Hugging Face's logo

stereovoid
/
Z-Image-Turbo-4bit

Safetensors
Model card Files
xet
Community
Justfinethanks commited on
Commit
57a3fbb
·
verified ·
1 Parent(s): d136277

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. text_encoder/0.safetensors +3 -0
  3. text_encoder/1.safetensors +3 -0
  4. text_encoder/model.safetensors.index.json +913 -0
  5. tokenizer/chat_template.jinja +89 -0
  6. tokenizer/tokenizer.json +3 -0
  7. tokenizer/tokenizer_config.json +29 -0
  8. transformer/0.safetensors +3 -0
  9. transformer/1.safetensors +3 -0
  10. transformer/model.safetensors.index.json +1081 -0
  11. vae/0.safetensors +3 -0
  12. vae/model.safetensors.index.json +268 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
text_encoder/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195160fdda2e5c8f6dc47ce0c44d7438fc50644579a07b9a156499c3afe0be42
3
+ size 2135435091
text_encoder/1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c276182d5b90209f20f7b5a6e2768a74834afe8d9572bd5899a54039cf3d7d73
3
+ size 127582107
text_encoder/model.safetensors.index.json ADDED
@@ -0,0 +1,913 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "4",
4
+ "mflux_version": "0.14.1"
5
+ },
6
+ "weight_map": {
7
+ "embed_tokens.weight": "0.safetensors",
8
+ "embed_tokens.scales": "0.safetensors",
9
+ "embed_tokens.biases": "0.safetensors",
10
+ "layers.0.input_layernorm.weight": "0.safetensors",
11
+ "layers.0.post_attention_layernorm.weight": "0.safetensors",
12
+ "layers.0.self_attn.q_proj.weight": "0.safetensors",
13
+ "layers.0.self_attn.q_proj.scales": "0.safetensors",
14
+ "layers.0.self_attn.q_proj.biases": "0.safetensors",
15
+ "layers.0.self_attn.k_proj.weight": "0.safetensors",
16
+ "layers.0.self_attn.k_proj.scales": "0.safetensors",
17
+ "layers.0.self_attn.k_proj.biases": "0.safetensors",
18
+ "layers.0.self_attn.v_proj.weight": "0.safetensors",
19
+ "layers.0.self_attn.v_proj.scales": "0.safetensors",
20
+ "layers.0.self_attn.v_proj.biases": "0.safetensors",
21
+ "layers.0.self_attn.o_proj.weight": "0.safetensors",
22
+ "layers.0.self_attn.o_proj.scales": "0.safetensors",
23
+ "layers.0.self_attn.o_proj.biases": "0.safetensors",
24
+ "layers.0.self_attn.q_norm.weight": "0.safetensors",
25
+ "layers.0.self_attn.k_norm.weight": "0.safetensors",
26
+ "layers.0.mlp.gate_proj.weight": "0.safetensors",
27
+ "layers.0.mlp.gate_proj.scales": "0.safetensors",
28
+ "layers.0.mlp.gate_proj.biases": "0.safetensors",
29
+ "layers.0.mlp.up_proj.weight": "0.safetensors",
30
+ "layers.0.mlp.up_proj.scales": "0.safetensors",
31
+ "layers.0.mlp.up_proj.biases": "0.safetensors",
32
+ "layers.0.mlp.down_proj.weight": "0.safetensors",
33
+ "layers.0.mlp.down_proj.scales": "0.safetensors",
34
+ "layers.0.mlp.down_proj.biases": "0.safetensors",
35
+ "layers.1.input_layernorm.weight": "0.safetensors",
36
+ "layers.1.post_attention_layernorm.weight": "0.safetensors",
37
+ "layers.1.self_attn.q_proj.weight": "0.safetensors",
38
+ "layers.1.self_attn.q_proj.scales": "0.safetensors",
39
+ "layers.1.self_attn.q_proj.biases": "0.safetensors",
40
+ "layers.1.self_attn.k_proj.weight": "0.safetensors",
41
+ "layers.1.self_attn.k_proj.scales": "0.safetensors",
42
+ "layers.1.self_attn.k_proj.biases": "0.safetensors",
43
+ "layers.1.self_attn.v_proj.weight": "0.safetensors",
44
+ "layers.1.self_attn.v_proj.scales": "0.safetensors",
45
+ "layers.1.self_attn.v_proj.biases": "0.safetensors",
46
+ "layers.1.self_attn.o_proj.weight": "0.safetensors",
47
+ "layers.1.self_attn.o_proj.scales": "0.safetensors",
48
+ "layers.1.self_attn.o_proj.biases": "0.safetensors",
49
+ "layers.1.self_attn.q_norm.weight": "0.safetensors",
50
+ "layers.1.self_attn.k_norm.weight": "0.safetensors",
51
+ "layers.1.mlp.gate_proj.weight": "0.safetensors",
52
+ "layers.1.mlp.gate_proj.scales": "0.safetensors",
53
+ "layers.1.mlp.gate_proj.biases": "0.safetensors",
54
+ "layers.1.mlp.up_proj.weight": "0.safetensors",
55
+ "layers.1.mlp.up_proj.scales": "0.safetensors",
56
+ "layers.1.mlp.up_proj.biases": "0.safetensors",
57
+ "layers.1.mlp.down_proj.weight": "0.safetensors",
58
+ "layers.1.mlp.down_proj.scales": "0.safetensors",
59
+ "layers.1.mlp.down_proj.biases": "0.safetensors",
60
+ "layers.2.input_layernorm.weight": "0.safetensors",
61
+ "layers.2.post_attention_layernorm.weight": "0.safetensors",
62
+ "layers.2.self_attn.q_proj.weight": "0.safetensors",
63
+ "layers.2.self_attn.q_proj.scales": "0.safetensors",
64
+ "layers.2.self_attn.q_proj.biases": "0.safetensors",
65
+ "layers.2.self_attn.k_proj.weight": "0.safetensors",
66
+ "layers.2.self_attn.k_proj.scales": "0.safetensors",
67
+ "layers.2.self_attn.k_proj.biases": "0.safetensors",
68
+ "layers.2.self_attn.v_proj.weight": "0.safetensors",
69
+ "layers.2.self_attn.v_proj.scales": "0.safetensors",
70
+ "layers.2.self_attn.v_proj.biases": "0.safetensors",
71
+ "layers.2.self_attn.o_proj.weight": "0.safetensors",
72
+ "layers.2.self_attn.o_proj.scales": "0.safetensors",
73
+ "layers.2.self_attn.o_proj.biases": "0.safetensors",
74
+ "layers.2.self_attn.q_norm.weight": "0.safetensors",
75
+ "layers.2.self_attn.k_norm.weight": "0.safetensors",
76
+ "layers.2.mlp.gate_proj.weight": "0.safetensors",
77
+ "layers.2.mlp.gate_proj.scales": "0.safetensors",
78
+ "layers.2.mlp.gate_proj.biases": "0.safetensors",
79
+ "layers.2.mlp.up_proj.weight": "0.safetensors",
80
+ "layers.2.mlp.up_proj.scales": "0.safetensors",
81
+ "layers.2.mlp.up_proj.biases": "0.safetensors",
82
+ "layers.2.mlp.down_proj.weight": "0.safetensors",
83
+ "layers.2.mlp.down_proj.scales": "0.safetensors",
84
+ "layers.2.mlp.down_proj.biases": "0.safetensors",
85
+ "layers.3.input_layernorm.weight": "0.safetensors",
86
+ "layers.3.post_attention_layernorm.weight": "0.safetensors",
87
+ "layers.3.self_attn.q_proj.weight": "0.safetensors",
88
+ "layers.3.self_attn.q_proj.scales": "0.safetensors",
89
+ "layers.3.self_attn.q_proj.biases": "0.safetensors",
90
+ "layers.3.self_attn.k_proj.weight": "0.safetensors",
91
+ "layers.3.self_attn.k_proj.scales": "0.safetensors",
92
+ "layers.3.self_attn.k_proj.biases": "0.safetensors",
93
+ "layers.3.self_attn.v_proj.weight": "0.safetensors",
94
+ "layers.3.self_attn.v_proj.scales": "0.safetensors",
95
+ "layers.3.self_attn.v_proj.biases": "0.safetensors",
96
+ "layers.3.self_attn.o_proj.weight": "0.safetensors",
97
+ "layers.3.self_attn.o_proj.scales": "0.safetensors",
98
+ "layers.3.self_attn.o_proj.biases": "0.safetensors",
99
+ "layers.3.self_attn.q_norm.weight": "0.safetensors",
100
+ "layers.3.self_attn.k_norm.weight": "0.safetensors",
101
+ "layers.3.mlp.gate_proj.weight": "0.safetensors",
102
+ "layers.3.mlp.gate_proj.scales": "0.safetensors",
103
+ "layers.3.mlp.gate_proj.biases": "0.safetensors",
104
+ "layers.3.mlp.up_proj.weight": "0.safetensors",
105
+ "layers.3.mlp.up_proj.scales": "0.safetensors",
106
+ "layers.3.mlp.up_proj.biases": "0.safetensors",
107
+ "layers.3.mlp.down_proj.weight": "0.safetensors",
108
+ "layers.3.mlp.down_proj.scales": "0.safetensors",
109
+ "layers.3.mlp.down_proj.biases": "0.safetensors",
110
+ "layers.4.input_layernorm.weight": "0.safetensors",
111
+ "layers.4.post_attention_layernorm.weight": "0.safetensors",
112
+ "layers.4.self_attn.q_proj.weight": "0.safetensors",
113
+ "layers.4.self_attn.q_proj.scales": "0.safetensors",
114
+ "layers.4.self_attn.q_proj.biases": "0.safetensors",
115
+ "layers.4.self_attn.k_proj.weight": "0.safetensors",
116
+ "layers.4.self_attn.k_proj.scales": "0.safetensors",
117
+ "layers.4.self_attn.k_proj.biases": "0.safetensors",
118
+ "layers.4.self_attn.v_proj.weight": "0.safetensors",
119
+ "layers.4.self_attn.v_proj.scales": "0.safetensors",
120
+ "layers.4.self_attn.v_proj.biases": "0.safetensors",
121
+ "layers.4.self_attn.o_proj.weight": "0.safetensors",
122
+ "layers.4.self_attn.o_proj.scales": "0.safetensors",
123
+ "layers.4.self_attn.o_proj.biases": "0.safetensors",
124
+ "layers.4.self_attn.q_norm.weight": "0.safetensors",
125
+ "layers.4.self_attn.k_norm.weight": "0.safetensors",
126
+ "layers.4.mlp.gate_proj.weight": "0.safetensors",
127
+ "layers.4.mlp.gate_proj.scales": "0.safetensors",
128
+ "layers.4.mlp.gate_proj.biases": "0.safetensors",
129
+ "layers.4.mlp.up_proj.weight": "0.safetensors",
130
+ "layers.4.mlp.up_proj.scales": "0.safetensors",
131
+ "layers.4.mlp.up_proj.biases": "0.safetensors",
132
+ "layers.4.mlp.down_proj.weight": "0.safetensors",
133
+ "layers.4.mlp.down_proj.scales": "0.safetensors",
134
+ "layers.4.mlp.down_proj.biases": "0.safetensors",
135
+ "layers.5.input_layernorm.weight": "0.safetensors",
136
+ "layers.5.post_attention_layernorm.weight": "0.safetensors",
137
+ "layers.5.self_attn.q_proj.weight": "0.safetensors",
138
+ "layers.5.self_attn.q_proj.scales": "0.safetensors",
139
+ "layers.5.self_attn.q_proj.biases": "0.safetensors",
140
+ "layers.5.self_attn.k_proj.weight": "0.safetensors",
141
+ "layers.5.self_attn.k_proj.scales": "0.safetensors",
142
+ "layers.5.self_attn.k_proj.biases": "0.safetensors",
143
+ "layers.5.self_attn.v_proj.weight": "0.safetensors",
144
+ "layers.5.self_attn.v_proj.scales": "0.safetensors",
145
+ "layers.5.self_attn.v_proj.biases": "0.safetensors",
146
+ "layers.5.self_attn.o_proj.weight": "0.safetensors",
147
+ "layers.5.self_attn.o_proj.scales": "0.safetensors",
148
+ "layers.5.self_attn.o_proj.biases": "0.safetensors",
149
+ "layers.5.self_attn.q_norm.weight": "0.safetensors",
150
+ "layers.5.self_attn.k_norm.weight": "0.safetensors",
151
+ "layers.5.mlp.gate_proj.weight": "0.safetensors",
152
+ "layers.5.mlp.gate_proj.scales": "0.safetensors",
153
+ "layers.5.mlp.gate_proj.biases": "0.safetensors",
154
+ "layers.5.mlp.up_proj.weight": "0.safetensors",
155
+ "layers.5.mlp.up_proj.scales": "0.safetensors",
156
+ "layers.5.mlp.up_proj.biases": "0.safetensors",
157
+ "layers.5.mlp.down_proj.weight": "0.safetensors",
158
+ "layers.5.mlp.down_proj.scales": "0.safetensors",
159
+ "layers.5.mlp.down_proj.biases": "0.safetensors",
160
+ "layers.6.input_layernorm.weight": "0.safetensors",
161
+ "layers.6.post_attention_layernorm.weight": "0.safetensors",
162
+ "layers.6.self_attn.q_proj.weight": "0.safetensors",
163
+ "layers.6.self_attn.q_proj.scales": "0.safetensors",
164
+ "layers.6.self_attn.q_proj.biases": "0.safetensors",
165
+ "layers.6.self_attn.k_proj.weight": "0.safetensors",
166
+ "layers.6.self_attn.k_proj.scales": "0.safetensors",
167
+ "layers.6.self_attn.k_proj.biases": "0.safetensors",
168
+ "layers.6.self_attn.v_proj.weight": "0.safetensors",
169
+ "layers.6.self_attn.v_proj.scales": "0.safetensors",
170
+ "layers.6.self_attn.v_proj.biases": "0.safetensors",
171
+ "layers.6.self_attn.o_proj.weight": "0.safetensors",
172
+ "layers.6.self_attn.o_proj.scales": "0.safetensors",
173
+ "layers.6.self_attn.o_proj.biases": "0.safetensors",
174
+ "layers.6.self_attn.q_norm.weight": "0.safetensors",
175
+ "layers.6.self_attn.k_norm.weight": "0.safetensors",
176
+ "layers.6.mlp.gate_proj.weight": "0.safetensors",
177
+ "layers.6.mlp.gate_proj.scales": "0.safetensors",
178
+ "layers.6.mlp.gate_proj.biases": "0.safetensors",
179
+ "layers.6.mlp.up_proj.weight": "0.safetensors",
180
+ "layers.6.mlp.up_proj.scales": "0.safetensors",
181
+ "layers.6.mlp.up_proj.biases": "0.safetensors",
182
+ "layers.6.mlp.down_proj.weight": "0.safetensors",
183
+ "layers.6.mlp.down_proj.scales": "0.safetensors",
184
+ "layers.6.mlp.down_proj.biases": "0.safetensors",
185
+ "layers.7.input_layernorm.weight": "0.safetensors",
186
+ "layers.7.post_attention_layernorm.weight": "0.safetensors",
187
+ "layers.7.self_attn.q_proj.weight": "0.safetensors",
188
+ "layers.7.self_attn.q_proj.scales": "0.safetensors",
189
+ "layers.7.self_attn.q_proj.biases": "0.safetensors",
190
+ "layers.7.self_attn.k_proj.weight": "0.safetensors",
191
+ "layers.7.self_attn.k_proj.scales": "0.safetensors",
192
+ "layers.7.self_attn.k_proj.biases": "0.safetensors",
193
+ "layers.7.self_attn.v_proj.weight": "0.safetensors",
194
+ "layers.7.self_attn.v_proj.scales": "0.safetensors",
195
+ "layers.7.self_attn.v_proj.biases": "0.safetensors",
196
+ "layers.7.self_attn.o_proj.weight": "0.safetensors",
197
+ "layers.7.self_attn.o_proj.scales": "0.safetensors",
198
+ "layers.7.self_attn.o_proj.biases": "0.safetensors",
199
+ "layers.7.self_attn.q_norm.weight": "0.safetensors",
200
+ "layers.7.self_attn.k_norm.weight": "0.safetensors",
201
+ "layers.7.mlp.gate_proj.weight": "0.safetensors",
202
+ "layers.7.mlp.gate_proj.scales": "0.safetensors",
203
+ "layers.7.mlp.gate_proj.biases": "0.safetensors",
204
+ "layers.7.mlp.up_proj.weight": "0.safetensors",
205
+ "layers.7.mlp.up_proj.scales": "0.safetensors",
206
+ "layers.7.mlp.up_proj.biases": "0.safetensors",
207
+ "layers.7.mlp.down_proj.weight": "0.safetensors",
208
+ "layers.7.mlp.down_proj.scales": "0.safetensors",
209
+ "layers.7.mlp.down_proj.biases": "0.safetensors",
210
+ "layers.8.input_layernorm.weight": "0.safetensors",
211
+ "layers.8.post_attention_layernorm.weight": "0.safetensors",
212
+ "layers.8.self_attn.q_proj.weight": "0.safetensors",
213
+ "layers.8.self_attn.q_proj.scales": "0.safetensors",
214
+ "layers.8.self_attn.q_proj.biases": "0.safetensors",
215
+ "layers.8.self_attn.k_proj.weight": "0.safetensors",
216
+ "layers.8.self_attn.k_proj.scales": "0.safetensors",
217
+ "layers.8.self_attn.k_proj.biases": "0.safetensors",
218
+ "layers.8.self_attn.v_proj.weight": "0.safetensors",
219
+ "layers.8.self_attn.v_proj.scales": "0.safetensors",
220
+ "layers.8.self_attn.v_proj.biases": "0.safetensors",
221
+ "layers.8.self_attn.o_proj.weight": "0.safetensors",
222
+ "layers.8.self_attn.o_proj.scales": "0.safetensors",
223
+ "layers.8.self_attn.o_proj.biases": "0.safetensors",
224
+ "layers.8.self_attn.q_norm.weight": "0.safetensors",
225
+ "layers.8.self_attn.k_norm.weight": "0.safetensors",
226
+ "layers.8.mlp.gate_proj.weight": "0.safetensors",
227
+ "layers.8.mlp.gate_proj.scales": "0.safetensors",
228
+ "layers.8.mlp.gate_proj.biases": "0.safetensors",
229
+ "layers.8.mlp.up_proj.weight": "0.safetensors",
230
+ "layers.8.mlp.up_proj.scales": "0.safetensors",
231
+ "layers.8.mlp.up_proj.biases": "0.safetensors",
232
+ "layers.8.mlp.down_proj.weight": "0.safetensors",
233
+ "layers.8.mlp.down_proj.scales": "0.safetensors",
234
+ "layers.8.mlp.down_proj.biases": "0.safetensors",
235
+ "layers.9.input_layernorm.weight": "0.safetensors",
236
+ "layers.9.post_attention_layernorm.weight": "0.safetensors",
237
+ "layers.9.self_attn.q_proj.weight": "0.safetensors",
238
+ "layers.9.self_attn.q_proj.scales": "0.safetensors",
239
+ "layers.9.self_attn.q_proj.biases": "0.safetensors",
240
+ "layers.9.self_attn.k_proj.weight": "0.safetensors",
241
+ "layers.9.self_attn.k_proj.scales": "0.safetensors",
242
+ "layers.9.self_attn.k_proj.biases": "0.safetensors",
243
+ "layers.9.self_attn.v_proj.weight": "0.safetensors",
244
+ "layers.9.self_attn.v_proj.scales": "0.safetensors",
245
+ "layers.9.self_attn.v_proj.biases": "0.safetensors",
246
+ "layers.9.self_attn.o_proj.weight": "0.safetensors",
247
+ "layers.9.self_attn.o_proj.scales": "0.safetensors",
248
+ "layers.9.self_attn.o_proj.biases": "0.safetensors",
249
+ "layers.9.self_attn.q_norm.weight": "0.safetensors",
250
+ "layers.9.self_attn.k_norm.weight": "0.safetensors",
251
+ "layers.9.mlp.gate_proj.weight": "0.safetensors",
252
+ "layers.9.mlp.gate_proj.scales": "0.safetensors",
253
+ "layers.9.mlp.gate_proj.biases": "0.safetensors",
254
+ "layers.9.mlp.up_proj.weight": "0.safetensors",
255
+ "layers.9.mlp.up_proj.scales": "0.safetensors",
256
+ "layers.9.mlp.up_proj.biases": "0.safetensors",
257
+ "layers.9.mlp.down_proj.weight": "0.safetensors",
258
+ "layers.9.mlp.down_proj.scales": "0.safetensors",
259
+ "layers.9.mlp.down_proj.biases": "0.safetensors",
260
+ "layers.10.input_layernorm.weight": "0.safetensors",
261
+ "layers.10.post_attention_layernorm.weight": "0.safetensors",
262
+ "layers.10.self_attn.q_proj.weight": "0.safetensors",
263
+ "layers.10.self_attn.q_proj.scales": "0.safetensors",
264
+ "layers.10.self_attn.q_proj.biases": "0.safetensors",
265
+ "layers.10.self_attn.k_proj.weight": "0.safetensors",
266
+ "layers.10.self_attn.k_proj.scales": "0.safetensors",
267
+ "layers.10.self_attn.k_proj.biases": "0.safetensors",
268
+ "layers.10.self_attn.v_proj.weight": "0.safetensors",
269
+ "layers.10.self_attn.v_proj.scales": "0.safetensors",
270
+ "layers.10.self_attn.v_proj.biases": "0.safetensors",
271
+ "layers.10.self_attn.o_proj.weight": "0.safetensors",
272
+ "layers.10.self_attn.o_proj.scales": "0.safetensors",
273
+ "layers.10.self_attn.o_proj.biases": "0.safetensors",
274
+ "layers.10.self_attn.q_norm.weight": "0.safetensors",
275
+ "layers.10.self_attn.k_norm.weight": "0.safetensors",
276
+ "layers.10.mlp.gate_proj.weight": "0.safetensors",
277
+ "layers.10.mlp.gate_proj.scales": "0.safetensors",
278
+ "layers.10.mlp.gate_proj.biases": "0.safetensors",
279
+ "layers.10.mlp.up_proj.weight": "0.safetensors",
280
+ "layers.10.mlp.up_proj.scales": "0.safetensors",
281
+ "layers.10.mlp.up_proj.biases": "0.safetensors",
282
+ "layers.10.mlp.down_proj.weight": "0.safetensors",
283
+ "layers.10.mlp.down_proj.scales": "0.safetensors",
284
+ "layers.10.mlp.down_proj.biases": "0.safetensors",
285
+ "layers.11.input_layernorm.weight": "0.safetensors",
286
+ "layers.11.post_attention_layernorm.weight": "0.safetensors",
287
+ "layers.11.self_attn.q_proj.weight": "0.safetensors",
288
+ "layers.11.self_attn.q_proj.scales": "0.safetensors",
289
+ "layers.11.self_attn.q_proj.biases": "0.safetensors",
290
+ "layers.11.self_attn.k_proj.weight": "0.safetensors",
291
+ "layers.11.self_attn.k_proj.scales": "0.safetensors",
292
+ "layers.11.self_attn.k_proj.biases": "0.safetensors",
293
+ "layers.11.self_attn.v_proj.weight": "0.safetensors",
294
+ "layers.11.self_attn.v_proj.scales": "0.safetensors",
295
+ "layers.11.self_attn.v_proj.biases": "0.safetensors",
296
+ "layers.11.self_attn.o_proj.weight": "0.safetensors",
297
+ "layers.11.self_attn.o_proj.scales": "0.safetensors",
298
+ "layers.11.self_attn.o_proj.biases": "0.safetensors",
299
+ "layers.11.self_attn.q_norm.weight": "0.safetensors",
300
+ "layers.11.self_attn.k_norm.weight": "0.safetensors",
301
+ "layers.11.mlp.gate_proj.weight": "0.safetensors",
302
+ "layers.11.mlp.gate_proj.scales": "0.safetensors",
303
+ "layers.11.mlp.gate_proj.biases": "0.safetensors",
304
+ "layers.11.mlp.up_proj.weight": "0.safetensors",
305
+ "layers.11.mlp.up_proj.scales": "0.safetensors",
306
+ "layers.11.mlp.up_proj.biases": "0.safetensors",
307
+ "layers.11.mlp.down_proj.weight": "0.safetensors",
308
+ "layers.11.mlp.down_proj.scales": "0.safetensors",
309
+ "layers.11.mlp.down_proj.biases": "0.safetensors",
310
+ "layers.12.input_layernorm.weight": "0.safetensors",
311
+ "layers.12.post_attention_layernorm.weight": "0.safetensors",
312
+ "layers.12.self_attn.q_proj.weight": "0.safetensors",
313
+ "layers.12.self_attn.q_proj.scales": "0.safetensors",
314
+ "layers.12.self_attn.q_proj.biases": "0.safetensors",
315
+ "layers.12.self_attn.k_proj.weight": "0.safetensors",
316
+ "layers.12.self_attn.k_proj.scales": "0.safetensors",
317
+ "layers.12.self_attn.k_proj.biases": "0.safetensors",
318
+ "layers.12.self_attn.v_proj.weight": "0.safetensors",
319
+ "layers.12.self_attn.v_proj.scales": "0.safetensors",
320
+ "layers.12.self_attn.v_proj.biases": "0.safetensors",
321
+ "layers.12.self_attn.o_proj.weight": "0.safetensors",
322
+ "layers.12.self_attn.o_proj.scales": "0.safetensors",
323
+ "layers.12.self_attn.o_proj.biases": "0.safetensors",
324
+ "layers.12.self_attn.q_norm.weight": "0.safetensors",
325
+ "layers.12.self_attn.k_norm.weight": "0.safetensors",
326
+ "layers.12.mlp.gate_proj.weight": "0.safetensors",
327
+ "layers.12.mlp.gate_proj.scales": "0.safetensors",
328
+ "layers.12.mlp.gate_proj.biases": "0.safetensors",
329
+ "layers.12.mlp.up_proj.weight": "0.safetensors",
330
+ "layers.12.mlp.up_proj.scales": "0.safetensors",
331
+ "layers.12.mlp.up_proj.biases": "0.safetensors",
332
+ "layers.12.mlp.down_proj.weight": "0.safetensors",
333
+ "layers.12.mlp.down_proj.scales": "0.safetensors",
334
+ "layers.12.mlp.down_proj.biases": "0.safetensors",
335
+ "layers.13.input_layernorm.weight": "0.safetensors",
336
+ "layers.13.post_attention_layernorm.weight": "0.safetensors",
337
+ "layers.13.self_attn.q_proj.weight": "0.safetensors",
338
+ "layers.13.self_attn.q_proj.scales": "0.safetensors",
339
+ "layers.13.self_attn.q_proj.biases": "0.safetensors",
340
+ "layers.13.self_attn.k_proj.weight": "0.safetensors",
341
+ "layers.13.self_attn.k_proj.scales": "0.safetensors",
342
+ "layers.13.self_attn.k_proj.biases": "0.safetensors",
343
+ "layers.13.self_attn.v_proj.weight": "0.safetensors",
344
+ "layers.13.self_attn.v_proj.scales": "0.safetensors",
345
+ "layers.13.self_attn.v_proj.biases": "0.safetensors",
346
+ "layers.13.self_attn.o_proj.weight": "0.safetensors",
347
+ "layers.13.self_attn.o_proj.scales": "0.safetensors",
348
+ "layers.13.self_attn.o_proj.biases": "0.safetensors",
349
+ "layers.13.self_attn.q_norm.weight": "0.safetensors",
350
+ "layers.13.self_attn.k_norm.weight": "0.safetensors",
351
+ "layers.13.mlp.gate_proj.weight": "0.safetensors",
352
+ "layers.13.mlp.gate_proj.scales": "0.safetensors",
353
+ "layers.13.mlp.gate_proj.biases": "0.safetensors",
354
+ "layers.13.mlp.up_proj.weight": "0.safetensors",
355
+ "layers.13.mlp.up_proj.scales": "0.safetensors",
356
+ "layers.13.mlp.up_proj.biases": "0.safetensors",
357
+ "layers.13.mlp.down_proj.weight": "0.safetensors",
358
+ "layers.13.mlp.down_proj.scales": "0.safetensors",
359
+ "layers.13.mlp.down_proj.biases": "0.safetensors",
360
+ "layers.14.input_layernorm.weight": "0.safetensors",
361
+ "layers.14.post_attention_layernorm.weight": "0.safetensors",
362
+ "layers.14.self_attn.q_proj.weight": "0.safetensors",
363
+ "layers.14.self_attn.q_proj.scales": "0.safetensors",
364
+ "layers.14.self_attn.q_proj.biases": "0.safetensors",
365
+ "layers.14.self_attn.k_proj.weight": "0.safetensors",
366
+ "layers.14.self_attn.k_proj.scales": "0.safetensors",
367
+ "layers.14.self_attn.k_proj.biases": "0.safetensors",
368
+ "layers.14.self_attn.v_proj.weight": "0.safetensors",
369
+ "layers.14.self_attn.v_proj.scales": "0.safetensors",
370
+ "layers.14.self_attn.v_proj.biases": "0.safetensors",
371
+ "layers.14.self_attn.o_proj.weight": "0.safetensors",
372
+ "layers.14.self_attn.o_proj.scales": "0.safetensors",
373
+ "layers.14.self_attn.o_proj.biases": "0.safetensors",
374
+ "layers.14.self_attn.q_norm.weight": "0.safetensors",
375
+ "layers.14.self_attn.k_norm.weight": "0.safetensors",
376
+ "layers.14.mlp.gate_proj.weight": "0.safetensors",
377
+ "layers.14.mlp.gate_proj.scales": "0.safetensors",
378
+ "layers.14.mlp.gate_proj.biases": "0.safetensors",
379
+ "layers.14.mlp.up_proj.weight": "0.safetensors",
380
+ "layers.14.mlp.up_proj.scales": "0.safetensors",
381
+ "layers.14.mlp.up_proj.biases": "0.safetensors",
382
+ "layers.14.mlp.down_proj.weight": "0.safetensors",
383
+ "layers.14.mlp.down_proj.scales": "0.safetensors",
384
+ "layers.14.mlp.down_proj.biases": "0.safetensors",
385
+ "layers.15.input_layernorm.weight": "0.safetensors",
386
+ "layers.15.post_attention_layernorm.weight": "0.safetensors",
387
+ "layers.15.self_attn.q_proj.weight": "0.safetensors",
388
+ "layers.15.self_attn.q_proj.scales": "0.safetensors",
389
+ "layers.15.self_attn.q_proj.biases": "0.safetensors",
390
+ "layers.15.self_attn.k_proj.weight": "0.safetensors",
391
+ "layers.15.self_attn.k_proj.scales": "0.safetensors",
392
+ "layers.15.self_attn.k_proj.biases": "0.safetensors",
393
+ "layers.15.self_attn.v_proj.weight": "0.safetensors",
394
+ "layers.15.self_attn.v_proj.scales": "0.safetensors",
395
+ "layers.15.self_attn.v_proj.biases": "0.safetensors",
396
+ "layers.15.self_attn.o_proj.weight": "0.safetensors",
397
+ "layers.15.self_attn.o_proj.scales": "0.safetensors",
398
+ "layers.15.self_attn.o_proj.biases": "0.safetensors",
399
+ "layers.15.self_attn.q_norm.weight": "0.safetensors",
400
+ "layers.15.self_attn.k_norm.weight": "0.safetensors",
401
+ "layers.15.mlp.gate_proj.weight": "0.safetensors",
402
+ "layers.15.mlp.gate_proj.scales": "0.safetensors",
403
+ "layers.15.mlp.gate_proj.biases": "0.safetensors",
404
+ "layers.15.mlp.up_proj.weight": "0.safetensors",
405
+ "layers.15.mlp.up_proj.scales": "0.safetensors",
406
+ "layers.15.mlp.up_proj.biases": "0.safetensors",
407
+ "layers.15.mlp.down_proj.weight": "0.safetensors",
408
+ "layers.15.mlp.down_proj.scales": "0.safetensors",
409
+ "layers.15.mlp.down_proj.biases": "0.safetensors",
410
+ "layers.16.input_layernorm.weight": "0.safetensors",
411
+ "layers.16.post_attention_layernorm.weight": "0.safetensors",
412
+ "layers.16.self_attn.q_proj.weight": "0.safetensors",
413
+ "layers.16.self_attn.q_proj.scales": "0.safetensors",
414
+ "layers.16.self_attn.q_proj.biases": "0.safetensors",
415
+ "layers.16.self_attn.k_proj.weight": "0.safetensors",
416
+ "layers.16.self_attn.k_proj.scales": "0.safetensors",
417
+ "layers.16.self_attn.k_proj.biases": "0.safetensors",
418
+ "layers.16.self_attn.v_proj.weight": "0.safetensors",
419
+ "layers.16.self_attn.v_proj.scales": "0.safetensors",
420
+ "layers.16.self_attn.v_proj.biases": "0.safetensors",
421
+ "layers.16.self_attn.o_proj.weight": "0.safetensors",
422
+ "layers.16.self_attn.o_proj.scales": "0.safetensors",
423
+ "layers.16.self_attn.o_proj.biases": "0.safetensors",
424
+ "layers.16.self_attn.q_norm.weight": "0.safetensors",
425
+ "layers.16.self_attn.k_norm.weight": "0.safetensors",
426
+ "layers.16.mlp.gate_proj.weight": "0.safetensors",
427
+ "layers.16.mlp.gate_proj.scales": "0.safetensors",
428
+ "layers.16.mlp.gate_proj.biases": "0.safetensors",
429
+ "layers.16.mlp.up_proj.weight": "0.safetensors",
430
+ "layers.16.mlp.up_proj.scales": "0.safetensors",
431
+ "layers.16.mlp.up_proj.biases": "0.safetensors",
432
+ "layers.16.mlp.down_proj.weight": "0.safetensors",
433
+ "layers.16.mlp.down_proj.scales": "0.safetensors",
434
+ "layers.16.mlp.down_proj.biases": "0.safetensors",
435
+ "layers.17.input_layernorm.weight": "0.safetensors",
436
+ "layers.17.post_attention_layernorm.weight": "0.safetensors",
437
+ "layers.17.self_attn.q_proj.weight": "0.safetensors",
438
+ "layers.17.self_attn.q_proj.scales": "0.safetensors",
439
+ "layers.17.self_attn.q_proj.biases": "0.safetensors",
440
+ "layers.17.self_attn.k_proj.weight": "0.safetensors",
441
+ "layers.17.self_attn.k_proj.scales": "0.safetensors",
442
+ "layers.17.self_attn.k_proj.biases": "0.safetensors",
443
+ "layers.17.self_attn.v_proj.weight": "0.safetensors",
444
+ "layers.17.self_attn.v_proj.scales": "0.safetensors",
445
+ "layers.17.self_attn.v_proj.biases": "0.safetensors",
446
+ "layers.17.self_attn.o_proj.weight": "0.safetensors",
447
+ "layers.17.self_attn.o_proj.scales": "0.safetensors",
448
+ "layers.17.self_attn.o_proj.biases": "0.safetensors",
449
+ "layers.17.self_attn.q_norm.weight": "0.safetensors",
450
+ "layers.17.self_attn.k_norm.weight": "0.safetensors",
451
+ "layers.17.mlp.gate_proj.weight": "0.safetensors",
452
+ "layers.17.mlp.gate_proj.scales": "0.safetensors",
453
+ "layers.17.mlp.gate_proj.biases": "0.safetensors",
454
+ "layers.17.mlp.up_proj.weight": "0.safetensors",
455
+ "layers.17.mlp.up_proj.scales": "0.safetensors",
456
+ "layers.17.mlp.up_proj.biases": "0.safetensors",
457
+ "layers.17.mlp.down_proj.weight": "0.safetensors",
458
+ "layers.17.mlp.down_proj.scales": "0.safetensors",
459
+ "layers.17.mlp.down_proj.biases": "0.safetensors",
460
+ "layers.18.input_layernorm.weight": "0.safetensors",
461
+ "layers.18.post_attention_layernorm.weight": "0.safetensors",
462
+ "layers.18.self_attn.q_proj.weight": "0.safetensors",
463
+ "layers.18.self_attn.q_proj.scales": "0.safetensors",
464
+ "layers.18.self_attn.q_proj.biases": "0.safetensors",
465
+ "layers.18.self_attn.k_proj.weight": "0.safetensors",
466
+ "layers.18.self_attn.k_proj.scales": "0.safetensors",
467
+ "layers.18.self_attn.k_proj.biases": "0.safetensors",
468
+ "layers.18.self_attn.v_proj.weight": "0.safetensors",
469
+ "layers.18.self_attn.v_proj.scales": "0.safetensors",
470
+ "layers.18.self_attn.v_proj.biases": "0.safetensors",
471
+ "layers.18.self_attn.o_proj.weight": "0.safetensors",
472
+ "layers.18.self_attn.o_proj.scales": "0.safetensors",
473
+ "layers.18.self_attn.o_proj.biases": "0.safetensors",
474
+ "layers.18.self_attn.q_norm.weight": "0.safetensors",
475
+ "layers.18.self_attn.k_norm.weight": "0.safetensors",
476
+ "layers.18.mlp.gate_proj.weight": "0.safetensors",
477
+ "layers.18.mlp.gate_proj.scales": "0.safetensors",
478
+ "layers.18.mlp.gate_proj.biases": "0.safetensors",
479
+ "layers.18.mlp.up_proj.weight": "0.safetensors",
480
+ "layers.18.mlp.up_proj.scales": "0.safetensors",
481
+ "layers.18.mlp.up_proj.biases": "0.safetensors",
482
+ "layers.18.mlp.down_proj.weight": "0.safetensors",
483
+ "layers.18.mlp.down_proj.scales": "0.safetensors",
484
+ "layers.18.mlp.down_proj.biases": "0.safetensors",
485
+ "layers.19.input_layernorm.weight": "0.safetensors",
486
+ "layers.19.post_attention_layernorm.weight": "0.safetensors",
487
+ "layers.19.self_attn.q_proj.weight": "0.safetensors",
488
+ "layers.19.self_attn.q_proj.scales": "0.safetensors",
489
+ "layers.19.self_attn.q_proj.biases": "0.safetensors",
490
+ "layers.19.self_attn.k_proj.weight": "0.safetensors",
491
+ "layers.19.self_attn.k_proj.scales": "0.safetensors",
492
+ "layers.19.self_attn.k_proj.biases": "0.safetensors",
493
+ "layers.19.self_attn.v_proj.weight": "0.safetensors",
494
+ "layers.19.self_attn.v_proj.scales": "0.safetensors",
495
+ "layers.19.self_attn.v_proj.biases": "0.safetensors",
496
+ "layers.19.self_attn.o_proj.weight": "0.safetensors",
497
+ "layers.19.self_attn.o_proj.scales": "0.safetensors",
498
+ "layers.19.self_attn.o_proj.biases": "0.safetensors",
499
+ "layers.19.self_attn.q_norm.weight": "0.safetensors",
500
+ "layers.19.self_attn.k_norm.weight": "0.safetensors",
501
+ "layers.19.mlp.gate_proj.weight": "0.safetensors",
502
+ "layers.19.mlp.gate_proj.scales": "0.safetensors",
503
+ "layers.19.mlp.gate_proj.biases": "0.safetensors",
504
+ "layers.19.mlp.up_proj.weight": "0.safetensors",
505
+ "layers.19.mlp.up_proj.scales": "0.safetensors",
506
+ "layers.19.mlp.up_proj.biases": "0.safetensors",
507
+ "layers.19.mlp.down_proj.weight": "0.safetensors",
508
+ "layers.19.mlp.down_proj.scales": "0.safetensors",
509
+ "layers.19.mlp.down_proj.biases": "0.safetensors",
510
+ "layers.20.input_layernorm.weight": "0.safetensors",
511
+ "layers.20.post_attention_layernorm.weight": "0.safetensors",
512
+ "layers.20.self_attn.q_proj.weight": "0.safetensors",
513
+ "layers.20.self_attn.q_proj.scales": "0.safetensors",
514
+ "layers.20.self_attn.q_proj.biases": "0.safetensors",
515
+ "layers.20.self_attn.k_proj.weight": "0.safetensors",
516
+ "layers.20.self_attn.k_proj.scales": "0.safetensors",
517
+ "layers.20.self_attn.k_proj.biases": "0.safetensors",
518
+ "layers.20.self_attn.v_proj.weight": "0.safetensors",
519
+ "layers.20.self_attn.v_proj.scales": "0.safetensors",
520
+ "layers.20.self_attn.v_proj.biases": "0.safetensors",
521
+ "layers.20.self_attn.o_proj.weight": "0.safetensors",
522
+ "layers.20.self_attn.o_proj.scales": "0.safetensors",
523
+ "layers.20.self_attn.o_proj.biases": "0.safetensors",
524
+ "layers.20.self_attn.q_norm.weight": "0.safetensors",
525
+ "layers.20.self_attn.k_norm.weight": "0.safetensors",
526
+ "layers.20.mlp.gate_proj.weight": "0.safetensors",
527
+ "layers.20.mlp.gate_proj.scales": "0.safetensors",
528
+ "layers.20.mlp.gate_proj.biases": "0.safetensors",
529
+ "layers.20.mlp.up_proj.weight": "0.safetensors",
530
+ "layers.20.mlp.up_proj.scales": "0.safetensors",
531
+ "layers.20.mlp.up_proj.biases": "0.safetensors",
532
+ "layers.20.mlp.down_proj.weight": "0.safetensors",
533
+ "layers.20.mlp.down_proj.scales": "0.safetensors",
534
+ "layers.20.mlp.down_proj.biases": "0.safetensors",
535
+ "layers.21.input_layernorm.weight": "0.safetensors",
536
+ "layers.21.post_attention_layernorm.weight": "0.safetensors",
537
+ "layers.21.self_attn.q_proj.weight": "0.safetensors",
538
+ "layers.21.self_attn.q_proj.scales": "0.safetensors",
539
+ "layers.21.self_attn.q_proj.biases": "0.safetensors",
540
+ "layers.21.self_attn.k_proj.weight": "0.safetensors",
541
+ "layers.21.self_attn.k_proj.scales": "0.safetensors",
542
+ "layers.21.self_attn.k_proj.biases": "0.safetensors",
543
+ "layers.21.self_attn.v_proj.weight": "0.safetensors",
544
+ "layers.21.self_attn.v_proj.scales": "0.safetensors",
545
+ "layers.21.self_attn.v_proj.biases": "0.safetensors",
546
+ "layers.21.self_attn.o_proj.weight": "0.safetensors",
547
+ "layers.21.self_attn.o_proj.scales": "0.safetensors",
548
+ "layers.21.self_attn.o_proj.biases": "0.safetensors",
549
+ "layers.21.self_attn.q_norm.weight": "0.safetensors",
550
+ "layers.21.self_attn.k_norm.weight": "0.safetensors",
551
+ "layers.21.mlp.gate_proj.weight": "0.safetensors",
552
+ "layers.21.mlp.gate_proj.scales": "0.safetensors",
553
+ "layers.21.mlp.gate_proj.biases": "0.safetensors",
554
+ "layers.21.mlp.up_proj.weight": "0.safetensors",
555
+ "layers.21.mlp.up_proj.scales": "0.safetensors",
556
+ "layers.21.mlp.up_proj.biases": "0.safetensors",
557
+ "layers.21.mlp.down_proj.weight": "0.safetensors",
558
+ "layers.21.mlp.down_proj.scales": "0.safetensors",
559
+ "layers.21.mlp.down_proj.biases": "0.safetensors",
560
+ "layers.22.input_layernorm.weight": "0.safetensors",
561
+ "layers.22.post_attention_layernorm.weight": "0.safetensors",
562
+ "layers.22.self_attn.q_proj.weight": "0.safetensors",
563
+ "layers.22.self_attn.q_proj.scales": "0.safetensors",
564
+ "layers.22.self_attn.q_proj.biases": "0.safetensors",
565
+ "layers.22.self_attn.k_proj.weight": "0.safetensors",
566
+ "layers.22.self_attn.k_proj.scales": "0.safetensors",
567
+ "layers.22.self_attn.k_proj.biases": "0.safetensors",
568
+ "layers.22.self_attn.v_proj.weight": "0.safetensors",
569
+ "layers.22.self_attn.v_proj.scales": "0.safetensors",
570
+ "layers.22.self_attn.v_proj.biases": "0.safetensors",
571
+ "layers.22.self_attn.o_proj.weight": "0.safetensors",
572
+ "layers.22.self_attn.o_proj.scales": "0.safetensors",
573
+ "layers.22.self_attn.o_proj.biases": "0.safetensors",
574
+ "layers.22.self_attn.q_norm.weight": "0.safetensors",
575
+ "layers.22.self_attn.k_norm.weight": "0.safetensors",
576
+ "layers.22.mlp.gate_proj.weight": "0.safetensors",
577
+ "layers.22.mlp.gate_proj.scales": "0.safetensors",
578
+ "layers.22.mlp.gate_proj.biases": "0.safetensors",
579
+ "layers.22.mlp.up_proj.weight": "0.safetensors",
580
+ "layers.22.mlp.up_proj.scales": "0.safetensors",
581
+ "layers.22.mlp.up_proj.biases": "0.safetensors",
582
+ "layers.22.mlp.down_proj.weight": "0.safetensors",
583
+ "layers.22.mlp.down_proj.scales": "0.safetensors",
584
+ "layers.22.mlp.down_proj.biases": "0.safetensors",
585
+ "layers.23.input_layernorm.weight": "0.safetensors",
586
+ "layers.23.post_attention_layernorm.weight": "0.safetensors",
587
+ "layers.23.self_attn.q_proj.weight": "0.safetensors",
588
+ "layers.23.self_attn.q_proj.scales": "0.safetensors",
589
+ "layers.23.self_attn.q_proj.biases": "0.safetensors",
590
+ "layers.23.self_attn.k_proj.weight": "0.safetensors",
591
+ "layers.23.self_attn.k_proj.scales": "0.safetensors",
592
+ "layers.23.self_attn.k_proj.biases": "0.safetensors",
593
+ "layers.23.self_attn.v_proj.weight": "0.safetensors",
594
+ "layers.23.self_attn.v_proj.scales": "0.safetensors",
595
+ "layers.23.self_attn.v_proj.biases": "0.safetensors",
596
+ "layers.23.self_attn.o_proj.weight": "0.safetensors",
597
+ "layers.23.self_attn.o_proj.scales": "0.safetensors",
598
+ "layers.23.self_attn.o_proj.biases": "0.safetensors",
599
+ "layers.23.self_attn.q_norm.weight": "0.safetensors",
600
+ "layers.23.self_attn.k_norm.weight": "0.safetensors",
601
+ "layers.23.mlp.gate_proj.weight": "0.safetensors",
602
+ "layers.23.mlp.gate_proj.scales": "0.safetensors",
603
+ "layers.23.mlp.gate_proj.biases": "0.safetensors",
604
+ "layers.23.mlp.up_proj.weight": "0.safetensors",
605
+ "layers.23.mlp.up_proj.scales": "0.safetensors",
606
+ "layers.23.mlp.up_proj.biases": "0.safetensors",
607
+ "layers.23.mlp.down_proj.weight": "0.safetensors",
608
+ "layers.23.mlp.down_proj.scales": "0.safetensors",
609
+ "layers.23.mlp.down_proj.biases": "0.safetensors",
610
+ "layers.24.input_layernorm.weight": "0.safetensors",
611
+ "layers.24.post_attention_layernorm.weight": "0.safetensors",
612
+ "layers.24.self_attn.q_proj.weight": "0.safetensors",
613
+ "layers.24.self_attn.q_proj.scales": "0.safetensors",
614
+ "layers.24.self_attn.q_proj.biases": "0.safetensors",
615
+ "layers.24.self_attn.k_proj.weight": "0.safetensors",
616
+ "layers.24.self_attn.k_proj.scales": "0.safetensors",
617
+ "layers.24.self_attn.k_proj.biases": "0.safetensors",
618
+ "layers.24.self_attn.v_proj.weight": "0.safetensors",
619
+ "layers.24.self_attn.v_proj.scales": "0.safetensors",
620
+ "layers.24.self_attn.v_proj.biases": "0.safetensors",
621
+ "layers.24.self_attn.o_proj.weight": "0.safetensors",
622
+ "layers.24.self_attn.o_proj.scales": "0.safetensors",
623
+ "layers.24.self_attn.o_proj.biases": "0.safetensors",
624
+ "layers.24.self_attn.q_norm.weight": "0.safetensors",
625
+ "layers.24.self_attn.k_norm.weight": "0.safetensors",
626
+ "layers.24.mlp.gate_proj.weight": "0.safetensors",
627
+ "layers.24.mlp.gate_proj.scales": "0.safetensors",
628
+ "layers.24.mlp.gate_proj.biases": "0.safetensors",
629
+ "layers.24.mlp.up_proj.weight": "0.safetensors",
630
+ "layers.24.mlp.up_proj.scales": "0.safetensors",
631
+ "layers.24.mlp.up_proj.biases": "0.safetensors",
632
+ "layers.24.mlp.down_proj.weight": "0.safetensors",
633
+ "layers.24.mlp.down_proj.scales": "0.safetensors",
634
+ "layers.24.mlp.down_proj.biases": "0.safetensors",
635
+ "layers.25.input_layernorm.weight": "0.safetensors",
636
+ "layers.25.post_attention_layernorm.weight": "0.safetensors",
637
+ "layers.25.self_attn.q_proj.weight": "0.safetensors",
638
+ "layers.25.self_attn.q_proj.scales": "0.safetensors",
639
+ "layers.25.self_attn.q_proj.biases": "0.safetensors",
640
+ "layers.25.self_attn.k_proj.weight": "0.safetensors",
641
+ "layers.25.self_attn.k_proj.scales": "0.safetensors",
642
+ "layers.25.self_attn.k_proj.biases": "0.safetensors",
643
+ "layers.25.self_attn.v_proj.weight": "0.safetensors",
644
+ "layers.25.self_attn.v_proj.scales": "0.safetensors",
645
+ "layers.25.self_attn.v_proj.biases": "0.safetensors",
646
+ "layers.25.self_attn.o_proj.weight": "0.safetensors",
647
+ "layers.25.self_attn.o_proj.scales": "0.safetensors",
648
+ "layers.25.self_attn.o_proj.biases": "0.safetensors",
649
+ "layers.25.self_attn.q_norm.weight": "0.safetensors",
650
+ "layers.25.self_attn.k_norm.weight": "0.safetensors",
651
+ "layers.25.mlp.gate_proj.weight": "0.safetensors",
652
+ "layers.25.mlp.gate_proj.scales": "0.safetensors",
653
+ "layers.25.mlp.gate_proj.biases": "0.safetensors",
654
+ "layers.25.mlp.up_proj.weight": "0.safetensors",
655
+ "layers.25.mlp.up_proj.scales": "0.safetensors",
656
+ "layers.25.mlp.up_proj.biases": "0.safetensors",
657
+ "layers.25.mlp.down_proj.weight": "0.safetensors",
658
+ "layers.25.mlp.down_proj.scales": "0.safetensors",
659
+ "layers.25.mlp.down_proj.biases": "0.safetensors",
660
+ "layers.26.input_layernorm.weight": "0.safetensors",
661
+ "layers.26.post_attention_layernorm.weight": "0.safetensors",
662
+ "layers.26.self_attn.q_proj.weight": "0.safetensors",
663
+ "layers.26.self_attn.q_proj.scales": "0.safetensors",
664
+ "layers.26.self_attn.q_proj.biases": "0.safetensors",
665
+ "layers.26.self_attn.k_proj.weight": "0.safetensors",
666
+ "layers.26.self_attn.k_proj.scales": "0.safetensors",
667
+ "layers.26.self_attn.k_proj.biases": "0.safetensors",
668
+ "layers.26.self_attn.v_proj.weight": "0.safetensors",
669
+ "layers.26.self_attn.v_proj.scales": "0.safetensors",
670
+ "layers.26.self_attn.v_proj.biases": "0.safetensors",
671
+ "layers.26.self_attn.o_proj.weight": "0.safetensors",
672
+ "layers.26.self_attn.o_proj.scales": "0.safetensors",
673
+ "layers.26.self_attn.o_proj.biases": "0.safetensors",
674
+ "layers.26.self_attn.q_norm.weight": "0.safetensors",
675
+ "layers.26.self_attn.k_norm.weight": "0.safetensors",
676
+ "layers.26.mlp.gate_proj.weight": "0.safetensors",
677
+ "layers.26.mlp.gate_proj.scales": "0.safetensors",
678
+ "layers.26.mlp.gate_proj.biases": "0.safetensors",
679
+ "layers.26.mlp.up_proj.weight": "0.safetensors",
680
+ "layers.26.mlp.up_proj.scales": "0.safetensors",
681
+ "layers.26.mlp.up_proj.biases": "0.safetensors",
682
+ "layers.26.mlp.down_proj.weight": "0.safetensors",
683
+ "layers.26.mlp.down_proj.scales": "0.safetensors",
684
+ "layers.26.mlp.down_proj.biases": "0.safetensors",
685
+ "layers.27.input_layernorm.weight": "0.safetensors",
686
+ "layers.27.post_attention_layernorm.weight": "0.safetensors",
687
+ "layers.27.self_attn.q_proj.weight": "0.safetensors",
688
+ "layers.27.self_attn.q_proj.scales": "0.safetensors",
689
+ "layers.27.self_attn.q_proj.biases": "0.safetensors",
690
+ "layers.27.self_attn.k_proj.weight": "0.safetensors",
691
+ "layers.27.self_attn.k_proj.scales": "0.safetensors",
692
+ "layers.27.self_attn.k_proj.biases": "0.safetensors",
693
+ "layers.27.self_attn.v_proj.weight": "0.safetensors",
694
+ "layers.27.self_attn.v_proj.scales": "0.safetensors",
695
+ "layers.27.self_attn.v_proj.biases": "0.safetensors",
696
+ "layers.27.self_attn.o_proj.weight": "0.safetensors",
697
+ "layers.27.self_attn.o_proj.scales": "0.safetensors",
698
+ "layers.27.self_attn.o_proj.biases": "0.safetensors",
699
+ "layers.27.self_attn.q_norm.weight": "0.safetensors",
700
+ "layers.27.self_attn.k_norm.weight": "0.safetensors",
701
+ "layers.27.mlp.gate_proj.weight": "0.safetensors",
702
+ "layers.27.mlp.gate_proj.scales": "0.safetensors",
703
+ "layers.27.mlp.gate_proj.biases": "0.safetensors",
704
+ "layers.27.mlp.up_proj.weight": "0.safetensors",
705
+ "layers.27.mlp.up_proj.scales": "0.safetensors",
706
+ "layers.27.mlp.up_proj.biases": "0.safetensors",
707
+ "layers.27.mlp.down_proj.weight": "0.safetensors",
708
+ "layers.27.mlp.down_proj.scales": "0.safetensors",
709
+ "layers.27.mlp.down_proj.biases": "0.safetensors",
710
+ "layers.28.input_layernorm.weight": "0.safetensors",
711
+ "layers.28.post_attention_layernorm.weight": "0.safetensors",
712
+ "layers.28.self_attn.q_proj.weight": "0.safetensors",
713
+ "layers.28.self_attn.q_proj.scales": "0.safetensors",
714
+ "layers.28.self_attn.q_proj.biases": "0.safetensors",
715
+ "layers.28.self_attn.k_proj.weight": "0.safetensors",
716
+ "layers.28.self_attn.k_proj.scales": "0.safetensors",
717
+ "layers.28.self_attn.k_proj.biases": "0.safetensors",
718
+ "layers.28.self_attn.v_proj.weight": "0.safetensors",
719
+ "layers.28.self_attn.v_proj.scales": "0.safetensors",
720
+ "layers.28.self_attn.v_proj.biases": "0.safetensors",
721
+ "layers.28.self_attn.o_proj.weight": "0.safetensors",
722
+ "layers.28.self_attn.o_proj.scales": "0.safetensors",
723
+ "layers.28.self_attn.o_proj.biases": "0.safetensors",
724
+ "layers.28.self_attn.q_norm.weight": "0.safetensors",
725
+ "layers.28.self_attn.k_norm.weight": "0.safetensors",
726
+ "layers.28.mlp.gate_proj.weight": "0.safetensors",
727
+ "layers.28.mlp.gate_proj.scales": "0.safetensors",
728
+ "layers.28.mlp.gate_proj.biases": "0.safetensors",
729
+ "layers.28.mlp.up_proj.weight": "0.safetensors",
730
+ "layers.28.mlp.up_proj.scales": "0.safetensors",
731
+ "layers.28.mlp.up_proj.biases": "0.safetensors",
732
+ "layers.28.mlp.down_proj.weight": "0.safetensors",
733
+ "layers.28.mlp.down_proj.scales": "0.safetensors",
734
+ "layers.28.mlp.down_proj.biases": "0.safetensors",
735
+ "layers.29.input_layernorm.weight": "0.safetensors",
736
+ "layers.29.post_attention_layernorm.weight": "0.safetensors",
737
+ "layers.29.self_attn.q_proj.weight": "0.safetensors",
738
+ "layers.29.self_attn.q_proj.scales": "0.safetensors",
739
+ "layers.29.self_attn.q_proj.biases": "0.safetensors",
740
+ "layers.29.self_attn.k_proj.weight": "0.safetensors",
741
+ "layers.29.self_attn.k_proj.scales": "0.safetensors",
742
+ "layers.29.self_attn.k_proj.biases": "0.safetensors",
743
+ "layers.29.self_attn.v_proj.weight": "0.safetensors",
744
+ "layers.29.self_attn.v_proj.scales": "0.safetensors",
745
+ "layers.29.self_attn.v_proj.biases": "0.safetensors",
746
+ "layers.29.self_attn.o_proj.weight": "0.safetensors",
747
+ "layers.29.self_attn.o_proj.scales": "0.safetensors",
748
+ "layers.29.self_attn.o_proj.biases": "0.safetensors",
749
+ "layers.29.self_attn.q_norm.weight": "0.safetensors",
750
+ "layers.29.self_attn.k_norm.weight": "0.safetensors",
751
+ "layers.29.mlp.gate_proj.weight": "0.safetensors",
752
+ "layers.29.mlp.gate_proj.scales": "0.safetensors",
753
+ "layers.29.mlp.gate_proj.biases": "0.safetensors",
754
+ "layers.29.mlp.up_proj.weight": "0.safetensors",
755
+ "layers.29.mlp.up_proj.scales": "0.safetensors",
756
+ "layers.29.mlp.up_proj.biases": "0.safetensors",
757
+ "layers.29.mlp.down_proj.weight": "0.safetensors",
758
+ "layers.29.mlp.down_proj.scales": "0.safetensors",
759
+ "layers.29.mlp.down_proj.biases": "0.safetensors",
760
+ "layers.30.input_layernorm.weight": "0.safetensors",
761
+ "layers.30.post_attention_layernorm.weight": "0.safetensors",
762
+ "layers.30.self_attn.q_proj.weight": "0.safetensors",
763
+ "layers.30.self_attn.q_proj.scales": "0.safetensors",
764
+ "layers.30.self_attn.q_proj.biases": "0.safetensors",
765
+ "layers.30.self_attn.k_proj.weight": "0.safetensors",
766
+ "layers.30.self_attn.k_proj.scales": "0.safetensors",
767
+ "layers.30.self_attn.k_proj.biases": "0.safetensors",
768
+ "layers.30.self_attn.v_proj.weight": "0.safetensors",
769
+ "layers.30.self_attn.v_proj.scales": "0.safetensors",
770
+ "layers.30.self_attn.v_proj.biases": "0.safetensors",
771
+ "layers.30.self_attn.o_proj.weight": "0.safetensors",
772
+ "layers.30.self_attn.o_proj.scales": "0.safetensors",
773
+ "layers.30.self_attn.o_proj.biases": "0.safetensors",
774
+ "layers.30.self_attn.q_norm.weight": "0.safetensors",
775
+ "layers.30.self_attn.k_norm.weight": "0.safetensors",
776
+ "layers.30.mlp.gate_proj.weight": "0.safetensors",
777
+ "layers.30.mlp.gate_proj.scales": "0.safetensors",
778
+ "layers.30.mlp.gate_proj.biases": "0.safetensors",
779
+ "layers.30.mlp.up_proj.weight": "0.safetensors",
780
+ "layers.30.mlp.up_proj.scales": "0.safetensors",
781
+ "layers.30.mlp.up_proj.biases": "0.safetensors",
782
+ "layers.30.mlp.down_proj.weight": "0.safetensors",
783
+ "layers.30.mlp.down_proj.scales": "0.safetensors",
784
+ "layers.30.mlp.down_proj.biases": "0.safetensors",
785
+ "layers.31.input_layernorm.weight": "0.safetensors",
786
+ "layers.31.post_attention_layernorm.weight": "0.safetensors",
787
+ "layers.31.self_attn.q_proj.weight": "0.safetensors",
788
+ "layers.31.self_attn.q_proj.scales": "0.safetensors",
789
+ "layers.31.self_attn.q_proj.biases": "0.safetensors",
790
+ "layers.31.self_attn.k_proj.weight": "0.safetensors",
791
+ "layers.31.self_attn.k_proj.scales": "0.safetensors",
792
+ "layers.31.self_attn.k_proj.biases": "0.safetensors",
793
+ "layers.31.self_attn.v_proj.weight": "0.safetensors",
794
+ "layers.31.self_attn.v_proj.scales": "0.safetensors",
795
+ "layers.31.self_attn.v_proj.biases": "0.safetensors",
796
+ "layers.31.self_attn.o_proj.weight": "0.safetensors",
797
+ "layers.31.self_attn.o_proj.scales": "0.safetensors",
798
+ "layers.31.self_attn.o_proj.biases": "0.safetensors",
799
+ "layers.31.self_attn.q_norm.weight": "0.safetensors",
800
+ "layers.31.self_attn.k_norm.weight": "0.safetensors",
801
+ "layers.31.mlp.gate_proj.weight": "0.safetensors",
802
+ "layers.31.mlp.gate_proj.scales": "0.safetensors",
803
+ "layers.31.mlp.gate_proj.biases": "0.safetensors",
804
+ "layers.31.mlp.up_proj.weight": "0.safetensors",
805
+ "layers.31.mlp.up_proj.scales": "0.safetensors",
806
+ "layers.31.mlp.up_proj.biases": "0.safetensors",
807
+ "layers.31.mlp.down_proj.weight": "0.safetensors",
808
+ "layers.31.mlp.down_proj.scales": "0.safetensors",
809
+ "layers.31.mlp.down_proj.biases": "0.safetensors",
810
+ "layers.32.input_layernorm.weight": "0.safetensors",
811
+ "layers.32.post_attention_layernorm.weight": "0.safetensors",
812
+ "layers.32.self_attn.q_proj.weight": "0.safetensors",
813
+ "layers.32.self_attn.q_proj.scales": "0.safetensors",
814
+ "layers.32.self_attn.q_proj.biases": "0.safetensors",
815
+ "layers.32.self_attn.k_proj.weight": "0.safetensors",
816
+ "layers.32.self_attn.k_proj.scales": "0.safetensors",
817
+ "layers.32.self_attn.k_proj.biases": "0.safetensors",
818
+ "layers.32.self_attn.v_proj.weight": "0.safetensors",
819
+ "layers.32.self_attn.v_proj.scales": "0.safetensors",
820
+ "layers.32.self_attn.v_proj.biases": "0.safetensors",
821
+ "layers.32.self_attn.o_proj.weight": "0.safetensors",
822
+ "layers.32.self_attn.o_proj.scales": "0.safetensors",
823
+ "layers.32.self_attn.o_proj.biases": "0.safetensors",
824
+ "layers.32.self_attn.q_norm.weight": "0.safetensors",
825
+ "layers.32.self_attn.k_norm.weight": "0.safetensors",
826
+ "layers.32.mlp.gate_proj.weight": "0.safetensors",
827
+ "layers.32.mlp.gate_proj.scales": "0.safetensors",
828
+ "layers.32.mlp.gate_proj.biases": "0.safetensors",
829
+ "layers.32.mlp.up_proj.weight": "0.safetensors",
830
+ "layers.32.mlp.up_proj.scales": "0.safetensors",
831
+ "layers.32.mlp.up_proj.biases": "0.safetensors",
832
+ "layers.32.mlp.down_proj.weight": "0.safetensors",
833
+ "layers.32.mlp.down_proj.scales": "0.safetensors",
834
+ "layers.32.mlp.down_proj.biases": "0.safetensors",
835
+ "layers.33.input_layernorm.weight": "0.safetensors",
836
+ "layers.33.post_attention_layernorm.weight": "0.safetensors",
837
+ "layers.33.self_attn.q_proj.weight": "0.safetensors",
838
+ "layers.33.self_attn.q_proj.scales": "0.safetensors",
839
+ "layers.33.self_attn.q_proj.biases": "0.safetensors",
840
+ "layers.33.self_attn.k_proj.weight": "0.safetensors",
841
+ "layers.33.self_attn.k_proj.scales": "0.safetensors",
842
+ "layers.33.self_attn.k_proj.biases": "0.safetensors",
843
+ "layers.33.self_attn.v_proj.weight": "0.safetensors",
844
+ "layers.33.self_attn.v_proj.scales": "0.safetensors",
845
+ "layers.33.self_attn.v_proj.biases": "0.safetensors",
846
+ "layers.33.self_attn.o_proj.weight": "0.safetensors",
847
+ "layers.33.self_attn.o_proj.scales": "0.safetensors",
848
+ "layers.33.self_attn.o_proj.biases": "0.safetensors",
849
+ "layers.33.self_attn.q_norm.weight": "0.safetensors",
850
+ "layers.33.self_attn.k_norm.weight": "0.safetensors",
851
+ "layers.33.mlp.gate_proj.weight": "0.safetensors",
852
+ "layers.33.mlp.gate_proj.scales": "0.safetensors",
853
+ "layers.33.mlp.gate_proj.biases": "0.safetensors",
854
+ "layers.33.mlp.up_proj.weight": "0.safetensors",
855
+ "layers.33.mlp.up_proj.scales": "0.safetensors",
856
+ "layers.33.mlp.up_proj.biases": "0.safetensors",
857
+ "layers.33.mlp.down_proj.weight": "1.safetensors",
858
+ "layers.33.mlp.down_proj.scales": "1.safetensors",
859
+ "layers.33.mlp.down_proj.biases": "1.safetensors",
860
+ "layers.34.input_layernorm.weight": "1.safetensors",
861
+ "layers.34.post_attention_layernorm.weight": "1.safetensors",
862
+ "layers.34.self_attn.q_proj.weight": "1.safetensors",
863
+ "layers.34.self_attn.q_proj.scales": "1.safetensors",
864
+ "layers.34.self_attn.q_proj.biases": "1.safetensors",
865
+ "layers.34.self_attn.k_proj.weight": "1.safetensors",
866
+ "layers.34.self_attn.k_proj.scales": "1.safetensors",
867
+ "layers.34.self_attn.k_proj.biases": "1.safetensors",
868
+ "layers.34.self_attn.v_proj.weight": "1.safetensors",
869
+ "layers.34.self_attn.v_proj.scales": "1.safetensors",
870
+ "layers.34.self_attn.v_proj.biases": "1.safetensors",
871
+ "layers.34.self_attn.o_proj.weight": "1.safetensors",
872
+ "layers.34.self_attn.o_proj.scales": "1.safetensors",
873
+ "layers.34.self_attn.o_proj.biases": "1.safetensors",
874
+ "layers.34.self_attn.q_norm.weight": "1.safetensors",
875
+ "layers.34.self_attn.k_norm.weight": "1.safetensors",
876
+ "layers.34.mlp.gate_proj.weight": "1.safetensors",
877
+ "layers.34.mlp.gate_proj.scales": "1.safetensors",
878
+ "layers.34.mlp.gate_proj.biases": "1.safetensors",
879
+ "layers.34.mlp.up_proj.weight": "1.safetensors",
880
+ "layers.34.mlp.up_proj.scales": "1.safetensors",
881
+ "layers.34.mlp.up_proj.biases": "1.safetensors",
882
+ "layers.34.mlp.down_proj.weight": "1.safetensors",
883
+ "layers.34.mlp.down_proj.scales": "1.safetensors",
884
+ "layers.34.mlp.down_proj.biases": "1.safetensors",
885
+ "layers.35.input_layernorm.weight": "1.safetensors",
886
+ "layers.35.post_attention_layernorm.weight": "1.safetensors",
887
+ "layers.35.self_attn.q_proj.weight": "1.safetensors",
888
+ "layers.35.self_attn.q_proj.scales": "1.safetensors",
889
+ "layers.35.self_attn.q_proj.biases": "1.safetensors",
890
+ "layers.35.self_attn.k_proj.weight": "1.safetensors",
891
+ "layers.35.self_attn.k_proj.scales": "1.safetensors",
892
+ "layers.35.self_attn.k_proj.biases": "1.safetensors",
893
+ "layers.35.self_attn.v_proj.weight": "1.safetensors",
894
+ "layers.35.self_attn.v_proj.scales": "1.safetensors",
895
+ "layers.35.self_attn.v_proj.biases": "1.safetensors",
896
+ "layers.35.self_attn.o_proj.weight": "1.safetensors",
897
+ "layers.35.self_attn.o_proj.scales": "1.safetensors",
898
+ "layers.35.self_attn.o_proj.biases": "1.safetensors",
899
+ "layers.35.self_attn.q_norm.weight": "1.safetensors",
900
+ "layers.35.self_attn.k_norm.weight": "1.safetensors",
901
+ "layers.35.mlp.gate_proj.weight": "1.safetensors",
902
+ "layers.35.mlp.gate_proj.scales": "1.safetensors",
903
+ "layers.35.mlp.gate_proj.biases": "1.safetensors",
904
+ "layers.35.mlp.up_proj.weight": "1.safetensors",
905
+ "layers.35.mlp.up_proj.scales": "1.safetensors",
906
+ "layers.35.mlp.up_proj.biases": "1.safetensors",
907
+ "layers.35.mlp.down_proj.weight": "1.safetensors",
908
+ "layers.35.mlp.down_proj.scales": "1.safetensors",
909
+ "layers.35.mlp.down_proj.biases": "1.safetensors",
910
+ "norm.weight": "1.safetensors",
911
+ "rotary_emb.inv_freq": "1.safetensors"
912
+ }
913
+ }
tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": true,
24
+ "model_max_length": 131072,
25
+ "pad_token": "<|endoftext|>",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
+ "unk_token": null
29
+ }
transformer/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4bc39330320a5a48056c3875a971e9d42dcef6585d3dca96ae98e069caf9a4
3
+ size 2140225936
transformer/1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b810a927a6f6c0cb9fc395599d794339aa9f57f83a4eeb73c2d01438bd9fb3
3
+ size 1323528959
transformer/model.safetensors.index.json ADDED
@@ -0,0 +1,1081 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "4",
4
+ "mflux_version": "0.14.1"
5
+ },
6
+ "weight_map": {
7
+ "all_x_embedder.2-1.weight": "0.safetensors",
8
+ "all_x_embedder.2-1.scales": "0.safetensors",
9
+ "all_x_embedder.2-1.biases": "0.safetensors",
10
+ "all_x_embedder.2-1.bias": "0.safetensors",
11
+ "all_final_layer.2-1.linear.weight": "0.safetensors",
12
+ "all_final_layer.2-1.linear.scales": "0.safetensors",
13
+ "all_final_layer.2-1.linear.biases": "0.safetensors",
14
+ "all_final_layer.2-1.linear.bias": "0.safetensors",
15
+ "all_final_layer.2-1.adaLN_modulation.0.weight": "0.safetensors",
16
+ "all_final_layer.2-1.adaLN_modulation.0.scales": "0.safetensors",
17
+ "all_final_layer.2-1.adaLN_modulation.0.biases": "0.safetensors",
18
+ "all_final_layer.2-1.adaLN_modulation.0.bias": "0.safetensors",
19
+ "t_embedder.linear1.weight": "0.safetensors",
20
+ "t_embedder.linear1.scales": "0.safetensors",
21
+ "t_embedder.linear1.biases": "0.safetensors",
22
+ "t_embedder.linear1.bias": "0.safetensors",
23
+ "t_embedder.linear2.weight": "0.safetensors",
24
+ "t_embedder.linear2.scales": "0.safetensors",
25
+ "t_embedder.linear2.biases": "0.safetensors",
26
+ "t_embedder.linear2.bias": "0.safetensors",
27
+ "cap_embedder.0.weight": "0.safetensors",
28
+ "cap_embedder.1.weight": "0.safetensors",
29
+ "cap_embedder.1.scales": "0.safetensors",
30
+ "cap_embedder.1.biases": "0.safetensors",
31
+ "cap_embedder.1.bias": "0.safetensors",
32
+ "x_pad_token": "0.safetensors",
33
+ "cap_pad_token": "0.safetensors",
34
+ "noise_refiner.0.attention.to_q.weight": "0.safetensors",
35
+ "noise_refiner.0.attention.to_q.scales": "0.safetensors",
36
+ "noise_refiner.0.attention.to_q.biases": "0.safetensors",
37
+ "noise_refiner.0.attention.to_k.weight": "0.safetensors",
38
+ "noise_refiner.0.attention.to_k.scales": "0.safetensors",
39
+ "noise_refiner.0.attention.to_k.biases": "0.safetensors",
40
+ "noise_refiner.0.attention.to_v.weight": "0.safetensors",
41
+ "noise_refiner.0.attention.to_v.scales": "0.safetensors",
42
+ "noise_refiner.0.attention.to_v.biases": "0.safetensors",
43
+ "noise_refiner.0.attention.to_out.0.weight": "0.safetensors",
44
+ "noise_refiner.0.attention.to_out.0.scales": "0.safetensors",
45
+ "noise_refiner.0.attention.to_out.0.biases": "0.safetensors",
46
+ "noise_refiner.0.attention.norm_q.weight": "0.safetensors",
47
+ "noise_refiner.0.attention.norm_k.weight": "0.safetensors",
48
+ "noise_refiner.0.feed_forward.w1.weight": "0.safetensors",
49
+ "noise_refiner.0.feed_forward.w1.scales": "0.safetensors",
50
+ "noise_refiner.0.feed_forward.w1.biases": "0.safetensors",
51
+ "noise_refiner.0.feed_forward.w2.weight": "0.safetensors",
52
+ "noise_refiner.0.feed_forward.w2.scales": "0.safetensors",
53
+ "noise_refiner.0.feed_forward.w2.biases": "0.safetensors",
54
+ "noise_refiner.0.feed_forward.w3.weight": "0.safetensors",
55
+ "noise_refiner.0.feed_forward.w3.scales": "0.safetensors",
56
+ "noise_refiner.0.feed_forward.w3.biases": "0.safetensors",
57
+ "noise_refiner.0.attention_norm1.weight": "0.safetensors",
58
+ "noise_refiner.0.attention_norm2.weight": "0.safetensors",
59
+ "noise_refiner.0.ffn_norm1.weight": "0.safetensors",
60
+ "noise_refiner.0.ffn_norm2.weight": "0.safetensors",
61
+ "noise_refiner.0.adaLN_modulation.0.weight": "0.safetensors",
62
+ "noise_refiner.0.adaLN_modulation.0.scales": "0.safetensors",
63
+ "noise_refiner.0.adaLN_modulation.0.biases": "0.safetensors",
64
+ "noise_refiner.0.adaLN_modulation.0.bias": "0.safetensors",
65
+ "noise_refiner.1.attention.to_q.weight": "0.safetensors",
66
+ "noise_refiner.1.attention.to_q.scales": "0.safetensors",
67
+ "noise_refiner.1.attention.to_q.biases": "0.safetensors",
68
+ "noise_refiner.1.attention.to_k.weight": "0.safetensors",
69
+ "noise_refiner.1.attention.to_k.scales": "0.safetensors",
70
+ "noise_refiner.1.attention.to_k.biases": "0.safetensors",
71
+ "noise_refiner.1.attention.to_v.weight": "0.safetensors",
72
+ "noise_refiner.1.attention.to_v.scales": "0.safetensors",
73
+ "noise_refiner.1.attention.to_v.biases": "0.safetensors",
74
+ "noise_refiner.1.attention.to_out.0.weight": "0.safetensors",
75
+ "noise_refiner.1.attention.to_out.0.scales": "0.safetensors",
76
+ "noise_refiner.1.attention.to_out.0.biases": "0.safetensors",
77
+ "noise_refiner.1.attention.norm_q.weight": "0.safetensors",
78
+ "noise_refiner.1.attention.norm_k.weight": "0.safetensors",
79
+ "noise_refiner.1.feed_forward.w1.weight": "0.safetensors",
80
+ "noise_refiner.1.feed_forward.w1.scales": "0.safetensors",
81
+ "noise_refiner.1.feed_forward.w1.biases": "0.safetensors",
82
+ "noise_refiner.1.feed_forward.w2.weight": "0.safetensors",
83
+ "noise_refiner.1.feed_forward.w2.scales": "0.safetensors",
84
+ "noise_refiner.1.feed_forward.w2.biases": "0.safetensors",
85
+ "noise_refiner.1.feed_forward.w3.weight": "0.safetensors",
86
+ "noise_refiner.1.feed_forward.w3.scales": "0.safetensors",
87
+ "noise_refiner.1.feed_forward.w3.biases": "0.safetensors",
88
+ "noise_refiner.1.attention_norm1.weight": "0.safetensors",
89
+ "noise_refiner.1.attention_norm2.weight": "0.safetensors",
90
+ "noise_refiner.1.ffn_norm1.weight": "0.safetensors",
91
+ "noise_refiner.1.ffn_norm2.weight": "0.safetensors",
92
+ "noise_refiner.1.adaLN_modulation.0.weight": "0.safetensors",
93
+ "noise_refiner.1.adaLN_modulation.0.scales": "0.safetensors",
94
+ "noise_refiner.1.adaLN_modulation.0.biases": "0.safetensors",
95
+ "noise_refiner.1.adaLN_modulation.0.bias": "0.safetensors",
96
+ "context_refiner.0.attention.to_q.weight": "0.safetensors",
97
+ "context_refiner.0.attention.to_q.scales": "0.safetensors",
98
+ "context_refiner.0.attention.to_q.biases": "0.safetensors",
99
+ "context_refiner.0.attention.to_k.weight": "0.safetensors",
100
+ "context_refiner.0.attention.to_k.scales": "0.safetensors",
101
+ "context_refiner.0.attention.to_k.biases": "0.safetensors",
102
+ "context_refiner.0.attention.to_v.weight": "0.safetensors",
103
+ "context_refiner.0.attention.to_v.scales": "0.safetensors",
104
+ "context_refiner.0.attention.to_v.biases": "0.safetensors",
105
+ "context_refiner.0.attention.to_out.0.weight": "0.safetensors",
106
+ "context_refiner.0.attention.to_out.0.scales": "0.safetensors",
107
+ "context_refiner.0.attention.to_out.0.biases": "0.safetensors",
108
+ "context_refiner.0.attention.norm_q.weight": "0.safetensors",
109
+ "context_refiner.0.attention.norm_k.weight": "0.safetensors",
110
+ "context_refiner.0.feed_forward.w1.weight": "0.safetensors",
111
+ "context_refiner.0.feed_forward.w1.scales": "0.safetensors",
112
+ "context_refiner.0.feed_forward.w1.biases": "0.safetensors",
113
+ "context_refiner.0.feed_forward.w2.weight": "0.safetensors",
114
+ "context_refiner.0.feed_forward.w2.scales": "0.safetensors",
115
+ "context_refiner.0.feed_forward.w2.biases": "0.safetensors",
116
+ "context_refiner.0.feed_forward.w3.weight": "0.safetensors",
117
+ "context_refiner.0.feed_forward.w3.scales": "0.safetensors",
118
+ "context_refiner.0.feed_forward.w3.biases": "0.safetensors",
119
+ "context_refiner.0.attention_norm1.weight": "0.safetensors",
120
+ "context_refiner.0.attention_norm2.weight": "0.safetensors",
121
+ "context_refiner.0.ffn_norm1.weight": "0.safetensors",
122
+ "context_refiner.0.ffn_norm2.weight": "0.safetensors",
123
+ "context_refiner.1.attention.to_q.weight": "0.safetensors",
124
+ "context_refiner.1.attention.to_q.scales": "0.safetensors",
125
+ "context_refiner.1.attention.to_q.biases": "0.safetensors",
126
+ "context_refiner.1.attention.to_k.weight": "0.safetensors",
127
+ "context_refiner.1.attention.to_k.scales": "0.safetensors",
128
+ "context_refiner.1.attention.to_k.biases": "0.safetensors",
129
+ "context_refiner.1.attention.to_v.weight": "0.safetensors",
130
+ "context_refiner.1.attention.to_v.scales": "0.safetensors",
131
+ "context_refiner.1.attention.to_v.biases": "0.safetensors",
132
+ "context_refiner.1.attention.to_out.0.weight": "0.safetensors",
133
+ "context_refiner.1.attention.to_out.0.scales": "0.safetensors",
134
+ "context_refiner.1.attention.to_out.0.biases": "0.safetensors",
135
+ "context_refiner.1.attention.norm_q.weight": "0.safetensors",
136
+ "context_refiner.1.attention.norm_k.weight": "0.safetensors",
137
+ "context_refiner.1.feed_forward.w1.weight": "0.safetensors",
138
+ "context_refiner.1.feed_forward.w1.scales": "0.safetensors",
139
+ "context_refiner.1.feed_forward.w1.biases": "0.safetensors",
140
+ "context_refiner.1.feed_forward.w2.weight": "0.safetensors",
141
+ "context_refiner.1.feed_forward.w2.scales": "0.safetensors",
142
+ "context_refiner.1.feed_forward.w2.biases": "0.safetensors",
143
+ "context_refiner.1.feed_forward.w3.weight": "0.safetensors",
144
+ "context_refiner.1.feed_forward.w3.scales": "0.safetensors",
145
+ "context_refiner.1.feed_forward.w3.biases": "0.safetensors",
146
+ "context_refiner.1.attention_norm1.weight": "0.safetensors",
147
+ "context_refiner.1.attention_norm2.weight": "0.safetensors",
148
+ "context_refiner.1.ffn_norm1.weight": "0.safetensors",
149
+ "context_refiner.1.ffn_norm2.weight": "0.safetensors",
150
+ "layers.0.attention.to_q.weight": "0.safetensors",
151
+ "layers.0.attention.to_q.scales": "0.safetensors",
152
+ "layers.0.attention.to_q.biases": "0.safetensors",
153
+ "layers.0.attention.to_k.weight": "0.safetensors",
154
+ "layers.0.attention.to_k.scales": "0.safetensors",
155
+ "layers.0.attention.to_k.biases": "0.safetensors",
156
+ "layers.0.attention.to_v.weight": "0.safetensors",
157
+ "layers.0.attention.to_v.scales": "0.safetensors",
158
+ "layers.0.attention.to_v.biases": "0.safetensors",
159
+ "layers.0.attention.to_out.0.weight": "0.safetensors",
160
+ "layers.0.attention.to_out.0.scales": "0.safetensors",
161
+ "layers.0.attention.to_out.0.biases": "0.safetensors",
162
+ "layers.0.attention.norm_q.weight": "0.safetensors",
163
+ "layers.0.attention.norm_k.weight": "0.safetensors",
164
+ "layers.0.feed_forward.w1.weight": "0.safetensors",
165
+ "layers.0.feed_forward.w1.scales": "0.safetensors",
166
+ "layers.0.feed_forward.w1.biases": "0.safetensors",
167
+ "layers.0.feed_forward.w2.weight": "0.safetensors",
168
+ "layers.0.feed_forward.w2.scales": "0.safetensors",
169
+ "layers.0.feed_forward.w2.biases": "0.safetensors",
170
+ "layers.0.feed_forward.w3.weight": "0.safetensors",
171
+ "layers.0.feed_forward.w3.scales": "0.safetensors",
172
+ "layers.0.feed_forward.w3.biases": "0.safetensors",
173
+ "layers.0.attention_norm1.weight": "0.safetensors",
174
+ "layers.0.attention_norm2.weight": "0.safetensors",
175
+ "layers.0.ffn_norm1.weight": "0.safetensors",
176
+ "layers.0.ffn_norm2.weight": "0.safetensors",
177
+ "layers.0.adaLN_modulation.0.weight": "0.safetensors",
178
+ "layers.0.adaLN_modulation.0.scales": "0.safetensors",
179
+ "layers.0.adaLN_modulation.0.biases": "0.safetensors",
180
+ "layers.0.adaLN_modulation.0.bias": "0.safetensors",
181
+ "layers.1.attention.to_q.weight": "0.safetensors",
182
+ "layers.1.attention.to_q.scales": "0.safetensors",
183
+ "layers.1.attention.to_q.biases": "0.safetensors",
184
+ "layers.1.attention.to_k.weight": "0.safetensors",
185
+ "layers.1.attention.to_k.scales": "0.safetensors",
186
+ "layers.1.attention.to_k.biases": "0.safetensors",
187
+ "layers.1.attention.to_v.weight": "0.safetensors",
188
+ "layers.1.attention.to_v.scales": "0.safetensors",
189
+ "layers.1.attention.to_v.biases": "0.safetensors",
190
+ "layers.1.attention.to_out.0.weight": "0.safetensors",
191
+ "layers.1.attention.to_out.0.scales": "0.safetensors",
192
+ "layers.1.attention.to_out.0.biases": "0.safetensors",
193
+ "layers.1.attention.norm_q.weight": "0.safetensors",
194
+ "layers.1.attention.norm_k.weight": "0.safetensors",
195
+ "layers.1.feed_forward.w1.weight": "0.safetensors",
196
+ "layers.1.feed_forward.w1.scales": "0.safetensors",
197
+ "layers.1.feed_forward.w1.biases": "0.safetensors",
198
+ "layers.1.feed_forward.w2.weight": "0.safetensors",
199
+ "layers.1.feed_forward.w2.scales": "0.safetensors",
200
+ "layers.1.feed_forward.w2.biases": "0.safetensors",
201
+ "layers.1.feed_forward.w3.weight": "0.safetensors",
202
+ "layers.1.feed_forward.w3.scales": "0.safetensors",
203
+ "layers.1.feed_forward.w3.biases": "0.safetensors",
204
+ "layers.1.attention_norm1.weight": "0.safetensors",
205
+ "layers.1.attention_norm2.weight": "0.safetensors",
206
+ "layers.1.ffn_norm1.weight": "0.safetensors",
207
+ "layers.1.ffn_norm2.weight": "0.safetensors",
208
+ "layers.1.adaLN_modulation.0.weight": "0.safetensors",
209
+ "layers.1.adaLN_modulation.0.scales": "0.safetensors",
210
+ "layers.1.adaLN_modulation.0.biases": "0.safetensors",
211
+ "layers.1.adaLN_modulation.0.bias": "0.safetensors",
212
+ "layers.2.attention.to_q.weight": "0.safetensors",
213
+ "layers.2.attention.to_q.scales": "0.safetensors",
214
+ "layers.2.attention.to_q.biases": "0.safetensors",
215
+ "layers.2.attention.to_k.weight": "0.safetensors",
216
+ "layers.2.attention.to_k.scales": "0.safetensors",
217
+ "layers.2.attention.to_k.biases": "0.safetensors",
218
+ "layers.2.attention.to_v.weight": "0.safetensors",
219
+ "layers.2.attention.to_v.scales": "0.safetensors",
220
+ "layers.2.attention.to_v.biases": "0.safetensors",
221
+ "layers.2.attention.to_out.0.weight": "0.safetensors",
222
+ "layers.2.attention.to_out.0.scales": "0.safetensors",
223
+ "layers.2.attention.to_out.0.biases": "0.safetensors",
224
+ "layers.2.attention.norm_q.weight": "0.safetensors",
225
+ "layers.2.attention.norm_k.weight": "0.safetensors",
226
+ "layers.2.feed_forward.w1.weight": "0.safetensors",
227
+ "layers.2.feed_forward.w1.scales": "0.safetensors",
228
+ "layers.2.feed_forward.w1.biases": "0.safetensors",
229
+ "layers.2.feed_forward.w2.weight": "0.safetensors",
230
+ "layers.2.feed_forward.w2.scales": "0.safetensors",
231
+ "layers.2.feed_forward.w2.biases": "0.safetensors",
232
+ "layers.2.feed_forward.w3.weight": "0.safetensors",
233
+ "layers.2.feed_forward.w3.scales": "0.safetensors",
234
+ "layers.2.feed_forward.w3.biases": "0.safetensors",
235
+ "layers.2.attention_norm1.weight": "0.safetensors",
236
+ "layers.2.attention_norm2.weight": "0.safetensors",
237
+ "layers.2.ffn_norm1.weight": "0.safetensors",
238
+ "layers.2.ffn_norm2.weight": "0.safetensors",
239
+ "layers.2.adaLN_modulation.0.weight": "0.safetensors",
240
+ "layers.2.adaLN_modulation.0.scales": "0.safetensors",
241
+ "layers.2.adaLN_modulation.0.biases": "0.safetensors",
242
+ "layers.2.adaLN_modulation.0.bias": "0.safetensors",
243
+ "layers.3.attention.to_q.weight": "0.safetensors",
244
+ "layers.3.attention.to_q.scales": "0.safetensors",
245
+ "layers.3.attention.to_q.biases": "0.safetensors",
246
+ "layers.3.attention.to_k.weight": "0.safetensors",
247
+ "layers.3.attention.to_k.scales": "0.safetensors",
248
+ "layers.3.attention.to_k.biases": "0.safetensors",
249
+ "layers.3.attention.to_v.weight": "0.safetensors",
250
+ "layers.3.attention.to_v.scales": "0.safetensors",
251
+ "layers.3.attention.to_v.biases": "0.safetensors",
252
+ "layers.3.attention.to_out.0.weight": "0.safetensors",
253
+ "layers.3.attention.to_out.0.scales": "0.safetensors",
254
+ "layers.3.attention.to_out.0.biases": "0.safetensors",
255
+ "layers.3.attention.norm_q.weight": "0.safetensors",
256
+ "layers.3.attention.norm_k.weight": "0.safetensors",
257
+ "layers.3.feed_forward.w1.weight": "0.safetensors",
258
+ "layers.3.feed_forward.w1.scales": "0.safetensors",
259
+ "layers.3.feed_forward.w1.biases": "0.safetensors",
260
+ "layers.3.feed_forward.w2.weight": "0.safetensors",
261
+ "layers.3.feed_forward.w2.scales": "0.safetensors",
262
+ "layers.3.feed_forward.w2.biases": "0.safetensors",
263
+ "layers.3.feed_forward.w3.weight": "0.safetensors",
264
+ "layers.3.feed_forward.w3.scales": "0.safetensors",
265
+ "layers.3.feed_forward.w3.biases": "0.safetensors",
266
+ "layers.3.attention_norm1.weight": "0.safetensors",
267
+ "layers.3.attention_norm2.weight": "0.safetensors",
268
+ "layers.3.ffn_norm1.weight": "0.safetensors",
269
+ "layers.3.ffn_norm2.weight": "0.safetensors",
270
+ "layers.3.adaLN_modulation.0.weight": "0.safetensors",
271
+ "layers.3.adaLN_modulation.0.scales": "0.safetensors",
272
+ "layers.3.adaLN_modulation.0.biases": "0.safetensors",
273
+ "layers.3.adaLN_modulation.0.bias": "0.safetensors",
274
+ "layers.4.attention.to_q.weight": "0.safetensors",
275
+ "layers.4.attention.to_q.scales": "0.safetensors",
276
+ "layers.4.attention.to_q.biases": "0.safetensors",
277
+ "layers.4.attention.to_k.weight": "0.safetensors",
278
+ "layers.4.attention.to_k.scales": "0.safetensors",
279
+ "layers.4.attention.to_k.biases": "0.safetensors",
280
+ "layers.4.attention.to_v.weight": "0.safetensors",
281
+ "layers.4.attention.to_v.scales": "0.safetensors",
282
+ "layers.4.attention.to_v.biases": "0.safetensors",
283
+ "layers.4.attention.to_out.0.weight": "0.safetensors",
284
+ "layers.4.attention.to_out.0.scales": "0.safetensors",
285
+ "layers.4.attention.to_out.0.biases": "0.safetensors",
286
+ "layers.4.attention.norm_q.weight": "0.safetensors",
287
+ "layers.4.attention.norm_k.weight": "0.safetensors",
288
+ "layers.4.feed_forward.w1.weight": "0.safetensors",
289
+ "layers.4.feed_forward.w1.scales": "0.safetensors",
290
+ "layers.4.feed_forward.w1.biases": "0.safetensors",
291
+ "layers.4.feed_forward.w2.weight": "0.safetensors",
292
+ "layers.4.feed_forward.w2.scales": "0.safetensors",
293
+ "layers.4.feed_forward.w2.biases": "0.safetensors",
294
+ "layers.4.feed_forward.w3.weight": "0.safetensors",
295
+ "layers.4.feed_forward.w3.scales": "0.safetensors",
296
+ "layers.4.feed_forward.w3.biases": "0.safetensors",
297
+ "layers.4.attention_norm1.weight": "0.safetensors",
298
+ "layers.4.attention_norm2.weight": "0.safetensors",
299
+ "layers.4.ffn_norm1.weight": "0.safetensors",
300
+ "layers.4.ffn_norm2.weight": "0.safetensors",
301
+ "layers.4.adaLN_modulation.0.weight": "0.safetensors",
302
+ "layers.4.adaLN_modulation.0.scales": "0.safetensors",
303
+ "layers.4.adaLN_modulation.0.biases": "0.safetensors",
304
+ "layers.4.adaLN_modulation.0.bias": "0.safetensors",
305
+ "layers.5.attention.to_q.weight": "0.safetensors",
306
+ "layers.5.attention.to_q.scales": "0.safetensors",
307
+ "layers.5.attention.to_q.biases": "0.safetensors",
308
+ "layers.5.attention.to_k.weight": "0.safetensors",
309
+ "layers.5.attention.to_k.scales": "0.safetensors",
310
+ "layers.5.attention.to_k.biases": "0.safetensors",
311
+ "layers.5.attention.to_v.weight": "0.safetensors",
312
+ "layers.5.attention.to_v.scales": "0.safetensors",
313
+ "layers.5.attention.to_v.biases": "0.safetensors",
314
+ "layers.5.attention.to_out.0.weight": "0.safetensors",
315
+ "layers.5.attention.to_out.0.scales": "0.safetensors",
316
+ "layers.5.attention.to_out.0.biases": "0.safetensors",
317
+ "layers.5.attention.norm_q.weight": "0.safetensors",
318
+ "layers.5.attention.norm_k.weight": "0.safetensors",
319
+ "layers.5.feed_forward.w1.weight": "0.safetensors",
320
+ "layers.5.feed_forward.w1.scales": "0.safetensors",
321
+ "layers.5.feed_forward.w1.biases": "0.safetensors",
322
+ "layers.5.feed_forward.w2.weight": "0.safetensors",
323
+ "layers.5.feed_forward.w2.scales": "0.safetensors",
324
+ "layers.5.feed_forward.w2.biases": "0.safetensors",
325
+ "layers.5.feed_forward.w3.weight": "0.safetensors",
326
+ "layers.5.feed_forward.w3.scales": "0.safetensors",
327
+ "layers.5.feed_forward.w3.biases": "0.safetensors",
328
+ "layers.5.attention_norm1.weight": "0.safetensors",
329
+ "layers.5.attention_norm2.weight": "0.safetensors",
330
+ "layers.5.ffn_norm1.weight": "0.safetensors",
331
+ "layers.5.ffn_norm2.weight": "0.safetensors",
332
+ "layers.5.adaLN_modulation.0.weight": "0.safetensors",
333
+ "layers.5.adaLN_modulation.0.scales": "0.safetensors",
334
+ "layers.5.adaLN_modulation.0.biases": "0.safetensors",
335
+ "layers.5.adaLN_modulation.0.bias": "0.safetensors",
336
+ "layers.6.attention.to_q.weight": "0.safetensors",
337
+ "layers.6.attention.to_q.scales": "0.safetensors",
338
+ "layers.6.attention.to_q.biases": "0.safetensors",
339
+ "layers.6.attention.to_k.weight": "0.safetensors",
340
+ "layers.6.attention.to_k.scales": "0.safetensors",
341
+ "layers.6.attention.to_k.biases": "0.safetensors",
342
+ "layers.6.attention.to_v.weight": "0.safetensors",
343
+ "layers.6.attention.to_v.scales": "0.safetensors",
344
+ "layers.6.attention.to_v.biases": "0.safetensors",
345
+ "layers.6.attention.to_out.0.weight": "0.safetensors",
346
+ "layers.6.attention.to_out.0.scales": "0.safetensors",
347
+ "layers.6.attention.to_out.0.biases": "0.safetensors",
348
+ "layers.6.attention.norm_q.weight": "0.safetensors",
349
+ "layers.6.attention.norm_k.weight": "0.safetensors",
350
+ "layers.6.feed_forward.w1.weight": "0.safetensors",
351
+ "layers.6.feed_forward.w1.scales": "0.safetensors",
352
+ "layers.6.feed_forward.w1.biases": "0.safetensors",
353
+ "layers.6.feed_forward.w2.weight": "0.safetensors",
354
+ "layers.6.feed_forward.w2.scales": "0.safetensors",
355
+ "layers.6.feed_forward.w2.biases": "0.safetensors",
356
+ "layers.6.feed_forward.w3.weight": "0.safetensors",
357
+ "layers.6.feed_forward.w3.scales": "0.safetensors",
358
+ "layers.6.feed_forward.w3.biases": "0.safetensors",
359
+ "layers.6.attention_norm1.weight": "0.safetensors",
360
+ "layers.6.attention_norm2.weight": "0.safetensors",
361
+ "layers.6.ffn_norm1.weight": "0.safetensors",
362
+ "layers.6.ffn_norm2.weight": "0.safetensors",
363
+ "layers.6.adaLN_modulation.0.weight": "0.safetensors",
364
+ "layers.6.adaLN_modulation.0.scales": "0.safetensors",
365
+ "layers.6.adaLN_modulation.0.biases": "0.safetensors",
366
+ "layers.6.adaLN_modulation.0.bias": "0.safetensors",
367
+ "layers.7.attention.to_q.weight": "0.safetensors",
368
+ "layers.7.attention.to_q.scales": "0.safetensors",
369
+ "layers.7.attention.to_q.biases": "0.safetensors",
370
+ "layers.7.attention.to_k.weight": "0.safetensors",
371
+ "layers.7.attention.to_k.scales": "0.safetensors",
372
+ "layers.7.attention.to_k.biases": "0.safetensors",
373
+ "layers.7.attention.to_v.weight": "0.safetensors",
374
+ "layers.7.attention.to_v.scales": "0.safetensors",
375
+ "layers.7.attention.to_v.biases": "0.safetensors",
376
+ "layers.7.attention.to_out.0.weight": "0.safetensors",
377
+ "layers.7.attention.to_out.0.scales": "0.safetensors",
378
+ "layers.7.attention.to_out.0.biases": "0.safetensors",
379
+ "layers.7.attention.norm_q.weight": "0.safetensors",
380
+ "layers.7.attention.norm_k.weight": "0.safetensors",
381
+ "layers.7.feed_forward.w1.weight": "0.safetensors",
382
+ "layers.7.feed_forward.w1.scales": "0.safetensors",
383
+ "layers.7.feed_forward.w1.biases": "0.safetensors",
384
+ "layers.7.feed_forward.w2.weight": "0.safetensors",
385
+ "layers.7.feed_forward.w2.scales": "0.safetensors",
386
+ "layers.7.feed_forward.w2.biases": "0.safetensors",
387
+ "layers.7.feed_forward.w3.weight": "0.safetensors",
388
+ "layers.7.feed_forward.w3.scales": "0.safetensors",
389
+ "layers.7.feed_forward.w3.biases": "0.safetensors",
390
+ "layers.7.attention_norm1.weight": "0.safetensors",
391
+ "layers.7.attention_norm2.weight": "0.safetensors",
392
+ "layers.7.ffn_norm1.weight": "0.safetensors",
393
+ "layers.7.ffn_norm2.weight": "0.safetensors",
394
+ "layers.7.adaLN_modulation.0.weight": "0.safetensors",
395
+ "layers.7.adaLN_modulation.0.scales": "0.safetensors",
396
+ "layers.7.adaLN_modulation.0.biases": "0.safetensors",
397
+ "layers.7.adaLN_modulation.0.bias": "0.safetensors",
398
+ "layers.8.attention.to_q.weight": "0.safetensors",
399
+ "layers.8.attention.to_q.scales": "0.safetensors",
400
+ "layers.8.attention.to_q.biases": "0.safetensors",
401
+ "layers.8.attention.to_k.weight": "0.safetensors",
402
+ "layers.8.attention.to_k.scales": "0.safetensors",
403
+ "layers.8.attention.to_k.biases": "0.safetensors",
404
+ "layers.8.attention.to_v.weight": "0.safetensors",
405
+ "layers.8.attention.to_v.scales": "0.safetensors",
406
+ "layers.8.attention.to_v.biases": "0.safetensors",
407
+ "layers.8.attention.to_out.0.weight": "0.safetensors",
408
+ "layers.8.attention.to_out.0.scales": "0.safetensors",
409
+ "layers.8.attention.to_out.0.biases": "0.safetensors",
410
+ "layers.8.attention.norm_q.weight": "0.safetensors",
411
+ "layers.8.attention.norm_k.weight": "0.safetensors",
412
+ "layers.8.feed_forward.w1.weight": "0.safetensors",
413
+ "layers.8.feed_forward.w1.scales": "0.safetensors",
414
+ "layers.8.feed_forward.w1.biases": "0.safetensors",
415
+ "layers.8.feed_forward.w2.weight": "0.safetensors",
416
+ "layers.8.feed_forward.w2.scales": "0.safetensors",
417
+ "layers.8.feed_forward.w2.biases": "0.safetensors",
418
+ "layers.8.feed_forward.w3.weight": "0.safetensors",
419
+ "layers.8.feed_forward.w3.scales": "0.safetensors",
420
+ "layers.8.feed_forward.w3.biases": "0.safetensors",
421
+ "layers.8.attention_norm1.weight": "0.safetensors",
422
+ "layers.8.attention_norm2.weight": "0.safetensors",
423
+ "layers.8.ffn_norm1.weight": "0.safetensors",
424
+ "layers.8.ffn_norm2.weight": "0.safetensors",
425
+ "layers.8.adaLN_modulation.0.weight": "0.safetensors",
426
+ "layers.8.adaLN_modulation.0.scales": "0.safetensors",
427
+ "layers.8.adaLN_modulation.0.biases": "0.safetensors",
428
+ "layers.8.adaLN_modulation.0.bias": "0.safetensors",
429
+ "layers.9.attention.to_q.weight": "0.safetensors",
430
+ "layers.9.attention.to_q.scales": "0.safetensors",
431
+ "layers.9.attention.to_q.biases": "0.safetensors",
432
+ "layers.9.attention.to_k.weight": "0.safetensors",
433
+ "layers.9.attention.to_k.scales": "0.safetensors",
434
+ "layers.9.attention.to_k.biases": "0.safetensors",
435
+ "layers.9.attention.to_v.weight": "0.safetensors",
436
+ "layers.9.attention.to_v.scales": "0.safetensors",
437
+ "layers.9.attention.to_v.biases": "0.safetensors",
438
+ "layers.9.attention.to_out.0.weight": "0.safetensors",
439
+ "layers.9.attention.to_out.0.scales": "0.safetensors",
440
+ "layers.9.attention.to_out.0.biases": "0.safetensors",
441
+ "layers.9.attention.norm_q.weight": "0.safetensors",
442
+ "layers.9.attention.norm_k.weight": "0.safetensors",
443
+ "layers.9.feed_forward.w1.weight": "0.safetensors",
444
+ "layers.9.feed_forward.w1.scales": "0.safetensors",
445
+ "layers.9.feed_forward.w1.biases": "0.safetensors",
446
+ "layers.9.feed_forward.w2.weight": "0.safetensors",
447
+ "layers.9.feed_forward.w2.scales": "0.safetensors",
448
+ "layers.9.feed_forward.w2.biases": "0.safetensors",
449
+ "layers.9.feed_forward.w3.weight": "0.safetensors",
450
+ "layers.9.feed_forward.w3.scales": "0.safetensors",
451
+ "layers.9.feed_forward.w3.biases": "0.safetensors",
452
+ "layers.9.attention_norm1.weight": "0.safetensors",
453
+ "layers.9.attention_norm2.weight": "0.safetensors",
454
+ "layers.9.ffn_norm1.weight": "0.safetensors",
455
+ "layers.9.ffn_norm2.weight": "0.safetensors",
456
+ "layers.9.adaLN_modulation.0.weight": "0.safetensors",
457
+ "layers.9.adaLN_modulation.0.scales": "0.safetensors",
458
+ "layers.9.adaLN_modulation.0.biases": "0.safetensors",
459
+ "layers.9.adaLN_modulation.0.bias": "0.safetensors",
460
+ "layers.10.attention.to_q.weight": "0.safetensors",
461
+ "layers.10.attention.to_q.scales": "0.safetensors",
462
+ "layers.10.attention.to_q.biases": "0.safetensors",
463
+ "layers.10.attention.to_k.weight": "0.safetensors",
464
+ "layers.10.attention.to_k.scales": "0.safetensors",
465
+ "layers.10.attention.to_k.biases": "0.safetensors",
466
+ "layers.10.attention.to_v.weight": "0.safetensors",
467
+ "layers.10.attention.to_v.scales": "0.safetensors",
468
+ "layers.10.attention.to_v.biases": "0.safetensors",
469
+ "layers.10.attention.to_out.0.weight": "0.safetensors",
470
+ "layers.10.attention.to_out.0.scales": "0.safetensors",
471
+ "layers.10.attention.to_out.0.biases": "0.safetensors",
472
+ "layers.10.attention.norm_q.weight": "0.safetensors",
473
+ "layers.10.attention.norm_k.weight": "0.safetensors",
474
+ "layers.10.feed_forward.w1.weight": "0.safetensors",
475
+ "layers.10.feed_forward.w1.scales": "0.safetensors",
476
+ "layers.10.feed_forward.w1.biases": "0.safetensors",
477
+ "layers.10.feed_forward.w2.weight": "0.safetensors",
478
+ "layers.10.feed_forward.w2.scales": "0.safetensors",
479
+ "layers.10.feed_forward.w2.biases": "0.safetensors",
480
+ "layers.10.feed_forward.w3.weight": "0.safetensors",
481
+ "layers.10.feed_forward.w3.scales": "0.safetensors",
482
+ "layers.10.feed_forward.w3.biases": "0.safetensors",
483
+ "layers.10.attention_norm1.weight": "0.safetensors",
484
+ "layers.10.attention_norm2.weight": "0.safetensors",
485
+ "layers.10.ffn_norm1.weight": "0.safetensors",
486
+ "layers.10.ffn_norm2.weight": "0.safetensors",
487
+ "layers.10.adaLN_modulation.0.weight": "0.safetensors",
488
+ "layers.10.adaLN_modulation.0.scales": "0.safetensors",
489
+ "layers.10.adaLN_modulation.0.biases": "0.safetensors",
490
+ "layers.10.adaLN_modulation.0.bias": "0.safetensors",
491
+ "layers.11.attention.to_q.weight": "0.safetensors",
492
+ "layers.11.attention.to_q.scales": "0.safetensors",
493
+ "layers.11.attention.to_q.biases": "0.safetensors",
494
+ "layers.11.attention.to_k.weight": "0.safetensors",
495
+ "layers.11.attention.to_k.scales": "0.safetensors",
496
+ "layers.11.attention.to_k.biases": "0.safetensors",
497
+ "layers.11.attention.to_v.weight": "0.safetensors",
498
+ "layers.11.attention.to_v.scales": "0.safetensors",
499
+ "layers.11.attention.to_v.biases": "0.safetensors",
500
+ "layers.11.attention.to_out.0.weight": "0.safetensors",
501
+ "layers.11.attention.to_out.0.scales": "0.safetensors",
502
+ "layers.11.attention.to_out.0.biases": "0.safetensors",
503
+ "layers.11.attention.norm_q.weight": "0.safetensors",
504
+ "layers.11.attention.norm_k.weight": "0.safetensors",
505
+ "layers.11.feed_forward.w1.weight": "0.safetensors",
506
+ "layers.11.feed_forward.w1.scales": "0.safetensors",
507
+ "layers.11.feed_forward.w1.biases": "0.safetensors",
508
+ "layers.11.feed_forward.w2.weight": "0.safetensors",
509
+ "layers.11.feed_forward.w2.scales": "0.safetensors",
510
+ "layers.11.feed_forward.w2.biases": "0.safetensors",
511
+ "layers.11.feed_forward.w3.weight": "0.safetensors",
512
+ "layers.11.feed_forward.w3.scales": "0.safetensors",
513
+ "layers.11.feed_forward.w3.biases": "0.safetensors",
514
+ "layers.11.attention_norm1.weight": "0.safetensors",
515
+ "layers.11.attention_norm2.weight": "0.safetensors",
516
+ "layers.11.ffn_norm1.weight": "0.safetensors",
517
+ "layers.11.ffn_norm2.weight": "0.safetensors",
518
+ "layers.11.adaLN_modulation.0.weight": "0.safetensors",
519
+ "layers.11.adaLN_modulation.0.scales": "0.safetensors",
520
+ "layers.11.adaLN_modulation.0.biases": "0.safetensors",
521
+ "layers.11.adaLN_modulation.0.bias": "0.safetensors",
522
+ "layers.12.attention.to_q.weight": "0.safetensors",
523
+ "layers.12.attention.to_q.scales": "0.safetensors",
524
+ "layers.12.attention.to_q.biases": "0.safetensors",
525
+ "layers.12.attention.to_k.weight": "0.safetensors",
526
+ "layers.12.attention.to_k.scales": "0.safetensors",
527
+ "layers.12.attention.to_k.biases": "0.safetensors",
528
+ "layers.12.attention.to_v.weight": "0.safetensors",
529
+ "layers.12.attention.to_v.scales": "0.safetensors",
530
+ "layers.12.attention.to_v.biases": "0.safetensors",
531
+ "layers.12.attention.to_out.0.weight": "0.safetensors",
532
+ "layers.12.attention.to_out.0.scales": "0.safetensors",
533
+ "layers.12.attention.to_out.0.biases": "0.safetensors",
534
+ "layers.12.attention.norm_q.weight": "0.safetensors",
535
+ "layers.12.attention.norm_k.weight": "0.safetensors",
536
+ "layers.12.feed_forward.w1.weight": "0.safetensors",
537
+ "layers.12.feed_forward.w1.scales": "0.safetensors",
538
+ "layers.12.feed_forward.w1.biases": "0.safetensors",
539
+ "layers.12.feed_forward.w2.weight": "0.safetensors",
540
+ "layers.12.feed_forward.w2.scales": "0.safetensors",
541
+ "layers.12.feed_forward.w2.biases": "0.safetensors",
542
+ "layers.12.feed_forward.w3.weight": "0.safetensors",
543
+ "layers.12.feed_forward.w3.scales": "0.safetensors",
544
+ "layers.12.feed_forward.w3.biases": "0.safetensors",
545
+ "layers.12.attention_norm1.weight": "0.safetensors",
546
+ "layers.12.attention_norm2.weight": "0.safetensors",
547
+ "layers.12.ffn_norm1.weight": "0.safetensors",
548
+ "layers.12.ffn_norm2.weight": "0.safetensors",
549
+ "layers.12.adaLN_modulation.0.weight": "0.safetensors",
550
+ "layers.12.adaLN_modulation.0.scales": "0.safetensors",
551
+ "layers.12.adaLN_modulation.0.biases": "0.safetensors",
552
+ "layers.12.adaLN_modulation.0.bias": "0.safetensors",
553
+ "layers.13.attention.to_q.weight": "0.safetensors",
554
+ "layers.13.attention.to_q.scales": "0.safetensors",
555
+ "layers.13.attention.to_q.biases": "0.safetensors",
556
+ "layers.13.attention.to_k.weight": "0.safetensors",
557
+ "layers.13.attention.to_k.scales": "0.safetensors",
558
+ "layers.13.attention.to_k.biases": "0.safetensors",
559
+ "layers.13.attention.to_v.weight": "0.safetensors",
560
+ "layers.13.attention.to_v.scales": "0.safetensors",
561
+ "layers.13.attention.to_v.biases": "0.safetensors",
562
+ "layers.13.attention.to_out.0.weight": "0.safetensors",
563
+ "layers.13.attention.to_out.0.scales": "0.safetensors",
564
+ "layers.13.attention.to_out.0.biases": "0.safetensors",
565
+ "layers.13.attention.norm_q.weight": "0.safetensors",
566
+ "layers.13.attention.norm_k.weight": "0.safetensors",
567
+ "layers.13.feed_forward.w1.weight": "0.safetensors",
568
+ "layers.13.feed_forward.w1.scales": "0.safetensors",
569
+ "layers.13.feed_forward.w1.biases": "0.safetensors",
570
+ "layers.13.feed_forward.w2.weight": "0.safetensors",
571
+ "layers.13.feed_forward.w2.scales": "0.safetensors",
572
+ "layers.13.feed_forward.w2.biases": "0.safetensors",
573
+ "layers.13.feed_forward.w3.weight": "0.safetensors",
574
+ "layers.13.feed_forward.w3.scales": "0.safetensors",
575
+ "layers.13.feed_forward.w3.biases": "0.safetensors",
576
+ "layers.13.attention_norm1.weight": "0.safetensors",
577
+ "layers.13.attention_norm2.weight": "0.safetensors",
578
+ "layers.13.ffn_norm1.weight": "0.safetensors",
579
+ "layers.13.ffn_norm2.weight": "0.safetensors",
580
+ "layers.13.adaLN_modulation.0.weight": "0.safetensors",
581
+ "layers.13.adaLN_modulation.0.scales": "0.safetensors",
582
+ "layers.13.adaLN_modulation.0.biases": "0.safetensors",
583
+ "layers.13.adaLN_modulation.0.bias": "0.safetensors",
584
+ "layers.14.attention.to_q.weight": "0.safetensors",
585
+ "layers.14.attention.to_q.scales": "0.safetensors",
586
+ "layers.14.attention.to_q.biases": "0.safetensors",
587
+ "layers.14.attention.to_k.weight": "0.safetensors",
588
+ "layers.14.attention.to_k.scales": "0.safetensors",
589
+ "layers.14.attention.to_k.biases": "0.safetensors",
590
+ "layers.14.attention.to_v.weight": "0.safetensors",
591
+ "layers.14.attention.to_v.scales": "0.safetensors",
592
+ "layers.14.attention.to_v.biases": "0.safetensors",
593
+ "layers.14.attention.to_out.0.weight": "0.safetensors",
594
+ "layers.14.attention.to_out.0.scales": "0.safetensors",
595
+ "layers.14.attention.to_out.0.biases": "0.safetensors",
596
+ "layers.14.attention.norm_q.weight": "0.safetensors",
597
+ "layers.14.attention.norm_k.weight": "0.safetensors",
598
+ "layers.14.feed_forward.w1.weight": "0.safetensors",
599
+ "layers.14.feed_forward.w1.scales": "0.safetensors",
600
+ "layers.14.feed_forward.w1.biases": "0.safetensors",
601
+ "layers.14.feed_forward.w2.weight": "0.safetensors",
602
+ "layers.14.feed_forward.w2.scales": "0.safetensors",
603
+ "layers.14.feed_forward.w2.biases": "0.safetensors",
604
+ "layers.14.feed_forward.w3.weight": "0.safetensors",
605
+ "layers.14.feed_forward.w3.scales": "0.safetensors",
606
+ "layers.14.feed_forward.w3.biases": "0.safetensors",
607
+ "layers.14.attention_norm1.weight": "0.safetensors",
608
+ "layers.14.attention_norm2.weight": "0.safetensors",
609
+ "layers.14.ffn_norm1.weight": "0.safetensors",
610
+ "layers.14.ffn_norm2.weight": "0.safetensors",
611
+ "layers.14.adaLN_modulation.0.weight": "0.safetensors",
612
+ "layers.14.adaLN_modulation.0.scales": "0.safetensors",
613
+ "layers.14.adaLN_modulation.0.biases": "0.safetensors",
614
+ "layers.14.adaLN_modulation.0.bias": "0.safetensors",
615
+ "layers.15.attention.to_q.weight": "0.safetensors",
616
+ "layers.15.attention.to_q.scales": "0.safetensors",
617
+ "layers.15.attention.to_q.biases": "0.safetensors",
618
+ "layers.15.attention.to_k.weight": "0.safetensors",
619
+ "layers.15.attention.to_k.scales": "0.safetensors",
620
+ "layers.15.attention.to_k.biases": "0.safetensors",
621
+ "layers.15.attention.to_v.weight": "0.safetensors",
622
+ "layers.15.attention.to_v.scales": "0.safetensors",
623
+ "layers.15.attention.to_v.biases": "0.safetensors",
624
+ "layers.15.attention.to_out.0.weight": "0.safetensors",
625
+ "layers.15.attention.to_out.0.scales": "0.safetensors",
626
+ "layers.15.attention.to_out.0.biases": "0.safetensors",
627
+ "layers.15.attention.norm_q.weight": "0.safetensors",
628
+ "layers.15.attention.norm_k.weight": "0.safetensors",
629
+ "layers.15.feed_forward.w1.weight": "0.safetensors",
630
+ "layers.15.feed_forward.w1.scales": "0.safetensors",
631
+ "layers.15.feed_forward.w1.biases": "0.safetensors",
632
+ "layers.15.feed_forward.w2.weight": "0.safetensors",
633
+ "layers.15.feed_forward.w2.scales": "0.safetensors",
634
+ "layers.15.feed_forward.w2.biases": "0.safetensors",
635
+ "layers.15.feed_forward.w3.weight": "0.safetensors",
636
+ "layers.15.feed_forward.w3.scales": "0.safetensors",
637
+ "layers.15.feed_forward.w3.biases": "0.safetensors",
638
+ "layers.15.attention_norm1.weight": "0.safetensors",
639
+ "layers.15.attention_norm2.weight": "0.safetensors",
640
+ "layers.15.ffn_norm1.weight": "0.safetensors",
641
+ "layers.15.ffn_norm2.weight": "0.safetensors",
642
+ "layers.15.adaLN_modulation.0.weight": "0.safetensors",
643
+ "layers.15.adaLN_modulation.0.scales": "0.safetensors",
644
+ "layers.15.adaLN_modulation.0.biases": "0.safetensors",
645
+ "layers.15.adaLN_modulation.0.bias": "0.safetensors",
646
+ "layers.16.attention.to_q.weight": "0.safetensors",
647
+ "layers.16.attention.to_q.scales": "0.safetensors",
648
+ "layers.16.attention.to_q.biases": "0.safetensors",
649
+ "layers.16.attention.to_k.weight": "0.safetensors",
650
+ "layers.16.attention.to_k.scales": "0.safetensors",
651
+ "layers.16.attention.to_k.biases": "0.safetensors",
652
+ "layers.16.attention.to_v.weight": "0.safetensors",
653
+ "layers.16.attention.to_v.scales": "0.safetensors",
654
+ "layers.16.attention.to_v.biases": "0.safetensors",
655
+ "layers.16.attention.to_out.0.weight": "0.safetensors",
656
+ "layers.16.attention.to_out.0.scales": "0.safetensors",
657
+ "layers.16.attention.to_out.0.biases": "0.safetensors",
658
+ "layers.16.attention.norm_q.weight": "0.safetensors",
659
+ "layers.16.attention.norm_k.weight": "0.safetensors",
660
+ "layers.16.feed_forward.w1.weight": "0.safetensors",
661
+ "layers.16.feed_forward.w1.scales": "0.safetensors",
662
+ "layers.16.feed_forward.w1.biases": "0.safetensors",
663
+ "layers.16.feed_forward.w2.weight": "0.safetensors",
664
+ "layers.16.feed_forward.w2.scales": "0.safetensors",
665
+ "layers.16.feed_forward.w2.biases": "0.safetensors",
666
+ "layers.16.feed_forward.w3.weight": "0.safetensors",
667
+ "layers.16.feed_forward.w3.scales": "0.safetensors",
668
+ "layers.16.feed_forward.w3.biases": "0.safetensors",
669
+ "layers.16.attention_norm1.weight": "0.safetensors",
670
+ "layers.16.attention_norm2.weight": "0.safetensors",
671
+ "layers.16.ffn_norm1.weight": "0.safetensors",
672
+ "layers.16.ffn_norm2.weight": "0.safetensors",
673
+ "layers.16.adaLN_modulation.0.weight": "0.safetensors",
674
+ "layers.16.adaLN_modulation.0.scales": "0.safetensors",
675
+ "layers.16.adaLN_modulation.0.biases": "0.safetensors",
676
+ "layers.16.adaLN_modulation.0.bias": "0.safetensors",
677
+ "layers.17.attention.to_q.weight": "1.safetensors",
678
+ "layers.17.attention.to_q.scales": "1.safetensors",
679
+ "layers.17.attention.to_q.biases": "1.safetensors",
680
+ "layers.17.attention.to_k.weight": "1.safetensors",
681
+ "layers.17.attention.to_k.scales": "1.safetensors",
682
+ "layers.17.attention.to_k.biases": "1.safetensors",
683
+ "layers.17.attention.to_v.weight": "1.safetensors",
684
+ "layers.17.attention.to_v.scales": "1.safetensors",
685
+ "layers.17.attention.to_v.biases": "1.safetensors",
686
+ "layers.17.attention.to_out.0.weight": "1.safetensors",
687
+ "layers.17.attention.to_out.0.scales": "1.safetensors",
688
+ "layers.17.attention.to_out.0.biases": "1.safetensors",
689
+ "layers.17.attention.norm_q.weight": "1.safetensors",
690
+ "layers.17.attention.norm_k.weight": "1.safetensors",
691
+ "layers.17.feed_forward.w1.weight": "1.safetensors",
692
+ "layers.17.feed_forward.w1.scales": "1.safetensors",
693
+ "layers.17.feed_forward.w1.biases": "1.safetensors",
694
+ "layers.17.feed_forward.w2.weight": "1.safetensors",
695
+ "layers.17.feed_forward.w2.scales": "1.safetensors",
696
+ "layers.17.feed_forward.w2.biases": "1.safetensors",
697
+ "layers.17.feed_forward.w3.weight": "1.safetensors",
698
+ "layers.17.feed_forward.w3.scales": "1.safetensors",
699
+ "layers.17.feed_forward.w3.biases": "1.safetensors",
700
+ "layers.17.attention_norm1.weight": "1.safetensors",
701
+ "layers.17.attention_norm2.weight": "1.safetensors",
702
+ "layers.17.ffn_norm1.weight": "1.safetensors",
703
+ "layers.17.ffn_norm2.weight": "1.safetensors",
704
+ "layers.17.adaLN_modulation.0.weight": "1.safetensors",
705
+ "layers.17.adaLN_modulation.0.scales": "1.safetensors",
706
+ "layers.17.adaLN_modulation.0.biases": "1.safetensors",
707
+ "layers.17.adaLN_modulation.0.bias": "1.safetensors",
708
+ "layers.18.attention.to_q.weight": "1.safetensors",
709
+ "layers.18.attention.to_q.scales": "1.safetensors",
710
+ "layers.18.attention.to_q.biases": "1.safetensors",
711
+ "layers.18.attention.to_k.weight": "1.safetensors",
712
+ "layers.18.attention.to_k.scales": "1.safetensors",
713
+ "layers.18.attention.to_k.biases": "1.safetensors",
714
+ "layers.18.attention.to_v.weight": "1.safetensors",
715
+ "layers.18.attention.to_v.scales": "1.safetensors",
716
+ "layers.18.attention.to_v.biases": "1.safetensors",
717
+ "layers.18.attention.to_out.0.weight": "1.safetensors",
718
+ "layers.18.attention.to_out.0.scales": "1.safetensors",
719
+ "layers.18.attention.to_out.0.biases": "1.safetensors",
720
+ "layers.18.attention.norm_q.weight": "1.safetensors",
721
+ "layers.18.attention.norm_k.weight": "1.safetensors",
722
+ "layers.18.feed_forward.w1.weight": "1.safetensors",
723
+ "layers.18.feed_forward.w1.scales": "1.safetensors",
724
+ "layers.18.feed_forward.w1.biases": "1.safetensors",
725
+ "layers.18.feed_forward.w2.weight": "1.safetensors",
726
+ "layers.18.feed_forward.w2.scales": "1.safetensors",
727
+ "layers.18.feed_forward.w2.biases": "1.safetensors",
728
+ "layers.18.feed_forward.w3.weight": "1.safetensors",
729
+ "layers.18.feed_forward.w3.scales": "1.safetensors",
730
+ "layers.18.feed_forward.w3.biases": "1.safetensors",
731
+ "layers.18.attention_norm1.weight": "1.safetensors",
732
+ "layers.18.attention_norm2.weight": "1.safetensors",
733
+ "layers.18.ffn_norm1.weight": "1.safetensors",
734
+ "layers.18.ffn_norm2.weight": "1.safetensors",
735
+ "layers.18.adaLN_modulation.0.weight": "1.safetensors",
736
+ "layers.18.adaLN_modulation.0.scales": "1.safetensors",
737
+ "layers.18.adaLN_modulation.0.biases": "1.safetensors",
738
+ "layers.18.adaLN_modulation.0.bias": "1.safetensors",
739
+ "layers.19.attention.to_q.weight": "1.safetensors",
740
+ "layers.19.attention.to_q.scales": "1.safetensors",
741
+ "layers.19.attention.to_q.biases": "1.safetensors",
742
+ "layers.19.attention.to_k.weight": "1.safetensors",
743
+ "layers.19.attention.to_k.scales": "1.safetensors",
744
+ "layers.19.attention.to_k.biases": "1.safetensors",
745
+ "layers.19.attention.to_v.weight": "1.safetensors",
746
+ "layers.19.attention.to_v.scales": "1.safetensors",
747
+ "layers.19.attention.to_v.biases": "1.safetensors",
748
+ "layers.19.attention.to_out.0.weight": "1.safetensors",
749
+ "layers.19.attention.to_out.0.scales": "1.safetensors",
750
+ "layers.19.attention.to_out.0.biases": "1.safetensors",
751
+ "layers.19.attention.norm_q.weight": "1.safetensors",
752
+ "layers.19.attention.norm_k.weight": "1.safetensors",
753
+ "layers.19.feed_forward.w1.weight": "1.safetensors",
754
+ "layers.19.feed_forward.w1.scales": "1.safetensors",
755
+ "layers.19.feed_forward.w1.biases": "1.safetensors",
756
+ "layers.19.feed_forward.w2.weight": "1.safetensors",
757
+ "layers.19.feed_forward.w2.scales": "1.safetensors",
758
+ "layers.19.feed_forward.w2.biases": "1.safetensors",
759
+ "layers.19.feed_forward.w3.weight": "1.safetensors",
760
+ "layers.19.feed_forward.w3.scales": "1.safetensors",
761
+ "layers.19.feed_forward.w3.biases": "1.safetensors",
762
+ "layers.19.attention_norm1.weight": "1.safetensors",
763
+ "layers.19.attention_norm2.weight": "1.safetensors",
764
+ "layers.19.ffn_norm1.weight": "1.safetensors",
765
+ "layers.19.ffn_norm2.weight": "1.safetensors",
766
+ "layers.19.adaLN_modulation.0.weight": "1.safetensors",
767
+ "layers.19.adaLN_modulation.0.scales": "1.safetensors",
768
+ "layers.19.adaLN_modulation.0.biases": "1.safetensors",
769
+ "layers.19.adaLN_modulation.0.bias": "1.safetensors",
770
+ "layers.20.attention.to_q.weight": "1.safetensors",
771
+ "layers.20.attention.to_q.scales": "1.safetensors",
772
+ "layers.20.attention.to_q.biases": "1.safetensors",
773
+ "layers.20.attention.to_k.weight": "1.safetensors",
774
+ "layers.20.attention.to_k.scales": "1.safetensors",
775
+ "layers.20.attention.to_k.biases": "1.safetensors",
776
+ "layers.20.attention.to_v.weight": "1.safetensors",
777
+ "layers.20.attention.to_v.scales": "1.safetensors",
778
+ "layers.20.attention.to_v.biases": "1.safetensors",
779
+ "layers.20.attention.to_out.0.weight": "1.safetensors",
780
+ "layers.20.attention.to_out.0.scales": "1.safetensors",
781
+ "layers.20.attention.to_out.0.biases": "1.safetensors",
782
+ "layers.20.attention.norm_q.weight": "1.safetensors",
783
+ "layers.20.attention.norm_k.weight": "1.safetensors",
784
+ "layers.20.feed_forward.w1.weight": "1.safetensors",
785
+ "layers.20.feed_forward.w1.scales": "1.safetensors",
786
+ "layers.20.feed_forward.w1.biases": "1.safetensors",
787
+ "layers.20.feed_forward.w2.weight": "1.safetensors",
788
+ "layers.20.feed_forward.w2.scales": "1.safetensors",
789
+ "layers.20.feed_forward.w2.biases": "1.safetensors",
790
+ "layers.20.feed_forward.w3.weight": "1.safetensors",
791
+ "layers.20.feed_forward.w3.scales": "1.safetensors",
792
+ "layers.20.feed_forward.w3.biases": "1.safetensors",
793
+ "layers.20.attention_norm1.weight": "1.safetensors",
794
+ "layers.20.attention_norm2.weight": "1.safetensors",
795
+ "layers.20.ffn_norm1.weight": "1.safetensors",
796
+ "layers.20.ffn_norm2.weight": "1.safetensors",
797
+ "layers.20.adaLN_modulation.0.weight": "1.safetensors",
798
+ "layers.20.adaLN_modulation.0.scales": "1.safetensors",
799
+ "layers.20.adaLN_modulation.0.biases": "1.safetensors",
800
+ "layers.20.adaLN_modulation.0.bias": "1.safetensors",
801
+ "layers.21.attention.to_q.weight": "1.safetensors",
802
+ "layers.21.attention.to_q.scales": "1.safetensors",
803
+ "layers.21.attention.to_q.biases": "1.safetensors",
804
+ "layers.21.attention.to_k.weight": "1.safetensors",
805
+ "layers.21.attention.to_k.scales": "1.safetensors",
806
+ "layers.21.attention.to_k.biases": "1.safetensors",
807
+ "layers.21.attention.to_v.weight": "1.safetensors",
808
+ "layers.21.attention.to_v.scales": "1.safetensors",
809
+ "layers.21.attention.to_v.biases": "1.safetensors",
810
+ "layers.21.attention.to_out.0.weight": "1.safetensors",
811
+ "layers.21.attention.to_out.0.scales": "1.safetensors",
812
+ "layers.21.attention.to_out.0.biases": "1.safetensors",
813
+ "layers.21.attention.norm_q.weight": "1.safetensors",
814
+ "layers.21.attention.norm_k.weight": "1.safetensors",
815
+ "layers.21.feed_forward.w1.weight": "1.safetensors",
816
+ "layers.21.feed_forward.w1.scales": "1.safetensors",
817
+ "layers.21.feed_forward.w1.biases": "1.safetensors",
818
+ "layers.21.feed_forward.w2.weight": "1.safetensors",
819
+ "layers.21.feed_forward.w2.scales": "1.safetensors",
820
+ "layers.21.feed_forward.w2.biases": "1.safetensors",
821
+ "layers.21.feed_forward.w3.weight": "1.safetensors",
822
+ "layers.21.feed_forward.w3.scales": "1.safetensors",
823
+ "layers.21.feed_forward.w3.biases": "1.safetensors",
824
+ "layers.21.attention_norm1.weight": "1.safetensors",
825
+ "layers.21.attention_norm2.weight": "1.safetensors",
826
+ "layers.21.ffn_norm1.weight": "1.safetensors",
827
+ "layers.21.ffn_norm2.weight": "1.safetensors",
828
+ "layers.21.adaLN_modulation.0.weight": "1.safetensors",
829
+ "layers.21.adaLN_modulation.0.scales": "1.safetensors",
830
+ "layers.21.adaLN_modulation.0.biases": "1.safetensors",
831
+ "layers.21.adaLN_modulation.0.bias": "1.safetensors",
832
+ "layers.22.attention.to_q.weight": "1.safetensors",
833
+ "layers.22.attention.to_q.scales": "1.safetensors",
834
+ "layers.22.attention.to_q.biases": "1.safetensors",
835
+ "layers.22.attention.to_k.weight": "1.safetensors",
836
+ "layers.22.attention.to_k.scales": "1.safetensors",
837
+ "layers.22.attention.to_k.biases": "1.safetensors",
838
+ "layers.22.attention.to_v.weight": "1.safetensors",
839
+ "layers.22.attention.to_v.scales": "1.safetensors",
840
+ "layers.22.attention.to_v.biases": "1.safetensors",
841
+ "layers.22.attention.to_out.0.weight": "1.safetensors",
842
+ "layers.22.attention.to_out.0.scales": "1.safetensors",
843
+ "layers.22.attention.to_out.0.biases": "1.safetensors",
844
+ "layers.22.attention.norm_q.weight": "1.safetensors",
845
+ "layers.22.attention.norm_k.weight": "1.safetensors",
846
+ "layers.22.feed_forward.w1.weight": "1.safetensors",
847
+ "layers.22.feed_forward.w1.scales": "1.safetensors",
848
+ "layers.22.feed_forward.w1.biases": "1.safetensors",
849
+ "layers.22.feed_forward.w2.weight": "1.safetensors",
850
+ "layers.22.feed_forward.w2.scales": "1.safetensors",
851
+ "layers.22.feed_forward.w2.biases": "1.safetensors",
852
+ "layers.22.feed_forward.w3.weight": "1.safetensors",
853
+ "layers.22.feed_forward.w3.scales": "1.safetensors",
854
+ "layers.22.feed_forward.w3.biases": "1.safetensors",
855
+ "layers.22.attention_norm1.weight": "1.safetensors",
856
+ "layers.22.attention_norm2.weight": "1.safetensors",
857
+ "layers.22.ffn_norm1.weight": "1.safetensors",
858
+ "layers.22.ffn_norm2.weight": "1.safetensors",
859
+ "layers.22.adaLN_modulation.0.weight": "1.safetensors",
860
+ "layers.22.adaLN_modulation.0.scales": "1.safetensors",
861
+ "layers.22.adaLN_modulation.0.biases": "1.safetensors",
862
+ "layers.22.adaLN_modulation.0.bias": "1.safetensors",
863
+ "layers.23.attention.to_q.weight": "1.safetensors",
864
+ "layers.23.attention.to_q.scales": "1.safetensors",
865
+ "layers.23.attention.to_q.biases": "1.safetensors",
866
+ "layers.23.attention.to_k.weight": "1.safetensors",
867
+ "layers.23.attention.to_k.scales": "1.safetensors",
868
+ "layers.23.attention.to_k.biases": "1.safetensors",
869
+ "layers.23.attention.to_v.weight": "1.safetensors",
870
+ "layers.23.attention.to_v.scales": "1.safetensors",
871
+ "layers.23.attention.to_v.biases": "1.safetensors",
872
+ "layers.23.attention.to_out.0.weight": "1.safetensors",
873
+ "layers.23.attention.to_out.0.scales": "1.safetensors",
874
+ "layers.23.attention.to_out.0.biases": "1.safetensors",
875
+ "layers.23.attention.norm_q.weight": "1.safetensors",
876
+ "layers.23.attention.norm_k.weight": "1.safetensors",
877
+ "layers.23.feed_forward.w1.weight": "1.safetensors",
878
+ "layers.23.feed_forward.w1.scales": "1.safetensors",
879
+ "layers.23.feed_forward.w1.biases": "1.safetensors",
880
+ "layers.23.feed_forward.w2.weight": "1.safetensors",
881
+ "layers.23.feed_forward.w2.scales": "1.safetensors",
882
+ "layers.23.feed_forward.w2.biases": "1.safetensors",
883
+ "layers.23.feed_forward.w3.weight": "1.safetensors",
884
+ "layers.23.feed_forward.w3.scales": "1.safetensors",
885
+ "layers.23.feed_forward.w3.biases": "1.safetensors",
886
+ "layers.23.attention_norm1.weight": "1.safetensors",
887
+ "layers.23.attention_norm2.weight": "1.safetensors",
888
+ "layers.23.ffn_norm1.weight": "1.safetensors",
889
+ "layers.23.ffn_norm2.weight": "1.safetensors",
890
+ "layers.23.adaLN_modulation.0.weight": "1.safetensors",
891
+ "layers.23.adaLN_modulation.0.scales": "1.safetensors",
892
+ "layers.23.adaLN_modulation.0.biases": "1.safetensors",
893
+ "layers.23.adaLN_modulation.0.bias": "1.safetensors",
894
+ "layers.24.attention.to_q.weight": "1.safetensors",
895
+ "layers.24.attention.to_q.scales": "1.safetensors",
896
+ "layers.24.attention.to_q.biases": "1.safetensors",
897
+ "layers.24.attention.to_k.weight": "1.safetensors",
898
+ "layers.24.attention.to_k.scales": "1.safetensors",
899
+ "layers.24.attention.to_k.biases": "1.safetensors",
900
+ "layers.24.attention.to_v.weight": "1.safetensors",
901
+ "layers.24.attention.to_v.scales": "1.safetensors",
902
+ "layers.24.attention.to_v.biases": "1.safetensors",
903
+ "layers.24.attention.to_out.0.weight": "1.safetensors",
904
+ "layers.24.attention.to_out.0.scales": "1.safetensors",
905
+ "layers.24.attention.to_out.0.biases": "1.safetensors",
906
+ "layers.24.attention.norm_q.weight": "1.safetensors",
907
+ "layers.24.attention.norm_k.weight": "1.safetensors",
908
+ "layers.24.feed_forward.w1.weight": "1.safetensors",
909
+ "layers.24.feed_forward.w1.scales": "1.safetensors",
910
+ "layers.24.feed_forward.w1.biases": "1.safetensors",
911
+ "layers.24.feed_forward.w2.weight": "1.safetensors",
912
+ "layers.24.feed_forward.w2.scales": "1.safetensors",
913
+ "layers.24.feed_forward.w2.biases": "1.safetensors",
914
+ "layers.24.feed_forward.w3.weight": "1.safetensors",
915
+ "layers.24.feed_forward.w3.scales": "1.safetensors",
916
+ "layers.24.feed_forward.w3.biases": "1.safetensors",
917
+ "layers.24.attention_norm1.weight": "1.safetensors",
918
+ "layers.24.attention_norm2.weight": "1.safetensors",
919
+ "layers.24.ffn_norm1.weight": "1.safetensors",
920
+ "layers.24.ffn_norm2.weight": "1.safetensors",
921
+ "layers.24.adaLN_modulation.0.weight": "1.safetensors",
922
+ "layers.24.adaLN_modulation.0.scales": "1.safetensors",
923
+ "layers.24.adaLN_modulation.0.biases": "1.safetensors",
924
+ "layers.24.adaLN_modulation.0.bias": "1.safetensors",
925
+ "layers.25.attention.to_q.weight": "1.safetensors",
926
+ "layers.25.attention.to_q.scales": "1.safetensors",
927
+ "layers.25.attention.to_q.biases": "1.safetensors",
928
+ "layers.25.attention.to_k.weight": "1.safetensors",
929
+ "layers.25.attention.to_k.scales": "1.safetensors",
930
+ "layers.25.attention.to_k.biases": "1.safetensors",
931
+ "layers.25.attention.to_v.weight": "1.safetensors",
932
+ "layers.25.attention.to_v.scales": "1.safetensors",
933
+ "layers.25.attention.to_v.biases": "1.safetensors",
934
+ "layers.25.attention.to_out.0.weight": "1.safetensors",
935
+ "layers.25.attention.to_out.0.scales": "1.safetensors",
936
+ "layers.25.attention.to_out.0.biases": "1.safetensors",
937
+ "layers.25.attention.norm_q.weight": "1.safetensors",
938
+ "layers.25.attention.norm_k.weight": "1.safetensors",
939
+ "layers.25.feed_forward.w1.weight": "1.safetensors",
940
+ "layers.25.feed_forward.w1.scales": "1.safetensors",
941
+ "layers.25.feed_forward.w1.biases": "1.safetensors",
942
+ "layers.25.feed_forward.w2.weight": "1.safetensors",
943
+ "layers.25.feed_forward.w2.scales": "1.safetensors",
944
+ "layers.25.feed_forward.w2.biases": "1.safetensors",
945
+ "layers.25.feed_forward.w3.weight": "1.safetensors",
946
+ "layers.25.feed_forward.w3.scales": "1.safetensors",
947
+ "layers.25.feed_forward.w3.biases": "1.safetensors",
948
+ "layers.25.attention_norm1.weight": "1.safetensors",
949
+ "layers.25.attention_norm2.weight": "1.safetensors",
950
+ "layers.25.ffn_norm1.weight": "1.safetensors",
951
+ "layers.25.ffn_norm2.weight": "1.safetensors",
952
+ "layers.25.adaLN_modulation.0.weight": "1.safetensors",
953
+ "layers.25.adaLN_modulation.0.scales": "1.safetensors",
954
+ "layers.25.adaLN_modulation.0.biases": "1.safetensors",
955
+ "layers.25.adaLN_modulation.0.bias": "1.safetensors",
956
+ "layers.26.attention.to_q.weight": "1.safetensors",
957
+ "layers.26.attention.to_q.scales": "1.safetensors",
958
+ "layers.26.attention.to_q.biases": "1.safetensors",
959
+ "layers.26.attention.to_k.weight": "1.safetensors",
960
+ "layers.26.attention.to_k.scales": "1.safetensors",
961
+ "layers.26.attention.to_k.biases": "1.safetensors",
962
+ "layers.26.attention.to_v.weight": "1.safetensors",
963
+ "layers.26.attention.to_v.scales": "1.safetensors",
964
+ "layers.26.attention.to_v.biases": "1.safetensors",
965
+ "layers.26.attention.to_out.0.weight": "1.safetensors",
966
+ "layers.26.attention.to_out.0.scales": "1.safetensors",
967
+ "layers.26.attention.to_out.0.biases": "1.safetensors",
968
+ "layers.26.attention.norm_q.weight": "1.safetensors",
969
+ "layers.26.attention.norm_k.weight": "1.safetensors",
970
+ "layers.26.feed_forward.w1.weight": "1.safetensors",
971
+ "layers.26.feed_forward.w1.scales": "1.safetensors",
972
+ "layers.26.feed_forward.w1.biases": "1.safetensors",
973
+ "layers.26.feed_forward.w2.weight": "1.safetensors",
974
+ "layers.26.feed_forward.w2.scales": "1.safetensors",
975
+ "layers.26.feed_forward.w2.biases": "1.safetensors",
976
+ "layers.26.feed_forward.w3.weight": "1.safetensors",
977
+ "layers.26.feed_forward.w3.scales": "1.safetensors",
978
+ "layers.26.feed_forward.w3.biases": "1.safetensors",
979
+ "layers.26.attention_norm1.weight": "1.safetensors",
980
+ "layers.26.attention_norm2.weight": "1.safetensors",
981
+ "layers.26.ffn_norm1.weight": "1.safetensors",
982
+ "layers.26.ffn_norm2.weight": "1.safetensors",
983
+ "layers.26.adaLN_modulation.0.weight": "1.safetensors",
984
+ "layers.26.adaLN_modulation.0.scales": "1.safetensors",
985
+ "layers.26.adaLN_modulation.0.biases": "1.safetensors",
986
+ "layers.26.adaLN_modulation.0.bias": "1.safetensors",
987
+ "layers.27.attention.to_q.weight": "1.safetensors",
988
+ "layers.27.attention.to_q.scales": "1.safetensors",
989
+ "layers.27.attention.to_q.biases": "1.safetensors",
990
+ "layers.27.attention.to_k.weight": "1.safetensors",
991
+ "layers.27.attention.to_k.scales": "1.safetensors",
992
+ "layers.27.attention.to_k.biases": "1.safetensors",
993
+ "layers.27.attention.to_v.weight": "1.safetensors",
994
+ "layers.27.attention.to_v.scales": "1.safetensors",
995
+ "layers.27.attention.to_v.biases": "1.safetensors",
996
+ "layers.27.attention.to_out.0.weight": "1.safetensors",
997
+ "layers.27.attention.to_out.0.scales": "1.safetensors",
998
+ "layers.27.attention.to_out.0.biases": "1.safetensors",
999
+ "layers.27.attention.norm_q.weight": "1.safetensors",
1000
+ "layers.27.attention.norm_k.weight": "1.safetensors",
1001
+ "layers.27.feed_forward.w1.weight": "1.safetensors",
1002
+ "layers.27.feed_forward.w1.scales": "1.safetensors",
1003
+ "layers.27.feed_forward.w1.biases": "1.safetensors",
1004
+ "layers.27.feed_forward.w2.weight": "1.safetensors",
1005
+ "layers.27.feed_forward.w2.scales": "1.safetensors",
1006
+ "layers.27.feed_forward.w2.biases": "1.safetensors",
1007
+ "layers.27.feed_forward.w3.weight": "1.safetensors",
1008
+ "layers.27.feed_forward.w3.scales": "1.safetensors",
1009
+ "layers.27.feed_forward.w3.biases": "1.safetensors",
1010
+ "layers.27.attention_norm1.weight": "1.safetensors",
1011
+ "layers.27.attention_norm2.weight": "1.safetensors",
1012
+ "layers.27.ffn_norm1.weight": "1.safetensors",
1013
+ "layers.27.ffn_norm2.weight": "1.safetensors",
1014
+ "layers.27.adaLN_modulation.0.weight": "1.safetensors",
1015
+ "layers.27.adaLN_modulation.0.scales": "1.safetensors",
1016
+ "layers.27.adaLN_modulation.0.biases": "1.safetensors",
1017
+ "layers.27.adaLN_modulation.0.bias": "1.safetensors",
1018
+ "layers.28.attention.to_q.weight": "1.safetensors",
1019
+ "layers.28.attention.to_q.scales": "1.safetensors",
1020
+ "layers.28.attention.to_q.biases": "1.safetensors",
1021
+ "layers.28.attention.to_k.weight": "1.safetensors",
1022
+ "layers.28.attention.to_k.scales": "1.safetensors",
1023
+ "layers.28.attention.to_k.biases": "1.safetensors",
1024
+ "layers.28.attention.to_v.weight": "1.safetensors",
1025
+ "layers.28.attention.to_v.scales": "1.safetensors",
1026
+ "layers.28.attention.to_v.biases": "1.safetensors",
1027
+ "layers.28.attention.to_out.0.weight": "1.safetensors",
1028
+ "layers.28.attention.to_out.0.scales": "1.safetensors",
1029
+ "layers.28.attention.to_out.0.biases": "1.safetensors",
1030
+ "layers.28.attention.norm_q.weight": "1.safetensors",
1031
+ "layers.28.attention.norm_k.weight": "1.safetensors",
1032
+ "layers.28.feed_forward.w1.weight": "1.safetensors",
1033
+ "layers.28.feed_forward.w1.scales": "1.safetensors",
1034
+ "layers.28.feed_forward.w1.biases": "1.safetensors",
1035
+ "layers.28.feed_forward.w2.weight": "1.safetensors",
1036
+ "layers.28.feed_forward.w2.scales": "1.safetensors",
1037
+ "layers.28.feed_forward.w2.biases": "1.safetensors",
1038
+ "layers.28.feed_forward.w3.weight": "1.safetensors",
1039
+ "layers.28.feed_forward.w3.scales": "1.safetensors",
1040
+ "layers.28.feed_forward.w3.biases": "1.safetensors",
1041
+ "layers.28.attention_norm1.weight": "1.safetensors",
1042
+ "layers.28.attention_norm2.weight": "1.safetensors",
1043
+ "layers.28.ffn_norm1.weight": "1.safetensors",
1044
+ "layers.28.ffn_norm2.weight": "1.safetensors",
1045
+ "layers.28.adaLN_modulation.0.weight": "1.safetensors",
1046
+ "layers.28.adaLN_modulation.0.scales": "1.safetensors",
1047
+ "layers.28.adaLN_modulation.0.biases": "1.safetensors",
1048
+ "layers.28.adaLN_modulation.0.bias": "1.safetensors",
1049
+ "layers.29.attention.to_q.weight": "1.safetensors",
1050
+ "layers.29.attention.to_q.scales": "1.safetensors",
1051
+ "layers.29.attention.to_q.biases": "1.safetensors",
1052
+ "layers.29.attention.to_k.weight": "1.safetensors",
1053
+ "layers.29.attention.to_k.scales": "1.safetensors",
1054
+ "layers.29.attention.to_k.biases": "1.safetensors",
1055
+ "layers.29.attention.to_v.weight": "1.safetensors",
1056
+ "layers.29.attention.to_v.scales": "1.safetensors",
1057
+ "layers.29.attention.to_v.biases": "1.safetensors",
1058
+ "layers.29.attention.to_out.0.weight": "1.safetensors",
1059
+ "layers.29.attention.to_out.0.scales": "1.safetensors",
1060
+ "layers.29.attention.to_out.0.biases": "1.safetensors",
1061
+ "layers.29.attention.norm_q.weight": "1.safetensors",
1062
+ "layers.29.attention.norm_k.weight": "1.safetensors",
1063
+ "layers.29.feed_forward.w1.weight": "1.safetensors",
1064
+ "layers.29.feed_forward.w1.scales": "1.safetensors",
1065
+ "layers.29.feed_forward.w1.biases": "1.safetensors",
1066
+ "layers.29.feed_forward.w2.weight": "1.safetensors",
1067
+ "layers.29.feed_forward.w2.scales": "1.safetensors",
1068
+ "layers.29.feed_forward.w2.biases": "1.safetensors",
1069
+ "layers.29.feed_forward.w3.weight": "1.safetensors",
1070
+ "layers.29.feed_forward.w3.scales": "1.safetensors",
1071
+ "layers.29.feed_forward.w3.biases": "1.safetensors",
1072
+ "layers.29.attention_norm1.weight": "1.safetensors",
1073
+ "layers.29.attention_norm2.weight": "1.safetensors",
1074
+ "layers.29.ffn_norm1.weight": "1.safetensors",
1075
+ "layers.29.ffn_norm2.weight": "1.safetensors",
1076
+ "layers.29.adaLN_modulation.0.weight": "1.safetensors",
1077
+ "layers.29.adaLN_modulation.0.scales": "1.safetensors",
1078
+ "layers.29.adaLN_modulation.0.biases": "1.safetensors",
1079
+ "layers.29.adaLN_modulation.0.bias": "1.safetensors"
1080
+ }
1081
+ }
vae/0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e25b27bad5c629878f1d56f6da680630d2cbe8dc271bc6cfd1673351c7727b3
3
+ size 164654111
vae/model.safetensors.index.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "quantization_level": "4",
4
+ "mflux_version": "0.14.1"
5
+ },
6
+ "weight_map": {
7
+ "encoder.conv_in.conv2d.weight": "0.safetensors",
8
+ "encoder.conv_in.conv2d.bias": "0.safetensors",
9
+ "encoder.down_blocks.0.resnets.0.norm1.bias": "0.safetensors",
10
+ "encoder.down_blocks.0.resnets.0.norm1.weight": "0.safetensors",
11
+ "encoder.down_blocks.0.resnets.0.conv1.weight": "0.safetensors",
12
+ "encoder.down_blocks.0.resnets.0.conv1.bias": "0.safetensors",
13
+ "encoder.down_blocks.0.resnets.0.norm2.bias": "0.safetensors",
14
+ "encoder.down_blocks.0.resnets.0.norm2.weight": "0.safetensors",
15
+ "encoder.down_blocks.0.resnets.0.conv2.weight": "0.safetensors",
16
+ "encoder.down_blocks.0.resnets.0.conv2.bias": "0.safetensors",
17
+ "encoder.down_blocks.0.resnets.1.norm1.bias": "0.safetensors",
18
+ "encoder.down_blocks.0.resnets.1.norm1.weight": "0.safetensors",
19
+ "encoder.down_blocks.0.resnets.1.conv1.weight": "0.safetensors",
20
+ "encoder.down_blocks.0.resnets.1.conv1.bias": "0.safetensors",
21
+ "encoder.down_blocks.0.resnets.1.norm2.bias": "0.safetensors",
22
+ "encoder.down_blocks.0.resnets.1.norm2.weight": "0.safetensors",
23
+ "encoder.down_blocks.0.resnets.1.conv2.weight": "0.safetensors",
24
+ "encoder.down_blocks.0.resnets.1.conv2.bias": "0.safetensors",
25
+ "encoder.down_blocks.0.downsamplers.0.conv.weight": "0.safetensors",
26
+ "encoder.down_blocks.0.downsamplers.0.conv.bias": "0.safetensors",
27
+ "encoder.down_blocks.1.resnets.0.norm1.bias": "0.safetensors",
28
+ "encoder.down_blocks.1.resnets.0.norm1.weight": "0.safetensors",
29
+ "encoder.down_blocks.1.resnets.0.conv1.weight": "0.safetensors",
30
+ "encoder.down_blocks.1.resnets.0.conv1.bias": "0.safetensors",
31
+ "encoder.down_blocks.1.resnets.0.norm2.bias": "0.safetensors",
32
+ "encoder.down_blocks.1.resnets.0.norm2.weight": "0.safetensors",
33
+ "encoder.down_blocks.1.resnets.0.conv2.weight": "0.safetensors",
34
+ "encoder.down_blocks.1.resnets.0.conv2.bias": "0.safetensors",
35
+ "encoder.down_blocks.1.resnets.0.conv_shortcut.weight": "0.safetensors",
36
+ "encoder.down_blocks.1.resnets.0.conv_shortcut.bias": "0.safetensors",
37
+ "encoder.down_blocks.1.resnets.1.norm1.bias": "0.safetensors",
38
+ "encoder.down_blocks.1.resnets.1.norm1.weight": "0.safetensors",
39
+ "encoder.down_blocks.1.resnets.1.conv1.weight": "0.safetensors",
40
+ "encoder.down_blocks.1.resnets.1.conv1.bias": "0.safetensors",
41
+ "encoder.down_blocks.1.resnets.1.norm2.bias": "0.safetensors",
42
+ "encoder.down_blocks.1.resnets.1.norm2.weight": "0.safetensors",
43
+ "encoder.down_blocks.1.resnets.1.conv2.weight": "0.safetensors",
44
+ "encoder.down_blocks.1.resnets.1.conv2.bias": "0.safetensors",
45
+ "encoder.down_blocks.1.downsamplers.0.conv.weight": "0.safetensors",
46
+ "encoder.down_blocks.1.downsamplers.0.conv.bias": "0.safetensors",
47
+ "encoder.down_blocks.2.resnets.0.norm1.bias": "0.safetensors",
48
+ "encoder.down_blocks.2.resnets.0.norm1.weight": "0.safetensors",
49
+ "encoder.down_blocks.2.resnets.0.conv1.weight": "0.safetensors",
50
+ "encoder.down_blocks.2.resnets.0.conv1.bias": "0.safetensors",
51
+ "encoder.down_blocks.2.resnets.0.norm2.bias": "0.safetensors",
52
+ "encoder.down_blocks.2.resnets.0.norm2.weight": "0.safetensors",
53
+ "encoder.down_blocks.2.resnets.0.conv2.weight": "0.safetensors",
54
+ "encoder.down_blocks.2.resnets.0.conv2.bias": "0.safetensors",
55
+ "encoder.down_blocks.2.resnets.0.conv_shortcut.weight": "0.safetensors",
56
+ "encoder.down_blocks.2.resnets.0.conv_shortcut.bias": "0.safetensors",
57
+ "encoder.down_blocks.2.resnets.1.norm1.bias": "0.safetensors",
58
+ "encoder.down_blocks.2.resnets.1.norm1.weight": "0.safetensors",
59
+ "encoder.down_blocks.2.resnets.1.conv1.weight": "0.safetensors",
60
+ "encoder.down_blocks.2.resnets.1.conv1.bias": "0.safetensors",
61
+ "encoder.down_blocks.2.resnets.1.norm2.bias": "0.safetensors",
62
+ "encoder.down_blocks.2.resnets.1.norm2.weight": "0.safetensors",
63
+ "encoder.down_blocks.2.resnets.1.conv2.weight": "0.safetensors",
64
+ "encoder.down_blocks.2.resnets.1.conv2.bias": "0.safetensors",
65
+ "encoder.down_blocks.2.downsamplers.0.conv.weight": "0.safetensors",
66
+ "encoder.down_blocks.2.downsamplers.0.conv.bias": "0.safetensors",
67
+ "encoder.down_blocks.3.resnets.0.norm1.bias": "0.safetensors",
68
+ "encoder.down_blocks.3.resnets.0.norm1.weight": "0.safetensors",
69
+ "encoder.down_blocks.3.resnets.0.conv1.weight": "0.safetensors",
70
+ "encoder.down_blocks.3.resnets.0.conv1.bias": "0.safetensors",
71
+ "encoder.down_blocks.3.resnets.0.norm2.bias": "0.safetensors",
72
+ "encoder.down_blocks.3.resnets.0.norm2.weight": "0.safetensors",
73
+ "encoder.down_blocks.3.resnets.0.conv2.weight": "0.safetensors",
74
+ "encoder.down_blocks.3.resnets.0.conv2.bias": "0.safetensors",
75
+ "encoder.down_blocks.3.resnets.1.norm1.bias": "0.safetensors",
76
+ "encoder.down_blocks.3.resnets.1.norm1.weight": "0.safetensors",
77
+ "encoder.down_blocks.3.resnets.1.conv1.weight": "0.safetensors",
78
+ "encoder.down_blocks.3.resnets.1.conv1.bias": "0.safetensors",
79
+ "encoder.down_blocks.3.resnets.1.norm2.bias": "0.safetensors",
80
+ "encoder.down_blocks.3.resnets.1.norm2.weight": "0.safetensors",
81
+ "encoder.down_blocks.3.resnets.1.conv2.weight": "0.safetensors",
82
+ "encoder.down_blocks.3.resnets.1.conv2.bias": "0.safetensors",
83
+ "encoder.mid_block.attentions.0.group_norm.bias": "0.safetensors",
84
+ "encoder.mid_block.attentions.0.group_norm.weight": "0.safetensors",
85
+ "encoder.mid_block.attentions.0.to_q.weight": "0.safetensors",
86
+ "encoder.mid_block.attentions.0.to_q.scales": "0.safetensors",
87
+ "encoder.mid_block.attentions.0.to_q.biases": "0.safetensors",
88
+ "encoder.mid_block.attentions.0.to_q.bias": "0.safetensors",
89
+ "encoder.mid_block.attentions.0.to_k.weight": "0.safetensors",
90
+ "encoder.mid_block.attentions.0.to_k.scales": "0.safetensors",
91
+ "encoder.mid_block.attentions.0.to_k.biases": "0.safetensors",
92
+ "encoder.mid_block.attentions.0.to_k.bias": "0.safetensors",
93
+ "encoder.mid_block.attentions.0.to_v.weight": "0.safetensors",
94
+ "encoder.mid_block.attentions.0.to_v.scales": "0.safetensors",
95
+ "encoder.mid_block.attentions.0.to_v.biases": "0.safetensors",
96
+ "encoder.mid_block.attentions.0.to_v.bias": "0.safetensors",
97
+ "encoder.mid_block.attentions.0.to_out.0.weight": "0.safetensors",
98
+ "encoder.mid_block.attentions.0.to_out.0.scales": "0.safetensors",
99
+ "encoder.mid_block.attentions.0.to_out.0.biases": "0.safetensors",
100
+ "encoder.mid_block.attentions.0.to_out.0.bias": "0.safetensors",
101
+ "encoder.mid_block.resnets.0.norm1.bias": "0.safetensors",
102
+ "encoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
103
+ "encoder.mid_block.resnets.0.conv1.weight": "0.safetensors",
104
+ "encoder.mid_block.resnets.0.conv1.bias": "0.safetensors",
105
+ "encoder.mid_block.resnets.0.norm2.bias": "0.safetensors",
106
+ "encoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
107
+ "encoder.mid_block.resnets.0.conv2.weight": "0.safetensors",
108
+ "encoder.mid_block.resnets.0.conv2.bias": "0.safetensors",
109
+ "encoder.mid_block.resnets.1.norm1.bias": "0.safetensors",
110
+ "encoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
111
+ "encoder.mid_block.resnets.1.conv1.weight": "0.safetensors",
112
+ "encoder.mid_block.resnets.1.conv1.bias": "0.safetensors",
113
+ "encoder.mid_block.resnets.1.norm2.bias": "0.safetensors",
114
+ "encoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
115
+ "encoder.mid_block.resnets.1.conv2.weight": "0.safetensors",
116
+ "encoder.mid_block.resnets.1.conv2.bias": "0.safetensors",
117
+ "encoder.conv_norm_out.norm.bias": "0.safetensors",
118
+ "encoder.conv_norm_out.norm.weight": "0.safetensors",
119
+ "encoder.conv_out.conv2d.weight": "0.safetensors",
120
+ "encoder.conv_out.conv2d.bias": "0.safetensors",
121
+ "decoder.conv_in.conv.weight": "0.safetensors",
122
+ "decoder.conv_in.conv.bias": "0.safetensors",
123
+ "decoder.mid_block.attentions.0.group_norm.bias": "0.safetensors",
124
+ "decoder.mid_block.attentions.0.group_norm.weight": "0.safetensors",
125
+ "decoder.mid_block.attentions.0.to_q.weight": "0.safetensors",
126
+ "decoder.mid_block.attentions.0.to_q.scales": "0.safetensors",
127
+ "decoder.mid_block.attentions.0.to_q.biases": "0.safetensors",
128
+ "decoder.mid_block.attentions.0.to_q.bias": "0.safetensors",
129
+ "decoder.mid_block.attentions.0.to_k.weight": "0.safetensors",
130
+ "decoder.mid_block.attentions.0.to_k.scales": "0.safetensors",
131
+ "decoder.mid_block.attentions.0.to_k.biases": "0.safetensors",
132
+ "decoder.mid_block.attentions.0.to_k.bias": "0.safetensors",
133
+ "decoder.mid_block.attentions.0.to_v.weight": "0.safetensors",
134
+ "decoder.mid_block.attentions.0.to_v.scales": "0.safetensors",
135
+ "decoder.mid_block.attentions.0.to_v.biases": "0.safetensors",
136
+ "decoder.mid_block.attentions.0.to_v.bias": "0.safetensors",
137
+ "decoder.mid_block.attentions.0.to_out.0.weight": "0.safetensors",
138
+ "decoder.mid_block.attentions.0.to_out.0.scales": "0.safetensors",
139
+ "decoder.mid_block.attentions.0.to_out.0.biases": "0.safetensors",
140
+ "decoder.mid_block.attentions.0.to_out.0.bias": "0.safetensors",
141
+ "decoder.mid_block.resnets.0.norm1.bias": "0.safetensors",
142
+ "decoder.mid_block.resnets.0.norm1.weight": "0.safetensors",
143
+ "decoder.mid_block.resnets.0.conv1.weight": "0.safetensors",
144
+ "decoder.mid_block.resnets.0.conv1.bias": "0.safetensors",
145
+ "decoder.mid_block.resnets.0.norm2.bias": "0.safetensors",
146
+ "decoder.mid_block.resnets.0.norm2.weight": "0.safetensors",
147
+ "decoder.mid_block.resnets.0.conv2.weight": "0.safetensors",
148
+ "decoder.mid_block.resnets.0.conv2.bias": "0.safetensors",
149
+ "decoder.mid_block.resnets.1.norm1.bias": "0.safetensors",
150
+ "decoder.mid_block.resnets.1.norm1.weight": "0.safetensors",
151
+ "decoder.mid_block.resnets.1.conv1.weight": "0.safetensors",
152
+ "decoder.mid_block.resnets.1.conv1.bias": "0.safetensors",
153
+ "decoder.mid_block.resnets.1.norm2.bias": "0.safetensors",
154
+ "decoder.mid_block.resnets.1.norm2.weight": "0.safetensors",
155
+ "decoder.mid_block.resnets.1.conv2.weight": "0.safetensors",
156
+ "decoder.mid_block.resnets.1.conv2.bias": "0.safetensors",
157
+ "decoder.up_blocks.0.resnets.0.norm1.bias": "0.safetensors",
158
+ "decoder.up_blocks.0.resnets.0.norm1.weight": "0.safetensors",
159
+ "decoder.up_blocks.0.resnets.0.conv1.weight": "0.safetensors",
160
+ "decoder.up_blocks.0.resnets.0.conv1.bias": "0.safetensors",
161
+ "decoder.up_blocks.0.resnets.0.norm2.bias": "0.safetensors",
162
+ "decoder.up_blocks.0.resnets.0.norm2.weight": "0.safetensors",
163
+ "decoder.up_blocks.0.resnets.0.conv2.weight": "0.safetensors",
164
+ "decoder.up_blocks.0.resnets.0.conv2.bias": "0.safetensors",
165
+ "decoder.up_blocks.0.resnets.1.norm1.bias": "0.safetensors",
166
+ "decoder.up_blocks.0.resnets.1.norm1.weight": "0.safetensors",
167
+ "decoder.up_blocks.0.resnets.1.conv1.weight": "0.safetensors",
168
+ "decoder.up_blocks.0.resnets.1.conv1.bias": "0.safetensors",
169
+ "decoder.up_blocks.0.resnets.1.norm2.bias": "0.safetensors",
170
+ "decoder.up_blocks.0.resnets.1.norm2.weight": "0.safetensors",
171
+ "decoder.up_blocks.0.resnets.1.conv2.weight": "0.safetensors",
172
+ "decoder.up_blocks.0.resnets.1.conv2.bias": "0.safetensors",
173
+ "decoder.up_blocks.0.resnets.2.norm1.bias": "0.safetensors",
174
+ "decoder.up_blocks.0.resnets.2.norm1.weight": "0.safetensors",
175
+ "decoder.up_blocks.0.resnets.2.conv1.weight": "0.safetensors",
176
+ "decoder.up_blocks.0.resnets.2.conv1.bias": "0.safetensors",
177
+ "decoder.up_blocks.0.resnets.2.norm2.bias": "0.safetensors",
178
+ "decoder.up_blocks.0.resnets.2.norm2.weight": "0.safetensors",
179
+ "decoder.up_blocks.0.resnets.2.conv2.weight": "0.safetensors",
180
+ "decoder.up_blocks.0.resnets.2.conv2.bias": "0.safetensors",
181
+ "decoder.up_blocks.0.upsamplers.0.conv.weight": "0.safetensors",
182
+ "decoder.up_blocks.0.upsamplers.0.conv.bias": "0.safetensors",
183
+ "decoder.up_blocks.1.resnets.0.norm1.bias": "0.safetensors",
184
+ "decoder.up_blocks.1.resnets.0.norm1.weight": "0.safetensors",
185
+ "decoder.up_blocks.1.resnets.0.conv1.weight": "0.safetensors",
186
+ "decoder.up_blocks.1.resnets.0.conv1.bias": "0.safetensors",
187
+ "decoder.up_blocks.1.resnets.0.norm2.bias": "0.safetensors",
188
+ "decoder.up_blocks.1.resnets.0.norm2.weight": "0.safetensors",
189
+ "decoder.up_blocks.1.resnets.0.conv2.weight": "0.safetensors",
190
+ "decoder.up_blocks.1.resnets.0.conv2.bias": "0.safetensors",
191
+ "decoder.up_blocks.1.resnets.1.norm1.bias": "0.safetensors",
192
+ "decoder.up_blocks.1.resnets.1.norm1.weight": "0.safetensors",
193
+ "decoder.up_blocks.1.resnets.1.conv1.weight": "0.safetensors",
194
+ "decoder.up_blocks.1.resnets.1.conv1.bias": "0.safetensors",
195
+ "decoder.up_blocks.1.resnets.1.norm2.bias": "0.safetensors",
196
+ "decoder.up_blocks.1.resnets.1.norm2.weight": "0.safetensors",
197
+ "decoder.up_blocks.1.resnets.1.conv2.weight": "0.safetensors",
198
+ "decoder.up_blocks.1.resnets.1.conv2.bias": "0.safetensors",
199
+ "decoder.up_blocks.1.resnets.2.norm1.bias": "0.safetensors",
200
+ "decoder.up_blocks.1.resnets.2.norm1.weight": "0.safetensors",
201
+ "decoder.up_blocks.1.resnets.2.conv1.weight": "0.safetensors",
202
+ "decoder.up_blocks.1.resnets.2.conv1.bias": "0.safetensors",
203
+ "decoder.up_blocks.1.resnets.2.norm2.bias": "0.safetensors",
204
+ "decoder.up_blocks.1.resnets.2.norm2.weight": "0.safetensors",
205
+ "decoder.up_blocks.1.resnets.2.conv2.weight": "0.safetensors",
206
+ "decoder.up_blocks.1.resnets.2.conv2.bias": "0.safetensors",
207
+ "decoder.up_blocks.1.upsamplers.0.conv.weight": "0.safetensors",
208
+ "decoder.up_blocks.1.upsamplers.0.conv.bias": "0.safetensors",
209
+ "decoder.up_blocks.2.resnets.0.norm1.bias": "0.safetensors",
210
+ "decoder.up_blocks.2.resnets.0.norm1.weight": "0.safetensors",
211
+ "decoder.up_blocks.2.resnets.0.conv1.weight": "0.safetensors",
212
+ "decoder.up_blocks.2.resnets.0.conv1.bias": "0.safetensors",
213
+ "decoder.up_blocks.2.resnets.0.norm2.bias": "0.safetensors",
214
+ "decoder.up_blocks.2.resnets.0.norm2.weight": "0.safetensors",
215
+ "decoder.up_blocks.2.resnets.0.conv2.weight": "0.safetensors",
216
+ "decoder.up_blocks.2.resnets.0.conv2.bias": "0.safetensors",
217
+ "decoder.up_blocks.2.resnets.0.conv_shortcut.weight": "0.safetensors",
218
+ "decoder.up_blocks.2.resnets.0.conv_shortcut.bias": "0.safetensors",
219
+ "decoder.up_blocks.2.resnets.1.norm1.bias": "0.safetensors",
220
+ "decoder.up_blocks.2.resnets.1.norm1.weight": "0.safetensors",
221
+ "decoder.up_blocks.2.resnets.1.conv1.weight": "0.safetensors",
222
+ "decoder.up_blocks.2.resnets.1.conv1.bias": "0.safetensors",
223
+ "decoder.up_blocks.2.resnets.1.norm2.bias": "0.safetensors",
224
+ "decoder.up_blocks.2.resnets.1.norm2.weight": "0.safetensors",
225
+ "decoder.up_blocks.2.resnets.1.conv2.weight": "0.safetensors",
226
+ "decoder.up_blocks.2.resnets.1.conv2.bias": "0.safetensors",
227
+ "decoder.up_blocks.2.resnets.2.norm1.bias": "0.safetensors",
228
+ "decoder.up_blocks.2.resnets.2.norm1.weight": "0.safetensors",
229
+ "decoder.up_blocks.2.resnets.2.conv1.weight": "0.safetensors",
230
+ "decoder.up_blocks.2.resnets.2.conv1.bias": "0.safetensors",
231
+ "decoder.up_blocks.2.resnets.2.norm2.bias": "0.safetensors",
232
+ "decoder.up_blocks.2.resnets.2.norm2.weight": "0.safetensors",
233
+ "decoder.up_blocks.2.resnets.2.conv2.weight": "0.safetensors",
234
+ "decoder.up_blocks.2.resnets.2.conv2.bias": "0.safetensors",
235
+ "decoder.up_blocks.2.upsamplers.0.conv.weight": "0.safetensors",
236
+ "decoder.up_blocks.2.upsamplers.0.conv.bias": "0.safetensors",
237
+ "decoder.up_blocks.3.resnets.0.norm1.bias": "0.safetensors",
238
+ "decoder.up_blocks.3.resnets.0.norm1.weight": "0.safetensors",
239
+ "decoder.up_blocks.3.resnets.0.conv1.weight": "0.safetensors",
240
+ "decoder.up_blocks.3.resnets.0.conv1.bias": "0.safetensors",
241
+ "decoder.up_blocks.3.resnets.0.norm2.bias": "0.safetensors",
242
+ "decoder.up_blocks.3.resnets.0.norm2.weight": "0.safetensors",
243
+ "decoder.up_blocks.3.resnets.0.conv2.weight": "0.safetensors",
244
+ "decoder.up_blocks.3.resnets.0.conv2.bias": "0.safetensors",
245
+ "decoder.up_blocks.3.resnets.0.conv_shortcut.weight": "0.safetensors",
246
+ "decoder.up_blocks.3.resnets.0.conv_shortcut.bias": "0.safetensors",
247
+ "decoder.up_blocks.3.resnets.1.norm1.bias": "0.safetensors",
248
+ "decoder.up_blocks.3.resnets.1.norm1.weight": "0.safetensors",
249
+ "decoder.up_blocks.3.resnets.1.conv1.weight": "0.safetensors",
250
+ "decoder.up_blocks.3.resnets.1.conv1.bias": "0.safetensors",
251
+ "decoder.up_blocks.3.resnets.1.norm2.bias": "0.safetensors",
252
+ "decoder.up_blocks.3.resnets.1.norm2.weight": "0.safetensors",
253
+ "decoder.up_blocks.3.resnets.1.conv2.weight": "0.safetensors",
254
+ "decoder.up_blocks.3.resnets.1.conv2.bias": "0.safetensors",
255
+ "decoder.up_blocks.3.resnets.2.norm1.bias": "0.safetensors",
256
+ "decoder.up_blocks.3.resnets.2.norm1.weight": "0.safetensors",
257
+ "decoder.up_blocks.3.resnets.2.conv1.weight": "0.safetensors",
258
+ "decoder.up_blocks.3.resnets.2.conv1.bias": "0.safetensors",
259
+ "decoder.up_blocks.3.resnets.2.norm2.bias": "0.safetensors",
260
+ "decoder.up_blocks.3.resnets.2.norm2.weight": "0.safetensors",
261
+ "decoder.up_blocks.3.resnets.2.conv2.weight": "0.safetensors",
262
+ "decoder.up_blocks.3.resnets.2.conv2.bias": "0.safetensors",
263
+ "decoder.conv_norm_out.norm.bias": "0.safetensors",
264
+ "decoder.conv_norm_out.norm.weight": "0.safetensors",
265
+ "decoder.conv_out.conv.weight": "0.safetensors",
266
+ "decoder.conv_out.conv.bias": "0.safetensors"
267
+ }
268
+ }