cocktailpeanut commited on
Commit
d434908
·
verified ·
1 Parent(s): 3346241
config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FluxTransformer2DModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "cocktailpeanut/xulf-s",
5
+ "attention_head_dim": 128,
6
+ "axes_dims_rope": [
7
+ 16,
8
+ 56,
9
+ 56
10
+ ],
11
+ "guidance_embeds": false,
12
+ "in_channels": 64,
13
+ "joint_attention_dim": 4096,
14
+ "num_attention_heads": 24,
15
+ "num_layers": 19,
16
+ "num_single_layers": 38,
17
+ "patch_size": 1,
18
+ "pooled_projection_dim": 768
19
+ }
diffusion_pytorch_model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d385ce08ab3c622286468fce95965899a809a7e01fe2d1f5942b3543a0c115f
3
+ size 9963974800
diffusion_pytorch_model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1e75c0191ee92546f31bc9945376769e36de004cadd6526496f7936448a81d
3
+ size 1936709400
diffusion_pytorch_model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quanto_qmap.json ADDED
@@ -0,0 +1,2010 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "time_text_embed.timestep_embedder.linear_1": {
3
+ "weights": "qfloat8_e4m3fn",
4
+ "activations": "none"
5
+ },
6
+ "time_text_embed.timestep_embedder.linear_2": {
7
+ "weights": "qfloat8_e4m3fn",
8
+ "activations": "none"
9
+ },
10
+ "time_text_embed.text_embedder.linear_1": {
11
+ "weights": "qfloat8_e4m3fn",
12
+ "activations": "none"
13
+ },
14
+ "time_text_embed.text_embedder.linear_2": {
15
+ "weights": "qfloat8_e4m3fn",
16
+ "activations": "none"
17
+ },
18
+ "context_embedder": {
19
+ "weights": "qfloat8_e4m3fn",
20
+ "activations": "none"
21
+ },
22
+ "x_embedder": {
23
+ "weights": "qfloat8_e4m3fn",
24
+ "activations": "none"
25
+ },
26
+ "transformer_blocks.0.norm1.linear": {
27
+ "weights": "qfloat8_e4m3fn",
28
+ "activations": "none"
29
+ },
30
+ "transformer_blocks.0.norm1_context.linear": {
31
+ "weights": "qfloat8_e4m3fn",
32
+ "activations": "none"
33
+ },
34
+ "transformer_blocks.0.attn.to_q": {
35
+ "weights": "qfloat8_e4m3fn",
36
+ "activations": "none"
37
+ },
38
+ "transformer_blocks.0.attn.to_k": {
39
+ "weights": "qfloat8_e4m3fn",
40
+ "activations": "none"
41
+ },
42
+ "transformer_blocks.0.attn.to_v": {
43
+ "weights": "qfloat8_e4m3fn",
44
+ "activations": "none"
45
+ },
46
+ "transformer_blocks.0.attn.add_k_proj": {
47
+ "weights": "qfloat8_e4m3fn",
48
+ "activations": "none"
49
+ },
50
+ "transformer_blocks.0.attn.add_v_proj": {
51
+ "weights": "qfloat8_e4m3fn",
52
+ "activations": "none"
53
+ },
54
+ "transformer_blocks.0.attn.add_q_proj": {
55
+ "weights": "qfloat8_e4m3fn",
56
+ "activations": "none"
57
+ },
58
+ "transformer_blocks.0.attn.to_out.0": {
59
+ "weights": "qfloat8_e4m3fn",
60
+ "activations": "none"
61
+ },
62
+ "transformer_blocks.0.attn.to_add_out": {
63
+ "weights": "qfloat8_e4m3fn",
64
+ "activations": "none"
65
+ },
66
+ "transformer_blocks.0.ff.net.0.proj": {
67
+ "weights": "qfloat8_e4m3fn",
68
+ "activations": "none"
69
+ },
70
+ "transformer_blocks.0.ff.net.2": {
71
+ "weights": "qfloat8_e4m3fn",
72
+ "activations": "none"
73
+ },
74
+ "transformer_blocks.0.ff_context.net.0.proj": {
75
+ "weights": "qfloat8_e4m3fn",
76
+ "activations": "none"
77
+ },
78
+ "transformer_blocks.0.ff_context.net.2": {
79
+ "weights": "qfloat8_e4m3fn",
80
+ "activations": "none"
81
+ },
82
+ "transformer_blocks.1.norm1.linear": {
83
+ "weights": "qfloat8_e4m3fn",
84
+ "activations": "none"
85
+ },
86
+ "transformer_blocks.1.norm1_context.linear": {
87
+ "weights": "qfloat8_e4m3fn",
88
+ "activations": "none"
89
+ },
90
+ "transformer_blocks.1.attn.to_q": {
91
+ "weights": "qfloat8_e4m3fn",
92
+ "activations": "none"
93
+ },
94
+ "transformer_blocks.1.attn.to_k": {
95
+ "weights": "qfloat8_e4m3fn",
96
+ "activations": "none"
97
+ },
98
+ "transformer_blocks.1.attn.to_v": {
99
+ "weights": "qfloat8_e4m3fn",
100
+ "activations": "none"
101
+ },
102
+ "transformer_blocks.1.attn.add_k_proj": {
103
+ "weights": "qfloat8_e4m3fn",
104
+ "activations": "none"
105
+ },
106
+ "transformer_blocks.1.attn.add_v_proj": {
107
+ "weights": "qfloat8_e4m3fn",
108
+ "activations": "none"
109
+ },
110
+ "transformer_blocks.1.attn.add_q_proj": {
111
+ "weights": "qfloat8_e4m3fn",
112
+ "activations": "none"
113
+ },
114
+ "transformer_blocks.1.attn.to_out.0": {
115
+ "weights": "qfloat8_e4m3fn",
116
+ "activations": "none"
117
+ },
118
+ "transformer_blocks.1.attn.to_add_out": {
119
+ "weights": "qfloat8_e4m3fn",
120
+ "activations": "none"
121
+ },
122
+ "transformer_blocks.1.ff.net.0.proj": {
123
+ "weights": "qfloat8_e4m3fn",
124
+ "activations": "none"
125
+ },
126
+ "transformer_blocks.1.ff.net.2": {
127
+ "weights": "qfloat8_e4m3fn",
128
+ "activations": "none"
129
+ },
130
+ "transformer_blocks.1.ff_context.net.0.proj": {
131
+ "weights": "qfloat8_e4m3fn",
132
+ "activations": "none"
133
+ },
134
+ "transformer_blocks.1.ff_context.net.2": {
135
+ "weights": "qfloat8_e4m3fn",
136
+ "activations": "none"
137
+ },
138
+ "transformer_blocks.2.norm1.linear": {
139
+ "weights": "qfloat8_e4m3fn",
140
+ "activations": "none"
141
+ },
142
+ "transformer_blocks.2.norm1_context.linear": {
143
+ "weights": "qfloat8_e4m3fn",
144
+ "activations": "none"
145
+ },
146
+ "transformer_blocks.2.attn.to_q": {
147
+ "weights": "qfloat8_e4m3fn",
148
+ "activations": "none"
149
+ },
150
+ "transformer_blocks.2.attn.to_k": {
151
+ "weights": "qfloat8_e4m3fn",
152
+ "activations": "none"
153
+ },
154
+ "transformer_blocks.2.attn.to_v": {
155
+ "weights": "qfloat8_e4m3fn",
156
+ "activations": "none"
157
+ },
158
+ "transformer_blocks.2.attn.add_k_proj": {
159
+ "weights": "qfloat8_e4m3fn",
160
+ "activations": "none"
161
+ },
162
+ "transformer_blocks.2.attn.add_v_proj": {
163
+ "weights": "qfloat8_e4m3fn",
164
+ "activations": "none"
165
+ },
166
+ "transformer_blocks.2.attn.add_q_proj": {
167
+ "weights": "qfloat8_e4m3fn",
168
+ "activations": "none"
169
+ },
170
+ "transformer_blocks.2.attn.to_out.0": {
171
+ "weights": "qfloat8_e4m3fn",
172
+ "activations": "none"
173
+ },
174
+ "transformer_blocks.2.attn.to_add_out": {
175
+ "weights": "qfloat8_e4m3fn",
176
+ "activations": "none"
177
+ },
178
+ "transformer_blocks.2.ff.net.0.proj": {
179
+ "weights": "qfloat8_e4m3fn",
180
+ "activations": "none"
181
+ },
182
+ "transformer_blocks.2.ff.net.2": {
183
+ "weights": "qfloat8_e4m3fn",
184
+ "activations": "none"
185
+ },
186
+ "transformer_blocks.2.ff_context.net.0.proj": {
187
+ "weights": "qfloat8_e4m3fn",
188
+ "activations": "none"
189
+ },
190
+ "transformer_blocks.2.ff_context.net.2": {
191
+ "weights": "qfloat8_e4m3fn",
192
+ "activations": "none"
193
+ },
194
+ "transformer_blocks.3.norm1.linear": {
195
+ "weights": "qfloat8_e4m3fn",
196
+ "activations": "none"
197
+ },
198
+ "transformer_blocks.3.norm1_context.linear": {
199
+ "weights": "qfloat8_e4m3fn",
200
+ "activations": "none"
201
+ },
202
+ "transformer_blocks.3.attn.to_q": {
203
+ "weights": "qfloat8_e4m3fn",
204
+ "activations": "none"
205
+ },
206
+ "transformer_blocks.3.attn.to_k": {
207
+ "weights": "qfloat8_e4m3fn",
208
+ "activations": "none"
209
+ },
210
+ "transformer_blocks.3.attn.to_v": {
211
+ "weights": "qfloat8_e4m3fn",
212
+ "activations": "none"
213
+ },
214
+ "transformer_blocks.3.attn.add_k_proj": {
215
+ "weights": "qfloat8_e4m3fn",
216
+ "activations": "none"
217
+ },
218
+ "transformer_blocks.3.attn.add_v_proj": {
219
+ "weights": "qfloat8_e4m3fn",
220
+ "activations": "none"
221
+ },
222
+ "transformer_blocks.3.attn.add_q_proj": {
223
+ "weights": "qfloat8_e4m3fn",
224
+ "activations": "none"
225
+ },
226
+ "transformer_blocks.3.attn.to_out.0": {
227
+ "weights": "qfloat8_e4m3fn",
228
+ "activations": "none"
229
+ },
230
+ "transformer_blocks.3.attn.to_add_out": {
231
+ "weights": "qfloat8_e4m3fn",
232
+ "activations": "none"
233
+ },
234
+ "transformer_blocks.3.ff.net.0.proj": {
235
+ "weights": "qfloat8_e4m3fn",
236
+ "activations": "none"
237
+ },
238
+ "transformer_blocks.3.ff.net.2": {
239
+ "weights": "qfloat8_e4m3fn",
240
+ "activations": "none"
241
+ },
242
+ "transformer_blocks.3.ff_context.net.0.proj": {
243
+ "weights": "qfloat8_e4m3fn",
244
+ "activations": "none"
245
+ },
246
+ "transformer_blocks.3.ff_context.net.2": {
247
+ "weights": "qfloat8_e4m3fn",
248
+ "activations": "none"
249
+ },
250
+ "transformer_blocks.4.norm1.linear": {
251
+ "weights": "qfloat8_e4m3fn",
252
+ "activations": "none"
253
+ },
254
+ "transformer_blocks.4.norm1_context.linear": {
255
+ "weights": "qfloat8_e4m3fn",
256
+ "activations": "none"
257
+ },
258
+ "transformer_blocks.4.attn.to_q": {
259
+ "weights": "qfloat8_e4m3fn",
260
+ "activations": "none"
261
+ },
262
+ "transformer_blocks.4.attn.to_k": {
263
+ "weights": "qfloat8_e4m3fn",
264
+ "activations": "none"
265
+ },
266
+ "transformer_blocks.4.attn.to_v": {
267
+ "weights": "qfloat8_e4m3fn",
268
+ "activations": "none"
269
+ },
270
+ "transformer_blocks.4.attn.add_k_proj": {
271
+ "weights": "qfloat8_e4m3fn",
272
+ "activations": "none"
273
+ },
274
+ "transformer_blocks.4.attn.add_v_proj": {
275
+ "weights": "qfloat8_e4m3fn",
276
+ "activations": "none"
277
+ },
278
+ "transformer_blocks.4.attn.add_q_proj": {
279
+ "weights": "qfloat8_e4m3fn",
280
+ "activations": "none"
281
+ },
282
+ "transformer_blocks.4.attn.to_out.0": {
283
+ "weights": "qfloat8_e4m3fn",
284
+ "activations": "none"
285
+ },
286
+ "transformer_blocks.4.attn.to_add_out": {
287
+ "weights": "qfloat8_e4m3fn",
288
+ "activations": "none"
289
+ },
290
+ "transformer_blocks.4.ff.net.0.proj": {
291
+ "weights": "qfloat8_e4m3fn",
292
+ "activations": "none"
293
+ },
294
+ "transformer_blocks.4.ff.net.2": {
295
+ "weights": "qfloat8_e4m3fn",
296
+ "activations": "none"
297
+ },
298
+ "transformer_blocks.4.ff_context.net.0.proj": {
299
+ "weights": "qfloat8_e4m3fn",
300
+ "activations": "none"
301
+ },
302
+ "transformer_blocks.4.ff_context.net.2": {
303
+ "weights": "qfloat8_e4m3fn",
304
+ "activations": "none"
305
+ },
306
+ "transformer_blocks.5.norm1.linear": {
307
+ "weights": "qfloat8_e4m3fn",
308
+ "activations": "none"
309
+ },
310
+ "transformer_blocks.5.norm1_context.linear": {
311
+ "weights": "qfloat8_e4m3fn",
312
+ "activations": "none"
313
+ },
314
+ "transformer_blocks.5.attn.to_q": {
315
+ "weights": "qfloat8_e4m3fn",
316
+ "activations": "none"
317
+ },
318
+ "transformer_blocks.5.attn.to_k": {
319
+ "weights": "qfloat8_e4m3fn",
320
+ "activations": "none"
321
+ },
322
+ "transformer_blocks.5.attn.to_v": {
323
+ "weights": "qfloat8_e4m3fn",
324
+ "activations": "none"
325
+ },
326
+ "transformer_blocks.5.attn.add_k_proj": {
327
+ "weights": "qfloat8_e4m3fn",
328
+ "activations": "none"
329
+ },
330
+ "transformer_blocks.5.attn.add_v_proj": {
331
+ "weights": "qfloat8_e4m3fn",
332
+ "activations": "none"
333
+ },
334
+ "transformer_blocks.5.attn.add_q_proj": {
335
+ "weights": "qfloat8_e4m3fn",
336
+ "activations": "none"
337
+ },
338
+ "transformer_blocks.5.attn.to_out.0": {
339
+ "weights": "qfloat8_e4m3fn",
340
+ "activations": "none"
341
+ },
342
+ "transformer_blocks.5.attn.to_add_out": {
343
+ "weights": "qfloat8_e4m3fn",
344
+ "activations": "none"
345
+ },
346
+ "transformer_blocks.5.ff.net.0.proj": {
347
+ "weights": "qfloat8_e4m3fn",
348
+ "activations": "none"
349
+ },
350
+ "transformer_blocks.5.ff.net.2": {
351
+ "weights": "qfloat8_e4m3fn",
352
+ "activations": "none"
353
+ },
354
+ "transformer_blocks.5.ff_context.net.0.proj": {
355
+ "weights": "qfloat8_e4m3fn",
356
+ "activations": "none"
357
+ },
358
+ "transformer_blocks.5.ff_context.net.2": {
359
+ "weights": "qfloat8_e4m3fn",
360
+ "activations": "none"
361
+ },
362
+ "transformer_blocks.6.norm1.linear": {
363
+ "weights": "qfloat8_e4m3fn",
364
+ "activations": "none"
365
+ },
366
+ "transformer_blocks.6.norm1_context.linear": {
367
+ "weights": "qfloat8_e4m3fn",
368
+ "activations": "none"
369
+ },
370
+ "transformer_blocks.6.attn.to_q": {
371
+ "weights": "qfloat8_e4m3fn",
372
+ "activations": "none"
373
+ },
374
+ "transformer_blocks.6.attn.to_k": {
375
+ "weights": "qfloat8_e4m3fn",
376
+ "activations": "none"
377
+ },
378
+ "transformer_blocks.6.attn.to_v": {
379
+ "weights": "qfloat8_e4m3fn",
380
+ "activations": "none"
381
+ },
382
+ "transformer_blocks.6.attn.add_k_proj": {
383
+ "weights": "qfloat8_e4m3fn",
384
+ "activations": "none"
385
+ },
386
+ "transformer_blocks.6.attn.add_v_proj": {
387
+ "weights": "qfloat8_e4m3fn",
388
+ "activations": "none"
389
+ },
390
+ "transformer_blocks.6.attn.add_q_proj": {
391
+ "weights": "qfloat8_e4m3fn",
392
+ "activations": "none"
393
+ },
394
+ "transformer_blocks.6.attn.to_out.0": {
395
+ "weights": "qfloat8_e4m3fn",
396
+ "activations": "none"
397
+ },
398
+ "transformer_blocks.6.attn.to_add_out": {
399
+ "weights": "qfloat8_e4m3fn",
400
+ "activations": "none"
401
+ },
402
+ "transformer_blocks.6.ff.net.0.proj": {
403
+ "weights": "qfloat8_e4m3fn",
404
+ "activations": "none"
405
+ },
406
+ "transformer_blocks.6.ff.net.2": {
407
+ "weights": "qfloat8_e4m3fn",
408
+ "activations": "none"
409
+ },
410
+ "transformer_blocks.6.ff_context.net.0.proj": {
411
+ "weights": "qfloat8_e4m3fn",
412
+ "activations": "none"
413
+ },
414
+ "transformer_blocks.6.ff_context.net.2": {
415
+ "weights": "qfloat8_e4m3fn",
416
+ "activations": "none"
417
+ },
418
+ "transformer_blocks.7.norm1.linear": {
419
+ "weights": "qfloat8_e4m3fn",
420
+ "activations": "none"
421
+ },
422
+ "transformer_blocks.7.norm1_context.linear": {
423
+ "weights": "qfloat8_e4m3fn",
424
+ "activations": "none"
425
+ },
426
+ "transformer_blocks.7.attn.to_q": {
427
+ "weights": "qfloat8_e4m3fn",
428
+ "activations": "none"
429
+ },
430
+ "transformer_blocks.7.attn.to_k": {
431
+ "weights": "qfloat8_e4m3fn",
432
+ "activations": "none"
433
+ },
434
+ "transformer_blocks.7.attn.to_v": {
435
+ "weights": "qfloat8_e4m3fn",
436
+ "activations": "none"
437
+ },
438
+ "transformer_blocks.7.attn.add_k_proj": {
439
+ "weights": "qfloat8_e4m3fn",
440
+ "activations": "none"
441
+ },
442
+ "transformer_blocks.7.attn.add_v_proj": {
443
+ "weights": "qfloat8_e4m3fn",
444
+ "activations": "none"
445
+ },
446
+ "transformer_blocks.7.attn.add_q_proj": {
447
+ "weights": "qfloat8_e4m3fn",
448
+ "activations": "none"
449
+ },
450
+ "transformer_blocks.7.attn.to_out.0": {
451
+ "weights": "qfloat8_e4m3fn",
452
+ "activations": "none"
453
+ },
454
+ "transformer_blocks.7.attn.to_add_out": {
455
+ "weights": "qfloat8_e4m3fn",
456
+ "activations": "none"
457
+ },
458
+ "transformer_blocks.7.ff.net.0.proj": {
459
+ "weights": "qfloat8_e4m3fn",
460
+ "activations": "none"
461
+ },
462
+ "transformer_blocks.7.ff.net.2": {
463
+ "weights": "qfloat8_e4m3fn",
464
+ "activations": "none"
465
+ },
466
+ "transformer_blocks.7.ff_context.net.0.proj": {
467
+ "weights": "qfloat8_e4m3fn",
468
+ "activations": "none"
469
+ },
470
+ "transformer_blocks.7.ff_context.net.2": {
471
+ "weights": "qfloat8_e4m3fn",
472
+ "activations": "none"
473
+ },
474
+ "transformer_blocks.8.norm1.linear": {
475
+ "weights": "qfloat8_e4m3fn",
476
+ "activations": "none"
477
+ },
478
+ "transformer_blocks.8.norm1_context.linear": {
479
+ "weights": "qfloat8_e4m3fn",
480
+ "activations": "none"
481
+ },
482
+ "transformer_blocks.8.attn.to_q": {
483
+ "weights": "qfloat8_e4m3fn",
484
+ "activations": "none"
485
+ },
486
+ "transformer_blocks.8.attn.to_k": {
487
+ "weights": "qfloat8_e4m3fn",
488
+ "activations": "none"
489
+ },
490
+ "transformer_blocks.8.attn.to_v": {
491
+ "weights": "qfloat8_e4m3fn",
492
+ "activations": "none"
493
+ },
494
+ "transformer_blocks.8.attn.add_k_proj": {
495
+ "weights": "qfloat8_e4m3fn",
496
+ "activations": "none"
497
+ },
498
+ "transformer_blocks.8.attn.add_v_proj": {
499
+ "weights": "qfloat8_e4m3fn",
500
+ "activations": "none"
501
+ },
502
+ "transformer_blocks.8.attn.add_q_proj": {
503
+ "weights": "qfloat8_e4m3fn",
504
+ "activations": "none"
505
+ },
506
+ "transformer_blocks.8.attn.to_out.0": {
507
+ "weights": "qfloat8_e4m3fn",
508
+ "activations": "none"
509
+ },
510
+ "transformer_blocks.8.attn.to_add_out": {
511
+ "weights": "qfloat8_e4m3fn",
512
+ "activations": "none"
513
+ },
514
+ "transformer_blocks.8.ff.net.0.proj": {
515
+ "weights": "qfloat8_e4m3fn",
516
+ "activations": "none"
517
+ },
518
+ "transformer_blocks.8.ff.net.2": {
519
+ "weights": "qfloat8_e4m3fn",
520
+ "activations": "none"
521
+ },
522
+ "transformer_blocks.8.ff_context.net.0.proj": {
523
+ "weights": "qfloat8_e4m3fn",
524
+ "activations": "none"
525
+ },
526
+ "transformer_blocks.8.ff_context.net.2": {
527
+ "weights": "qfloat8_e4m3fn",
528
+ "activations": "none"
529
+ },
530
+ "transformer_blocks.9.norm1.linear": {
531
+ "weights": "qfloat8_e4m3fn",
532
+ "activations": "none"
533
+ },
534
+ "transformer_blocks.9.norm1_context.linear": {
535
+ "weights": "qfloat8_e4m3fn",
536
+ "activations": "none"
537
+ },
538
+ "transformer_blocks.9.attn.to_q": {
539
+ "weights": "qfloat8_e4m3fn",
540
+ "activations": "none"
541
+ },
542
+ "transformer_blocks.9.attn.to_k": {
543
+ "weights": "qfloat8_e4m3fn",
544
+ "activations": "none"
545
+ },
546
+ "transformer_blocks.9.attn.to_v": {
547
+ "weights": "qfloat8_e4m3fn",
548
+ "activations": "none"
549
+ },
550
+ "transformer_blocks.9.attn.add_k_proj": {
551
+ "weights": "qfloat8_e4m3fn",
552
+ "activations": "none"
553
+ },
554
+ "transformer_blocks.9.attn.add_v_proj": {
555
+ "weights": "qfloat8_e4m3fn",
556
+ "activations": "none"
557
+ },
558
+ "transformer_blocks.9.attn.add_q_proj": {
559
+ "weights": "qfloat8_e4m3fn",
560
+ "activations": "none"
561
+ },
562
+ "transformer_blocks.9.attn.to_out.0": {
563
+ "weights": "qfloat8_e4m3fn",
564
+ "activations": "none"
565
+ },
566
+ "transformer_blocks.9.attn.to_add_out": {
567
+ "weights": "qfloat8_e4m3fn",
568
+ "activations": "none"
569
+ },
570
+ "transformer_blocks.9.ff.net.0.proj": {
571
+ "weights": "qfloat8_e4m3fn",
572
+ "activations": "none"
573
+ },
574
+ "transformer_blocks.9.ff.net.2": {
575
+ "weights": "qfloat8_e4m3fn",
576
+ "activations": "none"
577
+ },
578
+ "transformer_blocks.9.ff_context.net.0.proj": {
579
+ "weights": "qfloat8_e4m3fn",
580
+ "activations": "none"
581
+ },
582
+ "transformer_blocks.9.ff_context.net.2": {
583
+ "weights": "qfloat8_e4m3fn",
584
+ "activations": "none"
585
+ },
586
+ "transformer_blocks.10.norm1.linear": {
587
+ "weights": "qfloat8_e4m3fn",
588
+ "activations": "none"
589
+ },
590
+ "transformer_blocks.10.norm1_context.linear": {
591
+ "weights": "qfloat8_e4m3fn",
592
+ "activations": "none"
593
+ },
594
+ "transformer_blocks.10.attn.to_q": {
595
+ "weights": "qfloat8_e4m3fn",
596
+ "activations": "none"
597
+ },
598
+ "transformer_blocks.10.attn.to_k": {
599
+ "weights": "qfloat8_e4m3fn",
600
+ "activations": "none"
601
+ },
602
+ "transformer_blocks.10.attn.to_v": {
603
+ "weights": "qfloat8_e4m3fn",
604
+ "activations": "none"
605
+ },
606
+ "transformer_blocks.10.attn.add_k_proj": {
607
+ "weights": "qfloat8_e4m3fn",
608
+ "activations": "none"
609
+ },
610
+ "transformer_blocks.10.attn.add_v_proj": {
611
+ "weights": "qfloat8_e4m3fn",
612
+ "activations": "none"
613
+