Hugging Face's logo

mlx-community
/
MiMo-V2-Flash-mlx-8bit

Text Generation
MLX
Safetensors
Transformers
mimo_v2_flash
conversational
custom_code
8-bit precision
Model card Files
xet
Community
MiMo-V2-Flash-mlx-8bit
File size: 2,910 Bytes 
ab3e276
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "add_full_attention_sink_bias": false,
    "add_swa_attention_sink_bias": true,
    "architectures": [
        "MiMoV2FlashForCausalLM"
    ],
    "attention_bias": false,
    "attention_chunk_size": 128,
    "attention_dropout": 0.0,
    "attention_value_scale": 0.707,
    "auto_map": {
        "AutoConfig": "configuration_mimo_v2_flash.MiMoV2FlashConfig",
        "AutoModel": "modeling_mimo_v2_flash.MiMoV2FlashModel",
        "AutoModelForCausalLM": "modeling_mimo_v2_flash.MiMoV2FlashForCausalLM"
    },
    "head_dim": 192,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "hybrid_layer_pattern": [
        0,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0,
        1,
        1,
        1,
        1,
        1,
        0
    ],
    "initializer_range": 0.02,
    "intermediate_size": 16384,
    "layernorm_epsilon": 1e-05,
    "max_position_embeddings": 262144,
    "model_type": "mimo_v2_flash",
    "moe_intermediate_size": 2048,
    "moe_layer_freq": [
        0,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1,
        1
    ],
    "n_group": 1,
    "n_routed_experts": 256,
    "n_shared_experts": null,
    "norm_topk_prob": true,
    "num_attention_heads": 64,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 48,
    "num_key_value_heads": 4,
    "partial_rotary_factor": 0.334,
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "rope_theta": 5000000,
    "routed_scaling_factor": null,
    "scoring_func": "sigmoid",
    "sliding_window": 128,
    "sliding_window_size": 128,
    "swa_head_dim": 192,
    "swa_num_attention_heads": 64,
    "swa_num_key_value_heads": 8,
    "swa_rope_theta": 10000,
    "swa_v_head_dim": 128,
    "tie_word_embeddings": false,
    "topk_group": 1,
    "topk_method": "noaux_tc",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.40.1",
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 152576
}