1040 lines
42 KiB
Python
1040 lines
42 KiB
Python
|
#!/usr/bin/env python
|
||
|
|
# -*- coding: utf-8 -*-
|
||
|
|
#
|
||
|
|
# Copyright @2024 AI. Inspur Inc.
|
||
|
|
#
|
||
|
|
# @author: sunxian <sunxian@inspur.com>
|
||
|
|
# @date: 2024/07/18
|
||
|
|
#
|
||
|
|
|
||
|
|
import math
|
||
|
|
from typing import List
|
||
|
|
from typing import Optional
|
||
|
|
from typing import Tuple
|
||
|
|
from typing import Union
|
||
|
|
|
||
|
|
import torch
|
||
|
|
from torch import nn
|
||
|
|
from torch.nn import BCEWithLogitsLoss
|
||
|
|
from torch.nn import CrossEntropyLoss
|
||
|
|
from torch.nn import MSELoss
|
||
|
|
from transformers import Cache
|
||
|
|
from transformers import DynamicCache
|
||
|
|
from transformers import PreTrainedModel
|
||
|
|
from transformers import ROPE_INIT_FUNCTIONS
|
||
|
|
from transformers import StaticCache
|
||
|
|
from transformers.activations import ACT2FN
|
||
|
|
from transformers.modeling_attn_mask_utils import AttentionMaskConverter
|
||
|
|
from transformers.modeling_outputs import BaseModelOutputWithPast
|
||
|
|
from transformers.modeling_outputs import CausalLMOutputWithPast
|
||
|
|
from transformers.modeling_outputs import SequenceClassifierOutputWithPast
|
||
|
|
from transformers.modeling_outputs import TokenClassifierOutput
|
||
|
|
from transformers.pytorch_utils import ALL_LAYERNORM_LAYERS
|
||
|
|
from transformers.utils import is_flash_attn_2_available
|
||
|
|
from transformers.utils import is_flash_attn_greater_or_equal_2_10
|
||
|
|
from transformers.utils import logging
|
||
|
|
|
||
|
|
from .configuration_hairuo import HairuoConfig
|
||
|
|
|
||
|
|
|
||
|
|
if is_flash_attn_2_available():
|
||
|
|
from .modeling_flash_attention_utils import _flash_attention_forward
|
||
|
|
|
||
|
|
|
||
|
|
logger = logging.get_logger(__name__)
|
||
|
|
|
||
|
|
|
||
|
|
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,
|
||
|
|
min_dtype: float,
|
||
|
|
cache_position: torch.Tensor,
|
||
|
|
batch_size: int,
|
||
|
|
):
|
||
|
|
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:
|
||
|
|
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 HairuoRMSNorm(nn.Module):
|
||
|
|
def __init__(self, hidden_size, eps=1e-6):
|
||
|
|
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)
|
||
|
|
|
||
|
|
|
||
|
|
ALL_LAYERNORM_LAYERS.append(HairuoRMSNorm)
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoRotaryEmbedding(nn.Module):
|
||
|
|
def __init__(self, config: HairuoConfig, device=None):
|
||
|
|
super().__init__()
|
||
|
|
|
||
|
|
self.config = config
|
||
|
|
self.rope_init_fn = ROPE_INIT_FUNCTIONS[config.rope_scaling["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()
|
||
|
|
def forward(self, x, position_ids):
|
||
|
|
# Core RoPE block
|
||
|
|
# x: [bs, num_attention_heads, seq_len, head_size]
|
||
|
|
inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1)
|
||
|
|
position_ids_expanded = position_ids[:, None, :].float()
|
||
|
|
# Force float32 since bfloat16 loses precision on long contexts
|
||
|
|
# See https://github.com/huggingface/transformers/pull/29285
|
||
|
|
device_type = x.device.type
|
||
|
|
device_type = device_type if isinstance(device_type, str) and device_type != "mps" else "cpu"
|
||
|
|
with torch.autocast(device_type=device_type, enabled=False):
|
||
|
|
freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
|
||
|
|
emb = torch.cat((freqs, freqs), dim=-1)
|
||
|
|
cos = emb.cos()
|
||
|
|
sin = emb.sin()
|
||
|
|
|
||
|
|
# Advanced RoPE types (e.g. yarn) apply a post-processing scaling factor, equivalent to scaling attention
|
||
|
|
cos = cos * self.attention_scaling
|
||
|
|
sin = sin * self.attention_scaling
|
||
|
|
|
||
|
|
return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)
|
||
|
|
|
||
|
|
|
||
|
|
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)
|
||
|
|
|
||
|
|
|
||
|
|
def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
|
||
|
|
origin_dtype = k.dtype
|
||
|
|
|
||
|
|
if position_ids is not None:
|
||
|
|
cos = cos[position_ids].unsqueeze(unsqueeze_dim) # [bs, 1, seq_len, dim]
|
||
|
|
sin = sin[position_ids].unsqueeze(unsqueeze_dim) # [bs, 1, seq_len, dim]
|
||
|
|
else:
|
||
|
|
cos = cos.unsqueeze(unsqueeze_dim)
|
||
|
|
sin = sin.unsqueeze(unsqueeze_dim)
|
||
|
|
|
||
|
|
q_fp32 = q.to(dtype=torch.float32, device=q.device)
|
||
|
|
k_fp32 = k.to(dtype=torch.float32, device=k.device)
|
||
|
|
q_embed = (q_fp32 * cos) + (rotate_half(q_fp32) * sin)
|
||
|
|
k_embed = (k_fp32 * cos) + (rotate_half(k_fp32) * sin)
|
||
|
|
return q_embed.to(dtype=origin_dtype), k_embed.to(dtype=origin_dtype)
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoMLP(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, hidden_state):
|
||
|
|
return self.down_proj(self.act_fn(self.gate_proj(hidden_state)) * self.up_proj(hidden_state))
|
||
|
|
|
||
|
|
|
||
|
|
def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
|
||
|
|
"""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, seq_len, 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, seq_len, head_dim)
|
||
|
|
return hidden_states.reshape(batch, num_key_value_heads * n_rep, seq_len, head_dim)
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoAttention(nn.Module):
|
||
|
|
def __init__(self, config: HairuoConfig, 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=False)
|
||
|
|
self.k_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
|
||
|
|
self.v_proj = nn.Linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
|
||
|
|
self.o_proj = nn.Linear(self.hidden_size, self.hidden_size, bias=False)
|
||
|
|
|
||
|
|
self.rotary_emb = HairuoRotaryEmbedding(config=self.config)
|
||
|
|
|
||
|
|
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: bool = False,
|
||
|
|
use_cache: bool = False,
|
||
|
|
cache_position: Optional[torch.LongTensor] = None,
|
||
|
|
position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
|
||
|
|
cu_seqlens: Optional[torch.Tensor] = None,
|
||
|
|
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
|
||
|
|
bsz, q_len, _ = hidden_states.size()
|
||
|
|
|
||
|
|
query_states = self.q_proj(hidden_states)
|
||
|
|
key_states = self.k_proj(hidden_states)
|
||
|
|
value_states = self.v_proj(hidden_states)
|
||
|
|
|
||
|
|
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)
|
||
|
|
|
||
|
|
if position_embeddings is None:
|
||
|
|
logger.warning_once(
|
||
|
|
"The attention layers in this model are transitioning from computing the RoPE embeddings internally "
|
||
|
|
"through `position_ids` (2D tensor with the indexes of the tokens), to using externally computed "
|
||
|
|
"`position_embeddings` (Tuple of tensors, containing cos and sin). In v4.45 `position_ids` will be "
|
||
|
|
"removed and `position_embeddings` will be mandatory."
|
||
|
|
)
|
||
|
|
cos, sin = self.rotary_emb(value_states, position_ids)
|
||
|
|
else:
|
||
|
|
cos, sin = position_embeddings
|
||
|
|
|
||
|
|
query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
|
||
|
|
|
||
|
|
if past_key_value is not None:
|
||
|
|
# sin and cos are specific to RoPE models; cache_position needed for the static cache
|
||
|
|
cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
|
||
|
|
key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
|
||
|
|
|
||
|
|
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, -1)
|
||
|
|
attn_output = self.o_proj(attn_output)
|
||
|
|
|
||
|
|
if not output_attentions:
|
||
|
|
attn_weights = None
|
||
|
|
|
||
|
|
return attn_output, attn_weights, past_key_value
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoFlashAttention2(HairuoAttention):
|
||
|
|
def __init__(self, *args, **kwargs):
|
||
|
|
super().__init__(*args, **kwargs)
|
||
|
|
|
||
|
|
self._flash_attn_uses_top_left_mask = not is_flash_attn_greater_or_equal_2_10()
|
||
|
|
|
||
|
|
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: bool = False,
|
||
|
|
use_cache: bool = False,
|
||
|
|
cache_position: Optional[torch.LongTensor] = None,
|
||
|
|
position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
|
||
|
|
cu_seqlens: Optional[torch.Tensor] = None,
|
||
|
|
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
|
||
|
|
output_attentions = False
|
||
|
|
|
||
|
|
bsz, q_len, _ = hidden_states.size()
|
||
|
|
|
||
|
|
query_states = self.q_proj(hidden_states)
|
||
|
|
key_states = self.k_proj(hidden_states)
|
||
|
|
value_states = self.v_proj(hidden_states)
|
||
|
|
|
||
|
|
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)
|
||
|
|
|
||
|
|
if position_embeddings is None:
|
||
|
|
logger.warning_once(
|
||
|
|
"The attention layers in this model are transitioning from computing the RoPE embeddings internally "
|
||
|
|
"through `position_ids` (2D tensor with the indexes of the tokens), to using externally computed "
|
||
|
|
"`position_embeddings` (Tuple of tensors, containing cos and sin). In v4.45 `position_ids` will be "
|
||
|
|
"removed and `position_embeddings` will be mandatory."
|
||
|
|
)
|
||
|
|
cos, sin = self.rotary_emb(value_states, position_ids)
|
||
|
|
else:
|
||
|
|
cos, sin = position_embeddings
|
||
|
|
|
||
|
|
query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
|
||
|
|
|
||
|
|
if past_key_value is not None:
|
||
|
|
cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position} # Specific to RoPE models
|
||
|
|
key_states, value_states = past_key_value.update(key_states, value_states, self.layer_idx, cache_kwargs)
|
||
|
|
|
||
|
|
# Reshape to the expected shape for Flash Attention
|
||
|
|
query_states = query_states.transpose(1, 2)
|
||
|
|
key_states = key_states.transpose(1, 2)
|
||
|
|
value_states = value_states.transpose(1, 2)
|
||
|
|
|
||
|
|
dropout_rate = self.attention_dropout if self.training else 0.0
|
||
|
|
|
||
|
|
# In PEFT, usually we cast the layer norms in float32 for training stability reasons
|
||
|
|
# therefore the input hidden states gets silently casted in float32. Hence, we need
|
||
|
|
# cast them back in float16 just to be sure everything works as expected.
|
||
|
|
input_dtype = query_states.dtype
|
||
|
|
if input_dtype == torch.float32:
|
||
|
|
if torch.is_autocast_enabled():
|
||
|
|
target_dtype = torch.get_autocast_gpu_dtype()
|
||
|
|
# Handle the case where the model is quantized
|
||
|
|
elif hasattr(self.config, "_pre_quantization_dtype"):
|
||
|
|
target_dtype = self.config._pre_quantization_dtype
|
||
|
|
else:
|
||
|
|
target_dtype = self.q_proj.weight.dtype
|
||
|
|
|
||
|
|
logger.warning_once(
|
||
|
|
f"The input hidden states seems to be silently casted in float32, this might be related to"
|
||
|
|
f" the fact you have upcasted embedding or layer norm layers in float32. We will cast back the input in"
|
||
|
|
f" {target_dtype}."
|
||
|
|
)
|
||
|
|
|
||
|
|
query_states = query_states.to(target_dtype)
|
||
|
|
key_states = key_states.to(target_dtype)
|
||
|
|
value_states = value_states.to(target_dtype)
|
||
|
|
|
||
|
|
attn_output = _flash_attention_forward(
|
||
|
|
query_states,
|
||
|
|
key_states,
|
||
|
|
value_states,
|
||
|
|
attention_mask,
|
||
|
|
q_len,
|
||
|
|
position_ids=position_ids,
|
||
|
|
is_causal=self.is_causal,
|
||
|
|
dropout=dropout_rate,
|
||
|
|
use_top_left_mask=self._flash_attn_uses_top_left_mask,
|
||
|
|
cu_seqlens=cu_seqlens,
|
||
|
|
)
|
||
|
|
|
||
|
|
attn_output = attn_output.reshape(bsz, q_len, -1).contiguous()
|
||
|
|
attn_output = self.o_proj(attn_output)
|
||
|
|
|
||
|
|
attn_weights = False
|
||
|
|
if not output_attentions:
|
||
|
|
attn_weights = None
|
||
|
|
|
||
|
|
return attn_output, attn_weights, past_key_value
|
||
|
|
|
||
|
|
|
||
|
|
HAIRUO_ATTENTION_CLASSES = {
|
||
|
|
"eager": HairuoAttention,
|
||
|
|
"flash_attention_2": HairuoFlashAttention2,
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoDecoderLayer(nn.Module):
|
||
|
|
def __init__(self, config: HairuoConfig, layer_idx: int):
|
||
|
|
super().__init__()
|
||
|
|
|
||
|
|
self.hidden_size = config.hidden_size
|
||
|
|
|
||
|
|
self.self_attn = HAIRUO_ATTENTION_CLASSES[config._attn_implementation](config=config, layer_idx=layer_idx)
|
||
|
|
|
||
|
|
self.mlp = HairuoMLP(config)
|
||
|
|
self.input_layernorm = HairuoRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||
|
|
self.post_attention_layernorm = HairuoRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||
|
|
|
||
|
|
self.mup_scale_hidden_states = config.mup_scale_depth / math.sqrt(config.num_hidden_layers)
|
||
|
|
|
||
|
|
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,
|
||
|
|
cu_seqlens: Optional[torch.Tensor] = None,
|
||
|
|
**kwargs,
|
||
|
|
) -> Tuple[torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]]:
|
||
|
|
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,
|
||
|
|
cache_position=cache_position,
|
||
|
|
position_embeddings=position_embeddings,
|
||
|
|
cu_seqlens=cu_seqlens,
|
||
|
|
**kwargs,
|
||
|
|
)
|
||
|
|
hidden_states = residual + hidden_states * self.mup_scale_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 * self.mup_scale_hidden_states
|
||
|
|
|
||
|
|
outputs = (hidden_states,)
|
||
|
|
|
||
|
|
if output_attentions:
|
||
|
|
outputs += (self_attn_weights,)
|
||
|
|
|
||
|
|
if use_cache:
|
||
|
|
outputs += (present_key_value,)
|
||
|
|
|
||
|
|
return outputs
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoPreTrainedModel(PreTrainedModel):
|
||
|
|
config_class = HairuoConfig
|
||
|
|
base_model_prefix = "model"
|
||
|
|
supports_gradient_checkpointing = True
|
||
|
|
_no_split_modules = ["HairuoDecoderLayer"]
|
||
|
|
_skip_keys_device_placement = "past_key_values"
|
||
|
|
_supports_flash_attn_2 = True
|
||
|
|
_supports_sdpa = False
|
||
|
|
_supports_cache_class = True
|
||
|
|
_supports_static_cache = True
|
||
|
|
|
||
|
|
def _init_weights(self, module):
|
||
|
|
if isinstance(module, nn.Linear):
|
||
|
|
std = self.config.initializer_range / math.sqrt(self.config.mup_scale_width)
|
||
|
|
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=self.config.initializer_range)
|
||
|
|
if module.padding_idx is not None:
|
||
|
|
module.weight.data[module.padding_idx].zero_()
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoModel(HairuoPreTrainedModel):
|
||
|
|
def __init__(self, config: HairuoConfig):
|
||
|
|
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.layers = nn.ModuleList(
|
||
|
|
[HairuoDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
|
||
|
|
)
|
||
|
|
self.norm = HairuoRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||
|
|
self.rotary_emb = HairuoRotaryEmbedding(config=config)
|
||
|
|
|
||
|
|
self.gradient_checkpointing = False
|
||
|
|
|
||
|
|
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[Union[Cache, 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,
|
||
|
|
cache_position: Optional[torch.LongTensor] = None,
|
||
|
|
cu_seqlens: Optional[torch.Tensor] = 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
|
||
|
|
|
||
|
|
if (input_ids is None) ^ (inputs_embeds is not None):
|
||
|
|
raise ValueError(
|
||
|
|
"You cannot specify both input_ids and inputs_embeds at the same time, and must specify either one"
|
||
|
|
)
|
||
|
|
|
||
|
|
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) * self.config.mup_scale_emb
|
||
|
|
|
||
|
|
return_legacy_cache = False
|
||
|
|
if use_cache and not isinstance(past_key_values, Cache) and not self.training:
|
||
|
|
return_legacy_cache = True
|
||
|
|
past_key_values = DynamicCache.from_legacy_cache(past_key_values)
|
||
|
|
logger.warning_once(
|
||
|
|
"We detected that you are passing `past_key_values` as a tuple and this is deprecated and will "
|
||
|
|
"be removed in v4.43. Please use an appropriate `Cache` class ("
|
||
|
|
"https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)"
|
||
|
|
)
|
||
|
|
|
||
|
|
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
|
||
|
|
next_decoder_cache = None
|
||
|
|
|
||
|
|
for decoder_layer in 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,
|
||
|
|
causal_mask,
|
||
|
|
position_ids,
|
||
|
|
past_key_values,
|
||
|
|
output_attentions,
|
||
|
|
use_cache,
|
||
|
|
cache_position,
|
||
|
|
position_embeddings,
|
||
|
|
cu_seqlens,
|
||
|
|
)
|
||
|
|
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,
|
||
|
|
cu_seqlens=cu_seqlens,
|
||
|
|
)
|
||
|
|
|
||
|
|
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.norm(hidden_states)
|
||
|
|
|
||
|
|
if output_hidden_states:
|
||
|
|
all_hidden_states += (hidden_states,)
|
||
|
|
|
||
|
|
next_cache = next_decoder_cache if use_cache else None
|
||
|
|
if return_legacy_cache:
|
||
|
|
next_cache = next_cache.to_legacy_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,
|
||
|
|
)
|
||
|
|
|
||
|
|
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 0.0 in attention_mask:
|
||
|
|
return attention_mask
|
||
|
|
return None
|
||
|
|
|
||
|
|
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)
|
||
|
|
|
||
|
|
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
|
||
|
|
min_dtype = torch.finfo(dtype).min
|
||
|
|
sequence_length = input_tensor.shape[1]
|
||
|
|
if using_static_cache:
|
||
|
|
target_length = past_key_values.get_max_length()
|
||
|
|
else:
|
||
|
|
target_length = (
|
||
|
|
attention_mask.shape[-1]
|
||
|
|
if isinstance(attention_mask, torch.Tensor)
|
||
|
|
else past_seen_tokens + sequence_length + 1
|
||
|
|
)
|
||
|
|
|
||
|
|
causal_mask = _prepare_4d_causal_attention_mask_with_cache_position(
|
||
|
|
attention_mask,
|
||
|
|
sequence_length=sequence_length,
|
||
|
|
target_length=target_length,
|
||
|
|
dtype=dtype,
|
||
|
|
device=device,
|
||
|
|
min_dtype=min_dtype,
|
||
|
|
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
|
||
|
|
causal_mask = AttentionMaskConverter._unmask_unattended(causal_mask, min_dtype)
|
||
|
|
|
||
|
|
return causal_mask
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoForCausalLM(HairuoPreTrainedModel):
|
||
|
|
_tied_weights_keys = ["lm_head.weight"]
|
||
|
|
_auto_class = "AutoModel"
|
||
|
|
|
||
|
|
def __init__(self, config):
|
||
|
|
super().__init__(config)
|
||
|
|
self.model = HairuoModel(config)
|
||
|
|
self.vocab_size = config.vocab_size
|
||
|
|
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
|
||
|
|
|
||
|
|
self.post_init()
|
||
|
|
|
||
|
|
def _init_weights(self, module): # todo: should be remove when export
|
||
|
|
if isinstance(module, nn.Linear):
|
||
|
|
module.weight.data.normal_(mean=0.0, std=self.config.initializer_range)
|
||
|
|
if module.bias is not None:
|
||
|
|
module.bias.data.zero_()
|
||
|
|
|
||
|
|
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
|
||
|
|
|
||
|
|
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,
|
||
|
|
cu_seqlens: Optional[torch.Tensor] = None,
|
||
|
|
) -> Union[Tuple, CausalLMOutputWithPast]:
|
||
|
|
output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
|
||
|
|
if output_hidden_states is None:
|
||
|
|
output_hidden_states = 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,
|
||
|
|
cu_seqlens=cu_seqlens,
|
||
|
|
)
|
||
|
|
|
||
|
|
hidden_states = outputs[0]
|
||
|
|
hidden_states = hidden_states / self.config.mup_scale_width
|
||
|
|
|
||
|
|
logits = self.lm_head(hidden_states)
|
||
|
|
logits = logits.float()
|
||
|
|
|
||
|
|
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
|
||
|
|
shift_logits = shift_logits.view(-1, self.config.vocab_size)
|
||
|
|
shift_labels = shift_labels.view(-1)
|
||
|
|
# Ensure tensors are on the same device
|
||
|
|
shift_labels = shift_labels.to(shift_logits.device)
|
||
|
|
loss_fct = CrossEntropyLoss()
|
||
|
|
loss = loss_fct(shift_logits, shift_labels)
|
||
|
|
|
||
|
|
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,
|
||
|
|
)
|
||
|
|
|
||
|
|
def prepare_inputs_for_generation(
|
||
|
|
self,
|
||
|
|
input_ids,
|
||
|
|
past_key_values=None,
|
||
|
|
attention_mask=None,
|
||
|
|
inputs_embeds=None,
|
||
|
|
cache_position=None,
|
||
|
|
position_ids=None,
|
||
|
|
use_cache=True,
|
||
|
|
**kwargs,
|
||
|
|
):
|
||
|
|
# If we have cache: let's slice `input_ids` through `cache_position`, to keep only the unprocessed tokens
|
||
|
|
# Exception 1: when passing input_embeds, input_ids may be missing entries
|
||
|
|
# Exception 2: some generation methods do special slicing of input_ids, so we don't need to do it here
|
||
|
|
if past_key_values is not None:
|
||
|
|
if inputs_embeds is not None: # Exception 1
|
||
|
|
input_ids = input_ids[:, -cache_position.shape[0] :]
|
||
|
|
elif input_ids.shape[1] != cache_position.shape[0]: # Default case (the "else", a no op, is Exception 2)
|
||
|
|
input_ids = input_ids[:, cache_position]
|
||
|
|
|
||
|
|
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[:, -input_ids.shape[1] :]
|
||
|
|
|
||
|
|
# This `clone` call is needed to avoid recapturing cuda graphs with `torch.compile`'s
|
||
|
|
# `mode="reduce-overhead`, as otherwise the input `position_ids` would have various stride
|
||
|
|
# during the decoding. Here, simply using `.contiguous()` is not sufficient as in the batch size = 1 case,
|
||
|
|
# `position_ids` is already contiguous but with varying stride which retriggers a capture.
|
||
|
|
position_ids = position_ids.clone(memory_format=torch.contiguous_format)
|
||
|
|
|
||
|
|
# if `inputs_embeds` are passed, we only want to use them in the 1st generation step
|
||
|
|
if inputs_embeds is not None and cache_position[0] == 0:
|
||
|
|
model_inputs = {"inputs_embeds": inputs_embeds}
|
||
|
|
else:
|
||
|
|
model_inputs = {"input_ids": input_ids.contiguous()}
|
||
|
|
|
||
|
|
if isinstance(past_key_values, StaticCache) and attention_mask.ndim == 2:
|
||
|
|
if inputs_embeds is not None:
|
||
|
|
batch_size, sequence_length = inputs_embeds.shape
|
||
|
|
device = inputs_embeds.device
|
||
|
|
else:
|
||
|
|
batch_size, sequence_length = input_ids.shape
|
||
|
|
device = input_ids.device
|
||
|
|
|
||
|
|
dtype = self.lm_head.weight.dtype
|
||
|
|
min_dtype = torch.finfo(dtype).min
|
||
|
|
|
||
|
|
attention_mask = _prepare_4d_causal_attention_mask_with_cache_position(
|
||
|
|
attention_mask,
|
||
|
|
sequence_length=sequence_length,
|
||
|
|
target_length=past_key_values.get_max_length(),
|
||
|
|
dtype=dtype,
|
||
|
|
device=device,
|
||
|
|
min_dtype=min_dtype,
|
||
|
|
cache_position=cache_position,
|
||
|
|
batch_size=batch_size,
|
||
|
|
)
|
||
|
|
|
||
|
|
model_inputs.update(
|
||
|
|
{
|
||
|
|
"position_ids": position_ids,
|
||
|
|
"cache_position": cache_position,
|
||
|
|
"past_key_values": past_key_values,
|
||
|
|
"use_cache": use_cache,
|
||
|
|
"attention_mask": attention_mask,
|
||
|
|
}
|
||
|
|
)
|
||
|
|
return model_inputs
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoForSequenceClassification(HairuoPreTrainedModel):
|
||
|
|
def __init__(self, config):
|
||
|
|
super().__init__(config)
|
||
|
|
self.num_labels = config.num_labels
|
||
|
|
self.model = HairuoModel(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
|
||
|
|
|
||
|
|
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,
|
||
|
|
) -> Union[Tuple, SequenceClassifierOutputWithPast]:
|
||
|
|
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,
|
||
|
|
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:
|
||
|
|
# if no pad token found, use modulo instead of reverse indexing for ONNX compatibility
|
||
|
|
sequence_lengths = torch.eq(input_ids, self.config.pad_token_id).int().argmax(-1) - 1
|
||
|
|
sequence_lengths = sequence_lengths % input_ids.shape[-1]
|
||
|
|
sequence_lengths = sequence_lengths.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,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
class HairuoForTokenClassification(HairuoPreTrainedModel):
|
||
|
|
def __init__(self, config):
|
||
|
|
super().__init__(config)
|
||
|
|
self.num_labels = config.num_labels
|
||
|
|
self.model = HairuoModel(config)
|
||
|
|
if getattr(config, "classifier_dropout", None) is not None:
|
||
|
|
classifier_dropout = config.classifier_dropout
|
||
|
|
elif getattr(config, "hidden_dropout", None) is not None:
|
||
|
|
classifier_dropout = config.hidden_dropout
|
||
|
|
else:
|
||
|
|
classifier_dropout = 0.1
|
||
|
|
self.dropout = nn.Dropout(classifier_dropout)
|
||
|
|
self.score = nn.Linear(config.hidden_size, config.num_labels)
|
||
|
|
|
||
|
|
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 forward(
|
||
|
|
self,
|
||
|
|
input_ids: Optional[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,
|
||
|
|
return_dict: Optional[bool] = None,
|
||
|
|
) -> Union[Tuple, TokenClassifierOutput]:
|
||
|
|
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
|
||
|
|
|
||
|
|
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,
|
||
|
|
return_dict=return_dict,
|
||
|
|
)
|
||
|
|
sequence_output = outputs[0]
|
||
|
|
sequence_output = self.dropout(sequence_output)
|
||
|
|
logits = self.score(sequence_output)
|
||
|
|
|
||
|
|
loss = None
|
||
|
|
if labels is not None:
|
||
|
|
loss_fct = CrossEntropyLoss()
|
||
|
|
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
|
||
|
|
|
||
|
|
if not return_dict:
|
||
|
|
output = (logits,) + outputs[2:]
|
||
|
|
return ((loss,) + output) if loss is not None else output
|
||
|
|
|
||
|
|
return TokenClassifierOutput(
|
||
|
|
loss=loss,
|
||
|
|
logits=logits,
|
||
|
|
hidden_states=outputs.hidden_states,
|
||
|
|
attentions=outputs.attentions,
|
||
|
|
)
|