Hugging Face's logo

mlx-community
/
Laguna-XS.2-bf16

Text Generation
MLX
Safetensors
laguna
laguna-xs.2
conversational
custom_code
Model card Files
xet
 Community
Laguna-XS.2-bf16
File size: 4,070 Bytes
41149a6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
{
    "architectures": [
        "LagunaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_laguna.LagunaConfig",
        "AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
    },
    "bos_token_id": 2,
    "eos_token_id": [
        2,
        24
    ],
    "gating": true,
    "head_dim": 128,
    "hidden_size": 2048,
    "intermediate_size": 8192,
    "layer_types": [
        "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",
        "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"
    ],
    "max_position_embeddings": 131072,
    "mlp_layer_types": [
        "dense",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse",
        "sparse"
    ],
    "model_type": "laguna",
    "moe_apply_router_weight_on_input": false,
    "moe_intermediate_size": 512,
    "moe_routed_scaling_factor": 2.5,
    "num_attention_heads": 48,
    "num_attention_heads_per_layer": [
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64,
        48,
        64,
        64,
        64
    ],
    "num_experts": 256,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "pad_token_id": 9,
    "partial_rotary_factor": 0.5,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
        "full_attention": {
            "rope_theta": 500000.0,
            "rope_type": "yarn",
            "factor": 32.0,
            "original_max_position_embeddings": 4096,
            "beta_slow": 1.0,
            "beta_fast": 64.0,
            "attention_factor": 1.0,
            "partial_rotary_factor": 0.5
        },
        "sliding_attention": {
            "rope_type": "default",
            "rope_theta": 10000.0,
            "partial_rotary_factor": 1.0
        },
        "original_max_position_embeddings": 4096
    },
    "router_aux_loss_coef": 0.0,
    "shared_expert_intermediate_size": 512,
    "sliding_window": 512,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 100352
}