Hugging Face's logo

BlackSamorez
/
Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch

Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
Inference Endpoints
aqlm
Model card Files Community
Mixtral-8x7b-AQLM-2Bit-1x16-hf-test-dispatch
File size: 6,804 Bytes 
088443f
43230db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
    "vocab_size": 32000,
    "max_position_embeddings": 32768,
    "hidden_size": 4096,
    "intermediate_size": 14336,
    "num_hidden_layers": 32,
    "num_attention_heads": 32,
    "sliding_window": null,
    "num_key_value_heads": 8,
    "hidden_act": "silu",
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-05,
    "use_cache": true,
    "rope_theta": 1000000.0,
    "attention_dropout": 0.0,
    "num_experts_per_tok": 2,
    "num_local_experts": 8,
    "output_router_logits": false,
    "router_aux_loss_coef": 0.02,
    "torch_dtype": "float16",
    "tie_word_embeddings": false,
    "architectures": [
        "MixtralForCausalLM"
    ],
    "bos_token_id": 1,
    "eos_token_id": 2,
    "_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
    "transformers_version": "4.38.0.dev0",
    "model_type": "mixtral",
    "quantization_config": {
        "quant_method": "aqlm",
        "nbits_per_codebook": 16,
        "num_codebooks": 1,
        "out_group_size": 1,
        "in_group_size": 8,
        "linear_weights_not_to_quantize": [
            "model.layers.0.block_sparse_moe.gate.weight",
            "model.layers.0.input_layernorm.weight",
            "model.layers.0.post_attention_layernorm.weight",
            "model.layers.1.block_sparse_moe.gate.weight",
            "model.layers.1.input_layernorm.weight",
            "model.layers.1.post_attention_layernorm.weight",
            "model.layers.2.block_sparse_moe.gate.weight",
            "model.layers.2.input_layernorm.weight",
            "model.layers.2.post_attention_layernorm.weight",
            "model.layers.3.block_sparse_moe.gate.weight",
            "model.layers.3.input_layernorm.weight",
            "model.layers.3.post_attention_layernorm.weight",
            "model.layers.4.block_sparse_moe.gate.weight",
            "model.layers.4.input_layernorm.weight",
            "model.layers.4.post_attention_layernorm.weight",
            "model.layers.5.block_sparse_moe.gate.weight",
            "model.layers.5.input_layernorm.weight",
            "model.layers.5.post_attention_layernorm.weight",
            "model.layers.6.block_sparse_moe.gate.weight",
            "model.layers.6.input_layernorm.weight",
            "model.layers.6.post_attention_layernorm.weight",
            "model.layers.7.block_sparse_moe.gate.weight",
            "model.layers.7.input_layernorm.weight",
            "model.layers.7.post_attention_layernorm.weight",
            "model.layers.8.block_sparse_moe.gate.weight",
            "model.layers.8.input_layernorm.weight",
            "model.layers.8.post_attention_layernorm.weight",
            "model.layers.9.block_sparse_moe.gate.weight",
            "model.layers.9.input_layernorm.weight",
            "model.layers.9.post_attention_layernorm.weight",
            "model.layers.10.block_sparse_moe.gate.weight",
            "model.layers.10.input_layernorm.weight",
            "model.layers.10.post_attention_layernorm.weight",
            "model.layers.11.block_sparse_moe.gate.weight",
            "model.layers.11.input_layernorm.weight",
            "model.layers.11.post_attention_layernorm.weight",
            "model.layers.12.block_sparse_moe.gate.weight",
            "model.layers.12.input_layernorm.weight",
            "model.layers.12.post_attention_layernorm.weight",
            "model.layers.13.block_sparse_moe.gate.weight",
            "model.layers.13.input_layernorm.weight",
            "model.layers.13.post_attention_layernorm.weight",
            "model.layers.14.block_sparse_moe.gate.weight",
            "model.layers.14.input_layernorm.weight",
            "model.layers.14.post_attention_layernorm.weight",
            "model.layers.15.block_sparse_moe.gate.weight",
            "model.layers.15.input_layernorm.weight",
            "model.layers.15.post_attention_layernorm.weight",
            "model.layers.16.block_sparse_moe.gate.weight",
            "model.layers.16.input_layernorm.weight",
            "model.layers.16.post_attention_layernorm.weight",
            "model.layers.17.block_sparse_moe.gate.weight",
            "model.layers.17.input_layernorm.weight",
            "model.layers.17.post_attention_layernorm.weight",
            "model.layers.18.block_sparse_moe.gate.weight",
            "model.layers.18.input_layernorm.weight",
            "model.layers.18.post_attention_layernorm.weight",
            "model.layers.19.block_sparse_moe.gate.weight",
            "model.layers.19.input_layernorm.weight",
            "model.layers.19.post_attention_layernorm.weight",
            "model.layers.20.block_sparse_moe.gate.weight",
            "model.layers.20.input_layernorm.weight",
            "model.layers.20.post_attention_layernorm.weight",
            "model.layers.21.block_sparse_moe.gate.weight",
            "model.layers.21.input_layernorm.weight",
            "model.layers.21.post_attention_layernorm.weight",
            "model.layers.22.block_sparse_moe.gate.weight",
            "model.layers.22.input_layernorm.weight",
            "model.layers.22.post_attention_layernorm.weight",
            "model.layers.23.block_sparse_moe.gate.weight",
            "model.layers.23.input_layernorm.weight",
            "model.layers.23.post_attention_layernorm.weight",
            "model.layers.24.block_sparse_moe.gate.weight",
            "model.layers.24.input_layernorm.weight",
            "model.layers.24.post_attention_layernorm.weight",
            "model.layers.25.block_sparse_moe.gate.weight",
            "model.layers.25.input_layernorm.weight",
            "model.layers.25.post_attention_layernorm.weight",
            "model.layers.26.block_sparse_moe.gate.weight",
            "model.layers.26.input_layernorm.weight",
            "model.layers.26.post_attention_layernorm.weight",
            "model.layers.27.block_sparse_moe.gate.weight",
            "model.layers.27.input_layernorm.weight",
            "model.layers.27.post_attention_layernorm.weight",
            "model.layers.28.block_sparse_moe.gate.weight",
            "model.layers.28.input_layernorm.weight",
            "model.layers.28.post_attention_layernorm.weight",
            "model.layers.29.block_sparse_moe.gate.weight",
            "model.layers.29.input_layernorm.weight",
            "model.layers.29.post_attention_layernorm.weight",
            "model.layers.30.block_sparse_moe.gate.weight",
            "model.layers.30.input_layernorm.weight",
            "model.layers.30.post_attention_layernorm.weight",
            "model.layers.31.block_sparse_moe.gate.weight",
            "model.layers.31.input_layernorm.weight",
            "model.layers.31.post_attention_layernorm.weight",
            "model.embed_tokens.weight",
            "model.norm.weight",
            "lm_head.weight"
        ]
    }
}