internlm-7b / modeling_internlm.py

update copyright (#9)

154a736 verified 4 months ago

No virus

58.5 kB

	# Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
	#
	# This code is based on transformers/src/transformers/models/llama/modeling_llama.py
	#
	# Licensed under the Apache License, Version 2.0 (the "License");
	# you may not use this file except in compliance with the License.
	# You may obtain a copy of the License at
	#
	# http://www.apache.org/licenses/LICENSE-2.0
	#
	# Unless required by applicable law or agreed to in writing, software
	# distributed under the License is distributed on an "AS IS" BASIS,
	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
	# See the License for the specific language governing permissions and
	# limitations under the License.
	""" PyTorch InternLM model."""
	import math
	import queue
	import threading
	from typing import List, Optional, Tuple, Union

	import torch
	import torch.utils.checkpoint
	from torch import nn
	from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
	from transformers.activations import ACT2FN
	from transformers.modeling_outputs import (
	BaseModelOutputWithPast,
	CausalLMOutputWithPast,
	SequenceClassifierOutputWithPast,
	)
	from transformers.modeling_utils import PreTrainedModel
	from transformers.utils import (
	add_start_docstrings,
	add_start_docstrings_to_model_forward,
	logging,
	replace_return_docstrings,
	)

	try:
	from transformers.generation.streamers import BaseStreamer
	except: # noqa # pylint: disable=bare-except
	BaseStreamer = None

	from .configuration_internlm import InternLMConfig

	logger = logging.get_logger(__name__)

	_CONFIG_FOR_DOC = "InternLMConfig"

	flash_attn_func, flash_attn_varlen_func = None, None
	pad_input, index_first_axis, unpad_input = None, None, None
	def _import_flash_attn():
	global flash_attn_func, flash_attn_varlen_func
	global pad_input, index_first_axis, unpad_input
	try:
	from flash_attn import flash_attn_func as _flash_attn_func, flash_attn_varlen_func as _flash_attn_varlen_func
	from flash_attn.bert_padding import pad_input as _pad_input, index_first_axis as _index_first_axis, unpad_input as _unpad_input
	flash_attn_func, flash_attn_varlen_func = _flash_attn_func, _flash_attn_varlen_func
	pad_input, index_first_axis, unpad_input = _pad_input, _index_first_axis, _unpad_input
	except ImportError:
	raise ImportError("flash_attn is not installed.")


	def _get_unpad_data(attention_mask):
	seqlens_in_batch = attention_mask.sum(dim=-1, dtype=torch.int32)
	indices = torch.nonzero(attention_mask.flatten(), as_tuple=False).flatten()
	max_seqlen_in_batch = seqlens_in_batch.max().item()
	cu_seqlens = nn.functional.pad(torch.cumsum(seqlens_in_batch, dim=0, dtype=torch.torch.int32), (1, 0))
	return (
	indices,
	cu_seqlens,
	max_seqlen_in_batch,
	)


	# Copied from transformers.models.llama.modeling_llama._make_causal_mask
	def _make_causal_mask(
	input_ids_shape: torch.Size, dtype: torch.dtype, device: torch.device, past_key_values_length: int = 0
	):
	"""
	Make causal mask used for bi-directional self-attention.
	"""
	bsz, tgt_len = input_ids_shape
	mask = torch.full((tgt_len, tgt_len), torch.tensor(torch.finfo(dtype).min, device=device), 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.llama.modeling_llama._expand_mask
	def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
	"""
	Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
	"""
	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.llama.modeling_llama.LlamaRMSNorm with Llama->InternLM
	class InternLMRMSNorm(nn.Module):
	"""RMSNorm implemention."""

	def __init__(self, hidden_size, eps=1e-6):
	"""
	InternLMRMSNorm is equivalent to T5LayerNorm
	"""
	super().__init__()
	self.weight = nn.Parameter(torch.ones(hidden_size))
	self.variance_epsilon = eps

	def forward(self, hidden_states):
	variance = hidden_states.to(torch.float32).pow(2).mean(-1, keepdim=True)
	hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)

	# convert into half-precision if necessary
	if self.weight.dtype in [torch.float16, torch.bfloat16]:
	hidden_states = hidden_states.to(self.weight.dtype)

	return self.weight * hidden_states


	# Copied from transformers.models.llama.modeling_llama.LlamaRotaryEmbedding with Llama->InternLM
	class InternLMRotaryEmbedding(torch.nn.Module):
	"""Implement InternLM's rotary embedding.

	Args:
	dim (int): Characteristic dimension of each self-attentional head.
	max_position_embeddings (int, optional): Model's training length. Defaults to 2048.
	base (int, optional): The rotation position encodes the rotation Angle base number. Defaults to 10000.
	device (Any, optional): Running device. Defaults to None.
	"""

	def __init__(self, dim, max_position_embeddings=2048, base=10000, device=None):
	super().__init__()
	inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float().to(device) / dim))
	self.register_buffer("inv_freq", inv_freq, persistent=False)

	# Build here to make `torch.jit.trace` work.
	self.max_seq_len_cached = max_position_embeddings
	t = torch.arange(self.max_seq_len_cached, device=self.inv_freq.device, dtype=self.inv_freq.dtype)
	freqs = torch.einsum("i,j->ij", t, self.inv_freq)
	# Different from paper, but it uses a different permutation in order to obtain the same calculation
	emb = torch.cat((freqs, freqs), dim=-1)
	self.register_buffer("cos_cached", emb.cos().to(torch.float32), persistent=False)
	self.register_buffer("sin_cached", emb.sin().to(torch.float32), persistent=False)

	def forward(self, x, seq_len=None):
	# x: [bs, num_attention_heads, seq_len, head_size]
	# This `if` block is unlikely to be run after we build sin/cos in `__init__`. Keep the logic here just in case.
	if seq_len > self.max_seq_len_cached:
	self.max_seq_len_cached = seq_len
	t = torch.arange(self.max_seq_len_cached, device=x.device, dtype=self.inv_freq.dtype)
	freqs = torch.einsum("i,j->ij", t, self.inv_freq)
	# Different from paper, but it uses a different permutation in order to obtain the same calculation
	emb = torch.cat((freqs, freqs), dim=-1).to(x.device)
	self.register_buffer("cos_cached", emb.cos(), persistent=False)
	self.register_buffer("sin_cached", emb.sin(), persistent=False)
	return (
	self.cos_cached[:seq_len, ...].to(dtype=x.dtype),
	self.sin_cached[:seq_len, ...].to(dtype=x.dtype),
	)


	# Copied from transformers.models.llama.modeling_llama.LlamaDynamicNTKScalingRotaryEmbedding with Llama->InternLM
	class InternLMDynamicNTKScalingRotaryEmbedding(torch.nn.Module):
	"""Implement InternLM's DyanmicNTK extrapolation method, thereby broadening the model support context to 16K.

	Args:
	dim (int): Characteristic dimension of each self-attentional head.
	max_position_embeddings (int, optional): Model's training length. Defaults to 2048.
	base (int, optional): The rotation position encodes the rotation Angle base number. Defaults to 10000.
	device (Any, optional): Running device. Defaults to None.
	scaling_factor (float, optional): NTK method extrapolation coefficient. Defaults to 1.0.
	"""

	def __init__(self, dim, max_position_embeddings=2048, base=10000, device=None, scaling_factor=1.0):
	super().__init__()
	inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float().to(device) / dim))
	self.register_buffer("inv_freq", inv_freq, persistent=False)
	self.dim = dim
	self.base = base
	self.scaling_factor = scaling_factor

	# Build here to make `torch.jit.trace` work.
	self.max_position_embeddings = max_position_embeddings
	self.max_seq_len_cached = max_position_embeddings
	t = torch.arange(self.max_seq_len_cached, device=self.inv_freq.device, dtype=self.inv_freq.dtype)
	freqs = torch.einsum("i,j->ij", t, self.inv_freq)
	# Different from paper, but it uses a different permutation in order to obtain the same calculation
	emb = torch.cat((freqs, freqs), dim=-1)
	self.register_buffer("cos_cached", emb.cos(), persistent=False)
	self.register_buffer("sin_cached", emb.sin(), persistent=False)

	def _update_cached(self, x, seq_len=None):
	self.max_seq_len_cached = max(seq_len, self.max_position_embeddings)
	if seq_len > self.max_position_embeddings:
	base = self.base * (
	(self.scaling_factor * seq_len / self.max_position_embeddings) - (self.scaling_factor - 1)
	) ** (self.dim / (self.dim - 2))
	inv_freq = 1.0 / (base ** (torch.arange(0, self.dim, 2).float().to(x.device) / self.dim))
	else:
	inv_freq = self.inv_freq
	t = torch.arange(self.max_seq_len_cached, device=inv_freq.device, dtype=inv_freq.dtype)
	freqs = torch.einsum("i,j->ij", t, inv_freq)
	emb = torch.cat((freqs, freqs), dim=-1)
	self.register_buffer("cos_cached", emb.cos(), persistent=False)
	self.register_buffer("sin_cached", emb.sin(), persistent=False)

	def forward(self, x, seq_len=None):
	# x: [bs, num_attention_heads, seq_len, head_size]
	# This `if` block is unlikely to be run after we build sin/cos in `__init__`. Keep the logic here just in case.
	if seq_len <= self.max_position_embeddings:
	# Reset the tables if the sequence length has changed,
	if self.max_seq_len_cached > self.max_position_embeddings:
	self._update_cached(x, seq_len)
	else:
	self._update_cached(x, seq_len)

	return (
	self.cos_cached[:seq_len, ...].to(dtype=x.dtype),
	self.sin_cached[:seq_len, ...].to(dtype=x.dtype),
	)


	# Copied from transformers.model.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.model.llama.modeling_llama.apply_rotary_pos_emb
	def apply_rotary_pos_emb(q, k, cos, sin, position_ids):
	if position_ids.size(1) == 1:
	q_cos = cos[position_ids].unsqueeze(1).expand(q.shape)
	q_sin = sin[position_ids].unsqueeze(1).expand(q.shape)
	q_embed = (q * q_cos) + (rotate_half(q) * q_sin)

	position_ids = position_ids.flatten() + 1
	max_length = max(position_ids)
	position_ids = torch.stack([torch.cat([torch.ones(max_length - w, dtype=torch.long), torch.arange(w)]) for w in position_ids])
	k_cos = cos[position_ids].unsqueeze(1).expand(k.shape)
	k_sin = sin[position_ids].unsqueeze(1).expand(k.shape)
	k_embed = (k * k_cos) + (rotate_half(k) * k_sin)
	else:
	cos = cos[position_ids].unsqueeze(1)
	sin = sin[position_ids].unsqueeze(1)
	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.llama.modeling_llama.LlamaMLP with Llama->InternLM
	class InternLMMLP(nn.Module):
	def __init__(
	self,
	hidden_size: int,
	intermediate_size: int,
	hidden_act: str,
	):
	super().__init__()
	self.gate_proj = nn.Linear(hidden_size, intermediate_size, bias=False)
	self.down_proj = nn.Linear(intermediate_size, hidden_size, bias=False)
	self.up_proj = nn.Linear(hidden_size, intermediate_size, bias=False)
	self.act_fn = ACT2FN[hidden_act]

	def forward(self, x):
	return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))


	# Copied from transformers.models.llama.modeling_llama.LlamaAttention with Llama->InternLM
	class InternLMAttention(nn.Module):
	"""Multi-headed attention from 'Attention Is All You Need' paper"""

	def __init__(self, config: InternLMConfig):
	super().__init__()
	self.config = config
	self.hidden_size = config.hidden_size
	self.num_heads = config.num_attention_heads
	self.head_dim = self.hidden_size // self.num_heads
	self.max_position_embeddings = config.max_position_embeddings

	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.bias)
	self.k_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=config.bias)
	self.v_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=config.bias)
	self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=config.bias)
	self.rotary_emb = self._init_rope()
	self.is_causal = True

	def _init_rope(self):
	if self.config.rotary["type"] == "origin":
	self.rotary_emb = InternLMRotaryEmbedding(
	self.head_dim,
	max_position_embeddings=self.max_position_embeddings,
	base=self.config.rotary["base"],
	)
	elif self.config.rotary["type"] == "dynamic":
	self.rotary_emb = InternLMDynamicNTKScalingRotaryEmbedding(
	self.head_dim,
	max_position_embeddings=self.max_position_embeddings,
	base=self.config.rotary["base"],
	scaling_factor=self.config.rotary.get("scaling_factor", 1.0),
	)
	else:
	raise ValueError("Currently we only support rotary embedding's type being one of ('origin', 'dynamic').")
	return self.rotary_emb

	def _shape(self, tensor: torch.Tensor, seq_len: int, bsz: int):
	return tensor.view(bsz, seq_len, self.num_heads, self.head_dim).transpose(1, 2).contiguous()

	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,
	) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
	bsz, q_len, _ = hidden_states.size()

	query_states = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
	key_states = self.k_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
	value_states = self.v_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)

	if past_key_value is not None:
	# reuse k, v, self_attention
	key_states = torch.cat([past_key_value[0], key_states], dim=2)
	value_states = torch.cat([past_key_value[1], value_states], dim=2)

	past_key_value = (key_states, value_states) if use_cache else None

	kv_seq_len = key_states.shape[-2]
	cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
	query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)

	attn_weights = torch.matmul(query_states, key_states.transpose(2, 3)) / math.sqrt(self.head_dim)

	if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
	raise ValueError(
	f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is"
	f" {attn_weights.size()}"
	)

	if attention_mask is not None:
	if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
	raise ValueError(
	f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
	)
	attn_weights = attn_weights + attention_mask
	attn_weights = torch.max(attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min))

	# upcast attention to fp32
	attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
	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)
	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

	# Copied from transformers.models.llama.modeling_llama.LlamaFlashAttention2 with Llama->InternLM
	class InternLMFlashAttention2(InternLMAttention):
	"""
	InternLM flash attention module. This module inherits from `InternLMAttention` as the weights of the module stays
	untouched. The only required change would be on the forward pass where it needs to correctly call the public API of
	flash attention and deal with padding tokens in case the input contains any of them.
	"""

	def forward(
	self,
	hidden_states: torch.Tensor,
	attention_mask: Optional[torch.LongTensor] = 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]]]:
	# InternLMFlashAttention2 attention does not support output_attentions
	bsz, q_len, _ = hidden_states.size()

	query_states = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
	key_states = self.k_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
	value_states = self.v_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)

	if past_key_value is not None:
	# reuse k, v, self_attention
	key_states = torch.cat([past_key_value[0], key_states], dim=2)
	value_states = torch.cat([past_key_value[1], value_states], dim=2)

	past_key_value = (key_states, value_states) if use_cache else None

	kv_seq_len = key_states.shape[-2]
	cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
	query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin, position_ids)

	query_states = query_states.transpose(1, 2)
	key_states = key_states.transpose(1, 2)
	value_states = value_states.transpose(1, 2)

	attn_output = self._flash_attention_forward(
	query_states, key_states, value_states, attention_mask, q_len
	)
	attn_output = attn_output.reshape(bsz, q_len, self.hidden_size).contiguous()
	attn_output = self.o_proj(attn_output)

	if not output_attentions:
	attn_weights = None

	return attn_output, attn_weights, past_key_value

	def _flash_attention_forward(
	self, query_states, key_states, value_states, attention_mask, query_length, dropout=0.0, softmax_scale=None
	):
	"""
	Calls the forward method of Flash Attention - if the input hidden states contain at least one padding token
	first unpad the input, then computes the attention scores and pad the final attention scores.

	Args:
	query_states (`torch.Tensor`):
	Input query states to be passed to Flash Attention API
	key_states (`torch.Tensor`):
	Input key states to be passed to Flash Attention API
	value_states (`torch.Tensor`):
	Input value states to be passed to Flash Attention API
	attention_mask (`torch.Tensor`):
	The padding mask - corresponds to a tensor of size `(batch_size, seq_len)` where 0 stands for the
	position of padding tokens and 1 for the position of non-padding tokens.
	dropout (`int`, optional):
	Attention dropout
	softmax_scale (`float`, optional):
	The scaling of QK^T before applying softmax. Default to 1 / sqrt(head_dim)
	"""
	# Contains at least one padding token in the sequence
	causal = self.is_causal and query_length != 1
	if attention_mask is not None:
	batch_size = query_states.shape[0]
	query_states, key_states, value_states, indices_q, cu_seq_lens, max_seq_lens = self._unpad_input(
	query_states, key_states, value_states, attention_mask, query_length
	)

	cu_seqlens_q, cu_seqlens_k = cu_seq_lens
	max_seqlen_in_batch_q, max_seqlen_in_batch_k = max_seq_lens

	attn_output_unpad = flash_attn_varlen_func(
	query_states,
	key_states,
	value_states,
	cu_seqlens_q=cu_seqlens_q,
	cu_seqlens_k=cu_seqlens_k,
	max_seqlen_q=max_seqlen_in_batch_q,
	max_seqlen_k=max_seqlen_in_batch_k,
	dropout_p=dropout,
	softmax_scale=softmax_scale,
	causal=causal,
	)

	attn_output = pad_input(attn_output_unpad, indices_q, batch_size, query_length)
	else:
	attn_output = flash_attn_func(
	query_states, key_states, value_states, dropout, softmax_scale=softmax_scale, causal=causal
	)

	return attn_output

	def _unpad_input(self, query_layer, key_layer, value_layer, attention_mask, query_length):
	indices_k, cu_seqlens_k, max_seqlen_in_batch_k = _get_unpad_data(attention_mask)
	batch_size, kv_seq_len, num_heads, head_dim = key_layer.shape

	key_layer = index_first_axis(
	key_layer.reshape(batch_size * kv_seq_len, num_heads, head_dim), indices_k
	)
	value_layer = index_first_axis(
	value_layer.reshape(batch_size * kv_seq_len, num_heads, head_dim), indices_k
	)

	if query_length == kv_seq_len:
	query_layer = index_first_axis(
	query_layer.reshape(batch_size * kv_seq_len, self.num_heads, head_dim), indices_k
	)
	cu_seqlens_q = cu_seqlens_k
	max_seqlen_in_batch_q = max_seqlen_in_batch_k
	indices_q = indices_k
	elif query_length == 1:
	max_seqlen_in_batch_q = 1
	cu_seqlens_q = torch.arange(
	batch_size + 1, dtype=torch.int32, device=query_layer.device
	) # There is a memcpy here, that is very bad.
	indices_q = cu_seqlens_q[:-1]
	query_layer = query_layer.squeeze(1)
	else:
	# The -q_len: slice assumes left padding.
	attention_mask = attention_mask[:, -query_length:]
	query_layer, indices_q, cu_seqlens_q, max_seqlen_in_batch_q = unpad_input(query_layer, attention_mask)

	return (
	query_layer,
	key_layer,
	value_layer,
	indices_q.to(torch.int64),
	(cu_seqlens_q, cu_seqlens_k),
	(max_seqlen_in_batch_q, max_seqlen_in_batch_k),
	)

	INTERNLM_ATTENTION_CLASSES = {
	"eager": InternLMAttention,
	"flash_attention_2": InternLMFlashAttention2,
	}

	# Copied from transformers.models.llama.modeling_llama.LlamaDecoderLayer with Llama->InternLM
	class InternLMDecoderLayer(nn.Module):
	def __init__(self, config: InternLMConfig):
	super().__init__()
	self.hidden_size = config.hidden_size

	self.self_attn = INTERNLM_ATTENTION_CLASSES[config.attn_implementation](config=config)

	self.mlp = InternLMMLP(
	hidden_size=self.hidden_size,
	intermediate_size=config.intermediate_size,
	hidden_act=config.hidden_act,
	)
	self.input_layernorm = InternLMRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
	self.post_attention_layernorm = InternLMRMSNorm(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,
	use_cache: Optional[bool] = False,
	) -> 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, 1, tgt_len, src_len)` where padding elements are indicated by very large negative 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.
	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 = self.mlp(hidden_states)
	hidden_states = residual + hidden_states

	outputs = (hidden_states,)

	if output_attentions:
	outputs += (self_attn_weights,)

	if use_cache:
	outputs += (present_key_value,)

	return outputs


	INTERNLM_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 ([`InternLMConfig`]):
	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.
	"""


	# Copied from transformers.models.llama.modeling_llama.LlamaPretrainedModel with Llama->InternLM
	@add_start_docstrings(
	"The bare InternLM Model outputting raw hidden-states without any specific head on top.",
	INTERNLM_START_DOCSTRING,
	)
	class InternLMPreTrainedModel(PreTrainedModel):
	config_class = InternLMConfig
	base_model_prefix = "model"
	supports_gradient_checkpointing = True
	_no_split_modules = ["InternLMDecoderLayer"]
	_keys_to_ignore_on_load_unexpected = [r"decoder\.version"]

	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_()

	def _set_gradient_checkpointing(self, module, value=False):
	if isinstance(module, InternLMModel):
	module.gradient_checkpointing = value


	INTERNLM_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.
	"""


	# Copied from transformers.models.llama.modeling_llama.LlamaModel with Llama->InternLM
	@add_start_docstrings(
	"The bare InternLM Model outputting raw hidden-states without any specific head on top.",
	INTERNLM_START_DOCSTRING,
	)
	class InternLMModel(InternLMPreTrainedModel):
	"""
	Transformer decoder consisting of config.num_hidden_layers layers. Each layer is a [`InternLMDecoderLayer`]
	Args:
	config: InternLMConfig
	"""

	_auto_class = "AutoModel"

	def __init__(self, config: InternLMConfig):
	super().__init__(config)
	self.padding_idx = config.pad_token_id
	self.vocab_size = config.vocab_size
	self.config = config

	self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)

	self.layers = nn.ModuleList([InternLMDecoderLayer(config) for _ in range(config.num_hidden_layers)])
	self.norm = InternLMRMSNorm(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,
	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
	)

	return combined_attention_mask

	@add_start_docstrings_to_model_forward(INTERNLM_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,
	use_cache: Optional[bool] = None,
	output_attentions: Optional[bool] = None,
	output_hidden_states: Optional[bool] = None,
	return_dict: Optional[bool] = None,
	) -> Union[Tuple, BaseModelOutputWithPast]:
	output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
	output_hidden_states = (
	output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
	)
	use_cache = use_cache if use_cache is not None else self.config.use_cache

	return_dict = return_dict if return_dict is not None else self.config.use_return_dict

	if self.config.attn_implementation == "flash_attention_2":
	_import_flash_attn()

	# 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)
	if self.config.attn_implementation == "flash_attention_2":
	attention_mask = attention_mask if (attention_mask is not None and 0 in attention_mask) else None
	else:
	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 output_hidden_states else None
	all_self_attns = () if output_attentions else None
	next_decoder_cache = () if use_cache else None

	for idx, decoder_layer in enumerate(self.layers):
	if output_hidden_states:
	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, 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,
	use_cache=use_cache,
	)

	hidden_states = layer_outputs[0]

	if use_cache:
	next_decoder_cache += (layer_outputs[2 if output_attentions else 1],)

	if output_attentions:
	all_self_attns += (layer_outputs[1],)

	hidden_states = self.norm(hidden_states)

	# add hidden states from the last decoder layer
	if output_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] 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,
	)


	# Copied from transformers.models.llama.modeling_llama.LlamaForCausalLM with Llama->InternLM
	class InternLMForCausalLM(InternLMPreTrainedModel):
	_auto_class = "AutoModelForCausalLM"

	def __init__(self, config):
	super().__init__(config)
	self.model = InternLMModel(config)

	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(INTERNLM_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[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, 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]`.
	Returns:

	Example:
	```python
	>>> from transformers import AutoTokenizer, InternLMForCausalLM
	>>> model = InternLMForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
	>>> tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
	>>> prompt = "Hey, are you consciours? 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 consciours? Can you talk to me?\nI'm not consciours, 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,
	)

	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)

	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, **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) for past_state in layer_past),)
	return reordered_past

	def build_inputs(self, tokenizer, query: str, history: List[Tuple[str, str]] = [], meta_instruction=""):
	if tokenizer.add_bos_token:
	prompt = ""
	else:
	prompt = tokenizer.bos_token
	if meta_instruction:
	prompt += f"""<\|System\|>:{meta_instruction}\n"""
	for record in history:
	prompt += f"""<\|User\|>:{record[0]}\n<\|Bot\|>:{record[1]}<eoa>\n"""
	prompt += f"""<\|User\|>:{query}\n<\|Bot\|>:"""
	return tokenizer([prompt], return_tensors="pt")

	@torch.no_grad()
	def chat(
	self,
	tokenizer,
	query: str,
	history: List[Tuple[str, str]] = [],
	streamer: Optional[BaseStreamer] = None,
	max_new_tokens: int = 1024,
	do_sample: bool = True,
	temperature: float = 0.8,
	top_p: float = 0.8,
	meta_instruction: str = "You are an AI assistant whose name is InternLM (书生·浦语).\n"
	"- InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.\n"
	"- InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.",
	**kwargs,
	):
	inputs = self.build_inputs(tokenizer, query, history, meta_instruction)
	inputs = {k: v.to(self.device) for k, v in inputs.items() if torch.is_tensor(v)}
	outputs = self.generate(
	**inputs,
	streamer=streamer,
	max_new_tokens=max_new_tokens,
	do_sample=do_sample,
	temperature=temperature,
	top_p=top_p,
	**kwargs,
	)
	outputs = outputs[0].cpu().tolist()[len(inputs["input_ids"][0]) :]
	response = tokenizer.decode(outputs, skip_special_tokens=True)
	response = response.split("<eoa>")[0]
	history = history + [(query, response)]
	return response, history

	@torch.no_grad()
	def stream_chat(
	self,
	tokenizer,
	query: str,
	history: List[Tuple[str, str]] = [],
	max_new_tokens: int = 1024,
	do_sample: bool = True,
	temperature: float = 0.8,
	top_p: float = 0.8,
	**kwargs,
	):
	"""
	Return a generator in format: (response, history)
	Eg.
	('你好，有什么可以帮助您的吗', [('你好', '你好，有什么可以帮助您的吗')])
	('你好，有什么可以帮助您的吗？', [('你好', '你好，有什么可以帮助您的吗？')])
	"""
	if BaseStreamer is None:
	raise ModuleNotFoundError(
	"The version of `transformers` is too low. Please make sure "
	"that you have installed `transformers>=4.28.0`."
	)

	response_queue = queue.Queue(maxsize=20)

	class ChatStreamer(BaseStreamer):
	def __init__(self, tokenizer) -> None:
	super().__init__()
	self.tokenizer = tokenizer
	self.queue = response_queue
	self.query = query
	self.history = history
	self.response = ""
	self.cache = []
	self.received_inputs = False
	self.queue.put((self.response, history + [(self.query, self.response)]))

	def put(self, value):
	if len(value.shape) > 1 and value.shape[0] > 1:
	raise ValueError("ChatStreamer only supports batch size 1")
	elif len(value.shape) > 1:
	value = value[0]

	if not self.received_inputs:
	# The first received value is input_ids, ignore here
	self.received_inputs = True
	return

	self.cache.extend(value.tolist())
	token = self.tokenizer.decode(self.cache, skip_special_tokens=True)
	if "�" in token and len(token) <= 5:
	return
	if token.strip() != "<eoa>":
	self.response = self.response + token
	history = self.history + [(self.query, self.response)]
	self.queue.put((self.response, history))
	self.cache = []
	else:
	self.end()

	def end(self):
	self.queue.put(None)

	def stream_producer():
	return self.chat(
	tokenizer=tokenizer,
	query=query,
	streamer=ChatStreamer(tokenizer=tokenizer),
	history=history,
	max_new_tokens=max_new_tokens,
	do_sample=do_sample,
	temperature=temperature,
	top_p=top_p,
	**kwargs,
	)

	def consumer():
	producer = threading.Thread(target=stream_producer)
	producer.start()
	while True:
	res = response_queue.get()
	if res is None:
	return
	yield res

	return consumer()


	@add_start_docstrings(
	"""
	The InternLM Model transformer with a sequence classification head on top (linear layer).
	[`InternLMForSequenceClassification`] 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).
	""",
	INTERNLM_START_DOCSTRING,
	)
	class InternLMForSequenceClassification(InternLMPreTrainedModel):
	_keys_to_ignore_on_load_missing = [r"lm_head.weight"]

	def __init__(self, config):
	super().__init__(config)
	self.num_labels = config.num_labels
	self.model = InternLMModel(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(INTERNLM_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,
	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,
	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,
	)