Hugging Face's logo

mlx-community
/
DeepSeek-V4-Pro

Text Generation
MLX
Safetensors
English
deepseek_v4
8-bit precision
Model card Files
xet
 Community
DeepSeek-V4-Pro
File size: 2,435 Bytes
b15fba8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "architectures": [
        "DeepseekV4ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "compress_ratios": [
        128,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        128,
        4,
        0
    ],
    "compress_rope_theta": 160000,
    "eos_token_id": 1,
    "hc_eps": 1e-06,
    "hc_mult": 4,
    "hc_sinkhorn_iters": 20,
    "head_dim": 512,
    "hidden_act": "silu",
    "hidden_size": 7168,
    "index_head_dim": 128,
    "index_n_heads": 64,
    "index_topk": 1024,
    "initializer_range": 0.02,
    "max_position_embeddings": 1048576,
    "model_type": "deepseek_v4",
    "moe_intermediate_size": 3072,
    "n_routed_experts": 384,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 128,
    "num_experts_per_tok": 6,
    "num_hash_layers": 3,
    "num_hidden_layers": 61,
    "num_key_value_heads": 1,
    "num_nextn_predict_layers": 1,
    "o_groups": 16,
    "o_lora_rank": 1024,
    "q_lora_rank": 1536,
    "qk_rope_head_dim": 64,
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
        "beta_fast": 32,
        "beta_slow": 1,
        "factor": 16,
        "original_max_position_embeddings": 65536,
        "type": "yarn"
    },
    "rope_theta": 10000,
    "routed_scaling_factor": 2.5,
    "scoring_func": "sqrtsoftplus",
    "sliding_window": 128,
    "swiglu_limit": 10.0,
    "tie_word_embeddings": false,
    "topk_method": "noaux_tc",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.57.1",
    "use_cache": true,
    "vocab_size": 129280
}