Text Generation
Transformers
qwen
roleplay
self_instruct
custom_code
File size: 2,263 Bytes
bceb637
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9430783
 
bceb637
 
 
 
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
# Copyright (c) Alibaba Cloud.
#
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.

from transformers import PretrainedConfig


class QWenConfig(PretrainedConfig):
    model_type = "qwen"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=151936,
        hidden_size=4096,
        num_hidden_layers=32,
        num_attention_heads=32,
        emb_dropout_prob=0.0,
        attn_dropout_prob=0.0,
        layer_norm_epsilon=1e-6,
        initializer_range=0.02,
        max_position_embeddings=8192,
        scale_attn_weights=True,
        use_cache=True,
        bf16=False,
        fp16=False,
        fp32=False,
        kv_channels=128,
        rotary_pct=1.0,
        rotary_emb_base=10000,
        use_dynamic_ntk=True,
        use_logn_attn=True,
        use_flash_attn="auto",
        intermediate_size=22016,
        no_bias=True,
        tie_word_embeddings=False,
        use_cache_quantization=False,
        use_cache_kernel=False,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.emb_dropout_prob = emb_dropout_prob
        self.attn_dropout_prob = attn_dropout_prob
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.scale_attn_weights = scale_attn_weights
        self.use_cache = use_cache
        self.max_position_embeddings = max_position_embeddings
        self.bf16 = bf16
        self.fp16 = fp16
        self.fp32 = fp32
        self.kv_channels = kv_channels
        self.rotary_pct = rotary_pct
        self.rotary_emb_base = rotary_emb_base
        self.use_dynamic_ntk = use_dynamic_ntk
        self.use_logn_attn = use_logn_attn
        self.use_flash_attn = use_flash_attn
        self.no_bias = no_bias
        self.use_cache_quantization=use_cache_quantization
        self.use_cache_kernel=use_cache_kernel
        super().__init__(
            tie_word_embeddings=tie_word_embeddings,
            **kwargs
        )