File size: 5,316 Bytes
7d5b73d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2023 The OpenAI Team Authors and HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" RWKV configuration"""

from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)

RWKV_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    
}


class Rwkv5Config(PretrainedConfig):
    """
    This is the configuration class to store the configuration of a [`RwkvModel`]. It is used to instantiate a RWKV
    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 RWVK-4
    [RWKV/rwkv-4-169m-pile](https://huggingface.co/RWKV/rwkv-4-169m-pile) architecture.

    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 50277):
            Vocabulary size of the RWKV model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`RwkvModel`].
        context_length (`int`, *optional*, defaults to 1024):
            The maximum sequence length that this model can be be used with in a single forward (using it in RNN mode
            lets use any sequence length).
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimensionality of the embeddings and hidden states.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the model.
        attention_hidden_size (`int`, *optional*):
            Dimensionality of the attention hidden states. Will default to `hidden_size` if unset.
        intermediate_size (`int`, *optional*):
            Dimensionality of the inner feed-forward layers. Will default to 4 times `hidden_size` if unset.
        layer_norm_eps (`float`, *optional*, defaults to 1e-5):
            The epsilon to use in the layer normalization layers.
        bos_token_id (`int`, *optional*, defaults to 0):
            The id of the beginning of sentence token in the vocabulary. Defaults to 0 as RWKV uses the same tokenizer
            as GPTNeoX.
        eos_token_id (`int`, *optional*, defaults to 0):
            The id of the end of sentence token in the vocabulary. Defaults to 0 as RWKV uses the same tokenizer as
            GPTNeoX.
        rescale_every (`int`, *optional*, default to 6):
            At inference, the hidden states (and weights of the correponding output layers) are divided by 2 every
            `rescale_every` layer. If set to 0 or a negative number, no rescale is done.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether or not to tie the word embeddings with the input token embeddings.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last state.


    Example:

    ```python
    >>> from transformers import RwkvConfig, RwkvModel

    >>> # Initializing a Rwkv configuration
    >>> configuration = RwkvConfig()

    >>> # Initializing a model (with random weights) from the configuration
    >>> model = RwkvModel(configuration)

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

    model_type = "rwkv5"
    attribute_map = {"max_position_embeddings": "context_length"}

    def __init__( #1.5B World
        self,
        vocab_size=65536,
        context_length=4096,
        hidden_size=768,
        num_hidden_layers=24,
        attention_hidden_size=None,
        head_size=64,
        intermediate_size=None,
        layer_norm_epsilon=1e-5,
        bos_token_id=0,
        eos_token_id=0,
        rescale_every=6,
        tie_word_embeddings=False,
        use_cache=True,
        model_version="5_2",
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.context_length = context_length
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.attention_hidden_size = attention_hidden_size if attention_hidden_size is not None else hidden_size
        self.head_size = head_size
        self.intermediate_size = None
        self.layer_norm_epsilon = layer_norm_epsilon
        self.rescale_every = rescale_every
        self.use_cache = use_cache

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id
        self.model_version = model_version

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