upload

LMConfig.py

@@ -0,0 +1,61 @@
+from transformers import PretrainedConfig
+from typing import List
+
+
+class LMConfig(PretrainedConfig):
+    model_type = "minimind"
+
+    def __init__(
+            self,
+            dim: int = 512,
+            n_layers: int = 8,
+            n_heads: int = 8,
+            n_kv_heads: int = 2,
+            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.n_heads = n_heads
+        self.n_kv_heads = n_kv_heads
+        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
+        ####################################################
+        # 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)

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "MiniMindLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "LMConfig.LMConfig",
+    "AutoModelForCausalLM": "model.MiniMindLM"
+  },
+  "aux_loss_alpha": 0.1,
+  "dim": 512,
+  "dropout": 0.0,
+  "flash_attn": true,
+  "hidden_dim": 1408,
+  "max_seq_len": 512,
+  "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": "4.48.0",
+  "use_moe": false,
+  "vocab_size": 6400
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.48.0"
+}

model.py

@@ -0,0 +1,385 @@
+import math
+import struct
+import inspect
+import time
+
+from .LMConfig import LMConfig
+from typing import Any, Optional, Tuple, List, Union
+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
+
+
+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):
+        return self.weight * self._norm(x.float()).type_as(x)
+
+
+def precompute_pos_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)  # 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 Attention(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=False)
+        self.wk = nn.Linear(args.dim, self.n_kv_heads * self.head_dim, bias=False)
+        self.wv = nn.Linear(args.dim, self.n_kv_heads * self.head_dim, bias=False)
+        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.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
+            )
+        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 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:
+            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 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
+        # 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: LMConfig):
+        super().__init__()
+        self.n_heads = config.n_heads
+        self.dim = config.dim
+        self.head_dim = config.dim // config.n_heads
+        self.attention = Attention(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 MiniMindLM(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([MiniMindBlock(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)
+        self.tok_embeddings.weight = self.output.weight
+        self.register_buffer("pos_cis",
+                             precompute_pos_cis(dim=params.dim // params.n_heads, 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,
+                logits_to_keep: Union[int, torch.Tensor] = 0,
+                **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)
+
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.output(self.norm(h)[:, slice_indices, :])
+        aux_loss = sum(l.feed_forward.aux_loss for l in self.layers if isinstance(l.feed_forward, MOEFeedForward))
+        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
+
+    @torch.inference_mode()
+    def generate(self, input_ids, eos_token_id=2, max_new_tokens=1024, temperature=0.75, top_p=0.90,
+                 stream=False, rp=1., use_cache=True, pad_token_id=0, num_return_sequences=1, **args):
+        # 流式生成
+        if stream:
+            return self._stream(input_ids, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache, **args)
+
+        # 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)
+            for _ in range(num_return_sequences):
+                out = self._stream(non_pad, eos_token_id, max_new_tokens, temperature, top_p, rp, use_cache, **args)
+                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
+        ]
+        output = torch.cat(generated, dim=0)
+        res = output.view(input_ids.size(0) * num_return_sequences, -1)
+        return res
+
+    def _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, **args), False
+            else:
+                out = self(input_ids[:, -1:], past_key_values=past_kvs, use_cache=use_cache,
+                           start_pos=input_ids.shape[1] - 1, **args)
+            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 sha256:4a054638e92d96fccc65e541a8ad72844a513b28910332923452d58599431159
+size 103342988

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +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>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}