File size: 10,193 Bytes
f229d1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging

logger = logging.get_logger(__name__)

DEEPSEEK_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
class DeepseekConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`DeepseekModel`]. It is used to instantiate an DeepSeek
    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
    defaults will yield a similar configuration to that of the DeepSeek-7B.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.


    Args:
        vocab_size (`int`, *optional*, defaults to 102400):
            Vocabulary size of the Deep model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`DeepseekModel`]
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 11008):
            Dimension of the MLP representations.
        moe_intermediate_size (`int`, *optional*, defaults to 1407):
            Dimension of the MoE representations.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer decoder.
        n_shared_experts (`int`, *optional*, defaults to None):
            Number of shared experts, None means dense model.
        n_routed_experts (`int`, *optional*, defaults to None):
            Number of routed experts, None means dense model.
        num_experts_per_tok (`int`, *optional*, defaults to None):
            Number of selected experts, None means dense model.
        moe_layer_freq (`int`, *optional*, defaults to 1):
            The frequency of the MoE layer: one expert layer for every `moe_layer_freq - 1` dense layers.
        first_k_dense_replace (`int`, *optional*, defaults to 0):
            Number of dense layers in shallow layers(embed->dense->dense->...->dense->moe->moe...->lm_head).
                                                            \--k dense layers--/
        norm_topk_prob (`bool`, *optional*, defaults to False):
            Whether to normalize the weights of the routed experts.
        scoring_func (`str`, *optional*, defaults to 'softmax'):
            Method of computing expert weights.
        aux_loss_alpha (`float`, *optional*, defaults to 0.001):
            Auxiliary loss weight coefficient.
        seq_aux = (`bool`, *optional*, defaults to True):
            Whether to compute the auxiliary loss for each individual sample.
        num_key_value_heads (`int`, *optional*):
            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
            by meanpooling all the original heads within that group. For more details checkout [this
            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
            `num_attention_heads`.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the rms normalization layers.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        pad_token_id (`int`, *optional*):
            Padding token id.
        bos_token_id (`int`, *optional*, defaults to 1):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 2):
            End of stream token id.
        pretraining_tp (`int`, *optional*, defaults to 1):
            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
            issue](https://github.com/pytorch/pytorch/issues/76232).
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to tie weight embeddings
        rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the RoPE embeddings.
        rope_scaling (`Dict`, *optional*):
            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
            strategies: linear and dynamic. Their scaling factor must be a float greater than 1. The expected format is
            `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
            `max_position_embeddings` to the expected new maximum.
        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
            Whether to use a bias in the query, key, value and output projection layers during self-attention.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.

    ```python
    >>> from transformers import DeepseekModel, DeepseekConfig

    >>> # Initializing a Deepseek deepseek-7b style configuration
    >>> configuration = DeepseekConfig()

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "deepseek"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=102400,
        hidden_size=4096,
        intermediate_size=11008,
        moe_intermediate_size = 1407,
        num_hidden_layers=30,
        num_attention_heads=32,
        num_key_value_heads=32,
        n_shared_experts = None,
        n_routed_experts = None,
        num_experts_per_tok = None,
        moe_layer_freq = 1,
        first_k_dense_replace = 0,
        norm_topk_prob = False,
        scoring_func = 'softmax',
        aux_loss_alpha = 0.001,
        seq_aux = True,
        hidden_act="silu",
        max_position_embeddings=2048,
        initializer_range=0.02,
        rms_norm_eps=1e-6,
        use_cache=True,
        pad_token_id=None,
        bos_token_id=100000,
        eos_token_id=100001,
        pretraining_tp=1,
        tie_word_embeddings=False,
        rope_theta=10000.0,
        rope_scaling=None,
        attention_bias=False,
        attention_dropout=0.0,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.moe_intermediate_size = moe_intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.n_shared_experts = n_shared_experts
        self.n_routed_experts = n_routed_experts
        self.num_experts_per_tok = num_experts_per_tok
        self.moe_layer_freq = moe_layer_freq
        self.first_k_dense_replace = first_k_dense_replace
        self.norm_topk_prob = norm_topk_prob
        self.scoring_func = scoring_func
        self.aux_loss_alpha = aux_loss_alpha
        self.seq_aux = seq_aux
        # for backward compatibility
        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads

        self.num_key_value_heads = num_key_value_heads
        self.hidden_act = hidden_act
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.pretraining_tp = pretraining_tp
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self._rope_scaling_validation()
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout

        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )

    def _rope_scaling_validation(self):
        """
        Validate the `rope_scaling` configuration.
        """
        if self.rope_scaling is None:
            return

        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
            raise ValueError(
                "`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, "
                f"got {self.rope_scaling}"
            )
        rope_scaling_type = self.rope_scaling.get("type", None)
        rope_scaling_factor = self.rope_scaling.get("factor", None)
        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
            raise ValueError(
                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
            )
        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
            raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")