523 lines
22 KiB
Python
523 lines
22 KiB
Python
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# This file was automatically generated from src/transformers/models/phi/modular_phi.py.
|
|
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
|
# the file from the modular. If any change should be done, please apply the change to the
|
|
# modular_phi.py file directly. One of our CI enforces this.
|
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
from typing import Callable, Optional, Union
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
from ...activations import ACT2FN
|
|
from ...cache_utils import Cache, DynamicCache
|
|
from ...generation import GenerationMixin
|
|
from ...masking_utils import create_causal_mask
|
|
from ...modeling_layers import (
|
|
GenericForSequenceClassification,
|
|
GenericForTokenClassification,
|
|
GradientCheckpointingLayer,
|
|
)
|
|
from ...modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
|
|
from ...modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
|
|
from ...modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
|
|
from ...processing_utils import Unpack
|
|
from ...utils import TransformersKwargs, auto_docstring, can_return_tuple, logging
|
|
from ...utils.generic import check_model_inputs
|
|
from .configuration_phi import PhiConfig
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
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):
|
|
"""Applies Rotary Position Embedding to the query and key tensors.
|
|
|
|
Args:
|
|
q (`torch.Tensor`): The query tensor.
|
|
k (`torch.Tensor`): The key tensor.
|
|
cos (`torch.Tensor`): The cosine part of the rotary embedding.
|
|
sin (`torch.Tensor`): The sine part of the rotary embedding.
|
|
position_ids (`torch.Tensor`, *optional*):
|
|
Deprecated and unused.
|
|
unsqueeze_dim (`int`, *optional*, defaults to 1):
|
|
The 'unsqueeze_dim' argument specifies the dimension along which to unsqueeze cos[position_ids] and
|
|
sin[position_ids] so that they can be properly broadcasted to the dimensions of q and k. For example, note
|
|
that cos[position_ids] and sin[position_ids] have the shape [batch_size, seq_len, head_dim]. Then, if q and
|
|
k have the shape [batch_size, heads, seq_len, head_dim], then setting unsqueeze_dim=1 makes
|
|
cos[position_ids] and sin[position_ids] broadcastable to the shapes of q and k. Similarly, if q and k have
|
|
the shape [batch_size, seq_len, heads, head_dim], then set unsqueeze_dim=2.
|
|
Returns:
|
|
`tuple(torch.Tensor)` comprising of the query and key tensors rotated using the Rotary Position Embedding.
|
|
"""
|
|
cos = cos.unsqueeze(unsqueeze_dim)
|
|
sin = sin.unsqueeze(unsqueeze_dim)
|
|
q_embed = (q * cos) + (rotate_half(q) * sin)
|
|
k_embed = (k * cos) + (rotate_half(k) * sin)
|
|
return q_embed, k_embed
|
|
|
|
|
|
def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
|
|
"""
|
|
This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
|
|
num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
|
|
"""
|
|
batch, num_key_value_heads, slen, head_dim = hidden_states.shape
|
|
if n_rep == 1:
|
|
return hidden_states
|
|
hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim)
|
|
return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)
|
|
|
|
|
|
def eager_attention_forward(
|
|
module: nn.Module,
|
|
query: torch.Tensor,
|
|
key: torch.Tensor,
|
|
value: torch.Tensor,
|
|
attention_mask: Optional[torch.Tensor],
|
|
scaling: float,
|
|
dropout: float = 0.0,
|
|
**kwargs: Unpack[TransformersKwargs],
|
|
):
|
|
key_states = repeat_kv(key, module.num_key_value_groups)
|
|
value_states = repeat_kv(value, module.num_key_value_groups)
|
|
|
|
attn_weights = torch.matmul(query, key_states.transpose(2, 3)) * scaling
|
|
if attention_mask is not None:
|
|
causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
|
|
attn_weights = attn_weights + causal_mask
|
|
|
|
attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query.dtype)
|
|
attn_weights = nn.functional.dropout(attn_weights, p=dropout, training=module.training)
|
|
attn_output = torch.matmul(attn_weights, value_states)
|
|
attn_output = attn_output.transpose(1, 2).contiguous()
|
|
|
|
return attn_output, attn_weights
|
|
|
|
|
|
class PhiAttention(nn.Module):
|
|
"""Multi-headed attention from 'Attention Is All You Need' paper"""
|
|
|
|
def __init__(self, config: PhiConfig, layer_idx: int):
|
|
super().__init__()
|
|
self.config = config
|
|
self.layer_idx = layer_idx
|
|
self.head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads)
|
|
self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads
|
|
self.scaling = self.head_dim**-0.5
|
|
self.attention_dropout = config.attention_dropout
|
|
self.is_causal = True
|
|
self.q_proj = nn.Linear(config.hidden_size, config.num_attention_heads * self.head_dim, bias=True)
|
|
self.k_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=True)
|
|
self.v_proj = nn.Linear(config.hidden_size, config.num_key_value_heads * self.head_dim, bias=True)
|
|
self.dense = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=True)
|
|
self.rotary_ndims = int(self.head_dim * config.partial_rotary_factor)
|
|
self.qk_layernorm = config.qk_layernorm
|
|
if self.qk_layernorm:
|
|
self.q_layernorm = nn.LayerNorm(
|
|
config.hidden_size // config.num_attention_heads, eps=config.layer_norm_eps, elementwise_affine=True
|
|
)
|
|
self.k_layernorm = nn.LayerNorm(
|
|
config.hidden_size // config.num_attention_heads, eps=config.layer_norm_eps, elementwise_affine=True
|
|
)
|
|
|
|
def forward(
|
|
self,
|
|
hidden_states: torch.Tensor,
|
|
position_embeddings: tuple[torch.Tensor, torch.Tensor],
|
|
attention_mask: Optional[torch.Tensor],
|
|
past_key_value: Optional[Cache] = None,
|
|
cache_position: Optional[torch.LongTensor] = None,
|
|
**kwargs,
|
|
) -> tuple[torch.Tensor, Optional[torch.Tensor], Optional[tuple[torch.Tensor]]]:
|
|
input_shape = hidden_states.shape[:-1]
|
|
hidden_shape = (*input_shape, -1, self.head_dim)
|
|
|
|
query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
|
|
key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
|
|
value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
|
|
|
|
if self.qk_layernorm:
|
|
query_states = self.q_layernorm(query_states)
|
|
key_states = self.k_layernorm(key_states)
|
|
|
|
cos, sin = position_embeddings
|
|
# Partial rotary embedding
|
|
query_rot, query_pass = (
|
|
query_states[..., : self.rotary_ndims],
|
|
query_states[..., self.rotary_ndims :],
|
|
)
|
|
key_rot, key_pass = (
|
|
key_states[..., : self.rotary_ndims],
|
|
key_states[..., self.rotary_ndims :],
|
|
)
|
|
# [batch_size, seq_length, num_heads, head_dim // config.partial_rotary_factor]
|
|
query_rot, key_rot = apply_rotary_pos_emb(query_rot, key_rot, cos, sin)
|
|
|
|
# [batch_size, seq_length, num_heads, head_dim]
|
|
query_states = torch.cat((query_rot, query_pass), dim=-1)
|
|
key_states = torch.cat((key_rot, key_pass), dim=-1)
|
|
|
|
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)
|
|
|
|
attention_interface: Callable = eager_attention_forward
|
|
if self.config._attn_implementation != "eager":
|
|
attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
|
|
|
|
attn_output, attn_weights = attention_interface(
|
|
self,
|
|
query_states,
|
|
key_states,
|
|
value_states,
|
|
attention_mask,
|
|
dropout=0.0 if not self.training else self.attention_dropout,
|
|
scaling=self.scaling,
|
|
**kwargs,
|
|
)
|
|
|
|
attn_output = attn_output.reshape(*input_shape, -1).contiguous()
|
|
attn_output = self.dense(attn_output)
|
|
return attn_output, attn_weights
|
|
|
|
|
|
class PhiMLP(nn.Module):
|
|
def __init__(self, config):
|
|
super().__init__()
|
|
self.config = config
|
|
self.activation_fn = ACT2FN[config.hidden_act]
|
|
self.fc1 = nn.Linear(config.hidden_size, config.intermediate_size)
|
|
self.fc2 = nn.Linear(config.intermediate_size, config.hidden_size)
|
|
|
|
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
|
|
hidden_states = self.fc1(hidden_states)
|
|
hidden_states = self.activation_fn(hidden_states)
|
|
hidden_states = self.fc2(hidden_states)
|
|
return hidden_states
|
|
|
|
|
|
class PhiDecoderLayer(GradientCheckpointingLayer):
|
|
def __init__(self, config: PhiConfig, layer_idx: int):
|
|
super().__init__()
|
|
self.self_attn = PhiAttention(config, layer_idx=layer_idx)
|
|
self.mlp = PhiMLP(config)
|
|
self.input_layernorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
|
|
self.resid_dropout = nn.Dropout(config.resid_pdrop)
|
|
|
|
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,
|
|
cache_position: Optional[torch.LongTensor] = None,
|
|
position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None, # necessary, but kept here for BC
|
|
**kwargs,
|
|
) -> tuple[torch.FloatTensor, Optional[tuple[torch.FloatTensor, torch.FloatTensor]]]:
|
|
residual = hidden_states
|
|
|
|
hidden_states = self.input_layernorm(hidden_states)
|
|
|
|
# Self Attention
|
|
attn_outputs, self_attn_weights = self.self_attn(
|
|
hidden_states=hidden_states,
|
|
attention_mask=attention_mask,
|
|
position_ids=position_ids,
|
|
past_key_value=past_key_value,
|
|
output_attentions=output_attentions,
|
|
use_cache=use_cache,
|
|
cache_position=cache_position,
|
|
position_embeddings=position_embeddings,
|
|
**kwargs,
|
|
)
|
|
attn_outputs = self.resid_dropout(attn_outputs)
|
|
|
|
feed_forward_hidden_states = self.resid_dropout(self.mlp(hidden_states))
|
|
hidden_states = attn_outputs + feed_forward_hidden_states + residual
|
|
outputs = (hidden_states,)
|
|
|
|
if output_attentions:
|
|
outputs += (self_attn_weights,)
|
|
|
|
return outputs
|
|
|
|
|
|
class PhiRotaryEmbedding(nn.Module):
|
|
def __init__(self, config: PhiConfig, device=None):
|
|
super().__init__()
|
|
# BC: "rope_type" was originally "type"
|
|
if hasattr(config, "rope_scaling") and isinstance(config.rope_scaling, dict):
|
|
self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
|
|
else:
|
|
self.rope_type = "default"
|
|
self.max_seq_len_cached = config.max_position_embeddings
|
|
self.original_max_seq_len = config.max_position_embeddings
|
|
|
|
self.config = config
|
|
self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
|
|
|
|
inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
|
|
self.register_buffer("inv_freq", inv_freq, persistent=False)
|
|
self.original_inv_freq = self.inv_freq
|
|
|
|
@torch.no_grad()
|
|
@dynamic_rope_update # power user: used with advanced RoPE types (e.g. dynamic rope)
|
|
def forward(self, x, position_ids):
|
|
inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device)
|
|
position_ids_expanded = position_ids[:, None, :].float()
|
|
|
|
device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu"
|
|
with torch.autocast(device_type=device_type, enabled=False): # Force float32
|
|
freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
|
|
emb = torch.cat((freqs, freqs), dim=-1)
|
|
cos = emb.cos() * self.attention_scaling
|
|
sin = emb.sin() * self.attention_scaling
|
|
|
|
return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)
|
|
|
|
|
|
@auto_docstring
|
|
class PhiPreTrainedModel(PreTrainedModel):
|
|
config: PhiConfig
|
|
base_model_prefix = "model"
|
|
supports_gradient_checkpointing = True
|
|
_no_split_modules = ["PhiDecoderLayer"]
|
|
_skip_keys_device_placement = ["past_key_values"]
|
|
_supports_flash_attn = True
|
|
_supports_sdpa = True
|
|
_supports_flex_attn = True
|
|
|
|
_can_compile_fullgraph = True
|
|
_supports_attention_backend = True
|
|
_can_record_outputs = {
|
|
"hidden_states": PhiDecoderLayer,
|
|
"attentions": PhiAttention,
|
|
}
|
|
|
|
|
|
@auto_docstring
|
|
class PhiModel(PhiPreTrainedModel):
|
|
def __init__(self, config: PhiConfig):
|
|
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(
|
|
[PhiDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
|
|
)
|
|
self.rotary_emb = PhiRotaryEmbedding(config=config)
|
|
self.gradient_checkpointing = False
|
|
self.embed_dropout = nn.Dropout(config.embd_pdrop)
|
|
self.final_layernorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
|
|
|
|
# Initialize weights and apply final processing
|
|
self.post_init()
|
|
|
|
@check_model_inputs
|
|
@auto_docstring
|
|
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[Cache] = None,
|
|
inputs_embeds: Optional[torch.FloatTensor] = None,
|
|
use_cache: Optional[bool] = None,
|
|
output_attentions: Optional[bool] = None,
|
|
output_hidden_states: Optional[bool] = None,
|
|
cache_position: Optional[torch.LongTensor] = None,
|
|
**kwargs: Unpack[TransformersKwargs],
|
|
) -> 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
|
|
|
|
if (input_ids is None) ^ (inputs_embeds is not None):
|
|
raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
|
|
|
|
if self.gradient_checkpointing and self.training and use_cache:
|
|
logger.warning_once(
|
|
"`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`."
|
|
)
|
|
use_cache = False
|
|
|
|
if inputs_embeds is None:
|
|
inputs_embeds = self.embed_tokens(input_ids)
|
|
|
|
if use_cache and past_key_values is None:
|
|
past_key_values = DynamicCache()
|
|
|
|
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 = create_causal_mask(
|
|
config=self.config,
|
|
input_embeds=inputs_embeds,
|
|
attention_mask=attention_mask,
|
|
cache_position=cache_position,
|
|
past_key_values=past_key_values,
|
|
position_ids=position_ids,
|
|
)
|
|
|
|
inputs_embeds = self.embed_dropout(inputs_embeds) # diff with Llama
|
|
hidden_states = inputs_embeds
|
|
|
|
# create position embeddings to be shared across the decoder layers
|
|
position_embeddings = self.rotary_emb(hidden_states, position_ids)
|
|
|
|
# decoder layers
|
|
all_hidden_states = () if output_hidden_states else None
|
|
all_self_attns = () if output_attentions else None
|
|
|
|
for decoder_layer in self.layers[: self.config.num_hidden_layers]:
|
|
if output_hidden_states:
|
|
all_hidden_states += (hidden_states,)
|
|
|
|
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,
|
|
**kwargs,
|
|
)
|
|
|
|
hidden_states = layer_outputs[0]
|
|
|
|
if output_attentions:
|
|
all_self_attns += (layer_outputs[1],)
|
|
|
|
hidden_states = self.final_layernorm(hidden_states) # diff with Llama
|
|
|
|
# add hidden states from the last decoder layer
|
|
if output_hidden_states:
|
|
all_hidden_states += (hidden_states,)
|
|
|
|
return BaseModelOutputWithPast(
|
|
last_hidden_state=hidden_states,
|
|
past_key_values=past_key_values if use_cache else None,
|
|
hidden_states=all_hidden_states,
|
|
attentions=all_self_attns,
|
|
)
|
|
|
|
|
|
@auto_docstring
|
|
class PhiForCausalLM(PhiPreTrainedModel, GenerationMixin):
|
|
_tied_weights_keys = ["lm_head.weight"]
|
|
_tp_plan = {"lm_head": "colwise_rep"}
|
|
_pp_plan = {"lm_head": (["hidden_states"], ["logits"])}
|
|
|
|
def __init__(self, config):
|
|
super().__init__(config)
|
|
self.model = PhiModel(config)
|
|
self.vocab_size = config.vocab_size
|
|
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=True)
|
|
|
|
# Initialize weights and apply final processing
|
|
self.post_init()
|
|
|
|
def set_decoder(self, decoder):
|
|
self.model = decoder
|
|
|
|
def get_decoder(self):
|
|
return self.model
|
|
|
|
@can_return_tuple
|
|
@auto_docstring
|
|
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[Cache] = None,
|
|
inputs_embeds: Optional[torch.FloatTensor] = None,
|
|
labels: Optional[torch.LongTensor] = None,
|
|
use_cache: Optional[bool] = None,
|
|
cache_position: Optional[torch.LongTensor] = None,
|
|
logits_to_keep: Union[int, torch.Tensor] = 0,
|
|
**kwargs: Unpack[TransformersKwargs],
|
|
) -> CausalLMOutputWithPast:
|
|
r"""
|
|
Example:
|
|
|
|
```python
|
|
>>> from transformers import AutoTokenizer, PhiForCausalLM
|
|
|
|
>>> model = PhiForCausalLM.from_pretrained("meta-phi/Phi-2-7b-hf")
|
|
>>> tokenizer = AutoTokenizer.from_pretrained("meta-phi/Phi-2-7b-hf")
|
|
|
|
>>> prompt = "Hey, are you conscious? Can you talk to me?"
|
|
>>> inputs = tokenizer(prompt, return_tensors="pt")
|
|
|
|
>>> # Generate
|
|
>>> generate_ids = model.generate(inputs.input_ids, max_length=30)
|
|
>>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
|
"Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
|
|
```"""
|
|
outputs: BaseModelOutputWithPast = 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,
|
|
cache_position=cache_position,
|
|
**kwargs,
|
|
)
|
|
|
|
hidden_states = outputs.last_hidden_state
|
|
# Only compute necessary logits, and do not upcast them to float if we are not computing the loss
|
|
slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
|
|
logits = self.lm_head(hidden_states[:, slice_indices, :])
|
|
|
|
loss = None
|
|
if labels is not None:
|
|
loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size, **kwargs)
|
|
|
|
return CausalLMOutputWithPast(
|
|
loss=loss,
|
|
logits=logits,
|
|
past_key_values=outputs.past_key_values,
|
|
hidden_states=outputs.hidden_states,
|
|
attentions=outputs.attentions,
|
|
)
|
|
|
|
|
|
class PhiForSequenceClassification(GenericForSequenceClassification, PhiPreTrainedModel):
|
|
pass
|
|
|
|
|
|
class PhiForTokenClassification(GenericForTokenClassification, PhiPreTrainedModel):
|
|
pass
|
|
|
|
|
|
__all__ = [
|
|
"PhiPreTrainedModel",
|
|
"PhiModel",
|
|
"PhiForCausalLM",
|
|
"PhiForSequenceClassification",
|
|
"PhiForTokenClassification",
|
|
]
|