Hugging Face's logo

DFloat11
/
BAGEL-7B-MoT-DF11

Any-to-Any
Safetensors
qwen2
dfloat11
df11
lossless compression
70% size, 100% accuracy
Model card Files Community
1
BAGEL-7B-MoT-DF11
File size: 9,585 Bytes 
97e2fbf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
185
186
187
188
189
190
 
{
  "dfloat11_config": {
    "bytes_per_thread": 8,
    "pattern_dict": {
      "language_model\\.model\\.embed_tokens": [],
      "language_model\\.model\\.layers.\\d+": [
          "self_attn.q_proj",
          "self_attn.k_proj",
          "self_attn.v_proj",
          "self_attn.o_proj",
          "self_attn.q_proj_moe_gen",
          "self_attn.k_proj_moe_gen",
          "self_attn.v_proj_moe_gen",
          "self_attn.o_proj_moe_gen",
          "mlp.gate_proj",
          "mlp.up_proj",
          "mlp.down_proj",
          "mlp_moe_gen.gate_proj",
          "mlp_moe_gen.up_proj",
          "mlp_moe_gen.down_proj"
      ],
      "language_model\\.lm_head": [],
      "vit_model": [
        "vision_model.encoder.layers.0.self_attn.k_proj",
        "vision_model.encoder.layers.0.self_attn.v_proj",
        "vision_model.encoder.layers.0.self_attn.q_proj",
        "vision_model.encoder.layers.0.self_attn.out_proj",
        "vision_model.encoder.layers.0.mlp.fc1",
        "vision_model.encoder.layers.0.mlp.fc2",
        "vision_model.encoder.layers.1.self_attn.k_proj",
        "vision_model.encoder.layers.1.self_attn.v_proj",
        "vision_model.encoder.layers.1.self_attn.q_proj",
        "vision_model.encoder.layers.1.self_attn.out_proj",
        "vision_model.encoder.layers.1.mlp.fc1",
        "vision_model.encoder.layers.1.mlp.fc2",
        "vision_model.encoder.layers.2.self_attn.k_proj",
        "vision_model.encoder.layers.2.self_attn.v_proj",
        "vision_model.encoder.layers.2.self_attn.q_proj",
        "vision_model.encoder.layers.2.self_attn.out_proj",
        "vision_model.encoder.layers.2.mlp.fc1",
        "vision_model.encoder.layers.2.mlp.fc2",
        "vision_model.encoder.layers.3.self_attn.k_proj",
        "vision_model.encoder.layers.3.self_attn.v_proj",
        "vision_model.encoder.layers.3.self_attn.q_proj",
        "vision_model.encoder.layers.3.self_attn.out_proj",
        "vision_model.encoder.layers.3.mlp.fc1",
        "vision_model.encoder.layers.3.mlp.fc2",
        "vision_model.encoder.layers.4.self_attn.k_proj",
        "vision_model.encoder.layers.4.self_attn.v_proj",
        "vision_model.encoder.layers.4.self_attn.q_proj",
        "vision_model.encoder.layers.4.self_attn.out_proj",
        "vision_model.encoder.layers.4.mlp.fc1",
        "vision_model.encoder.layers.4.mlp.fc2",
        "vision_model.encoder.layers.5.self_attn.k_proj",
        "vision_model.encoder.layers.5.self_attn.v_proj",
        "vision_model.encoder.layers.5.self_attn.q_proj",
        "vision_model.encoder.layers.5.self_attn.out_proj",
        "vision_model.encoder.layers.5.mlp.fc1",
        "vision_model.encoder.layers.5.mlp.fc2",
        "vision_model.encoder.layers.6.self_attn.k_proj",
        "vision_model.encoder.layers.6.self_attn.v_proj",
        "vision_model.encoder.layers.6.self_attn.q_proj",
        "vision_model.encoder.layers.6.self_attn.out_proj",
        "vision_model.encoder.layers.6.mlp.fc1",
        "vision_model.encoder.layers.6.mlp.fc2",
        "vision_model.encoder.layers.7.self_attn.k_proj",
        "vision_model.encoder.layers.7.self_attn.v_proj",
        "vision_model.encoder.layers.7.self_attn.q_proj",
        "vision_model.encoder.layers.7.self_attn.out_proj",
        "vision_model.encoder.layers.7.mlp.fc1",
        "vision_model.encoder.layers.7.mlp.fc2",
        "vision_model.encoder.layers.8.self_attn.k_proj",
        "vision_model.encoder.layers.8.self_attn.v_proj",
        "vision_model.encoder.layers.8.self_attn.q_proj",
        "vision_model.encoder.layers.8.self_attn.out_proj",
        "vision_model.encoder.layers.8.mlp.fc1",
        "vision_model.encoder.layers.8.mlp.fc2",
        "vision_model.encoder.layers.9.self_attn.k_proj",
        "vision_model.encoder.layers.9.self_attn.v_proj",
        "vision_model.encoder.layers.9.self_attn.q_proj",
        "vision_model.encoder.layers.9.self_attn.out_proj",
        "vision_model.encoder.layers.9.mlp.fc1",
        "vision_model.encoder.layers.9.mlp.fc2",
        "vision_model.encoder.layers.10.self_attn.k_proj",
        "vision_model.encoder.layers.10.self_attn.v_proj",
        "vision_model.encoder.layers.10.self_attn.q_proj",
        "vision_model.encoder.layers.10.self_attn.out_proj",
        "vision_model.encoder.layers.10.mlp.fc1",
        "vision_model.encoder.layers.10.mlp.fc2",
        "vision_model.encoder.layers.11.self_attn.k_proj",
        "vision_model.encoder.layers.11.self_attn.v_proj",
        "vision_model.encoder.layers.11.self_attn.q_proj",
        "vision_model.encoder.layers.11.self_attn.out_proj",
        "vision_model.encoder.layers.11.mlp.fc1",
        "vision_model.encoder.layers.11.mlp.fc2",
        "vision_model.encoder.layers.12.self_attn.k_proj",
        "vision_model.encoder.layers.12.self_attn.v_proj",
        "vision_model.encoder.layers.12.self_attn.q_proj",
        "vision_model.encoder.layers.12.self_attn.out_proj",
        "vision_model.encoder.layers.12.mlp.fc1",
        "vision_model.encoder.layers.12.mlp.fc2",
        "vision_model.encoder.layers.13.self_attn.k_proj",
        "vision_model.encoder.layers.13.self_attn.v_proj",
        "vision_model.encoder.layers.13.self_attn.q_proj",
        "vision_model.encoder.layers.13.self_attn.out_proj",
        "vision_model.encoder.layers.13.mlp.fc1",
        "vision_model.encoder.layers.13.mlp.fc2",
        "vision_model.encoder.layers.14.self_attn.k_proj",
        "vision_model.encoder.layers.14.self_attn.v_proj",
        "vision_model.encoder.layers.14.self_attn.q_proj",
        "vision_model.encoder.layers.14.self_attn.out_proj",
        "vision_model.encoder.layers.14.mlp.fc1",
        "vision_model.encoder.layers.14.mlp.fc2",
        "vision_model.encoder.layers.15.self_attn.k_proj",
        "vision_model.encoder.layers.15.self_attn.v_proj",
        "vision_model.encoder.layers.15.self_attn.q_proj",
        "vision_model.encoder.layers.15.self_attn.out_proj",
        "vision_model.encoder.layers.15.mlp.fc1",
        "vision_model.encoder.layers.15.mlp.fc2",
        "vision_model.encoder.layers.16.self_attn.k_proj",
        "vision_model.encoder.layers.16.self_attn.v_proj",
        "vision_model.encoder.layers.16.self_attn.q_proj",
        "vision_model.encoder.layers.16.self_attn.out_proj",
        "vision_model.encoder.layers.16.mlp.fc1",
        "vision_model.encoder.layers.16.mlp.fc2",
        "vision_model.encoder.layers.17.self_attn.k_proj",
        "vision_model.encoder.layers.17.self_attn.v_proj",
        "vision_model.encoder.layers.17.self_attn.q_proj",
        "vision_model.encoder.layers.17.self_attn.out_proj",
        "vision_model.encoder.layers.17.mlp.fc1",
        "vision_model.encoder.layers.17.mlp.fc2",
        "vision_model.encoder.layers.18.self_attn.k_proj",
        "vision_model.encoder.layers.18.self_attn.v_proj",
        "vision_model.encoder.layers.18.self_attn.q_proj",
        "vision_model.encoder.layers.18.self_attn.out_proj",
        "vision_model.encoder.layers.18.mlp.fc1",
        "vision_model.encoder.layers.18.mlp.fc2",
        "vision_model.encoder.layers.19.self_attn.k_proj",
        "vision_model.encoder.layers.19.self_attn.v_proj",
        "vision_model.encoder.layers.19.self_attn.q_proj",
        "vision_model.encoder.layers.19.self_attn.out_proj",
        "vision_model.encoder.layers.19.mlp.fc1",
        "vision_model.encoder.layers.19.mlp.fc2",
        "vision_model.encoder.layers.20.self_attn.k_proj",
        "vision_model.encoder.layers.20.self_attn.v_proj",
        "vision_model.encoder.layers.20.self_attn.q_proj",
        "vision_model.encoder.layers.20.self_attn.out_proj",
        "vision_model.encoder.layers.20.mlp.fc1",
        "vision_model.encoder.layers.20.mlp.fc2",
        "vision_model.encoder.layers.21.self_attn.k_proj",
        "vision_model.encoder.layers.21.self_attn.v_proj",
        "vision_model.encoder.layers.21.self_attn.q_proj",
        "vision_model.encoder.layers.21.self_attn.out_proj",
        "vision_model.encoder.layers.21.mlp.fc1",
        "vision_model.encoder.layers.21.mlp.fc2",
        "vision_model.encoder.layers.22.self_attn.k_proj",
        "vision_model.encoder.layers.22.self_attn.v_proj",
        "vision_model.encoder.layers.22.self_attn.q_proj",
        "vision_model.encoder.layers.22.self_attn.out_proj",
        "vision_model.encoder.layers.22.mlp.fc1",
        "vision_model.encoder.layers.22.mlp.fc2",
        "vision_model.encoder.layers.23.self_attn.k_proj",
        "vision_model.encoder.layers.23.self_attn.v_proj",
        "vision_model.encoder.layers.23.self_attn.q_proj",
        "vision_model.encoder.layers.23.self_attn.out_proj",
        "vision_model.encoder.layers.23.mlp.fc1",
        "vision_model.encoder.layers.23.mlp.fc2",
        "vision_model.encoder.layers.24.self_attn.k_proj",
        "vision_model.encoder.layers.24.self_attn.v_proj",
        "vision_model.encoder.layers.24.self_attn.q_proj",
        "vision_model.encoder.layers.24.self_attn.out_proj",
        "vision_model.encoder.layers.24.mlp.fc1",
        "vision_model.encoder.layers.24.mlp.fc2",
        "vision_model.encoder.layers.25.self_attn.k_proj",
        "vision_model.encoder.layers.25.self_attn.v_proj",
        "vision_model.encoder.layers.25.self_attn.q_proj",
        "vision_model.encoder.layers.25.self_attn.out_proj",
        "vision_model.encoder.layers.25.mlp.fc1",
        "vision_model.encoder.layers.25.mlp.fc2",
        "vision_model.embeddings.patch_embedding"
      ]
    },
    "threads_per_block": [
      512
    ],
    "version": "0.2.0"
  },
  "model_type": "qwen2"
}