Upload 7 files

config.json

@@ -1,32 +1,35 @@
-{
-  "architectures": [
-    "MiniMindLM"
-  ],
-  "auto_map": {
-    "AutoConfig": "LMConfig.LMConfig",
-    "AutoModelForCausalLM": "model.MiniMindLM"
-  },
-  "aux_loss_alpha": 0.1,
-  "dim": 640,
-  "dropout": 0.0,
-  "flash_attn": true,
-  "hidden_dim": 1728,
-  "max_seq_len": 8192,
-  "model_type": "minimind",
-  "multiple_of": 64,
-  "n_heads": 8,
-  "n_kv_heads": 2,
-  "n_layers": 8,
-  "n_routed_experts": 4,
-  "n_shared_experts": true,
-  "norm_eps": 1e-05,
-  "norm_topk_prob": true,
-  "num_experts_per_tok": 2,
-  "rope_theta": 1000000.0,
-  "scoring_func": "softmax",
-  "seq_aux": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
-  "use_moe": true,
-  "vocab_size": 6400
-}
+{
+  "architectures": [
+    "MiniMindForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "model_minimind.MiniMindConfig",
+    "AutoModelForCausalLM": "model_minimind.MiniMindForCausalLM"
+  },
+  "aux_loss_alpha": 0.1,
+  "bos_token_id": 1,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "flash_attn": true,
+  "hidden_act": "silu",
+  "hidden_size": 640,
+  "intermediate_size": 1728,
+  "max_position_embeddings": 32768,
+  "max_seq_len": 8192,
+  "model_type": "minimind",
+  "n_routed_experts": 4,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_moe": true,
+  "vocab_size": 6400
+}

generation_config.json

@@ -1,4 +1,6 @@
-{
-  "_from_model_config": true,
-  "transformers_version": "4.44.0"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

model_minimind.py

@@ -0,0 +1,446 @@
+# 📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘
+#                                             MiniMind Config
+# 📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘
+
+from transformers import PretrainedConfig
+
+
+class MiniMindConfig(PretrainedConfig):
+    model_type = "minimind"
+
+    def __init__(
+            self,
+            dropout: float = 0.0,
+            bos_token_id: int = 1,
+            eos_token_id: int = 2,
+            hidden_act: str = 'silu',
+            hidden_size: int = 512,
+            intermediate_size: int = None,
+            max_position_embeddings: int = 32768,
+            num_attention_heads: int = 8,
+            num_hidden_layers: int = 8,
+            num_key_value_heads: int = 2,
+            vocab_size: int = 6400,
+            rms_norm_eps: float = 1e-05,
+            rope_theta: int = 1000000.0,
+            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: int = 1,
+            scoring_func: str = 'softmax',
+            aux_loss_alpha: float = 0.1,
+            seq_aux: bool = True,
+            norm_topk_prob: bool = True,
+            **kwargs
+    ):
+        super().__init__(**kwargs)
+        self.dropout = dropout
+        self.bos_token_id = bos_token_id
+        self.eos_token_id = eos_token_id
+        self.hidden_act = hidden_act
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.max_position_embeddings = max_position_embeddings
+        self.num_attention_heads = num_attention_heads
+        self.num_hidden_layers = num_hidden_layers
+        self.num_key_value_heads = num_key_value_heads
+        self.vocab_size = vocab_size
+        self.rms_norm_eps = rms_norm_eps
+        self.rope_theta = rope_theta
+        self.flash_attn = flash_attn
+        ####################################################
+        # 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
+
+
+# 📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘
+#                                             MiniMind Model
+# 📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘📘
+
+import math
+import torch
+from torch import nn
+from transformers.activations import ACT2FN
+from typing import Optional, Tuple, List, Union
+import torch.nn.functional as F
+from transformers import PreTrainedModel, GenerationMixin, PretrainedConfig
+from transformers.modeling_outputs import CausalLMOutputWithPast
+
+
+class RMSNorm(torch.nn.Module):
+    def __init__(self, dim: int, eps: float = 1e-5):
+        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):
+        return self.weight * self._norm(x.float()).type_as(x)
+
+
+def precompute_freqs_cis(dim: int, end: int = int(32 * 1024), theta: float = 1e6):
+    freqs = 1.0 / (theta ** (torch.arange(0, dim, 2)[: (dim // 2)].float() / dim))
+    t = torch.arange(end, device=freqs.device)
+    freqs = torch.outer(t, freqs).float()
+    freqs_cos = torch.cat([torch.cos(freqs), torch.cos(freqs)], dim=-1)
+    freqs_sin = torch.cat([torch.sin(freqs), torch.sin(freqs)], dim=-1)
+    return freqs_cos, freqs_sin
+
+
+def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
+    def rotate_half(x):
+        return torch.cat((-x[..., x.shape[-1] // 2:], x[..., : x.shape[-1] // 2]), dim=-1)
+
+    q_embed = (q * cos.unsqueeze(unsqueeze_dim)) + (rotate_half(q) * sin.unsqueeze(unsqueeze_dim))
+    k_embed = (k * cos.unsqueeze(unsqueeze_dim)) + (rotate_half(k) * sin.unsqueeze(unsqueeze_dim))
+    return q_embed, k_embed
+
+
+def repeat_kv(x: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """torch.repeat_interleave(x, dim=2, repeats=n_rep)"""
+    bs, slen, num_key_value_heads, head_dim = x.shape
+    if n_rep == 1:
+        return x
+    return (
+        x[:, :, :, None, :]
+        .expand(bs, slen, num_key_value_heads, n_rep, head_dim)
+        .reshape(bs, slen, num_key_value_heads * n_rep, head_dim)
+    )
+
+
+class Attention(nn.Module):
+    def __init__(self, args: MiniMindConfig):
+        super().__init__()
+        self.num_key_value_heads = args.num_attention_heads if args.num_key_value_heads is None else args.num_key_value_heads
+        assert args.num_attention_heads % self.num_key_value_heads == 0
+        self.n_local_heads = args.num_attention_heads
+        self.n_local_kv_heads = self.num_key_value_heads
+        self.n_rep = self.n_local_heads // self.n_local_kv_heads
+        self.head_dim = args.hidden_size // args.num_attention_heads
+        self.q_proj = nn.Linear(args.hidden_size, args.num_attention_heads * self.head_dim, bias=False)
+        self.k_proj = nn.Linear(args.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
+        self.v_proj = nn.Linear(args.hidden_size, self.num_key_value_heads * self.head_dim, bias=False)
+        self.o_proj = nn.Linear(args.num_attention_heads * self.head_dim, args.hidden_size, bias=False)
+        self.attn_dropout = nn.Dropout(args.dropout)
+        self.resid_dropout = nn.Dropout(args.dropout)
+        self.dropout = args.dropout
+        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")
+
+    def forward(self,
+                x: torch.Tensor,
+                position_embeddings: Tuple[torch.Tensor, torch.Tensor],  # 修改为接收cos和sin
+                past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+                use_cache=False,
+                attention_mask: Optional[torch.Tensor] = None):
+        bsz, seq_len, _ = x.shape
+        xq, xk, xv = self.q_proj(x), self.k_proj(x), self.v_proj(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)
+
+        cos, sin = position_embeddings
+        xq, xk = apply_rotary_pos_emb(xq, xk, cos[:seq_len], sin[:seq_len])
+
+        # 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 False and self.flash and seq_len != 1:
+            dropout_p = self.dropout if self.training else 0.0
+            attn_mask = None
+            if attention_mask is not None:
+                attn_mask = attention_mask.view(bsz, 1, 1, -1).expand(bsz, self.n_local_heads, seq_len, -1)
+                attn_mask = attn_mask.bool() if attention_mask is not None else None
+
+            output = F.scaled_dot_product_attention(xq, xk, xv, attn_mask=attn_mask, dropout_p=dropout_p, is_causal=True)
+        else:
+            scores = (xq @ xk.transpose(-2, -1)) / math.sqrt(self.head_dim)
+            scores = scores + torch.triu(
+                torch.full((seq_len, seq_len), float("-inf"), device=scores.device),
+                diagonal=1
+            ).unsqueeze(0).unsqueeze(0)  # scores+mask
+
+            if attention_mask is not None:
+                extended_attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
+                extended_attention_mask = (1.0 - extended_attention_mask) * -1e9
+                scores = scores + extended_attention_mask
+
+            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.o_proj(output))
+        return output, past_kv
+
+
+class FeedForward(nn.Module):
+    def __init__(self, config: MiniMindConfig):
+        super().__init__()
+        if config.intermediate_size is None:
+            intermediate_size = int(config.hidden_size * 8 / 3)
+            config.intermediate_size = 64 * ((intermediate_size + 64 - 1) // 64)
+        self.gate_proj = nn.Linear(config.hidden_size, config.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(config.intermediate_size, config.hidden_size, bias=False)
+        self.up_proj = nn.Linear(config.hidden_size, config.intermediate_size, bias=False)
+        self.dropout = nn.Dropout(config.dropout)
+        self.act_fn = ACT2FN[config.hidden_act]
+
+    def forward(self, x):
+        return self.dropout(self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x)))
+
+
+class MoEGate(nn.Module):
+    def __init__(self, config: MiniMindConfig):
+        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.hidden_size
+        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: MiniMindConfig):
+        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 > 0:
+            self.shared_experts = nn.ModuleList([
+                FeedForward(config)
+                for _ in range(config.n_shared_experts)
+            ])
+
+    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:
+            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:
+            y = self.moe_infer(x, flat_topk_idx, topk_weight.view(-1, 1)).view(*orig_shape)
+        if self.config.n_shared_experts > 0:
+            for expert in self.shared_experts:
+                y = y + expert(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
+        # 当tokens_per_expert = [6, 15, 20, 26]，tokens_per_expert.shape[0]即为专家数量（此时为4）
+        # 且token_idxs = [3, 7, 19, 21, 24, 25,  4,  5,  6, 10, 11, 12...] 时
+        # 意味token_idxs[:6] -> [3, 7, 19, 21, 24, 25]这6个位置属于专家0处理的token（每个token有可能被多个专家处理，这取决于num_experts_per_tok）
+        # 接下来9个位置token_idxs[6:15] -> [4,  5,  6, 10, 11, 12...]属于专家1处理的token...依此类推
+        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]])
+            expert_cache.scatter_add_(0, exp_token_idx.view(-1, 1).repeat(1, x.shape[-1]), expert_out)
+
+        return expert_cache
+
+
+class MiniMindBlock(nn.Module):
+    def __init__(self, layer_id: int, config: MiniMindConfig):
+        super().__init__()
+        self.num_attention_heads = config.num_attention_heads
+        self.hidden_size = config.hidden_size
+        self.head_dim = config.hidden_size // config.num_attention_heads
+        self.self_attn = Attention(config)
+
+        self.layer_id = layer_id
+        self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.mlp = FeedForward(config) if not config.use_moe else MOEFeedForward(config)
+
+    def forward(self, hidden_states, position_embeddings, past_key_value=None, use_cache=False, attention_mask=None):
+        residual = hidden_states
+        hidden_states, present_key_value = self.self_attn(
+            self.input_layernorm(hidden_states), position_embeddings,
+            past_key_value, use_cache, attention_mask
+        )
+        hidden_states += residual
+        hidden_states = hidden_states + self.mlp(self.post_attention_layernorm(hidden_states))
+        return hidden_states, present_key_value
+
+
+class MiniMindModel(nn.Module):
+    def __init__(self, config: MiniMindConfig):
+        super().__init__()
+        self.config = config
+        self.vocab_size, self.num_hidden_layers = config.vocab_size, config.num_hidden_layers
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size)
+        self.dropout = nn.Dropout(config.dropout)
+        self.layers = nn.ModuleList([MiniMindBlock(l, config) for l in range(self.num_hidden_layers)])
+        self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+        freqs_cos, freqs_sin = precompute_freqs_cis(dim=config.hidden_size // config.num_attention_heads,
+                                                    end=config.max_position_embeddings, theta=config.rope_theta)
+        self.register_buffer("freqs_cos", freqs_cos, persistent=False)
+        self.register_buffer("freqs_sin", freqs_sin, persistent=False)
+
+    def forward(self,
+                input_ids: Optional[torch.Tensor] = None,
+                attention_mask: Optional[torch.Tensor] = None,
+                past_key_values: Optional[List[Tuple[torch.Tensor, torch.Tensor]]] = None,
+                use_cache: bool = False,
+                **kwargs):
+        batch_size, seq_length = input_ids.shape
+        past_key_values = past_key_values or [None] * len(self.layers)
+        start_pos = past_key_values[0][0].shape[1] if past_key_values[0] is not None else 0
+
+        hidden_states = self.dropout(self.embed_tokens(input_ids))
+
+        position_embeddings = (
+            self.freqs_cos[start_pos:start_pos + seq_length],
+            self.freqs_sin[start_pos:start_pos + seq_length]
+        )
+
+        presents = []
+        for layer_idx, (layer, past_key_value) in enumerate(zip(self.layers, past_key_values)):
+            hidden_states, present = layer(
+                hidden_states,
+                position_embeddings,
+                past_key_value=past_key_value,
+                use_cache=use_cache,
+                attention_mask=attention_mask
+            )
+            presents.append(present)
+
+        hidden_states = self.norm(hidden_states)
+
+        aux_loss = sum(
+            layer.mlp.aux_loss
+            for layer in self.layers
+            if isinstance(layer.mlp, MOEFeedForward)
+        )
+
+        return hidden_states, presents, aux_loss
+
+
+class MiniMindForCausalLM(PreTrainedModel, GenerationMixin):
+    config_class = MiniMindConfig
+
+    def __init__(self, config: MiniMindConfig = None):
+        self.config = config or MiniMindConfig()
+        super().__init__(self.config)
+        self.model = MiniMindModel(self.config)
+        self.lm_head = nn.Linear(self.config.hidden_size, self.config.vocab_size, bias=False)
+        self.model.embed_tokens.weight = self.lm_head.weight
+        self.OUT = CausalLMOutputWithPast()
+
+    def forward(self,
+                input_ids: Optional[torch.Tensor] = None,
+                attention_mask: Optional[torch.Tensor] = None,
+                past_key_values: Optional[List[Tuple[torch.Tensor, torch.Tensor]]] = None,
+                use_cache: bool = False,
+                logits_to_keep: Union[int, torch.Tensor] = 0,
+                **args):
+        h, past_kvs, aux_loss = self.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            **args
+        )
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.lm_head(h[:, slice_indices, :])
+        self.OUT.__setitem__('last_hidden_state', h)
+        self.OUT.__setitem__('logits', logits)
+        self.OUT.__setitem__('aux_loss', aux_loss)
+        self.OUT.__setitem__('past_key_values', past_kvs)
+        return self.OUT

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda2077ba415f651ff07e3e1408d268e1dcdc15a86364454747753a5b12d9f0e
+size 290118354

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1,43 +1,44 @@
-{
-  "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{{ '<s>system\\n' + system_message + '</s>\\n' }}{% else %}{{ '<s>system\\n你是 MiniMind，是一个有用的人工智能助手。</s>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<s>user\\n' + content + '</s>\\n<s>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 32768,
-  "pad_token": "<unk>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<unk>"
-}
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% else %}{{ '<|im_start|>system\\nYou are a helpful assistant<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "<|endoftext|>"
+}