Upload 11 files

LMConfig.py

@@ -0,0 +1,83 @@
+from transformers import PretrainedConfig
+from typing import List
+
+
+class LMConfig(PretrainedConfig):
+    model_type = "nanochat"
+
+    def __init__(
+            self,
+            dim: int = 512,
+            n_layers: int = 8,
+            tie_word_embeddings: bool = True,
+            ###########################################
+            attention:str='GQA',
+            #GQA
+            n_heads: int = 14,
+            n_kv_heads: int = 2,
+            #MLA
+            q_lora_rank: int=0,
+            kv_lora_rank: int=512,
+            qk_nope_head_dim: int=64,
+            qk_rope_head_dim:int=64,
+            v_head_dim:int=64,
+            #############################################
+            vocab_size: int = 151650,
+            # vocab_size: int = 6400,
+            hidden_dim: int = None,
+            multiple_of: int = 64,
+            norm_eps: float = 1e-5,
+            max_seq_len: int = 8192,
+            rope_theta: int = 1e6,
+            dropout: float = 0.0,
+            flash_attn: bool = True,
+            ####################################################
+            # Here are the specific configurations of MOE
+            # When use_moe is false, the following is invalid
+            ####################################################
+            use_moe: bool = False,
+            ####################################################
+            num_experts_per_tok: int = 2,
+            n_routed_experts: int = 4,
+            n_shared_experts: bool = True,
+            scoring_func: str = 'softmax',
+            aux_loss_alpha: float = 0.1,
+            seq_aux: bool = True,
+            norm_topk_prob: bool = True,
+            **kwargs,
+    ):
+        self.dim = dim
+        self.n_layers = n_layers
+        self.tie_word_embeddings = tie_word_embeddings
+        self.vocab_size = vocab_size
+        self.hidden_dim = hidden_dim
+        self.multiple_of = multiple_of
+        self.norm_eps = norm_eps
+        self.max_seq_len = max_seq_len
+        self.rope_theta = rope_theta
+        self.dropout = dropout
+        self.flash_attn = flash_attn
+        #####################################################
+        self.attention=attention
+        #GQA
+        self.n_heads = n_heads
+        self.n_kv_heads = n_kv_heads
+        #MLA
+        self.q_lora_rank = q_lora_rank
+        self.kv_lora_rank = kv_lora_rank
+        self.qk_nope_head_dim = qk_nope_head_dim
+        self.qk_rope_head_dim = qk_rope_head_dim
+        self.v_head_dim = v_head_dim
+        ####################################################
+        # Here are the specific configurations of MOE
+        # When use_moe is false, the following is invalid
+        ####################################################
+        self.use_moe = use_moe
+        self.num_experts_per_tok = num_experts_per_tok  # 每个token选择的专家数量
+        self.n_routed_experts = n_routed_experts  # 总的专家数量
+        self.n_shared_experts = n_shared_experts  # 共享专家
+        self.scoring_func = scoring_func  # 评分函数，默认为'softmax'
+        self.aux_loss_alpha = aux_loss_alpha  # 辅助损失的alpha参数
+        self.seq_aux = seq_aux  # 是否在序列级别上计算辅助损失
+        self.norm_topk_prob = norm_topk_prob  # 是否标准化top-k概率
+        super().__init__(**kwargs)

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "out_sft",
+  "architectures": [
+    "NanoChatLM"
+  ],
+  "attention": "GQA",
+  "auto_map": {
+    "AutoConfig": "LMConfig.LMConfig",
+    "AutoModel": "model.NanoChatLM",
+    "AutoModelForCausalLM": "model.NanoChatLM"
+  },
+  "aux_loss_alpha": 0.1,
+  "dim": 896,
+  "dropout": 0.0,
+  "flash_attn": true,
+  "hidden_dim": 2432,
+  "kv_lora_rank": 512,
+  "max_seq_len": 512,
+  "model_type": "nanochat",
+  "multiple_of": 64,
+  "n_heads": 14,
+  "n_kv_heads": 2,
+  "n_layers": 24,
+  "n_routed_experts": 4,
+  "n_shared_experts": true,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_experts_per_tok": 2,
+  "q_lora_rank": 0,
+  "qk_nope_head_dim": 64,
+  "qk_rope_head_dim": 64,
+  "rope_theta": 1000000.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_moe": false,
+  "v_head_dim": 64,
+  "vocab_size": 151650
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.42.4"
+}

model.py

@@ -0,0 +1,480 @@
+import math
+import struct
+import inspect
+import time
+
+from .LMConfig import LMConfig
+from typing import Any, Optional, Tuple, List
+import numpy as np
+import torch
+import torch.nn.functional as F
+from torch import nn
+from transformers import PreTrainedModel
+from transformers.modeling_outputs import CausalLMOutputWithPast
+from flash_attn import flash_attn_qkvpacked_func, flash_attn_func
+
+
+class RMSNorm(torch.nn.Module):
+    def __init__(self, dim: int, eps: float):
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def forward(self, x):
+        return self.weight * (x.float() * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps) ).type_as(x)
+
+
+def precompute_pos_cis(dim: int, end: int, theta: float = 1e4):
+    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
+    pos_cis = torch.polar(torch.ones_like(freqs), freqs)  # complex64
+    return pos_cis
+
+
+def apply_rotary_emb(xq, xk, pos_cis):
+    def unite_shape(pos_cis, x):
+        ndim = x.ndim
+        assert 0 <= 1 < ndim
+        assert pos_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 pos_cis.view(*shape)
+
+    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))
+    pos_cis = unite_shape(pos_cis, xq_)
+    xq_out = torch.view_as_real(xq_ * pos_cis).flatten(3)
+    xk_out = torch.view_as_real(xk_ * pos_cis).flatten(3)
+    return xq_out.type_as(xq), xk_out.type_as(xk)
+
+
+def repeat_kv(x: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """torch.repeat_interleave(x, dim=2, repeats=n_rep)"""
+    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)
+    )
+
+
+class GQA(nn.Module):
+    def __init__(self, args: LMConfig):
+        super().__init__()
+        self.n_kv_heads = args.n_heads if args.n_kv_heads is None else args.n_kv_heads
+        assert args.n_heads % self.n_kv_heads == 0
+        self.n_local_heads = args.n_heads
+        self.n_local_kv_heads = self.n_kv_heads
+        self.n_rep = self.n_local_heads // self.n_local_kv_heads
+        self.head_dim = args.dim // args.n_heads
+        self.wq = nn.Linear(args.dim, args.n_heads * self.head_dim, bias=True)
+        self.wk = nn.Linear(args.dim, self.n_kv_heads * self.head_dim, bias=True)
+        self.wv = nn.Linear(args.dim, self.n_kv_heads * self.head_dim, bias=True)
+        self.wo = nn.Linear(args.n_heads * self.head_dim, args.dim, bias=False)
+        self.attn_dropout = nn.Dropout(args.dropout)
+        self.resid_dropout = nn.Dropout(args.dropout)
+        self.dropout = args.dropout
+        self.softmax_scale=self.head_dim ** -0.5
+        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention') and args.flash_attn
+        # print("WARNING: using slow attention. Flash Attention requires PyTorch >= 2.0")
+        mask = torch.full((1, 1, args.max_seq_len, args.max_seq_len), float("-inf"))
+        mask = torch.triu(mask, diagonal=1)
+        self.register_buffer("mask", mask, persistent=False)
+
+    def forward(self,
+                x: torch.Tensor,
+                pos_cis: torch.Tensor,
+                past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+                use_cache=False):
+        bsz, seq_len, _ = x.shape
+        xq, xk, xv = self.wq(x), self.wk(x), self.wv(x)
+        xq = xq.view(bsz, seq_len, self.n_local_heads, self.head_dim)
+        xk = xk.view(bsz, seq_len, self.n_local_kv_heads, self.head_dim)
+        xv = xv.view(bsz, seq_len, self.n_local_kv_heads, self.head_dim)
+
+        xq, xk = apply_rotary_emb(xq, xk, pos_cis)
+        # kv_cache实现
+        if past_key_value is not None:
+            xk = torch.cat([past_key_value[0], xk], dim=1)
+            xv = torch.cat([past_key_value[1], xv], dim=1)
+        past_kv = (xk, xv) if use_cache else None
+
+        xq, xk, xv = (
+            xq.transpose(1, 2),
+            repeat_kv(xk, self.n_rep).transpose(1, 2),
+            repeat_kv(xv, self.n_rep).transpose(1, 2)
+        )
+        if self.flash and seq_len != 1:
+            dropout_p = self.dropout if self.training else 0.0
+            output = F.scaled_dot_product_attention(
+                xq, xk, xv,
+                attn_mask=None,
+                dropout_p=dropout_p,
+                is_causal=True
+            )
+            # output =flash_attn_func(
+            #     xq, xk, xv,
+            #     dropout_p=dropout_p,
+            #     softmax_scale=self.softmax_scale,
+            #     causal=True
+            # )
+        else:
+            scores = (xq @ xk.transpose(-2, -1)) / math.sqrt(self.head_dim)
+            scores += self.mask[:, :, :seq_len, :seq_len]
+            scores = F.softmax(scores.float(), dim=-1).type_as(xq)
+            scores = self.attn_dropout(scores)
+            output = scores @ xv
+
+        output = output.transpose(1, 2).reshape(bsz, seq_len, -1)
+        output = self.resid_dropout(self.wo(output))
+        return output, past_kv
+
+class MLA(nn.Module):
+    """
+    Multi-Headed Attention Layer (MLA).
+
+    Attributes:
+        dim (int): Dimensionality of the input features.
+        n_heads (int): Number of attention heads.
+        n_local_heads (int): Number of local attention heads for distributed systems.
+        q_lora_rank (int): Rank for low-rank query projection.
+        kv_lora_rank (int): Rank for low-rank key/value projection.
+        qk_nope_head_dim (int): Dimensionality of non-positional query/key projections.
+        qk_rope_head_dim (int): Dimensionality of rotary-positional query/key projections.
+        qk_head_dim (int): Total dimensionality of query/key projections.
+        v_head_dim (int): Dimensionality of value projections.
+        softmax_scale (float): Scaling factor for softmax in attention computation.
+    """
+    def __init__(self, args: LMConfig):
+        super().__init__()
+        self.dim = args.dim
+        self.n_heads = args.n_heads
+        self.n_local_heads = args.n_heads
+        self.q_lora_rank = args.q_lora_rank
+        self.kv_lora_rank = args.kv_lora_rank
+        self.qk_nope_head_dim = args.qk_nope_head_dim
+        self.qk_rope_head_dim = args.qk_rope_head_dim
+        self.qk_head_dim = args.qk_nope_head_dim + args.qk_rope_head_dim
+        self.v_head_dim = args.v_head_dim
+
+        if self.q_lora_rank == 0:
+            self.wq = nn.Linear(self.dim, self.n_heads * self.qk_head_dim,bias=False)
+        else:
+            self.wq_a = nn.Linear(self.dim, self.q_lora_rank)
+            self.q_norm = RMSNorm(self.q_lora_rank,eps=args.norm_eps)
+            self.wq_b = nn.Linear(self.q_lora_rank, self.n_heads * self.qk_head_dim)
+        self.wkv_a = nn.Linear(self.dim, self.kv_lora_rank + self.qk_rope_head_dim)
+        self.kv_norm = RMSNorm(self.kv_lora_rank,eps=args.norm_eps)
+        self.wkv_b = nn.Linear(self.kv_lora_rank, self.n_heads * (self.qk_nope_head_dim + self.v_head_dim))
+        self.wo = nn.Linear(self.n_heads * self.v_head_dim, self.dim)
+        self.softmax_scale = self.qk_head_dim ** -0.5
+        mask = torch.full((args.max_seq_len, args.max_seq_len), float("-inf")).triu_(1)
+        self.register_buffer("mask", mask, persistent=False)
+
+    def forward(self, 
+                x: torch.Tensor,  
+                freqs_cis: torch.Tensor, 
+                past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+                use_cache=False):
+        """
+        Forward pass for the Multi-Headed Attention Layer (MLA).
+
+        Args:
+            x (torch.Tensor): Input tensor of shape (batch_size, seq_len, dim).
+            start_pos (int): Starting position in the sequence for caching.
+            freqs_cis (torch.Tensor): Precomputed complex exponential values for rotary embeddings.
+            mask (Optional[torch.Tensor]): Mask tensor to exclude certain positions from attention.
+
+        Returns:
+            torch.Tensor: Output tensor with the same shape as the input.
+        """
+        bsz, seqlen, _ = x.size()
+
+        if self.q_lora_rank == 0:
+            q = self.wq(x)#x*Wqc
+        else:
+            q = self.wq_b(self.q_norm(self.wq_a(x)))#x*Wc'*Wqc
+        q = q.view(bsz, seqlen, self.n_local_heads, self.qk_head_dim)
+        q_nope, q_pe = torch.split(q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)
+
+        kv = self.wkv_a(x)#x*Wc
+        kv, k_pe = torch.split(kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
+        q_pe,k_pe=apply_rotary_emb(q_pe,k_pe.unsqueeze(2), freqs_cis)
+
+        wkv_b = self.wkv_b.weight
+        wkv_b = wkv_b.view(self.n_local_heads, -1, self.kv_lora_rank)
+        q_nope = torch.einsum("bshd,hdc->bshc", q_nope, wkv_b[:, :self.qk_nope_head_dim])
+        kv=self.kv_norm(kv)
+        k_pe=k_pe.squeeze(2)
+        if past_key_value is not None:
+            kv=torch.cat([past_key_value[0], kv], dim=1)
+            k_pe=torch.cat([past_key_value[1], k_pe], dim=1)
+        past_kv = (kv, k_pe) if use_cache else None
+        scores = (torch.einsum("bshc,btc->bsht", q_nope, kv) +
+                    torch.einsum("bshr,btr->bsht", q_pe, k_pe)) * self.softmax_scale
+        mask=self.mask.unsqueeze(1)
+        scores += mask[:seqlen,:,:seqlen]
+        scores = scores.softmax(dim=-1, dtype=torch.float32).type_as(x)
+
+        x = torch.einsum("bsht,btc->bshc", scores, kv)
+        x = torch.einsum("bshc,hdc->bshd", x, wkv_b[:, -self.v_head_dim:])
+        x = self.wo(x.flatten(2))
+
+        return x,past_kv
+
+class FeedForward(nn.Module):
+    def __init__(self, config: LMConfig):
+        super().__init__()
+        if config.hidden_dim is None:
+            hidden_dim = 4 * config.dim
+            hidden_dim = int(2 * hidden_dim / 3)
+            config.hidden_dim = config.multiple_of * ((hidden_dim + config.multiple_of - 1) // config.multiple_of)
+        self.w1 = nn.Linear(config.dim, config.hidden_dim, bias=False)
+        self.w2 = nn.Linear(config.hidden_dim, config.dim, bias=False)
+        self.w3 = nn.Linear(config.dim, config.hidden_dim, bias=False)
+        self.dropout = nn.Dropout(config.dropout)
+
+    def forward(self, x):
+        return self.dropout(self.w2(F.silu(self.w1(x)) * self.w3(x)))
+
+
+class MoEGate(nn.Module):
+    def __init__(self, config: LMConfig):
+        super().__init__()
+        self.config = config
+        self.top_k = config.num_experts_per_tok
+        self.n_routed_experts = config.n_routed_experts
+
+        self.scoring_func = config.scoring_func
+        self.alpha = config.aux_loss_alpha
+        self.seq_aux = config.seq_aux
+
+        self.norm_topk_prob = config.norm_topk_prob
+        self.gating_dim = config.dim
+        self.weight = nn.Parameter(torch.empty((self.n_routed_experts, self.gating_dim)))
+        self.reset_parameters()
+
+    def reset_parameters(self) -> None:
+        import torch.nn.init as init
+        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
+
+    def forward(self, hidden_states):
+        bsz, seq_len, h = hidden_states.shape
+        hidden_states = hidden_states.view(-1, h)
+        logits = F.linear(hidden_states, self.weight, None)
+        if self.scoring_func == 'softmax':
+            scores = logits.softmax(dim=-1)
+        else:
+            raise NotImplementedError(f'insupportable scoring function for MoE gating: {self.scoring_func}')
+
+        topk_weight, topk_idx = torch.topk(scores, k=self.top_k, dim=-1, sorted=False)
+
+        if self.top_k > 1 and self.norm_topk_prob:
+            denominator = topk_weight.sum(dim=-1, keepdim=True) + 1e-20
+            topk_weight = topk_weight / denominator
+
+        if self.training and self.alpha > 0.0:
+            scores_for_aux = scores
+            aux_topk = self.top_k
+            topk_idx_for_aux_loss = topk_idx.view(bsz, -1)
+            if self.seq_aux:
+                scores_for_seq_aux = scores_for_aux.view(bsz, seq_len, -1)
+                ce = torch.zeros(bsz, self.n_routed_experts, device=hidden_states.device)
+                ce.scatter_add_(1, topk_idx_for_aux_loss,
+                                torch.ones(bsz, seq_len * aux_topk, device=hidden_states.device)).div_(
+                    seq_len * aux_topk / self.n_routed_experts)
+                aux_loss = (ce * scores_for_seq_aux.mean(dim=1)).sum(dim=1).mean() * self.alpha
+            else:
+                mask_ce = F.one_hot(topk_idx_for_aux_loss.view(-1), num_classes=self.n_routed_experts)
+                ce = mask_ce.float().mean(0)
+                Pi = scores_for_aux.mean(0)
+                fi = ce * self.n_routed_experts
+                aux_loss = (Pi * fi).sum() * self.alpha
+        else:
+            aux_loss = 0
+        return topk_idx, topk_weight, aux_loss
+
+
+class MOEFeedForward(nn.Module):
+    def __init__(self, config: LMConfig):
+        super().__init__()
+        self.config = config
+        self.experts = nn.ModuleList([
+            FeedForward(config)
+            for _ in range(config.n_routed_experts)
+        ])
+        self.gate = MoEGate(config)
+        if config.n_shared_experts is not None:
+            self.shared_experts = FeedForward(config)
+
+    def forward(self, x):
+        identity = x
+        orig_shape = x.shape
+        bsz, seq_len, _ = x.shape
+        # 使用门控机制选择专家
+        topk_idx, topk_weight, aux_loss = self.gate(x)
+        x = x.view(-1, x.shape[-1])
+        flat_topk_idx = topk_idx.view(-1)
+        if self.training:
+            # 训练模式下，重复输入数据
+            x = x.repeat_interleave(self.config.num_experts_per_tok, dim=0)
+            y = torch.empty_like(x, dtype=torch.float16)
+            for i, expert in enumerate(self.experts):
+                y[flat_topk_idx == i] = expert(x[flat_topk_idx == i]).to(y.dtype)  # 确保类型一致
+            y = (y.view(*topk_weight.shape, -1) * topk_weight.unsqueeze(-1)).sum(dim=1)
+            y = y.view(*orig_shape)
+        else:
+            # 推理模式下，只选择最优专家
+            y = self.moe_infer(x, flat_topk_idx, topk_weight.view(-1, 1)).view(*orig_shape)
+        if self.config.n_shared_experts is not None:
+            y = y + self.shared_experts(identity)
+        self.aux_loss = aux_loss
+        return y
+
+    @torch.no_grad()
+    def moe_infer(self, x, flat_expert_indices, flat_expert_weights):
+        expert_cache = torch.zeros_like(x)
+        idxs = flat_expert_indices.argsort()
+        tokens_per_expert = flat_expert_indices.bincount().cpu().numpy().cumsum(0)
+        token_idxs = idxs // self.config.num_experts_per_tok
+        # 例如当tokens_per_expert=[6, 15, 20, 26, 33, 38, 46, 52]
+        # 当token_idxs=[3, 7, 19, 21, 24, 25,  4,  5,  6, 10, 11, 12...]
+        # 意味着当token_idxs[:6] -> [3,  7, 19, 21, 24, 25,  4]位���的token都由专家0处理，token_idxs[6:15]位置的token都由专家1处理......
+        for i, end_idx in enumerate(tokens_per_expert):
+            start_idx = 0 if i == 0 else tokens_per_expert[i - 1]
+            if start_idx == end_idx:
+                continue
+            expert = self.experts[i]
+            exp_token_idx = token_idxs[start_idx:end_idx]
+            expert_tokens = x[exp_token_idx]
+            expert_out = expert(expert_tokens).to(expert_cache.dtype)
+            expert_out.mul_(flat_expert_weights[idxs[start_idx:end_idx]])
+            # 使用 scatter_add_ 进行 sum 操作
+            expert_cache.scatter_add_(0, exp_token_idx.view(-1, 1).repeat(1, x.shape[-1]), expert_out)
+
+        return expert_cache
+
+
+class NanoChatBlock(nn.Module):
+    def __init__(self, layer_id: int, config: LMConfig):
+        super().__init__()
+        self.n_heads = config.n_heads
+        self.dim = config.dim
+        self.head_dim = config.dim // config.n_heads
+        if config.attention=='MLA':
+            self.attention = MLA(config)
+        elif config.attention=='GQA':
+            self.attention = GQA(config)
+
+        self.layer_id = layer_id
+        self.attention_norm = RMSNorm(config.dim, eps=config.norm_eps)
+        self.ffn_norm = RMSNorm(config.dim, eps=config.norm_eps)
+        self.feed_forward = FeedForward(config) if not config.use_moe else MOEFeedForward(config)
+
+    def forward(self, x, pos_cis, past_key_value=None, use_cache=False):
+        h_attn, past_kv = self.attention(
+            self.attention_norm(x),
+            pos_cis,
+            past_key_value=past_key_value,
+            use_cache=use_cache
+        )
+        h = x + h_attn
+        out = h + self.feed_forward(self.ffn_norm(h))
+        return out, past_kv
+
+
+class NanoChatLM(PreTrainedModel):
+    config_class = LMConfig
+
+    def __init__(self, params: LMConfig = None):
+        self.params = params or LMConfig()
+        super().__init__(self.params)
+        self.vocab_size, self.n_layers = params.vocab_size, params.n_layers
+        self.tok_embeddings = nn.Embedding(params.vocab_size, params.dim)
+        self.dropout = nn.Dropout(params.dropout)
+        self.layers = nn.ModuleList([NanoChatBlock(l, params) for l in range(self.n_layers)])
+        self.norm = RMSNorm(params.dim, eps=params.norm_eps)
+        self.output = nn.Linear(params.dim, params.vocab_size, bias=False)
+        if params.tie_word_embeddings:
+            self.output.weight = self.tok_embeddings.weight
+        self.register_buffer("pos_cis", precompute_pos_cis(params.dim // params.n_heads, params.max_seq_len,
+                                                           theta=params.rope_theta), persistent=False)
+        self.OUT = CausalLMOutputWithPast()
+
+    def forward(self,
+                input_ids: Optional[torch.Tensor] = None,
+                past_key_values: Optional[List[Tuple[torch.Tensor, torch.Tensor]]] = None,
+                use_cache: bool = False,
+                **args):
+        past_key_values = past_key_values or [None] * len(self.layers)
+        start_pos = args.get('start_pos', 0)
+        h = self.dropout(self.tok_embeddings(input_ids))
+        pos_cis = self.pos_cis[start_pos:start_pos + input_ids.size(1)]
+        past_kvs = []
+        for l, layer in enumerate(self.layers):
+            h, past_kv = layer(
+                h, pos_cis,
+                past_key_value=past_key_values[l],
+                use_cache=use_cache
+            )
+            past_kvs.append(past_kv)
+        logits = self.output(self.norm(h))
+        aux_loss = sum(l.feed_forward.aux_loss for l in self.layers if isinstance(l.feed_forward, MOEFeedForward))
+        self.OUT.__setitem__('logits', logits)
+        self.OUT.__setitem__('aux_loss', aux_loss)
+        self.OUT.__setitem__('past_key_values', past_kvs)
+        return self.OUT
+
+    @torch.inference_mode()
+    def generate(self, input_ids, eos_token_id=151643, max_new_tokens=1024, temperature=0.75, top_p=0.90,
+                 stream=False, rp=1., use_cache=True, pad_token_id=0, **args):
+        # 流式生成
+        if stream:
+            return self._generate_stream(input_ids, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache)
+
+        # 直接生成
+        generated = []
+        for i in range(input_ids.size(0)):
+            non_pad = input_ids[i][input_ids[i] != pad_token_id].unsqueeze(0)
+            out = self._generate_stream(non_pad, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache)
+            tokens_list = [tokens[:, -1:] for tokens in out]
+            gen = torch.cat(tokens_list, dim=-1) if tokens_list else non_pad
+            full_sequence = torch.cat([non_pad, gen], dim=-1)
+            generated.append(full_sequence)
+        max_length = max(seq.size(1) for seq in generated)
+        generated = [
+            torch.cat(
+                [seq, torch.full((1, max_length - seq.size(1)), pad_token_id, dtype=seq.dtype, device=seq.device)],
+                dim=-1)
+            for seq in generated
+        ]
+        return torch.cat(generated, dim=0)
+
+    def _generate_stream(self, input_ids, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache, **args):
+        start, first_seq, past_kvs = input_ids.shape[1], True, None
+        while input_ids.shape[1] < max_new_tokens - 1:
+            if first_seq or not use_cache:
+                out, first_seq = self(input_ids, past_key_values=past_kvs, use_cache=use_cache), False
+            else:
+                out = self(input_ids[:, -1:], past_key_values=past_kvs, use_cache=use_cache,
+                           start_pos=input_ids.shape[1] - 1)
+            logits, past_kvs = out.logits[:, -1, :], out.past_key_values
+            logits[:, list(set(input_ids.tolist()[0]))] /= rp
+            logits /= (temperature + 1e-9)
+            if top_p is not None and top_p < 1.0:
+                sorted_logits, sorted_indices = torch.sort(logits, descending=True, dim=-1)
+                sorted_probs = F.softmax(sorted_logits, dim=-1)
+                cumulative_probs = torch.cumsum(sorted_probs, dim=-1)
+                sorted_indices_to_remove = cumulative_probs > top_p
+                sorted_indices_to_remove[:, 1:] = sorted_indices_to_remove[:, :-1].clone()
+                sorted_indices_to_remove[:, 0] = False
+                indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
+                logits[indices_to_remove] = -float('Inf')
+            input_ids_next = torch.multinomial(F.softmax(logits, dim=-1), num_samples=1)
+            input_ids = torch.cat((input_ids, input_ids_next), dim=1)
+            yield input_ids[:, start:]
+            if input_ids_next.item() == eos_token_id:
+                break
+

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee4b365e9d90b07cc82f4ebfd15f7b2a3bc01a3614780b0421d521827ace4a4
+size 1347624082

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}