Nanbeige2-8B-Chat / modeling_nanbeige.py

Update Nanbeige1.5 8B Chat Model

144313d verified 2 months ago

No virus

40.1 kB

	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.generation.streamers import BaseStreamer
	from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, \
	SequenceClassifierOutputWithPast
	from transformers.modeling_utils import PreTrainedModel
	from transformers.utils import logging

	from .configuration_nanbeige import NanbeigeConfig

	logger = logging.get_logger(__name__)

	try:
	import flash_attn
	from flash_attn import flash_attn_func

	if int(flash_attn.__version__.split(".")[0]) >= 2 and int(flash_attn.__version__.split(".")[1]) >= 1:
	Version_ = True
	else:
	Version_ = False
	except:
	logger.warn(
	"Warning: import flash_attn fail, please install FlashAttention to get higher efficiency "
	"https://github.com/Dao-AILab/flash-attention"
	)
	Version_ = False
	flash_attn_func = None


	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)


	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)


	def find_correction_dim(num_rotations, dim, base=10000, max_position_embeddings=2048):
	return (dim * math.log(max_position_embeddings / (num_rotations * 2 * math.pi))) / (2 * math.log(base))


	def find_correction_range(low_rot, high_rot, dim, base=10000, max_position_embeddings=2048):
	low = math.floor(find_correction_dim(
	low_rot, dim, base, max_position_embeddings))
	high = math.ceil(find_correction_dim(
	high_rot, dim, base, max_position_embeddings))
	return max(low, 0), min(high, dim - 1) # Clamp values just in case


	def linear_ramp_mask(min, max, dim):
	if min == max:
	max += 0.001 # Prevent singularity

	linear_func = (torch.arange(dim, dtype=torch.float32) - min) / (max - min)
	ramp_func = torch.clamp(linear_func, 0, 1)
	return ramp_func


	def get_mscale(scale=1):
	if scale <= 1:
	return 1.0
	return 0.1 * math.log(scale) + 1.0


	class YaRNScaledRotaryEmbedding(torch.nn.Module):
	def __init__(self, dim, max_position_embeddings=4096, base=10000, scale=1, original_max_position_embeddings=4096,
	extrapolation_factor=1, attn_factor=1, beta_fast=32, beta_slow=1, finetuned=False, device=None):
	super().__init__()
	self.dim = dim
	self.max_position_embeddings = max_position_embeddings
	self.base = base
	self.scale = scale
	self.original_max_position_embeddings = original_max_position_embeddings
	self.extrapolation_factor = extrapolation_factor
	self.attn_factor = attn_factor
	self.beta_fast = beta_fast
	self.beta_slow = beta_slow

	self.yarn(device)

	# 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)
	dtype = torch.get_default_dtype()

	self.register_buffer("cos_cached", (emb.cos() * self.mscale)[None, None, :, :].to(dtype), persistent=False)
	self.register_buffer("sin_cached", (emb.sin() * self.mscale)[None, None, :, :].to(dtype), 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() * self.mscale)[None, None, :, :].to(x.dtype),
	persistent=False)
	self.register_buffer("sin_cached", (emb.sin() * self.mscale)[None, None, :, :].to(x.dtype),
	persistent=False)
	return (
	self.cos_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
	self.sin_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
	)

	def yarn(self, device):
	pos_freqs = self.base ** (torch.arange(0, self.dim, 2).float().to(device) / self.dim)
	inv_freq_extrapolation = 1.0 / pos_freqs
	inv_freq_interpolation = 1.0 / (self.scale * pos_freqs)

	low, high = find_correction_range(self.beta_fast, self.beta_slow, self.dim, self.base,
	self.original_max_position_embeddings)
	inv_freq_mask = (1 - linear_ramp_mask(low, high, self.dim // 2).float().to(
	device)) * self.extrapolation_factor # Get n-d rotational scaling corrected for extrapolation
	inv_freq = inv_freq_interpolation * (1 - inv_freq_mask) + inv_freq_extrapolation * inv_freq_mask

	self.register_buffer("inv_freq", inv_freq)
	self.mscale = float(
	get_mscale(self.scale) * self.attn_factor) # Get n-d magnitude scaling corrected for interpolation


	class RMSNorm(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):
	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


	class RotaryEmbedding(torch.nn.Module):
	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)
	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)
	emb = torch.cat((freqs, freqs), dim=-1)
	self.register_buffer("cos_cached", emb.cos()[None, None, :, :], persistent=False)
	self.register_buffer("sin_cached", emb.sin()[None, None, :, :], 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()[None, None, :, :], persistent=False)
	self.register_buffer("sin_cached", emb.sin()[None, None, :, :], persistent=False)
	return (
	self.cos_cached[:, :, :seq_len, ...].to(dtype=x.dtype),
	self.sin_cached[:, :, :seq_len, ...].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):
	# The first two dimensions of cos and sin are always 1, so we can `squeeze` them.
	cos = cos.squeeze(1).squeeze(0) # [seq_len, dim]
	sin = sin.squeeze(1).squeeze(0) # [seq_len, dim]
	cos = cos[position_ids].unsqueeze(1) # [bs, 1, seq_len, dim]
	sin = sin[position_ids].unsqueeze(1) # [bs, 1, seq_len, dim]
	q_embed = (q * cos) + (rotate_half(q) * sin)
	k_embed = (k * cos) + (rotate_half(k) * sin)
	return q_embed, k_embed


	class NanbeigeMLP(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))


	class NanbeigeAttention(nn.Module):
	"""Multi-headed attention from 'Attention Is All You Need' paper"""

	def __init__(self, config: NanbeigeConfig):
	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=False)
	self.k_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
	self.v_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
	self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)
	if self.config.yarn_scale > 1:
	self.rotary_emb = YaRNScaledRotaryEmbedding(self.head_dim, scale=self.config.yarn_scale,
	original_max_position_embeddings=self.max_position_embeddings)
	else:
	self.rotary_emb = RotaryEmbedding(self.head_dim, max_position_embeddings=self.max_position_embeddings)

	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)

	kv_seq_len = key_states.shape[-2]
	if past_key_value is not None:
	kv_seq_len += past_key_value[0].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)

	if past_key_value is not None:
	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

	if Version_ or (flash_attn_func and query_states.size() == key_states.size()):
	attn_output = flash_attn_func(query_states.transpose(1, 2), key_states.transpose(1, 2),
	value_states.transpose(1, 2), dropout_p=0.0, softmax_scale=None, causal=True)
	else:
	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


	class NanbeigeDecoderLayer(nn.Module):
	def __init__(self, config: NanbeigeConfig):
	super().__init__()
	self.hidden_size = config.hidden_size
	self.self_attn = NanbeigeAttention(config=config)
	self.mlp = NanbeigeMLP(
	hidden_size=self.hidden_size,
	intermediate_size=config.intermediate_size,
	hidden_act=config.hidden_act,
	)
	self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
	self.post_attention_layernorm = RMSNorm(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


	class NanbeigePreTrainedModel(PreTrainedModel):
	config_class = NanbeigeConfig
	base_model_prefix = "model"
	supports_gradient_checkpointing = True
	_no_split_modules = ["NanbeigeDecoderLayer"]
	_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, NanbeigeModel):
	module.gradient_checkpointing = value


	class NanbeigeModel(NanbeigePreTrainedModel):
	def __init__(self, config: NanbeigeConfig):
	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([NanbeigeDecoderLayer(config) for _ in range(config.num_hidden_layers)])
	self.norm = RMSNorm(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

	def forward(
	self,
	input_ids: torch.LongTensor = None,
	attention_mask: Optional[torch.Tensor] = None,
	position_ids: Optional[torch.LongTensor] = None,
	past_key_values: Optional[List[torch.FloatTensor]] = None,
	inputs_embeds: Optional[torch.FloatTensor] = None,
	use_cache: Optional[bool] = None,
	output_attentions: Optional[bool] = None,
	output_hidden_states: Optional[bool] = None,
	return_dict: Optional[bool] = None,
	) -> Union[Tuple, BaseModelOutputWithPast]:
	output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
	output_hidden_states = (
	output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
	)
	use_cache = use_cache if use_cache is not None else self.config.use_cache

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

	# retrieve input_ids and inputs_embeds
	if input_ids is not None and inputs_embeds is not None:
	raise ValueError("You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time")
	elif input_ids is not None:
	batch_size, seq_length = input_ids.shape
	elif inputs_embeds is not None:
	batch_size, seq_length, _ = inputs_embeds.shape
	else:
	raise ValueError("You have to specify either decoder_input_ids or decoder_inputs_embeds")

	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
	else:
	past_key_values = [None for _ in range(len(self.layers))]

	if position_ids is None:
	device = input_ids.device if input_ids is not None else inputs_embeds.device
	position_ids = torch.arange(
	past_key_values_length, seq_length + past_key_values_length, dtype=torch.long, device=device
	)
	position_ids = position_ids.unsqueeze(0).view(-1, seq_length)
	else:
	position_ids = position_ids.view(-1, seq_length).long()

	if inputs_embeds is None:
	inputs_embeds = self.embed_tokens(input_ids)
	# embed positions
	if attention_mask is None:
	attention_mask = torch.ones(
	(batch_size, seq_length_with_past), dtype=torch.bool, device=inputs_embeds.device
	)
	attention_mask = self._prepare_decoder_attention_mask(
	attention_mask, (batch_size, seq_length), inputs_embeds, past_key_values_length
	)

	hidden_states = inputs_embeds

	if self.gradient_checkpointing and self.training:
	if use_cache:
	logger.warning_once(
	"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
	)
	use_cache = False

	# decoder layers
	all_hidden_states = () if output_hidden_states else None
	all_self_attns = () if output_attentions else None
	next_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.pop(0) 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_cache.append(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,)

	if not return_dict:
	return tuple(v for v in [hidden_states, next_cache, all_hidden_states, all_self_attns] if v is not None)
	return BaseModelOutputWithPast(
	last_hidden_state=hidden_states,
	past_key_values=next_cache,
	hidden_states=all_hidden_states,
	attentions=all_self_attns,
	)


	class NanbeigeForCausalLM(NanbeigePreTrainedModel):
	def __init__(self, config):
	super().__init__(config)
	self.model = NanbeigeModel(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

	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]:

	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

	@torch.no_grad()
	def chat(self,
	tokenizer,
	query: str,
	messages: List[dict] = None,
	streamer: Optional[BaseStreamer] = None,
	max_new_tokens: int = 512,
	do_sample: bool = True,
	temperature: float = 0.3,
	top_p: float = 0.9,
	**kwargs):
	if messages is None:
	messages = []
	messages = messages + [{'role': 'user', 'content': query}]
	prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
	inputs = tokenizer(prompt, add_special_tokens=False, return_tensors='pt')
	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(tokenizer.eos_token)[0]
	messages.append({'role': 'user', 'content': query})
	messages.append({'role': 'assistant', 'content': response})
	return response, messages

	@torch.no_grad()
	def stream_chat(self,
	tokenizer,
	query: str,
	messages: List[dict] = None,
	max_new_tokens: int = 1024,
	do_sample: bool = True,
	temperature: float = 0.8,
	top_p: float = 0.8,
	**kwargs):

	response_queue = queue.Queue(maxsize=20)
	if messages is None:
	messages = [{'role': 'system', 'content': NANBEIGE_SYSTEM_PROMPT}]

	class ChatStreamer(BaseStreamer):
	def __init__(self, tokenizer) -> None:
	super().__init__()
	self.tokenizer = tokenizer
	self.queue = response_queue
	self.query = query
	self.messages = messages
	self.response = ""
	self.received_inputs = False
	self.queue.put((self.response, messages + [{'role': 'user', 'content': self.query},
	{'role': 'assistant', 'content': 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

	token = self.tokenizer.decode([value[-1]], skip_special_tokens=True)
	if token.strip() != "</s>":
	self.response = self.response + token
	messages = self.messages + [{'role': 'user', 'content': self.query},
	{'role': 'assistant', 'content': self.response}]
	self.queue.put((self.response, messages))

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

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

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

	return consumer()


	class NanbeigeForSequenceClassification(NanbeigePreTrainedModel):
	_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 = NanbeigeModel(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[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,
	)