codeShare commited on
Commit
e54b0fc
·
verified ·
1 Parent(s): 936cf9a

Delete T5_text_encoder

Browse files
T5_text_encoder/from_FLUX.txt DELETED
@@ -1 +0,0 @@
1
- THese is the T5 text encoder of the FLUX model: https://huggingface.co/black-forest-labs/FLUX.1-dev/tree/main/text_encoder_2
 
 
T5_text_encoder/keys.txt DELETED
@@ -1,223 +0,0 @@
1
- T5 text_encoder model-1 keys:
2
- encoder.block.0.layer.0.SelfAttention.k.weight
3
- encoder.block.0.layer.0.SelfAttention.o.weight
4
- encoder.block.0.layer.0.SelfAttention.q.weight
5
- encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight
6
- encoder.block.0.layer.0.SelfAttention.v.weight
7
- encoder.block.0.layer.0.layer_norm.weight
8
- encoder.block.0.layer.1.DenseReluDense.wi_0.weight
9
- encoder.block.0.layer.1.DenseReluDense.wi_1.weight
10
- encoder.block.0.layer.1.DenseReluDense.wo.weight
11
- encoder.block.0.layer.1.layer_norm.weight
12
- encoder.block.1.layer.0.SelfAttention.k.weight
13
- encoder.block.1.layer.0.SelfAttention.o.weight
14
- encoder.block.1.layer.0.SelfAttention.q.weight
15
- encoder.block.1.layer.0.SelfAttention.v.weight
16
- encoder.block.1.layer.0.layer_norm.weight
17
- encoder.block.1.layer.1.DenseReluDense.wi_0.weight
18
- encoder.block.1.layer.1.DenseReluDense.wi_1.weight
19
- encoder.block.1.layer.1.DenseReluDense.wo.weight
20
- encoder.block.1.layer.1.layer_norm.weight
21
- encoder.block.10.layer.0.SelfAttention.k.weight
22
- encoder.block.10.layer.0.SelfAttention.o.weight
23
- encoder.block.10.layer.0.SelfAttention.q.weight
24
- encoder.block.10.layer.0.SelfAttention.v.weight
25
- encoder.block.10.layer.0.layer_norm.weight
26
- encoder.block.10.layer.1.DenseReluDense.wi_0.weight
27
- encoder.block.10.layer.1.DenseReluDense.wi_1.weight
28
- encoder.block.10.layer.1.DenseReluDense.wo.weight
29
- encoder.block.10.layer.1.layer_norm.weight
30
- encoder.block.11.layer.0.SelfAttention.k.weight
31
- encoder.block.11.layer.0.SelfAttention.o.weight
32
- encoder.block.11.layer.0.SelfAttention.q.weight
33
- encoder.block.11.layer.0.SelfAttention.v.weight
34
- encoder.block.11.layer.0.layer_norm.weight
35
- encoder.block.11.layer.1.DenseReluDense.wi_0.weight
36
- encoder.block.11.layer.1.DenseReluDense.wi_1.weight
37
- encoder.block.11.layer.1.DenseReluDense.wo.weight
38
- encoder.block.11.layer.1.layer_norm.weight
39
- encoder.block.12.layer.0.SelfAttention.k.weight
40
- encoder.block.12.layer.0.SelfAttention.q.weight
41
- encoder.block.12.layer.0.SelfAttention.v.weight
42
- encoder.block.2.layer.0.SelfAttention.k.weight
43
- encoder.block.2.layer.0.SelfAttention.o.weight
44
- encoder.block.2.layer.0.SelfAttention.q.weight
45
- encoder.block.2.layer.0.SelfAttention.v.weight
46
- encoder.block.2.layer.0.layer_norm.weight
47
- encoder.block.2.layer.1.DenseReluDense.wi_0.weight
48
- encoder.block.2.layer.1.DenseReluDense.wi_1.weight
49
- encoder.block.2.layer.1.DenseReluDense.wo.weight
50
- encoder.block.2.layer.1.layer_norm.weight
51
- encoder.block.3.layer.0.SelfAttention.k.weight
52
- encoder.block.3.layer.0.SelfAttention.o.weight
53
- encoder.block.3.layer.0.SelfAttention.q.weight
54
- encoder.block.3.layer.0.SelfAttention.v.weight
55
- encoder.block.3.layer.0.layer_norm.weight
56
- encoder.block.3.layer.1.DenseReluDense.wi_0.weight
57
- encoder.block.3.layer.1.DenseReluDense.wi_1.weight
58
- encoder.block.3.layer.1.DenseReluDense.wo.weight
59
- encoder.block.3.layer.1.layer_norm.weight
60
- encoder.block.4.layer.0.SelfAttention.k.weight
61
- encoder.block.4.layer.0.SelfAttention.o.weight
62
- encoder.block.4.layer.0.SelfAttention.q.weight
63
- encoder.block.4.layer.0.SelfAttention.v.weight
64
- encoder.block.4.layer.0.layer_norm.weight
65
- encoder.block.4.layer.1.DenseReluDense.wi_0.weight
66
- encoder.block.4.layer.1.DenseReluDense.wi_1.weight
67
- encoder.block.4.layer.1.DenseReluDense.wo.weight
68
- encoder.block.4.layer.1.layer_norm.weight
69
- encoder.block.5.layer.0.SelfAttention.k.weight
70
- encoder.block.5.layer.0.SelfAttention.o.weight
71
- encoder.block.5.layer.0.SelfAttention.q.weight
72
- encoder.block.5.layer.0.SelfAttention.v.weight
73
- encoder.block.5.layer.0.layer_norm.weight
74
- encoder.block.5.layer.1.DenseReluDense.wi_0.weight
75
- encoder.block.5.layer.1.DenseReluDense.wi_1.weight
76
- encoder.block.5.layer.1.DenseReluDense.wo.weight
77
- encoder.block.5.layer.1.layer_norm.weight
78
- encoder.block.6.layer.0.SelfAttention.k.weight
79
- encoder.block.6.layer.0.SelfAttention.o.weight
80
- encoder.block.6.layer.0.SelfAttention.q.weight
81
- encoder.block.6.layer.0.SelfAttention.v.weight
82
- encoder.block.6.layer.0.layer_norm.weight
83
- encoder.block.6.layer.1.DenseReluDense.wi_0.weight
84
- encoder.block.6.layer.1.DenseReluDense.wi_1.weight
85
- encoder.block.6.layer.1.DenseReluDense.wo.weight
86
- encoder.block.6.layer.1.layer_norm.weight
87
- encoder.block.7.layer.0.SelfAttention.k.weight
88
- encoder.block.7.layer.0.SelfAttention.o.weight
89
- encoder.block.7.layer.0.SelfAttention.q.weight
90
- encoder.block.7.layer.0.SelfAttention.v.weight
91
- encoder.block.7.layer.0.layer_norm.weight
92
- encoder.block.7.layer.1.DenseReluDense.wi_0.weight
93
- encoder.block.7.layer.1.DenseReluDense.wi_1.weight
94
- encoder.block.7.layer.1.DenseReluDense.wo.weight
95
- encoder.block.7.layer.1.layer_norm.weight
96
- encoder.block.8.layer.0.SelfAttention.k.weight
97
- encoder.block.8.layer.0.SelfAttention.o.weight
98
- encoder.block.8.layer.0.SelfAttention.q.weight
99
- encoder.block.8.layer.0.SelfAttention.v.weight
100
- encoder.block.8.layer.0.layer_norm.weight
101
- encoder.block.8.layer.1.DenseReluDense.wi_0.weight
102
- encoder.block.8.layer.1.DenseReluDense.wi_1.weight
103
- encoder.block.8.layer.1.DenseReluDense.wo.weight
104
- encoder.block.8.layer.1.layer_norm.weight
105
- encoder.block.9.layer.0.SelfAttention.k.weight
106
- encoder.block.9.layer.0.SelfAttention.o.weight
107
- encoder.block.9.layer.0.SelfAttention.q.weight
108
- encoder.block.9.layer.0.SelfAttention.v.weight
109
- encoder.block.9.layer.0.layer_norm.weight
110
- encoder.block.9.layer.1.DenseReluDense.wi_0.weight
111
- encoder.block.9.layer.1.DenseReluDense.wi_1.weight
112
- encoder.block.9.layer.1.DenseReluDense.wo.weight
113
- encoder.block.9.layer.1.layer_norm.weight
114
- shared.weight
115
-
116
-
117
- T5 text_encoder model-2 keys:
118
- encoder.block.12.layer.0.SelfAttention.o.weight
119
- encoder.block.12.layer.0.layer_norm.weight
120
- encoder.block.12.layer.1.DenseReluDense.wi_0.weight
121
- encoder.block.12.layer.1.DenseReluDense.wi_1.weight
122
- encoder.block.12.layer.1.DenseReluDense.wo.weight
123
- encoder.block.12.layer.1.layer_norm.weight
124
- encoder.block.13.layer.0.SelfAttention.k.weight
125
- encoder.block.13.layer.0.SelfAttention.o.weight
126
- encoder.block.13.layer.0.SelfAttention.q.weight
127
- encoder.block.13.layer.0.SelfAttention.v.weight
128
- encoder.block.13.layer.0.layer_norm.weight
129
- encoder.block.13.layer.1.DenseReluDense.wi_0.weight
130
- encoder.block.13.layer.1.DenseReluDense.wi_1.weight
131
- encoder.block.13.layer.1.DenseReluDense.wo.weight
132
- encoder.block.13.layer.1.layer_norm.weight
133
- encoder.block.14.layer.0.SelfAttention.k.weight
134
- encoder.block.14.layer.0.SelfAttention.o.weight
135
- encoder.block.14.layer.0.SelfAttention.q.weight
136
- encoder.block.14.layer.0.SelfAttention.v.weight
137
- encoder.block.14.layer.0.layer_norm.weight
138
- encoder.block.14.layer.1.DenseReluDense.wi_0.weight
139
- encoder.block.14.layer.1.DenseReluDense.wi_1.weight
140
- encoder.block.14.layer.1.DenseReluDense.wo.weight
141
- encoder.block.14.layer.1.layer_norm.weight
142
- encoder.block.15.layer.0.SelfAttention.k.weight
143
- encoder.block.15.layer.0.SelfAttention.o.weight
144
- encoder.block.15.layer.0.SelfAttention.q.weight
145
- encoder.block.15.layer.0.SelfAttention.v.weight
146
- encoder.block.15.layer.0.layer_norm.weight
147
- encoder.block.15.layer.1.DenseReluDense.wi_0.weight
148
- encoder.block.15.layer.1.DenseReluDense.wi_1.weight
149
- encoder.block.15.layer.1.DenseReluDense.wo.weight
150
- encoder.block.15.layer.1.layer_norm.weight
151
- encoder.block.16.layer.0.SelfAttention.k.weight
152
- encoder.block.16.layer.0.SelfAttention.o.weight
153
- encoder.block.16.layer.0.SelfAttention.q.weight
154
- encoder.block.16.layer.0.SelfAttention.v.weight
155
- encoder.block.16.layer.0.layer_norm.weight
156
- encoder.block.16.layer.1.DenseReluDense.wi_0.weight
157
- encoder.block.16.layer.1.DenseReluDense.wi_1.weight
158
- encoder.block.16.layer.1.DenseReluDense.wo.weight
159
- encoder.block.16.layer.1.layer_norm.weight
160
- encoder.block.17.layer.0.SelfAttention.k.weight
161
- encoder.block.17.layer.0.SelfAttention.o.weight
162
- encoder.block.17.layer.0.SelfAttention.q.weight
163
- encoder.block.17.layer.0.SelfAttention.v.weight
164
- encoder.block.17.layer.0.layer_norm.weight
165
- encoder.block.17.layer.1.DenseReluDense.wi_0.weight
166
- encoder.block.17.layer.1.DenseReluDense.wi_1.weight
167
- encoder.block.17.layer.1.DenseReluDense.wo.weight
168
- encoder.block.17.layer.1.layer_norm.weight
169
- encoder.block.18.layer.0.SelfAttention.k.weight
170
- encoder.block.18.layer.0.SelfAttention.o.weight
171
- encoder.block.18.layer.0.SelfAttention.q.weight
172
- encoder.block.18.layer.0.SelfAttention.v.weight
173
- encoder.block.18.layer.0.layer_norm.weight
174
- encoder.block.18.layer.1.DenseReluDense.wi_0.weight
175
- encoder.block.18.layer.1.DenseReluDense.wi_1.weight
176
- encoder.block.18.layer.1.DenseReluDense.wo.weight
177
- encoder.block.18.layer.1.layer_norm.weight
178
- encoder.block.19.layer.0.SelfAttention.k.weight
179
- encoder.block.19.layer.0.SelfAttention.o.weight
180
- encoder.block.19.layer.0.SelfAttention.q.weight
181
- encoder.block.19.layer.0.SelfAttention.v.weight
182
- encoder.block.19.layer.0.layer_norm.weight
183
- encoder.block.19.layer.1.DenseReluDense.wi_0.weight
184
- encoder.block.19.layer.1.DenseReluDense.wi_1.weight
185
- encoder.block.19.layer.1.DenseReluDense.wo.weight
186
- encoder.block.19.layer.1.layer_norm.weight
187
- encoder.block.20.layer.0.SelfAttention.k.weight
188
- encoder.block.20.layer.0.SelfAttention.o.weight
189
- encoder.block.20.layer.0.SelfAttention.q.weight
190
- encoder.block.20.layer.0.SelfAttention.v.weight
191
- encoder.block.20.layer.0.layer_norm.weight
192
- encoder.block.20.layer.1.DenseReluDense.wi_0.weight
193
- encoder.block.20.layer.1.DenseReluDense.wi_1.weight
194
- encoder.block.20.layer.1.DenseReluDense.wo.weight
195
- encoder.block.20.layer.1.layer_norm.weight
196
- encoder.block.21.layer.0.SelfAttention.k.weight
197
- encoder.block.21.layer.0.SelfAttention.o.weight
198
- encoder.block.21.layer.0.SelfAttention.q.weight
199
- encoder.block.21.layer.0.SelfAttention.v.weight
200
- encoder.block.21.layer.0.layer_norm.weight
201
- encoder.block.21.layer.1.DenseReluDense.wi_0.weight
202
- encoder.block.21.layer.1.DenseReluDense.wi_1.weight
203
- encoder.block.21.layer.1.DenseReluDense.wo.weight
204
- encoder.block.21.layer.1.layer_norm.weight
205
- encoder.block.22.layer.0.SelfAttention.k.weight
206
- encoder.block.22.layer.0.SelfAttention.o.weight
207
- encoder.block.22.layer.0.SelfAttention.q.weight
208
- encoder.block.22.layer.0.SelfAttention.v.weight
209
- encoder.block.22.layer.0.layer_norm.weight
210
- encoder.block.22.layer.1.DenseReluDense.wi_0.weight
211
- encoder.block.22.layer.1.DenseReluDense.wi_1.weight
212
- encoder.block.22.layer.1.DenseReluDense.wo.weight
213
- encoder.block.22.layer.1.layer_norm.weight
214
- encoder.block.23.layer.0.SelfAttention.k.weight
215
- encoder.block.23.layer.0.SelfAttention.o.weight
216
- encoder.block.23.layer.0.SelfAttention.q.weight
217
- encoder.block.23.layer.0.SelfAttention.v.weight
218
- encoder.block.23.layer.0.layer_norm.weight
219
- encoder.block.23.layer.1.DenseReluDense.wi_0.weight
220
- encoder.block.23.layer.1.DenseReluDense.wi_1.weight
221
- encoder.block.23.layer.1.DenseReluDense.wo.weight
222
- encoder.block.23.layer.1.layer_norm.weight
223
- encoder.final_layer_norm.weight
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
T5_text_encoder/model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e
3
- size 4994582224
 
 
 
 
T5_text_encoder/model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5640855b301fcdbceddfa90ae8066cd9414aff020552a201a255ecf2059da00
3
- size 4530066360
 
 
 
 
T5_text_encoder/text_encoder_2_config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "_name_or_path": "google/t5-v1_1-xxl",
3
- "architectures": [
4
- "T5EncoderModel"
5
- ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 10240,
8
- "d_kv": 64,
9
- "d_model": 4096,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
16
- "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "num_decoder_layers": 24,
21
- "num_heads": 64,
22
- "num_layers": 24,
23
- "output_past": true,
24
- "pad_token_id": 0,
25
- "relative_attention_max_distance": 128,
26
- "relative_attention_num_buckets": 32,
27
- "tie_word_embeddings": false,
28
- "torch_dtype": "bfloat16",
29
- "transformers_version": "4.43.3",
30
- "use_cache": true,
31
- "vocab_size": 32128
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
T5_text_encoder/text_encoder_2_model.safetensors.index.json DELETED
@@ -1,226 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 9524621312
4
- },
5
- "weight_map": {
6
- "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
7
- "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
8
- "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
9
- "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
10
- "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
11
- "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
12
- "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
13
- "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
14
- "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
15
- "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
16
- "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
17
- "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
18
- "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
19
- "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
20
- "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
21
- "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
22
- "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
23
- "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
24
- "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
25
- "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
26
- "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
27
- "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
28
- "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
29
- "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
30
- "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
31
- "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
32
- "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
33
- "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
34
- "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
35
- "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
36
- "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
37
- "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
38
- "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
39
- "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
40
- "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
41
- "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
42
- "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
43
- "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
44
- "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
45
- "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
46
- "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
47
- "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
48
- "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
49
- "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
50
- "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
51
- "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
52
- "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
53
- "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
54
- "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
55
- "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
56
- "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
57
- "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
58
- "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
59
- "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
60
- "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
61
- "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
62
- "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
63
- "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
64
- "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
65
- "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
66
- "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
67
- "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
68
- "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
69
- "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
70
- "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
71
- "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
72
- "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
73
- "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
74
- "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
75
- "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
76
- "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
77
- "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
78
- "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
79
- "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
80
- "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
81
- "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
82
- "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
83
- "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
84
- "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
85
- "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
86
- "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
87
- "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
88
- "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
89
- "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
90
- "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
91
- "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
92
- "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
93
- "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
94
- "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
95
- "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
96
- "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
97
- "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
98
- "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
99
- "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
100
- "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
101
- "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
102
- "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
103
- "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
104
- "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
105
- "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
106
- "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
107
- "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
108
- "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
109
- "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
110
- "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
111
- "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
112
- "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
113
- "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
114
- "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
115
- "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
116
- "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
117
- "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
118
- "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
119
- "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
120
- "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
121
- "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
122
- "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
123
- "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
124
- "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
125
- "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
126
- "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
127
- "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
128
- "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
129
- "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
130
- "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
131
- "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
132
- "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
133
- "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
134
- "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
135
- "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
136
- "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
137
- "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
138
- "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
139
- "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
140
- "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
141
- "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
142
- "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
143
- "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
144
- "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
145
- "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
146
- "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
147
- "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
148
- "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
149
- "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
150
- "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
151
- "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
152
- "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
153
- "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
154
- "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
155
- "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
156
- "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
157
- "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
158
- "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
159
- "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
160
- "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
161
- "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
162
- "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
163
- "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
164
- "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
165
- "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
166
- "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
167
- "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
168
- "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
169
- "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
170
- "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
171
- "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
172
- "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
173
- "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
174
- "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
175
- "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
176
- "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
177
- "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
178
- "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
179
- "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
180
- "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
181
- "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
182
- "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
183
- "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
184
- "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
185
- "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
186
- "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
187
- "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
188
- "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
189
- "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
190
- "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
191
- "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
192
- "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
193
- "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
194
- "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
195
- "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
196
- "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
197
- "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
198
- "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
199
- "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
200
- "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
201
- "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
202
- "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
203
- "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
204
- "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
205
- "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
206
- "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
207
- "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
208
- "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
209
- "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
210
- "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
211
- "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
212
- "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
213
- "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
214
- "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
215
- "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
216
- "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
217
- "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
218
- "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
219
- "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
220
- "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
221
- "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
222
- "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
223
- "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
224
- "shared.weight": "model-00001-of-00002.safetensors"
225
- }
226
- }