Llama2 代码学习_llama 代码

准备学习llama2模型的代码

class ModelArgs:
    dim: int = 4096
    n_layers: int = 32
    n_heads: int = 32
    n_kv_heads: Optional[int] = None
    vocab_size: int = -1  # defined later by tokenizer
    multiple_of: int = 256  # make SwiGLU hidden layer size multiple of large power of 2
    ffn_dim_multiplier: Optional[float] = None
    norm_eps: float = 1e-5
 
    max_batch_size: int = 32
    max_seq_len: int = 2048

此段代码的作用是定义模型中需要用到的各种超参数，维度，层数，头数，kv头数，词典大小，ffn_dim_multiplier是隐藏维度的可选乘法因子，multiple_of是确保隐藏维度是这个值的倍数，norm_eps为标准化时防止0出现在分母上的一个极小参数，，还有批次大小，序列长度大小

class RMSNorm(torch.nn.Module):
    def __init__(self, dim: int, eps: float = 1e-6):
        super().__init__()
        self.eps = eps
        self.weight = nn.Parameter(torch.ones(dim))
 
    def _norm(self, x):
        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
 
    def forward(self, x):
        output = self._norm(x.float()).type_as(x)
        return output * self.weight

定义RMS正则化标准，eps为防止分母出现0的极小数，使用nn.Parameter创建一个可学习的参数，维度为dim，值全为1。

torch.rsqrt（）可以计算torch中逐个元素的平方根的倒数，tensor.mean(-1, keepdim=True)可以对输入张量（本函数中为最后一维）求平均。

def precompute_freqs_cis(dim: int, end: int, theta: float = 10000.0):
    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim))
    t = torch.arange(end, device=freqs.device)  # type: ignore
    freqs = torch.outer(t, freqs).float()  # type: ignore
    freqs_cis = torch.polar(torch.ones_like(freqs), freqs)  # complex64
    return freqs_cis

此段代码用于预计算频率，用于实现Rotary Positional Embedding，freqs是一个频率向量，（torch.arange(start,end,step)方法可以指定创建范围内的一维向量），torch.outer计算了一个频率矩阵，torch.polar将频率矩阵转化为复数形式，得到了预计算的频率项freqs_cis

def reshape_for_broadcast(freqs_cis: torch.Tensor, x: torch.Tensor):
    ndim = x.ndim
    assert 0 <= 1 < ndim
    assert freqs_cis.shape == (x.shape[1], x.shape[-1])
    shape = [d if i == 1 or i == ndim - 1 else 1 for i, d in enumerate(x.shape)]
    return freqs_cis.view(*shape)

调整freqs_cis张量形状与x进行广播，torch.ndim可以获取torch的维度（是几维向量），遍历x向量的第i个维度和第i个维度的大小，创建一个新形状shape，除了第二维和最后一维其余与x唯独一样，剩下的两维与freqs_cis一样，使用view方法调整freqs_cis的形状

def apply_rotary_emb(
    xq: torch.Tensor,
    xk: torch.Tensor,
    freqs_cis: torch.Tensor,
) -> Tuple[torch.Tensor, torch.Tensor]:
    xq_ = torch.view_as_complex(xq.float().reshape(*xq.shape[:-1], -1, 2))
    xk_ = torch.view_as_complex(xk.float().reshape(*xk.shape[:-1], -1, 2))
    freqs_cis = reshape_for_broadcast(freqs_cis, xq_)
    xq_out = torch.view_as_real(xq_ * freqs_cis).flatten(3)
    xk_out = torch.view_as_real(xk_ * freqs_cis).flatten(3)
    return xq_out.type_as(xq), xk_out.type_as(xk)

通过torch.view_as_complex函数将xq，xk变成复数形式，将freqs_cis广播为xq形式，将位置编码以复数相乘的方法加入xq，xk中，最后再返回实数形式

def repeat_kv(x: torch.Tensor, n_rep: int) -> torch.Tensor:
    bs, slen, n_kv_heads, head_dim = x.shape
    if n_rep == 1:
        return x
    return (
        x[:, :, :, None, :]
        .expand(bs, slen, n_kv_heads, n_rep, head_dim)
        .reshape(bs, slen, n_kv_heads * n_rep, head_dim)
    )

计算张量时，经常需要对齐张量，本函数在倒数第二维度增加一维，扩张成x*n_rep

class Attention(nn.Module):
    def __init__(self, args: ModelArgs):
        super().__init__()
        #不定义键值头的话就默认是本地注意力头的数量
        self.n_kv_heads = args.n_heads if args.n_kv_heads is None else args.n_kv_heads
        #定义模型并行大小
        model_parallel_size = fs_init.get_model_parallel_world_size()
        #本地注意力头（其实是一个显卡上分配的注意力头）
        self.n_local_heads = args.n_heads // model_parallel_size
        #键值头
        self.n_local_kv_heads = self.n_kv_heads // model_parallel_size
        #用于上一个函数中的张量对齐的数
        self.n_rep = self.n_local_heads // self.n_local_kv_heads
        self.head_dim = args.dim // args.n_heads
 
        self.wq = ColumnParallelLinear(
            args.dim,
            args.n_heads * self.head_dim,
            bias=False,
            gather_output=False,
            init_method=lambda x: x,
        )
        self.wk = ColumnParallelLinear(
            args.dim,
            self.n_kv_heads * self.head_dim,
            bias=False,
            gather_output=False,
            init_method=lambda x: x,
        )
        self.wv = ColumnParallelLinear(
            args.dim,
            self.n_kv_heads * self.head_dim,
            bias=False,
            gather_output=False,
            init_method=lambda x: x,
        )
        self.wo = RowParallelLinear(
            args.n_heads * self.head_dim,
            args.dim,
            bias=False,
            input_is_parallel=True,
            init_method=lambda x: x,
        )
 
        self.cache_k = torch.zeros(
            (
                args.max_batch_size,
                args.max_seq_len,
                self.n_local_kv_heads,
                self.head_dim,
            )
        ).cuda()
        self.cache_v = torch.zeros(
            (
                args.max_batch_size,
                args.max_seq_len,
                self.n_local_kv_heads,
                self.head_dim,
            )
        ).cuda()
 
    def forward(
        self,
        x: torch.Tensor,
        start_pos: int,
        freqs_cis: torch.Tensor,
        mask: Optional[torch.Tensor],
    ):
        bsz, seqlen, _ = x.shape
        xq, xk, xv = self.wq(x), self.wk(x), self.wv(x)
 
        xq = xq.view(bsz, seqlen, self.n_local_heads, self.head_dim)
        xk = xk.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
        xv = xv.view(bsz, seqlen, self.n_local_kv_heads, self.head_dim)
 
        xq, xk = apply_rotary_emb(xq, xk, freqs_cis=freqs_cis)
 
        self.cache_k = self.cache_k.to(xq)
        self.cache_v = self.cache_v.to(xq)
 
        self.cache_k[:bsz, start_pos : start_pos + seqlen] = xk
        self.cache_v[:bsz, start_pos : start_pos + seqlen] = xv
 
        keys = self.cache_k[:bsz, : start_pos + seqlen]
        values = self.cache_v[:bsz, : start_pos + seqlen]
 
        # repeat k/v heads if n_kv_heads < n_heads
        keys = repeat_kv(keys, self.n_rep)  # (bs, cache_len + seqlen, n_local_heads, head_dim)
        values = repeat_kv(values, self.n_rep)  # (bs, cache_len + seqlen, n_local_heads, head_dim)
 
        xq = xq.transpose(1, 2)  # (bs, n_local_heads, seqlen, head_dim)
        keys = keys.transpose(1, 2) # (bs, n_local_heads, cache_len + seqlen, head_dim)
        values = values.transpose(1, 2) # (bs, n_local_heads, cache_len + seqlen, head_dim)
        scores = torch.matmul(xq, keys.transpose(2, 3)) / math.sqrt(self.head_dim)
        if mask is not None:
            scores = scores + mask  # (bs, n_local_heads, seqlen, cache_len + seqlen)
        scores = F.softmax(scores.float(), dim=-1).type_as(xq)
        output = torch.matmul(scores, values)  # (bs, n_local_heads, seqlen, head_dim)
        output = output.transpose(1, 2).contiguous().view(bsz, seqlen, -1)
        return self.wo(output)

Attention类的定义，在init函数中将本地头和键值头根据模型并行数进行划分，定义了四个线形层wq，wk，wv，wo分别用于查询，键，值，输出。

在forward方法中，先获取x的shape，接着通过线性层计算查询，键，值（其实就是把x中的batch_size和seqlen提取出来，将x变为（bsz, seqlen, self.n_local_heads, self.head_dim）的形状），接着将键，值应用于旋转编码，放入缓存，再将k和v从缓存中取出，并对齐（此处主要是消除并行的影响），之后进行k,q,v的计算。

个人理解：这里注意力层整体的输入维度和输出维度即是x的维度(batch_size,seqlen,-1)

class FeedForward(nn.Module):
    def __init__(
        self,
        dim: int,
        hidden_dim: int,
        multiple_of: int,
        ffn_dim_multiplier: Optional[float],
    ):
        super().__init__()
        hidden_dim = int(2 * hidden_dim / 3)
        # custom dim factor multiplier
        if ffn_dim_multiplier is not None:
            hidden_dim = int(ffn_dim_multiplier * hidden_dim)
        hidden_dim = multiple_of * ((hidden_dim + multiple_of - 1) // multiple_of)
 
        self.w1 = ColumnParallelLinear(
            dim, hidden_dim, bias=False, gather_output=False, init_method=lambda x: x
        )
        self.w2 = RowParallelLinear(
            hidden_dim, dim, bias=False, input_is_parallel=True, init_method=lambda x: x
        )
        self.w3 = ColumnParallelLinear(
            dim, hidden_dim, bias=False, gather_output=False, init_method=lambda x: x
        )
 
    def forward(self, x):
        return self.w2(F.silu(self.w1(x)) * self.w3(x))

前馈网络层用于对注意力层的输出进行进一步的处理，每个transformer块中都有一个注意力层和前馈层，是一个全连接的神经网络，在每个位置上独立处理输入

class TransformerBlock(nn.Module):
    def __init__(self, layer_id: int, args: ModelArgs):
        super().__init__()
        self.n_heads = args.n_heads
        self.dim = args.dim
        self.head_dim = args.dim // args.n_heads
        self.attention = Attention(args)
        self.feed_forward = FeedForward(
            dim=args.dim,
            hidden_dim=4 * args.dim,
            multiple_of=args.multiple_of,
            ffn_dim_multiplier=args.ffn_dim_multiplier,
        )
        self.layer_id = layer_id
        self.attention_norm = RMSNorm(args.dim, eps=args.norm_eps)
        self.ffn_norm = RMSNorm(args.dim, eps=args.norm_eps)
 
    def forward(
        self,
        x: torch.Tensor,
        start_pos: int,
        freqs_cis: torch.Tensor,
        mask: Optional[torch.Tensor],
    ):
        h = x + self.attention.forward(
            self.attention_norm(x), start_pos, freqs_cis, mask
        )
        out = h + self.feed_forward.forward(self.ffn_norm(h))
        return out

transformer模块，包含注意力层和前馈层，每个层之前都需要正则化

class Transformer(nn.Module):
    def __init__(self, params: ModelArgs):
        super().__init__()
        self.params = params
        self.vocab_size = params.vocab_size
        self.n_layers = params.n_layers
 
        self.tok_embeddings = ParallelEmbedding(
            params.vocab_size, params.dim, init_method=lambda x: x
        )
 
        self.layers = torch.nn.ModuleList()
        for layer_id in range(params.n_layers):
            self.layers.append(TransformerBlock(layer_id, params))
 
        self.norm = RMSNorm(params.dim, eps=params.norm_eps)
        self.output = ColumnParallelLinear(
            params.dim, params.vocab_size, bias=False, init_method=lambda x: x
        )
 
        self.freqs_cis = precompute_freqs_cis(
            # Note that self.params.max_seq_len is multiplied by 2 because the token limit for the Llama 2 generation of models is 4096. 
            # Adding this multiplier instead of using 4096 directly allows for dynamism of token lengths while training or fine-tuning.
            self.params.dim // self.params.n_heads, self.params.max_seq_len * 2
        )
    @torch.inference_mode()
    def forward(self, tokens: torch.Tensor, start_pos: int):
        _bsz, seqlen = tokens.shape
        h = self.tok_embeddings(tokens)
        self.freqs_cis = self.freqs_cis.to(h.device)
        freqs_cis = self.freqs_cis[start_pos : start_pos + seqlen]
 
        mask = None
        if seqlen > 1:
            mask = torch.full(
                (seqlen, seqlen), float("-inf"), device=tokens.device
            )
 
            mask = torch.triu(mask, diagonal=1)
 
            # When performing key-value caching, we compute the attention scores
            # only for the new sequence. Thus, the matrix of scores is of size
            # (seqlen, cache_len + seqlen), and the only masked entries are (i, j) for
            # j > cache_len + i, since row i corresponds to token cache_len + i.
            mask = torch.hstack([
                torch.zeros((seqlen, start_pos), device=tokens.device),
                mask
            ]).type_as(h)
 
        for layer in self.layers:
            h = layer(h, start_pos, freqs_cis, mask)
        h = self.norm(h)
        output = self.output(h).float()
        return output

在forward函数中，对输入的 token 索引进行嵌入操作，通过freqs_cis提取频率信息，创建注意力掩码，遍历transformer层，正则化，输出。

将对角线以下的全0矩阵和以上的全mask矩阵进行水平拼接，并与输入数据h的数据类型保持一致

部分参考llama源码学习 | model.py - 知乎 (zhihu.com)