team-10/venv/Lib/site-packages/transformers/models/cohere2/modeling_cohere2.py
2025-08-02 02:00:33 +02:00

516 lines
23 KiB
Python

# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# This file was automatically generated from src/transformers/models/cohere2/modular_cohere2.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_cohere2.py file directly. One of our CI enforces this.
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# coding=utf-8
# Copyright 2024 Cohere Inc. HuggingFace Inc. team. All rights reserved.
#
#
# 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.
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, create_sliding_window_causal_mask
from ...modeling_flash_attention_utils import FlashAttentionKwargs
from ...modeling_layers import 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
from ...utils.deprecation import deprecate_kwarg
from ...utils.generic import check_model_inputs
from .configuration_cohere2 import Cohere2Config
class Cohere2RotaryEmbedding(nn.Module):
def __init__(self, config: Cohere2Config, 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)
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.repeat_interleave(freqs, 2, dim=-1) # diff from Llama: we interleave() instead of cat()
cos = emb.cos() * self.attention_scaling
sin = emb.sin() * self.attention_scaling
return cos.to(dtype=x.dtype), sin.to(dtype=x.dtype)
class Cohere2LayerNorm(nn.Module):
def __init__(self, hidden_size=None, eps=1e-5, bias=False):
"""The hidden size can be a tuple or an int. The tuple is used for QKNorm to normalize across head_dim"""
super().__init__()
self.weight = nn.Parameter(torch.ones(hidden_size))
self.variance_epsilon = eps
def forward(self, hidden_states):
input_dtype = hidden_states.dtype
hidden_states = hidden_states.to(torch.float32)
mean = hidden_states.mean(-1, keepdim=True)
variance = (hidden_states - mean).pow(2).mean(-1, keepdim=True)
hidden_states = (hidden_states - mean) * torch.rsqrt(variance + self.variance_epsilon)
hidden_states = self.weight.to(torch.float32) * hidden_states
return hidden_states.to(input_dtype)
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
def rotate_half(x):
# Split and rotate. Note that this function is different from e.g. Llama.
x1 = x[..., ::2]
x2 = x[..., 1::2]
rot_x = torch.stack([-x2, x1], dim=-1).flatten(-2)
return rot_x
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.
"""
dtype = q.dtype
q = q.float()
k = k.float()
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.to(dtype=dtype), k_embed.to(dtype=dtype)
class Cohere2Attention(nn.Module):
"""Multi-headed attention from 'Attention Is All You Need' paper"""
def __init__(self, config: Cohere2Config, layer_idx: Optional[int] = None):
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.sliding_window = config.sliding_window if config.layer_types[layer_idx] == "sliding_attention" else None
self.q_proj = nn.Linear(
config.hidden_size, config.num_attention_heads * self.head_dim, bias=config.attention_bias
)
self.k_proj = nn.Linear(
config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
)
self.v_proj = nn.Linear(
config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
)
self.o_proj = nn.Linear(
config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.attention_bias
)
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: Unpack[FlashAttentionKwargs],
) -> 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)
cos, sin = position_embeddings
if self.sliding_window is not None:
query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
if past_key_value is not None:
cache_kwargs = {"sin": sin, "cos": cos, "cache_position": cache_position}
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,
sliding_window=self.sliding_window,
**kwargs,
)
attn_output = attn_output.reshape(*input_shape, -1).contiguous()
attn_output = self.o_proj(attn_output)
return attn_output, attn_weights
class Cohere2MLP(nn.Module):
def __init__(self, config):
super().__init__()
self.config = config
self.hidden_size = config.hidden_size
self.intermediate_size = config.intermediate_size
self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
self.act_fn = ACT2FN[config.hidden_act]
def forward(self, x):
down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
return down_proj
class Cohere2DecoderLayer(GradientCheckpointingLayer):
def __init__(self, config: Cohere2Config, layer_idx: int):
super().__init__()
self.hidden_size = config.hidden_size
self.self_attn = Cohere2Attention(config=config, layer_idx=layer_idx)
self.mlp = Cohere2MLP(config)
self.input_layernorm = Cohere2LayerNorm(hidden_size=(config.hidden_size), eps=config.layer_norm_eps)
self.attention_type = config.layer_types[layer_idx]
@deprecate_kwarg("last_cache_position", version="4.53.0")
def forward(
self,
hidden_states: torch.Tensor,
position_embeddings: tuple[torch.Tensor, torch.Tensor],
attention_mask: Optional[torch.Tensor] = None,
past_key_value: Optional[Cache] = None,
use_cache: Optional[bool] = False,
cache_position: Optional[torch.LongTensor] = None,
**kwargs: Unpack[FlashAttentionKwargs],
) -> tuple[torch.FloatTensor, Optional[tuple[torch.FloatTensor, torch.FloatTensor]]]:
"""
Args:
hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
attention_mask (`torch.FloatTensor`, *optional*):
attention mask of size `(batch_size, sequence_length)` if flash attention is used or `(batch_size, 1,
query_sequence_length, key_sequence_length)` if default attention is used.
past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
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`).
cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*):
Indices depicting the position of the input sequence tokens in the sequence
position_embeddings (`tuple[torch.FloatTensor, torch.FloatTensor]`, *optional*):
Tuple containing the cosine and sine positional embeddings of shape `(batch_size, seq_len, head_dim)`,
with `head_dim` being the embedding dimension of each attention head.
"""
residual = hidden_states
hidden_states = self.input_layernorm(hidden_states)
hidden_states_attention, _ = self.self_attn(
hidden_states=hidden_states,
position_embeddings=position_embeddings,
attention_mask=attention_mask,
past_key_value=past_key_value,
use_cache=use_cache,
cache_position=cache_position,
**kwargs,
)
hidden_states_mlp = self.mlp(hidden_states)
hidden_states = residual + hidden_states_attention + hidden_states_mlp
return hidden_states
@auto_docstring
class Cohere2PreTrainedModel(PreTrainedModel):
config: Cohere2Config
base_model_prefix = "model"
supports_gradient_checkpointing = True
_no_split_modules = ["Cohere2DecoderLayer"]
_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": Cohere2DecoderLayer,
"attentions": Cohere2Attention,
}
@auto_docstring
class Cohere2Model(Cohere2PreTrainedModel):
def __init__(self, config: Cohere2Config):
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(
[Cohere2DecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
)
self.norm = Cohere2LayerNorm(hidden_size=(config.hidden_size), eps=config.layer_norm_eps)
self.rotary_emb = Cohere2RotaryEmbedding(config=config)
self.gradient_checkpointing = False
# 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,
cache_position: Optional[torch.LongTensor] = None,
**kwargs: Unpack[TransformersKwargs],
) -> BaseModelOutputWithPast:
if (input_ids is None) ^ (inputs_embeds is not None):
raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
if inputs_embeds is None:
inputs_embeds = self.embed_tokens(input_ids)
if use_cache and past_key_values is None and not self.training:
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)
if not isinstance(causal_mask_mapping := attention_mask, dict):
mask_kwargs = {
"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,
}
causal_mask_mapping = {
"full_attention": create_causal_mask(**mask_kwargs),
"sliding_attention": create_sliding_window_causal_mask(**mask_kwargs),
}
hidden_states = inputs_embeds
position_embeddings = self.rotary_emb(hidden_states, position_ids)
for decoder_layer in self.layers:
hidden_states = decoder_layer(
hidden_states,
position_embeddings=position_embeddings,
attention_mask=causal_mask_mapping[decoder_layer.attention_type],
past_key_value=past_key_values,
use_cache=use_cache,
cache_position=cache_position,
**kwargs,
)
hidden_states = self.norm(hidden_states)
return BaseModelOutputWithPast(
last_hidden_state=hidden_states,
past_key_values=past_key_values,
)
@auto_docstring
class Cohere2ForCausalLM(Cohere2PreTrainedModel, 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 = Cohere2Model(config)
self.vocab_size = config.vocab_size
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
self.logit_scale = config.logit_scale
self.tie_word_embeddings = config.tie_word_embeddings
# 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[Union[Cache, list[torch.FloatTensor]]] = None,
inputs_embeds: Optional[torch.FloatTensor] = None,
labels: Optional[torch.LongTensor] = None,
use_cache: Optional[bool] = None,
output_attentions: Optional[bool] = None,
output_hidden_states: Optional[bool] = None,
cache_position: Optional[torch.LongTensor] = None,
logits_to_keep: Union[int, torch.Tensor] = 0,
**kwargs: Unpack[TransformersKwargs],
) -> CausalLMOutputWithPast:
r"""
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]`.
Example:
```python
>> from transformers import AutoTokenizer, Cohere2ForCausalLM
>> model = Cohere2ForCausalLM.from_pretrained("Cohere2ForAI/c4ai-command-r-v01")
>> tokenizer = AutoTokenizer.from_pretrained("Cohere2ForAI/c4ai-command-r-v01")
>> 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."
```"""
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
)
# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
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,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
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, :])
logits = logits * self.logit_scale # main diff from Llama
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,
)
__all__ = ["Cohere2ForCausalLM", "Cohere2Model", "Cohere2PreTrainedModel"]