Hugging Face's logo

ssdataanalysis
/
AI21-Jamba2-Mini-mlx-8Bit

Text Generation
Transformers
Safetensors
MLX
jamba
conversational
8-bit precision
Model card Files
xet
Community
AI21-Jamba2-Mini-mlx-8Bit
File size: 4,864 Bytes 
c97d35c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "architectures": [
        "JambaForCausalLM"
    ],
    "attention_dropout": 0.0,
    "attn_layer_offset": 4,
    "attn_layer_period": 8,
    "bos_token_id": 1,
    "dtype": "bfloat16",
    "eos_token_id": 519,
    "expert_layer_offset": 1,
    "expert_layer_period": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "mamba_conv_bias": true,
    "mamba_d_conv": 4,
    "mamba_d_state": 16,
    "mamba_dt_rank": 256,
    "mamba_expand": 2,
    "mamba_proj_bias": false,
    "max_position_embeddings": 262144,
    "model_type": "jamba",
    "num_attention_heads": 32,
    "num_experts": 16,
    "num_experts_per_tok": 2,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "num_logits_to_keep": 1,
    "output_router_logits": false,
    "pad_token_id": 0,
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine",
        "model.layers.1.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.29.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.31.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        }
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine",
        "model.layers.1.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.29.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.31.feed_forward.router": {
            "group_size": 64,
            "bits": 8
        }
    },
    "rms_norm_eps": 1e-06,
    "router_aux_loss_coef": 0.001,
    "sliding_window": null,
    "tie_word_embeddings": false,
    "transformers_version": "4.56.1",
    "use_cache": true,
    "use_mamba_kernels": true,
    "vocab_size": 65536
}