Hugging Face's logo

AlphaOxO
/
Lizzy-7B-8bits-MLX

Text Generation
MLX
Safetensors
English
lizzy
conversational
custom_code
8-bit precision
Model card Files
xet
 Community
Lizzy-7B-8bits-MLX
File size: 4,602 Bytes
55b79ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
    "architectures": [
        "LizzyForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_lizzy.LizzyConfig",
        "AutoModel": "modeling_lizzy.LizzyModel",
        "AutoModelForCausalLM": "modeling_lizzy.LizzyForCausalLM",
        "AutoTokenizer": "tokenization_lizzy.LizzyTokenizerFast"
    },
    "bos_token_id": 100257,
    "embd_dropout": 0.0,
    "eos_token_id": 100257,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "layer_layouts": [
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm",
        "decoder_postnorm"
    ],
    "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",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention",
        "sliding_attention",
        "sliding_attention",
        "sliding_attention",
        "full_attention"
    ],
    "linear_a_log_max": null,
    "linear_a_log_min": null,
    "linear_allow_neg_eigval": null,
    "linear_conv_kernel_dim": null,
    "linear_dt_init_floor": null,
    "linear_dt_max": null,
    "linear_dt_min": null,
    "linear_key_head_dim": null,
    "linear_num_key_heads": null,
    "linear_num_value_heads": null,
    "linear_value_head_dim": null,
    "max_position_embeddings": 65536,
    "mlp_bias": false,
    "mlp_type": "gated",
    "model_type": "lizzy",
    "no_rope_layer_interval": null,
    "norm_eps": 1e-06,
    "norm_has_bias": false,
    "norm_type": "rmsnorm",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "pad_token_id": 100277,
    "position_embedding_type": "rope",
    "qk_norm_type": "rmsnorm",
    "quantization": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 8,
        "mode": "affine"
    },
    "resid_dropout": 0.0,
    "rope_layer_flags": [
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true,
        true
    ],
    "rope_scaling": {
        "attention_factor": 1.2079441541679836,
        "beta_fast": 32,
        "beta_slow": 1,
        "factor": 8.0,
        "original_max_position_embeddings": 8192,
        "rope_type": "default",
        "rope_theta": 500000
    },
    "rope_theta": 500000,
    "rope_type_overrides": {},
    "sliding_window": 4096,
    "tie_word_embeddings": false,
    "tokenizer_class": "LizzyTokenizerFast",
    "transformers_version": "5.4.0",
    "use_cache": true,
    "use_post_attn_norm": true,
    "use_post_mlp_norm": true,
    "use_pre_attn_norm": false,
    "use_pre_mlp_norm": false,
    "use_qk_norm": true,
    "vocab_size": 100278
}