Skip to content

vllm.transformers_utils.configs.minimax_text_01

MiniMaxText01 model configuration

MiniMaxText01Config

Bases: PretrainedConfig

Source code in vllm/transformers_utils/configs/minimax_text_01.py 
 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
class MiniMaxText01Config(PretrainedConfig):
    model_type = "MiniMaxText01"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=32000,
        hidden_size=4096,
        intermediate_size=14336,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=8,
        hidden_act="silu",
        max_position_embeddings=4096 * 32,
        initializer_range=0.02,
        rms_norm_eps=1e-5,
        use_cache=True,
        pad_token_id=None,
        bos_token_id=None,
        eos_token_id=None,
        tie_word_embeddings=False,
        rope_theta=1e6,
        sliding_window=None,
        attention_dropout=0.0,
        num_experts_per_tok=2,
        num_local_experts=8,
        output_router_logits=False,
        router_aux_loss_coef=0.001,
        router_jitter_noise=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.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.sliding_window = sliding_window

        # 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.use_cache = use_cache
        self.rope_theta = rope_theta
        self.attention_dropout = attention_dropout

        self.num_experts_per_tok = num_experts_per_tok
        self.num_local_experts = num_local_experts
        self.output_router_logits = output_router_logits
        self.router_aux_loss_coef = router_aux_loss_coef
        self.router_jitter_noise = router_jitter_noise
        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,
        )

attention_dropout instance-attribute 

attention_dropout = attention_dropout

hidden_act instance-attribute 

hidden_act = hidden_act

hidden_size instance-attribute 

hidden_size = hidden_size

initializer_range instance-attribute 

initializer_range = initializer_range

intermediate_size instance-attribute 

intermediate_size = intermediate_size

keys_to_ignore_at_inference class-attribute instance-attribute 

keys_to_ignore_at_inference = ['past_key_values']

max_position_embeddings instance-attribute 

max_position_embeddings = max_position_embeddings

model_type class-attribute instance-attribute 

model_type = 'MiniMaxText01'

num_attention_heads instance-attribute 

num_attention_heads = num_attention_heads

num_experts_per_tok instance-attribute 

num_experts_per_tok = num_experts_per_tok

num_hidden_layers instance-attribute 

num_hidden_layers = num_hidden_layers

num_key_value_heads instance-attribute 

num_key_value_heads = num_key_value_heads

num_local_experts instance-attribute 

num_local_experts = num_local_experts

output_router_logits instance-attribute 

output_router_logits = output_router_logits

rms_norm_eps instance-attribute 

rms_norm_eps = rms_norm_eps

rope_theta instance-attribute 

rope_theta = rope_theta

router_aux_loss_coef instance-attribute 

router_aux_loss_coef = router_aux_loss_coef

router_jitter_noise instance-attribute 

router_jitter_noise = router_jitter_noise

sliding_window instance-attribute 

sliding_window = sliding_window

use_cache instance-attribute 

use_cache = use_cache

vocab_size instance-attribute 

vocab_size = vocab_size

__init__ 

__init__(
    vocab_size=32000,
    hidden_size=4096,
    intermediate_size=14336,
    num_hidden_layers=32,
    num_attention_heads=32,
    num_key_value_heads=8,
    hidden_act="silu",
    max_position_embeddings=4096 * 32,
    initializer_range=0.02,
    rms_norm_eps=1e-05,
    use_cache=True,
    pad_token_id=None,
    bos_token_id=None,
    eos_token_id=None,
    tie_word_embeddings=False,
    rope_theta=1000000.0,
    sliding_window=None,
    attention_dropout=0.0,
    num_experts_per_tok=2,
    num_local_experts=8,
    output_router_logits=False,
    router_aux_loss_coef=0.001,
    router_jitter_noise=0.0,
    **kwargs,
)
Source code in vllm/transformers_utils/configs/minimax_text_01.py 
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
def __init__(
    self,
    vocab_size=32000,
    hidden_size=4096,
    intermediate_size=14336,
    num_hidden_layers=32,
    num_attention_heads=32,
    num_key_value_heads=8,
    hidden_act="silu",
    max_position_embeddings=4096 * 32,
    initializer_range=0.02,
    rms_norm_eps=1e-5,
    use_cache=True,
    pad_token_id=None,
    bos_token_id=None,
    eos_token_id=None,
    tie_word_embeddings=False,
    rope_theta=1e6,
    sliding_window=None,
    attention_dropout=0.0,
    num_experts_per_tok=2,
    num_local_experts=8,
    output_router_logits=False,
    router_aux_loss_coef=0.001,
    router_jitter_noise=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.num_hidden_layers = num_hidden_layers
    self.num_attention_heads = num_attention_heads
    self.sliding_window = sliding_window

    # 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.use_cache = use_cache
    self.rope_theta = rope_theta
    self.attention_dropout = attention_dropout

    self.num_experts_per_tok = num_experts_per_tok
    self.num_local_experts = num_local_experts
    self.output_router_logits = output_router_logits
    self.router_aux_loss_coef = router_aux_loss_coef
    self.router_jitter_noise = router_jitter_noise
    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,
    )