Qwen系列模型架构解析
Qwen
Qwen-72B模型
| Hyperparameter | Value |
|---|---|
| n_layers | 80 |
| n_heads | 64 |
| d_model | 8192 |
| vocab_size | 151851 |
| sequence_length | 32768 |
Qwen-VL
LLM Backbone：Qwen-7B Base 模型
Visual Encoder：ViT架构使用OpenCLIP预训练好的ViT-bigG模型（经过2B的训练数据训出来的ViT模型）。
VIT
标准的ViT实现输入图片先被调整成长宽比1:1的正方形， 再分割成固定大小的patch块。（分辨率和pathch的size都是固定的）
卷积操作=(输入长度+2*padding-卷积核大小)/步长+1
Patch Embedding：使用卷积核大小为16×16，步长(stride)为16，卷积核个数为768，卷积后再展平，size变化为：[224, 224, 3] -> [14, 14, 768] -> [196, 768]。
+[cls]+使用可学习的绝对位置编码
Image预处理：随机裁剪输入图像并将裁剪后的图像调整为224*224，以一定概率水平翻转，再转化为Tensor格式进行标准化处理。
Qwen2
configuration_qwen2.py
# Default tensor parallel plan for base model `Qwen2`
base_model_tp_plan = {
"layers.*.self_attn.q_proj": "colwise",
"layers.*.self_attn.k_proj": "colwise",
"layers.*.self_attn.v_proj": "colwise",
"layers.*.self_attn.o_proj": "rowwise",
"layers.*.mlp.gate_proj": "colwise",
"layers.*.mlp.up_proj": "colwise",
"layers.*.mlp.down_proj": "rowwise",
}
base_model_pp_plan = {
"embed_tokens": (["input_ids"], ["inputs_embeds"]),
"layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
"norm": (["hidden_states"], ["hidden_states"]),
}
张量并行TP：将模型权重矩阵拆分到多个GPUGPU上，"colwise"按列拆分，"rowwise"按行拆分。
流水线管道并行PP：将模型的不同层分配到不同GPU上，GPU0将input_ids输出为inputs_embeds传给下一个GPU，GPU1输入[“hidden_states”, “attention_mask”]输出[“hidden_states”]，以此类推。
modular_qwen2.py
class Qwen2MLP(LlamaMLP):
def __init__(self, config):
super().__init__(config)
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)
class LlamaMLP(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=config.mlp_bias)
self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=config.mlp_bias)
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
常规MLP代码 pass
class Qwen2Attention(LlamaAttention):
def __init__(self, config: Qwen2Config, layer_idx: int):
super().__init__(config, layer_idx)
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.o_proj = nn.Linear(config.num_attention_heads * self.head_dim, config.hidden_size, bias=False)
self.sliding_window = config.sliding_window if config.layer_types[layer_idx] == "sliding_attention" else None
@deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
def forward(
self,
hidden_states: torch.Tensor,
position_embeddings: tuple[torch.Tensor, torch.Tensor],
attention_mask: Optional[torch.Tensor],
past_key_values: Optional[Cache] = None,
cache_position: Optional[torch.LongTensor] = None,
**kwargs: Unpack[FlashAttentionKwargs],
) -> tuple[torch.Tensor, Optional[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
query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
if past_key_values 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_values.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, # main diff with Llama
**kwargs,
)
attn_output = attn_output.reshape(*input_shape, -1).contiguous()
attn_output = self.o_proj(attn_output)
return attn_output, attn_weights
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):
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
class LlamaAttention(nn.Module):
"""Multi-headed attention from 'Attention Is All You Need' paper"""
def __init__(self, config: LlamaConfig, 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=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
)
@deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
def forward(
self,
hidden_states: torch.Tensor,
position_embeddings: tuple[torch.Tensor, torch.Tensor],
attention_mask: Optional[torch.Tensor],
past_key_values: Optional[Cache] = None,
cache_position: Optional[torch.LongTensor] = None,
**kwargs: Unpack[TransformersKwargs],
) -> tuple[torch.Tensor, 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
query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
if past_key_values 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_values.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.o_proj(attn_output)
return attn_output, attn_weights
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 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)
这里提到sliding_window，具体滑动窗口计算注意力的实现代码没找到，但应该是仅计算其前后sliding_window//2范围内的注意力分数（超出窗口的位置被掩码屏蔽）。Qwen2应该就是对query和key加上rope位置编码使用滑动窗口的MHA。
class Qwen2RMSNorm(nn.Module):
def __init__(self, hidden_size, eps: float = 1e-6) -> None:
"""
Qwen2RMSNorm is equivalent to T5LayerNorm
"""
super().__init__()
self.weight = nn.Parameter(torch.ones(hidden_size))
self.variance_epsilon = eps
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
input_dtype = hidden_states.dtype
hidden_states = hidden_states.to(torch.float32)
variance = hidden_states.pow(2).mean(-1, keepdim=True)
hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
return self.weight * hidden_states.to(input_dtype)
def extra_repr(self):
return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"
常规RMSNorm
class Qwen2Model(MistralModel):
def __init__(self, config: Qwen2Config):
super().__init__(config)
self.has_sliding_layers = "sliding_attention" in self.config.layer_types
@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:
past_key_values = DynamicCache(config=self.config)
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)
# It may already have been prepared by e.g. `generate`
if not isinstance(causal_mask_mapping := attention_mask, dict):
# Prepare mask arguments
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,
}
# Create the masks
causal_mask_mapping = {
"full_attention": create_causal_mask(**mask_kwargs),
}
# The sliding window alternating layers are not always activated depending on the config
if self.has_sliding_layers:
causal_mask_mapping["sliding_attention"] = create_sliding_window_causal_mask(**mask_kwargs)
hidden_states = inputs_embeds
# create position embeddings to be shared across the decoder layers
position_embeddings = self.rotary_emb(hidden_states, position_ids)
for decoder_layer in self.layers[: self.config.num_hidden_layers]:
hidden_states = decoder_layer(
hidden_states,
attention_mask=causal_mask_mapping[decoder_layer.attention_type],
position_ids=position_ids,
past_key_values=past_key_values,
use_cache=use_cache,
cache_position=cache_position,
position_embeddings=position_embeddings,
**kwargs,
)
hidden_states = self.norm(hidden_states)
return BaseModelOutputWithPast(
last_hidden_state=hidden_states,
past_key_values=past_key_values if use_cache else None,
)
class MistralModel(MistralPreTrainedModel):
def __init__(self, config: MistralConfig):
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(
[MistralDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
)
self.norm = MistralRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
self.rotary_emb = MistralRotaryEmbedding(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:
past_key_values = DynamicCache(config=self.config)
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)
mask_function = create_causal_mask if self.config.sliding_window is None else create_sliding_window_causal_mask
causal_mask = mask_function(
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,
)
hidden_states = inputs_embeds
position_embeddings = self.rotary_emb(hidden_states, position_ids)
for decoder_layer in self.layers[: self.config.num_hidden_layers]:
hidden_states = decoder_layer(
hidden_states,
attention_mask=causal_mask,
position_ids=position_ids,
past_key_values=past_key_values,
use_cache=use_cache,
cache_position=cache_position,
position_embeddings=position_embeddings,
**kwargs,
)
hidden_states = self.norm(hidden_states)
return BaseModelOutputWithPast(
last_hidden_state=hidden_states,
past_key_values=past_key_values if use_cache else None,
)
class MistralDecoderLayer(GradientCheckpointingLayer):
def __init__(self, config: MistralConfig, layer_idx: int):
super().__init__()
self.hidden_size = config.hidden_size
self.self_attn = MistralAttention(config=config, layer_idx=layer_idx)
self.mlp = MistralMLP(config)
self.input_layernorm = MistralRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
self.post_attention_layernorm = MistralRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
@deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
def forward(
self,
hidden_states: torch.Tensor,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[Cache] = None,
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: Unpack[TransformersKwargs],
) -> torch.Tensor:
residual = hidden_states
hidden_states = self.input_layernorm(hidden_states)
# Self Attention
hidden_states, _ = self.self_attn(
hidden_states=hidden_states,
attention_mask=attention_mask,
position_ids=position_ids,
past_key_values=past_key_values,
use_cache=use_cache,
cache_position=cache_position,
position_embeddings=position_embeddings,
**kwargs,
)
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
return hidden_states
Qwen2模型架构，
补一下Mistral 7B模型好像是第一个使用Sliding Window Attention的，
Qwen2.5-VL
Qwen3
modular_qwen3_moe.py
class Qwen3MoeSparseMoeBlock(nn.Module):
def __init__(self, config):
super().__init__()
self.num_experts = config.num_experts
self.top_k = config.num_experts_per_tok
self.norm_topk_prob = config.norm_topk_prob
# gating
self.gate = nn.Linear(config.hidden_size, config.num_experts, bias=False)
self.experts = nn.ModuleList(
[Qwen3MoeMLP(config, intermediate_size=config.moe_intermediate_size) for _ in range(self.num_experts)]
)
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
""" """
batch_size, sequence_length, hidden_dim = hidden_states.shape
hidden_states = hidden_states.view(-1, hidden_dim)
# router_logits: (batch * sequence_length, n_experts)
router_logits = self.gate(hidden_states)
routing_weights = F.softmax(router_logits, dim=1, dtype=torch.float)
routing_weights, selected_experts = torch.topk(routing_weights, self.top_k, dim=-1)
if self.norm_topk_prob: # only diff with mixtral sparse moe block!
routing_weights /= routing_weights.sum(dim=-1, keepdim=True)
# we cast back to the input dtype
routing_weights = routing_weights.to(hidden_states.dtype)
final_hidden_states = torch.zeros(
(batch_size * sequence_length, hidden_dim), dtype=hidden_states.dtype, device=hidden_states.device
)
# One hot encode the selected experts to create an expert mask
# this will be used to easily index which expert is going to be sollicitated
expert_mask = torch.nn.functional.one_hot(selected_experts, num_classes=self.num_experts).permute(2, 1, 0)
# Loop over all available experts in the model and perform the computation on each expert
expert_hit = torch.greater(expert_mask.sum(dim=(-1, -2)), 0).nonzero()
for expert_idx in expert_hit:
expert_layer = self.experts[expert_idx]
idx, top_x = torch.where(expert_mask[expert_idx].squeeze(0))
# Index the correct hidden states and compute the expert hidden state for
# the current expert. We need to make sure to multiply the output hidden
# states by `routing_weights` on the corresponding tokens (top-1 and top-2)
current_state = hidden_states[None, top_x].reshape(-1, hidden_dim)
current_hidden_states = expert_layer(current_state) * routing_weights[top_x, idx, None]
# However `index_add_` only support torch tensors for indexing so we'll use
# the `top_x` tensor here.
final_hidden_states.index_add_(0, top_x, current_hidden_states.to(hidden_states.dtype))
final_hidden_states = final_hidden_states.reshape(batch_size, sequence_length, hidden_dim)
return final_hidden_states, router_logits
Qwen3-VL
模型架构
Transformer架构
llama架构
llama2架构
Qwen3架构
扫一扫
1114
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
