Hugging Face's logo

OpenMed
/
maple-preview-4bit-mlx

Text Generation
MLX
Safetensors
English
maple
mixture-of-experts
quantized
experimental
openmed
conversational
custom_code
4-bit precision
Model card Files
xet
 Community
maple-preview-4bit-mlx
File size: 2,722 Bytes
ce765ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "architectures": [
        "MapleForCausalLM"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_maple.MapleConfig",
        "AutoModel": "modeling_maple.MapleModel",
        "AutoModelForCausalLM": "modeling_maple.MapleForCausalLM"
    },
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "embedding_dropout": 0.0,
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_types": [
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention"
    ],
    "max_position_embeddings": 131072,
    "max_window_layers": 24,
    "model_file": "maple.py",
    "model_type": "maple",
    "moe_intermediate_size": 512,
    "moe_router_enable_expert_bias": false,
    "nope_on_global_attention": true,
    "norm_topk_prob": true,
    "num_attention_heads": 16,
    "num_experts": 256,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 24,
    "num_key_value_heads": 4,
    "num_shared_experts": 0,
    "output_dropout": 0.0,
    "output_router_logits": false,
    "pad_token_id": null,
    "partial_rotary_factor": 0.5,
    "preaffine": false,
    "quantization": {
        "group_size": 128,
        "bits": 4,
        "mode": "affine",
        "model.word_embeddings": {
            "group_size": 64,
            "bits": 4
        },
        "lm_head": {
            "group_size": 64,
            "bits": 4
        }
    },
    "quantization_config": {
        "group_size": 128,
        "bits": 4,
        "mode": "affine",
        "model.word_embeddings": {
            "group_size": 64,
            "bits": 4
        },
        "lm_head": {
            "group_size": 64,
            "bits": 4
        }
    },
    "quantize": true,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000,
    "router_dtype": "fp32",
    "sliding_window": 512,
    "tie_word_embeddings": false,
    "transformers_version": "4.57.1",
    "use_cache": true,
    "use_qk_norm": true,
    "use_rmsnorm": true,
    "vocab_size": 151936
}