNorm(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 # Copied from transformers.models.bart.modeling_bart.BartDecoder._prepare_decoder_attention_mask def _prepare_decoder_attention_mask( self, attention_mask, input_shape, inputs_embeds, past_key_values_length ): # create causal mask # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len] combined_attention_mask = None if input_shape[-1] > 1: combined_attention_mask = _make_causal_mask( input_shape, # inputs_embeds.dtype, torch.float32, # [MODIFIED] force to cast to float32 device=inputs_embeds.device, past_key_values_length=past_key_values_length, ) if attention_mask is not None: # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len] expanded_attn_mask = _expand_mask( attention_mask, inputs_embeds.dtype, tgt_len=input_shape[-1] ).to(inputs_embeds.device) combined_attention_mask = ( expanded_attn_mask if combined_attention_mask is None else expanded_attn_mask + combined_attention_mask ) if hasattr(self, "tree_mask") and self.tree_mask is not None: tree_mask = self.tree_mask tree_len = tree_mask.size(-1) combined_attention_mask[:, :, -tree_len:, -tree_len:][ tree_mask == 0 ] = combined_attention_mask.min() return combined_attention_mask @add_start_docstrings_to_model_forward(OLMOE_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=None, # [MODIFIED] past_key_value is KVCache class inputs_embeds: Optional[torch.FloatTensor] = None, use_cache: Optional[bool] = None, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, output_router_logits: Optional[bool] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple, MoeModelOutputWithPast]: output_attentions = ( output_attentions if output_attentions is not None else self.config.output_attentions ) output_router_logits = ( output_router_logits if output_router_logits is not None else self.config.output_router_logits ) 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" ) seq_length_with_past = seq_length past_key_values_length = 0 if past_key_values is not None: past_key_values_length = past_key_values[0][0].shape[2] seq_length_with_past = seq_length_with_past + past_key_values_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) # embed positions if attention_mask is None: attention_mask = torch.ones( (batch_size, seq_length_with_past), dtype=torch.bool, device=inputs_embeds.device, ) attention_mask = self._prepare_decoder_attention_mask( attention_mask, (batch_size, seq_length), inputs_embeds, past_key_values_length, ) hidden_states = 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 # decoder layers all_hidden_states = () if 1 else None all_self_attns = () if output_attentions else None all_router_logits = () if output_router_logits else None next_decoder_cache = () if use_cache else None expert_counter_list = [] #modified-shw for idx, decoder_layer in enumerate(self.layers): if idx==len(self.layers)-1 or idx==len(self.layers)//2 or idx==2: #modified-shw all_hidden_states += (hidden_states,) past_key_value = ( past_key_values[idx] if past_key_values is not None else None ) if self.gradient_checkpointing and self.training: def create_custom_forward(module): def custom_forward(*inputs): # None for past_key_value return module(*inputs, output_attentions, output_router_logits, None) return custom_forward layer_outputs = torch.utils.checkpoint.checkpoint( create_custom_forward(decoder_layer), hidden_states, attention_mask, position_ids, None, ) else: layer_outputs = decoder_layer( hidden_states, attention_mask=attention_mask, position_ids=position_ids, past_key_value=past_key_value, output_attentions=output_attentions, output_router_logits=output_router_logits, use_cache=use_cache, expert_counter_list=expert_counter_list, #modified-shw ) 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],) if output_router_logits and layer_outputs[-1] is not None: all_router_logits += (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,) # !!! # all_hidden_states += (hidden_states,) next_cache = next_decoder_cache if use_cache else None if not return_dict: return tuple( v for v in [hidden_states, next_cache, all_hidden_states, all_self_attns, all_router_logits] if v is not None ) if len(expert_counter_list) > 0: #modified-shw avg_expert = sum(expert_counter_list) / len(expert_counter_list) #modified-shw print(f"[MoE] 이번 main forward에서 layer별 unique expert 개수 평균: {avg_expert:.2f}") #modified-shw with open("expert_counter_list.txt", "a") as f: #modified-shw f.write(f"{avg_expert}\n") #modified-shw return MoeModelOutputWithPast( last_hidden_state=hidden_states, past_key_values=next_cache, hidden_states=all_hidden_states, attentions=all_self_attns, router_logits=all_router_logits, ) class OlmoeForCausalLM(OlmoePreTrainedModel, GenerationMixin): _tied_weights_keys = ["lm_head.weight"] def __init__(self, config): super().__init__(config) self.model = OlmoeModel(config) self.vocab_size = config.vocab_size self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False) self.router_aux_loss_coef = config.router_aux_loss_coef self.num_experts = config.num_experts self.num_experts_per_tok = config.num_experts_per_tok # 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(OLMOE_INPUTS_DOCSTRING) @replace_return_docstrings( output_type=MoeCausalLMOutputWithPast, 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=None, # [MODIFIED] past_key_value is KVCache class 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, 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, OlmoeForCausalLM >>> model = OlmoeForCausalLM.from_pretrained("allenai/OLMoE-1B-7B-0924") >>> tokenizer = AutoTokenizer.from_pretrained("allenai/OLMoE-1B-7B-0924") >>> 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 sure if you're conscious of this, but I'm' ```""" output_attentions = ( output_attentions if output_attentions is not None else self.config.output_attentions ) output_router_logits = ( output_router_logits if output_router_logits is not None else self.config.output_router_logits ) 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, output_router_logits=output_router_logits, return_dict=return_dict, ) hidden_states = outputs[0] logits = self.lm_head(hidden_states) loss = None if labels is not None: # Shift so that tokens < n predict n shift_logits = logits[..., :-1, :].contiguous() shift_labels = labels[..., 1:].contiguous() # Flatten the tokens loss_fct = CrossEntropyLoss() shift_logits = shift_logits.view(-1, self.config.vocab_size) shift_labels = shift_labels.view(-1) # Enable model parallelism shift_labels = shift_labels.to(shift_logits.device) loss = loss_fct(shift_logits, shift_labels) aux_loss = None if output_router_logits: aux_loss = load_balancing_loss_func( outputs.router_logits if return_dict else outputs[-1], self.num_experts, self.num_experts_per_tok, attention_mask, ) if labels is not None: loss += self.router_aux_loss_coef * aux_loss.to(loss.device) # make sure to reside in the same device if not return_dict: output = (logits,) + outputs[1:] if output_router_logits: output = (aux_loss,) + output return (loss,) + output if loss is not None else output return MoeCausalLMOutputWithPast( loss=loss, aux_loss=aux_loss, logits=logits, past_key_values=outputs.past_key_values, hidden_states=outputs.hidden_states, attentions=outputs.attentions, router_logits=outputs.router_logits, ) def prepare_inputs_for_generation( self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs, ): if past_key_values: input_ids = input_ids[:, -1:] position_ids = kwargs.get("position_ids", None) if attention_mask is not None and position_ids is None: # create position_ids on the fly for batch generation position_ids = attention_mask.long().cumsum(-1) - 1 position_ids.masked_fill_(attention_mask == 0, 1) if past_key_values: position_ids = position_ids[:, -1].unsqueeze(-1) # if `inputs_embeds` are passed, we only want to use them in the 1st generation step if inputs_embeds is not None and past_key_values is None: model_inputs = {"inputs_embeds": inputs_embeds} else: model_inputs = {"input_ids": input_ids} model_inputs.update( { "position_ids": position_ids, "past_key_values": past_key_values, "use_cache": kwargs.get("use_cache"), "attention_mask": attention_mask, } ) return model_inputs @staticmethod def _reorder_cache(past_key_values, beam_idx): reordered_past = () for layer_past in past_key_values: reordered_past += ( tuple( past_state.index_select(0, beam_idx.to(past_state.device)) for past_state in layer_past ), ) return reordered_past @add_start_docstrings( """ The OLMoE Model transformer with a sequence classification head on top (linear layer). [`OlmoeForSequenceClassification`] uses the last token in order to do the classification, as other causal models (e.g. GPT-2) do. Since it does classification on the last token, it requires to know the position of the last token. If a `pad_token_id` is defined in the configuration, it finds the last token that is not a padding token in each row. If no `pad_token_id` is defined, it simply takes the last value in each row of the batch. Since it cannot guess the padding tokens when `inputs_embeds` are passed instead of `input_ids`, it does the same (take the last value in each row of the batch). """, OLMOE_START_DOCSTRING, ) class OlmoeForSequenceClassification(OlmoePreTrainedModel): def __init__(self, config): super().__init__(config) self.num_labels = config.num_labels self.model = OlmoeModel(config) self.score = nn.Linear(config.hidden_size, self.num_labels, 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 @add_start_docstrings_to_model_forward(OLMOE_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[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, output_router_logits: Optional[bool] = None, return_dict: Optional[bool] = None, ) -> Union[Tuple, SequenceClassifierOutputWithPast]: r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy). """ return_dict = ( return_dict if return_dict is not None else self.config.use_return_dict ) transformer_outputs = self.model( 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, output_router_logits=output_router_logits, return_dict=return_dict, ) hidden_states = transformer_outputs[0] logits = self.score(hidden_states) if input_ids is not None: batch_size = input_ids.shape[0] else: batch_size = inputs_embeds.shape[0] if self.config.pad_token_id is None and batch_size != 1: raise ValueError( "Cannot handle batch sizes > 1 if no padding token is defined." ) if self.config.pad_token_id is None: sequence_lengths = -1 else: if input_ids is not None: sequence_lengths = ( torch.ne(input_ids, self.config.pad_token_id).sum(-1) - 1 ).to(logits.device) else: sequence_lengths = -1 pooled_logits = logits[ torch.arange(batch_size, device=logits.device), sequence_lengths ] loss = None if labels is not None: labels = labels.to(logits.device) if self.config.problem_type is None: if self.num_labels == 1: self.config.problem_type = "regression" elif self.num_labels > 1 and ( labels.dtype == torch.long or labels.dtype == torch.int ): self.config.problem_type = "single_label_classification" else: self.config.problem_type = "multi_label_classification" if self.config.problem_type == "regression": loss_fct = MSELoss() if self.num_labels == 1: loss = loss_fct(pooled_logits.squeeze(), labels.squeeze()) else: loss = loss_fct(pooled_logits, labels) elif self.config.problem_type == "single_label_classification": loss_fct = CrossEntropyLoss() loss = loss_fct( pooled_logits.view(-1, self.num_labels), labels.view(-1) ) elif self.config.problem_type == "multi_label_classification": loss_fct = BCEWithLogitsLoss() loss = loss_fct(pooled_logits, labels) if not return_dict: output = (pooled_logits,) + transformer_outputs[1:] return ((loss,) + output) if loss is not None else output return SequenceClassifierOutputWithPast( loss=loss, logits=pooled_logits, past_key_values=transformer_outputs.past_key_values, hidden_states=transformer_outputs.hidden_states, attentions=transformer_outputs.attentions, )