distil-whisper-ar-team commited on
Commit
fde616a
1 Parent(s): 87b43e1

Upload WhisperForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/beegfs/abdul.waheed/ASRs/asr-bench/distil-whisper/models/distil-large-v2-init-16-16-100K-225",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 1280,
17
+ "decoder_attention_heads": 20,
18
+ "decoder_ffn_dim": 5120,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 16,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 20,
24
+ "encoder_ffn_dim": 5120,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 16,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": [
29
+ [
30
+ 1,
31
+ 50259
32
+ ],
33
+ [
34
+ 2,
35
+ 50359
36
+ ],
37
+ [
38
+ 3,
39
+ 50363
40
+ ]
41
+ ],
42
+ "init_std": 0.02,
43
+ "is_encoder_decoder": true,
44
+ "mask_feature_length": 10,
45
+ "mask_feature_min_masks": 0,
46
+ "mask_feature_prob": 0.0,
47
+ "mask_time_length": 10,
48
+ "mask_time_min_masks": 2,
49
+ "mask_time_prob": 0.05,
50
+ "max_length": 448,
51
+ "max_source_positions": 1500,
52
+ "max_target_positions": 448,
53
+ "median_filter_width": 7,
54
+ "model_type": "whisper",
55
+ "num_hidden_layers": 32,
56
+ "num_mel_bins": 80,
57
+ "pad_token_id": 50257,
58
+ "scale_embedding": false,
59
+ "suppress_tokens": [
60
+ 1,
61
+ 2,
62
+ 7,
63
+ 8,
64
+ 9,
65
+ 10,
66
+ 14,
67
+ 25,
68
+ 26,
69
+ 27,
70
+ 28,
71
+ 29,
72
+ 31,
73
+ 58,
74
+ 59,
75
+ 60,
76
+ 61,
77
+ 62,
78
+ 63,
79
+ 90,
80
+ 91,
81
+ 92,
82
+ 93,
83
+ 359,
84
+ 503,
85
+ 522,
86
+ 542,
87
+ 873,
88
+ 893,
89
+ 902,
90
+ 918,
91
+ 922,
92
+ 931,
93
+ 1350,
94
+ 1853,
95
+ 1982,
96
+ 2460,
97
+ 2627,
98
+ 3246,
99
+ 3253,
100
+ 3268,
101
+ 3536,
102
+ 3846,
103
+ 3961,
104
+ 4183,
105
+ 4667,
106
+ 6585,
107
+ 6647,
108
+ 7273,
109
+ 9061,
110
+ 9383,
111
+ 10428,
112
+ 10929,
113
+ 11938,
114
+ 12033,
115
+ 12331,
116
+ 12562,
117
+ 13793,
118
+ 14157,
119
+ 14635,
120
+ 15265,
121
+ 15618,
122
+ 16553,
123
+ 16604,
124
+ 18362,
125
+ 18956,
126
+ 20075,
127
+ 21675,
128
+ 22520,
129
+ 26130,
130
+ 26161,
131
+ 26435,
132
+ 28279,
133
+ 29464,
134
+ 31650,
135
+ 32302,
136
+ 32470,
137
+ 36865,
138
+ 42863,
139
+ 47425,
140
+ 49870,
141
+ 50254,
142
+ 50258,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361,
147
+ 50362
148
+ ],
149
+ "torch_dtype": "float32",
150
+ "transformers_version": "4.35.1",
151
+ "use_cache": true,
152
+ "use_weighted_layer_sum": false,
153
+ "vocab_size": 51865
154
+ }
generation_config.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 10,
5
+ 12
6
+ ],
7
+ [
8
+ 13,
9
+ 17
10
+ ],
11
+ [
12
+ 16,
13
+ 11
14
+ ],
15
+ [
16
+ 16,
17
+ 12
18
+ ],
19
+ [
20
+ 16,
21
+ 13
22
+ ],
23
+ [
24
+ 17,
25
+ 15
26
+ ],
27
+ [
28
+ 17,
29
+ 16
30
+ ],
31
+ [
32
+ 18,
33
+ 4
34
+ ],
35
+ [
36
+ 18,
37
+ 11
38
+ ],
39
+ [
40
+ 18,
41
+ 19
42
+ ],
43
+ [
44
+ 19,
45
+ 11
46
+ ],
47
+ [
48
+ 21,
49
+ 2
50
+ ],
51
+ [
52
+ 21,
53
+ 3
54
+ ],
55
+ [
56
+ 22,
57
+ 3
58
+ ],
59
+ [
60
+ 22,
61
+ 9
62
+ ],
63
+ [
64
+ 22,
65
+ 12
66
+ ],
67
+ [
68
+ 23,
69
+ 5
70
+ ],
71
+ [
72
+ 23,
73
+ 7
74
+ ],
75
+ [
76
+ 23,
77
+ 13
78
+ ],
79
+ [
80
+ 25,
81
+ 5
82
+ ],
83
+ [
84
+ 26,
85
+ 1
86
+ ],
87
+ [
88
+ 26,
89
+ 12
90
+ ],
91
+ [
92
+ 27,
93
+ 15
94
+ ]
95
+ ],
96
+ "begin_suppress_tokens": [
97
+ 220,
98
+ 50257
99
+ ],
100
+ "bos_token_id": 50257,
101
+ "decoder_start_token_id": 50258,
102
+ "eos_token_id": 50257,
103
+ "forced_decoder_ids": [
104
+ [
105
+ 1,
106
+ null
107
+ ],
108
+ [
109
+ 2,
110
+ 50359
111
+ ]
112
+ ],
113
+ "is_multilingual": true,
114
+ "lang_to_id": {
115
+ "<|af|>": 50327,
116
+ "<|am|>": 50334,
117
+ "<|ar|>": 50272,
118
+ "<|as|>": 50350,
119
+ "<|az|>": 50304,
120
+ "<|ba|>": 50355,
121
+ "<|be|>": 50330,
122
+ "<|bg|>": 50292,
123
+ "<|bn|>": 50302,
124
+ "<|bo|>": 50347,
125
+ "<|br|>": 50309,
126
+ "<|bs|>": 50315,
127
+ "<|ca|>": 50270,
128
+ "<|cs|>": 50283,
129
+ "<|cy|>": 50297,
130
+ "<|da|>": 50285,
131
+ "<|de|>": 50261,
132
+ "<|el|>": 50281,
133
+ "<|en|>": 50259,
134
+ "<|es|>": 50262,
135
+ "<|et|>": 50307,
136
+ "<|eu|>": 50310,
137
+ "<|fa|>": 50300,
138
+ "<|fi|>": 50277,
139
+ "<|fo|>": 50338,
140
+ "<|fr|>": 50265,
141
+ "<|gl|>": 50319,
142
+ "<|gu|>": 50333,
143
+ "<|haw|>": 50352,
144
+ "<|ha|>": 50354,
145
+ "<|he|>": 50279,
146
+ "<|hi|>": 50276,
147
+ "<|hr|>": 50291,
148
+ "<|ht|>": 50339,
149
+ "<|hu|>": 50286,
150
+ "<|hy|>": 50312,
151
+ "<|id|>": 50275,
152
+ "<|is|>": 50311,
153
+ "<|it|>": 50274,
154
+ "<|ja|>": 50266,
155
+ "<|jw|>": 50356,
156
+ "<|ka|>": 50329,
157
+ "<|kk|>": 50316,
158
+ "<|km|>": 50323,
159
+ "<|kn|>": 50306,
160
+ "<|ko|>": 50264,
161
+ "<|la|>": 50294,
162
+ "<|lb|>": 50345,
163
+ "<|ln|>": 50353,
164
+ "<|lo|>": 50336,
165
+ "<|lt|>": 50293,
166
+ "<|lv|>": 50301,
167
+ "<|mg|>": 50349,
168
+ "<|mi|>": 50295,
169
+ "<|mk|>": 50308,
170
+ "<|ml|>": 50296,
171
+ "<|mn|>": 50314,
172
+ "<|mr|>": 50320,
173
+ "<|ms|>": 50282,
174
+ "<|mt|>": 50343,
175
+ "<|my|>": 50346,
176
+ "<|ne|>": 50313,
177
+ "<|nl|>": 50271,
178
+ "<|nn|>": 50342,
179
+ "<|no|>": 50288,
180
+ "<|oc|>": 50328,
181
+ "<|pa|>": 50321,
182
+ "<|pl|>": 50269,
183
+ "<|ps|>": 50340,
184
+ "<|pt|>": 50267,
185
+ "<|ro|>": 50284,
186
+ "<|ru|>": 50263,
187
+ "<|sa|>": 50344,
188
+ "<|sd|>": 50332,
189
+ "<|si|>": 50322,
190
+ "<|sk|>": 50298,
191
+ "<|sl|>": 50305,
192
+ "<|sn|>": 50324,
193
+ "<|so|>": 50326,
194
+ "<|sq|>": 50317,
195
+ "<|sr|>": 50303,
196
+ "<|su|>": 50357,
197
+ "<|sv|>": 50273,
198
+ "<|sw|>": 50318,
199
+ "<|ta|>": 50287,
200
+ "<|te|>": 50299,
201
+ "<|tg|>": 50331,
202
+ "<|th|>": 50289,
203
+ "<|tk|>": 50341,
204
+ "<|tl|>": 50348,
205
+ "<|tr|>": 50268,
206
+ "<|tt|>": 50351,
207
+ "<|uk|>": 50280,
208
+ "<|ur|>": 50290,
209
+ "<|uz|>": 50337,
210
+ "<|vi|>": 50278,
211
+ "<|yi|>": 50335,
212
+ "<|yo|>": 50325,
213
+ "<|zh|>": 50260
214
+ },
215
+ "max_initial_timestamp_index": 50,
216
+ "max_length": 448,
217
+ "no_timestamps_token_id": 50363,
218
+ "pad_token_id": 50257,
219
+ "prev_sot_token_id": 50361,
220
+ "return_timestamps": false,
221
+ "suppress_tokens": [
222
+ 1,
223
+ 2,
224
+ 7,
225
+ 8,
226
+ 9,
227
+ 10,
228
+ 14,
229
+ 25,
230
+ 26,
231
+ 27,
232
+ 28,
233
+ 29,
234
+ 31,
235
+ 58,
236
+ 59,
237
+ 60,
238
+ 61,
239
+ 62,
240
+ 63,
241
+ 90,
242
+ 91,
243
+ 92,
244
+ 93,
245
+ 359,
246
+ 503,
247
+ 522,
248
+ 542,
249
+ 873,
250
+ 893,
251
+ 902,
252
+ 918,
253
+ 922,
254
+ 931,
255
+ 1350,
256
+ 1853,
257
+ 1982,
258
+ 2460,
259
+ 2627,
260
+ 3246,
261
+ 3253,
262
+ 3268,
263
+ 3536,
264
+ 3846,
265
+ 3961,
266
+ 4183,
267
+ 4667,
268
+ 6585,
269
+ 6647,
270
+ 7273,
271
+ 9061,
272
+ 9383,
273
+ 10428,
274
+ 10929,
275
+ 11938,
276
+ 12033,
277
+ 12331,
278
+ 12562,
279
+ 13793,
280
+ 14157,
281
+ 14635,
282
+ 15265,
283
+ 15618,
284
+ 16553,
285
+ 16604,
286
+ 18362,
287
+ 18956,
288
+ 20075,
289
+ 21675,
290
+ 22520,
291
+ 26130,
292
+ 26161,
293
+ 26435,
294
+ 28279,
295
+ 29464,
296
+ 31650,
297
+ 32302,
298
+ 32470,
299
+ 36865,
300
+ 42863,
301
+ 47425,
302
+ 49870,
303
+ 50254,
304
+ 50258,
305
+ 50358,
306
+ 50359,
307
+ 50360,
308
+ 50361,
309
+ 50362
310
+ ],
311
+ "task_to_id": {
312
+ "transcribe": 50359,
313
+ "translate": 50358
314
+ },
315
+ "transformers_version": "4.35.1"
316
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eebc824248ef7e9bcb8923ccdf7ae5bc076728ee072bdd1f889a1572a55b570
3
+ size 474588368
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b96a8a00c609a23ae025d6233f0f506cc5e142a4559108550b2d16c0eb4b5e
3
+ size 498468456
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab7c364e81bbf583ffd6b323628a091cf059682738c5459bdbfeae9f3278ba7
3
+ size 314835968
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92ebe1eb2f886ccdb43a183912b11933386eab7d0105cd729650b89db73867d
3
+ size 497409400
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a467c297908dfa66ea1eee4c28ccde57665e721647fdd9dd657c858be1b52f37
3
+ size 478835520
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7177bf0e4f9b5c60e2757d53643047f895f0f9cc470823101eb41594c3b6d414
3
+ size 498502312
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19440cabe2dbd44567801604b497f764cb1c3201a14df693e2c269501d95315c
3
+ size 472265720
model.safetensors.index.json ADDED
@@ -0,0 +1,642 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 3234831360
4
+ },
5
+ "weight_map": {
6
+ "model.decoder.embed_positions.weight": "model-00004-of-00007.safetensors",
7
+ "model.decoder.embed_tokens.weight": "model-00004-of-00007.safetensors",
8
+ "model.decoder.layer_norm.bias": "model-00007-of-00007.safetensors",
9
+ "model.decoder.layer_norm.weight": "model-00007-of-00007.safetensors",
10
+ "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00004-of-00007.safetensors",
11
+ "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00004-of-00007.safetensors",
12
+ "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00004-of-00007.safetensors",
13
+ "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00004-of-00007.safetensors",
14
+ "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00004-of-00007.safetensors",
15
+ "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00004-of-00007.safetensors",
16
+ "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00004-of-00007.safetensors",
17
+ "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00004-of-00007.safetensors",
18
+ "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00004-of-00007.safetensors",
19
+ "model.decoder.layers.0.fc1.bias": "model-00004-of-00007.safetensors",
20
+ "model.decoder.layers.0.fc1.weight": "model-00004-of-00007.safetensors",
21
+ "model.decoder.layers.0.fc2.bias": "model-00004-of-00007.safetensors",
22
+ "model.decoder.layers.0.fc2.weight": "model-00004-of-00007.safetensors",
23
+ "model.decoder.layers.0.final_layer_norm.bias": "model-00004-of-00007.safetensors",
24
+ "model.decoder.layers.0.final_layer_norm.weight": "model-00004-of-00007.safetensors",
25
+ "model.decoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
26
+ "model.decoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00007.safetensors",
27
+ "model.decoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00007.safetensors",
28
+ "model.decoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
29
+ "model.decoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
30
+ "model.decoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
31
+ "model.decoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
32
+ "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00004-of-00007.safetensors",
33
+ "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00004-of-00007.safetensors",
34
+ "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00004-of-00007.safetensors",
35
+ "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00004-of-00007.safetensors",
36
+ "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00004-of-00007.safetensors",
37
+ "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00004-of-00007.safetensors",
38
+ "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00004-of-00007.safetensors",
39
+ "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00004-of-00007.safetensors",
40
+ "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00004-of-00007.safetensors",
41
+ "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00004-of-00007.safetensors",
42
+ "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00004-of-00007.safetensors",
43
+ "model.decoder.layers.1.fc1.bias": "model-00004-of-00007.safetensors",
44
+ "model.decoder.layers.1.fc1.weight": "model-00004-of-00007.safetensors",
45
+ "model.decoder.layers.1.fc2.bias": "model-00004-of-00007.safetensors",
46
+ "model.decoder.layers.1.fc2.weight": "model-00004-of-00007.safetensors",
47
+ "model.decoder.layers.1.final_layer_norm.bias": "model-00004-of-00007.safetensors",
48
+ "model.decoder.layers.1.final_layer_norm.weight": "model-00004-of-00007.safetensors",
49
+ "model.decoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
50
+ "model.decoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00007.safetensors",
51
+ "model.decoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00007.safetensors",
52
+ "model.decoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
53
+ "model.decoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
54
+ "model.decoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
55
+ "model.decoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
56
+ "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00007.safetensors",
57
+ "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00004-of-00007.safetensors",
58
+ "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00006-of-00007.safetensors",
59
+ "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00006-of-00007.safetensors",
60
+ "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00006-of-00007.safetensors",
61
+ "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00006-of-00007.safetensors",
62
+ "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00006-of-00007.safetensors",
63
+ "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00006-of-00007.safetensors",
64
+ "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00006-of-00007.safetensors",
65
+ "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
66
+ "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
67
+ "model.decoder.layers.10.fc1.bias": "model-00006-of-00007.safetensors",
68
+ "model.decoder.layers.10.fc1.weight": "model-00006-of-00007.safetensors",
69
+ "model.decoder.layers.10.fc2.bias": "model-00006-of-00007.safetensors",
70
+ "model.decoder.layers.10.fc2.weight": "model-00006-of-00007.safetensors",
71
+ "model.decoder.layers.10.final_layer_norm.bias": "model-00006-of-00007.safetensors",
72
+ "model.decoder.layers.10.final_layer_norm.weight": "model-00006-of-00007.safetensors",
73
+ "model.decoder.layers.10.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
74
+ "model.decoder.layers.10.self_attn.out_proj.bias": "model-00006-of-00007.safetensors",
75
+ "model.decoder.layers.10.self_attn.out_proj.weight": "model-00006-of-00007.safetensors",
76
+ "model.decoder.layers.10.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
77
+ "model.decoder.layers.10.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
78
+ "model.decoder.layers.10.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
79
+ "model.decoder.layers.10.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
80
+ "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
81
+ "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
82
+ "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00006-of-00007.safetensors",
83
+ "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00006-of-00007.safetensors",
84
+ "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00006-of-00007.safetensors",
85
+ "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00006-of-00007.safetensors",
86
+ "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00006-of-00007.safetensors",
87
+ "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00006-of-00007.safetensors",
88
+ "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00006-of-00007.safetensors",
89
+ "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
90
+ "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
91
+ "model.decoder.layers.11.fc1.bias": "model-00007-of-00007.safetensors",
92
+ "model.decoder.layers.11.fc1.weight": "model-00007-of-00007.safetensors",
93
+ "model.decoder.layers.11.fc2.bias": "model-00007-of-00007.safetensors",
94
+ "model.decoder.layers.11.fc2.weight": "model-00007-of-00007.safetensors",
95
+ "model.decoder.layers.11.final_layer_norm.bias": "model-00007-of-00007.safetensors",
96
+ "model.decoder.layers.11.final_layer_norm.weight": "model-00007-of-00007.safetensors",
97
+ "model.decoder.layers.11.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
98
+ "model.decoder.layers.11.self_attn.out_proj.bias": "model-00006-of-00007.safetensors",
99
+ "model.decoder.layers.11.self_attn.out_proj.weight": "model-00006-of-00007.safetensors",
100
+ "model.decoder.layers.11.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
101
+ "model.decoder.layers.11.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
102
+ "model.decoder.layers.11.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
103
+ "model.decoder.layers.11.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
104
+ "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
105
+ "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
106
+ "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00007-of-00007.safetensors",
107
+ "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00007-of-00007.safetensors",
108
+ "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00007-of-00007.safetensors",
109
+ "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00007-of-00007.safetensors",
110
+ "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00007-of-00007.safetensors",
111
+ "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00007-of-00007.safetensors",
112
+ "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00007-of-00007.safetensors",
113
+ "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
114
+ "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
115
+ "model.decoder.layers.12.fc1.bias": "model-00007-of-00007.safetensors",
116
+ "model.decoder.layers.12.fc1.weight": "model-00007-of-00007.safetensors",
117
+ "model.decoder.layers.12.fc2.bias": "model-00007-of-00007.safetensors",
118
+ "model.decoder.layers.12.fc2.weight": "model-00007-of-00007.safetensors",
119
+ "model.decoder.layers.12.final_layer_norm.bias": "model-00007-of-00007.safetensors",
120
+ "model.decoder.layers.12.final_layer_norm.weight": "model-00007-of-00007.safetensors",
121
+ "model.decoder.layers.12.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
122
+ "model.decoder.layers.12.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
123
+ "model.decoder.layers.12.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
124
+ "model.decoder.layers.12.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
125
+ "model.decoder.layers.12.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
126
+ "model.decoder.layers.12.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
127
+ "model.decoder.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
128
+ "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
129
+ "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
130
+ "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00007-of-00007.safetensors",
131
+ "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00007-of-00007.safetensors",
132
+ "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00007-of-00007.safetensors",
133
+ "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00007-of-00007.safetensors",
134
+ "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00007-of-00007.safetensors",
135
+ "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00007-of-00007.safetensors",
136
+ "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00007-of-00007.safetensors",
137
+ "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
138
+ "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
139
+ "model.decoder.layers.13.fc1.bias": "model-00007-of-00007.safetensors",
140
+ "model.decoder.layers.13.fc1.weight": "model-00007-of-00007.safetensors",
141
+ "model.decoder.layers.13.fc2.bias": "model-00007-of-00007.safetensors",
142
+ "model.decoder.layers.13.fc2.weight": "model-00007-of-00007.safetensors",
143
+ "model.decoder.layers.13.final_layer_norm.bias": "model-00007-of-00007.safetensors",
144
+ "model.decoder.layers.13.final_layer_norm.weight": "model-00007-of-00007.safetensors",
145
+ "model.decoder.layers.13.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
146
+ "model.decoder.layers.13.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
147
+ "model.decoder.layers.13.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
148
+ "model.decoder.layers.13.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
149
+ "model.decoder.layers.13.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
150
+ "model.decoder.layers.13.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
151
+ "model.decoder.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
152
+ "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
153
+ "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
154
+ "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00007-of-00007.safetensors",
155
+ "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00007-of-00007.safetensors",
156
+ "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00007-of-00007.safetensors",
157
+ "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00007-of-00007.safetensors",
158
+ "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00007-of-00007.safetensors",
159
+ "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00007-of-00007.safetensors",
160
+ "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00007-of-00007.safetensors",
161
+ "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
162
+ "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
163
+ "model.decoder.layers.14.fc1.bias": "model-00007-of-00007.safetensors",
164
+ "model.decoder.layers.14.fc1.weight": "model-00007-of-00007.safetensors",
165
+ "model.decoder.layers.14.fc2.bias": "model-00007-of-00007.safetensors",
166
+ "model.decoder.layers.14.fc2.weight": "model-00007-of-00007.safetensors",
167
+ "model.decoder.layers.14.final_layer_norm.bias": "model-00007-of-00007.safetensors",
168
+ "model.decoder.layers.14.final_layer_norm.weight": "model-00007-of-00007.safetensors",
169
+ "model.decoder.layers.14.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
170
+ "model.decoder.layers.14.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
171
+ "model.decoder.layers.14.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
172
+ "model.decoder.layers.14.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
173
+ "model.decoder.layers.14.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
174
+ "model.decoder.layers.14.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
175
+ "model.decoder.layers.14.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
176
+ "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
177
+ "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
178
+ "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00007-of-00007.safetensors",
179
+ "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00007-of-00007.safetensors",
180
+ "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00007-of-00007.safetensors",
181
+ "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00007-of-00007.safetensors",
182
+ "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00007-of-00007.safetensors",
183
+ "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00007-of-00007.safetensors",
184
+ "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00007-of-00007.safetensors",
185
+ "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
186
+ "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
187
+ "model.decoder.layers.15.fc1.bias": "model-00007-of-00007.safetensors",
188
+ "model.decoder.layers.15.fc1.weight": "model-00007-of-00007.safetensors",
189
+ "model.decoder.layers.15.fc2.bias": "model-00007-of-00007.safetensors",
190
+ "model.decoder.layers.15.fc2.weight": "model-00007-of-00007.safetensors",
191
+ "model.decoder.layers.15.final_layer_norm.bias": "model-00007-of-00007.safetensors",
192
+ "model.decoder.layers.15.final_layer_norm.weight": "model-00007-of-00007.safetensors",
193
+ "model.decoder.layers.15.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
194
+ "model.decoder.layers.15.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
195
+ "model.decoder.layers.15.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
196
+ "model.decoder.layers.15.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
197
+ "model.decoder.layers.15.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
198
+ "model.decoder.layers.15.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
199
+ "model.decoder.layers.15.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
200
+ "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00007-of-00007.safetensors",
201
+ "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00007-of-00007.safetensors",
202
+ "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00005-of-00007.safetensors",
203
+ "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00005-of-00007.safetensors",
204
+ "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00005-of-00007.safetensors",
205
+ "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00005-of-00007.safetensors",
206
+ "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00005-of-00007.safetensors",
207
+ "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00005-of-00007.safetensors",
208
+ "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00005-of-00007.safetensors",
209
+ "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
210
+ "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
211
+ "model.decoder.layers.2.fc1.bias": "model-00005-of-00007.safetensors",
212
+ "model.decoder.layers.2.fc1.weight": "model-00005-of-00007.safetensors",
213
+ "model.decoder.layers.2.fc2.bias": "model-00005-of-00007.safetensors",
214
+ "model.decoder.layers.2.fc2.weight": "model-00005-of-00007.safetensors",
215
+ "model.decoder.layers.2.final_layer_norm.bias": "model-00005-of-00007.safetensors",
216
+ "model.decoder.layers.2.final_layer_norm.weight": "model-00005-of-00007.safetensors",
217
+ "model.decoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
218
+ "model.decoder.layers.2.self_attn.out_proj.bias": "model-00005-of-00007.safetensors",
219
+ "model.decoder.layers.2.self_attn.out_proj.weight": "model-00005-of-00007.safetensors",
220
+ "model.decoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
221
+ "model.decoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
222
+ "model.decoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
223
+ "model.decoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
224
+ "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
225
+ "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
226
+ "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00005-of-00007.safetensors",
227
+ "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00005-of-00007.safetensors",
228
+ "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00005-of-00007.safetensors",
229
+ "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00005-of-00007.safetensors",
230
+ "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00005-of-00007.safetensors",
231
+ "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00005-of-00007.safetensors",
232
+ "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00005-of-00007.safetensors",
233
+ "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
234
+ "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
235
+ "model.decoder.layers.3.fc1.bias": "model-00005-of-00007.safetensors",
236
+ "model.decoder.layers.3.fc1.weight": "model-00005-of-00007.safetensors",
237
+ "model.decoder.layers.3.fc2.bias": "model-00005-of-00007.safetensors",
238
+ "model.decoder.layers.3.fc2.weight": "model-00005-of-00007.safetensors",
239
+ "model.decoder.layers.3.final_layer_norm.bias": "model-00005-of-00007.safetensors",
240
+ "model.decoder.layers.3.final_layer_norm.weight": "model-00005-of-00007.safetensors",
241
+ "model.decoder.layers.3.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
242
+ "model.decoder.layers.3.self_attn.out_proj.bias": "model-00005-of-00007.safetensors",
243
+ "model.decoder.layers.3.self_attn.out_proj.weight": "model-00005-of-00007.safetensors",
244
+ "model.decoder.layers.3.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
245
+ "model.decoder.layers.3.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
246
+ "model.decoder.layers.3.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
247
+ "model.decoder.layers.3.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
248
+ "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
249
+ "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
250
+ "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00005-of-00007.safetensors",
251
+ "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00005-of-00007.safetensors",
252
+ "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00005-of-00007.safetensors",
253
+ "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00005-of-00007.safetensors",
254
+ "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00005-of-00007.safetensors",
255
+ "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00005-of-00007.safetensors",
256
+ "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00005-of-00007.safetensors",
257
+ "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
258
+ "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
259
+ "model.decoder.layers.4.fc1.bias": "model-00005-of-00007.safetensors",
260
+ "model.decoder.layers.4.fc1.weight": "model-00005-of-00007.safetensors",
261
+ "model.decoder.layers.4.fc2.bias": "model-00005-of-00007.safetensors",
262
+ "model.decoder.layers.4.fc2.weight": "model-00005-of-00007.safetensors",
263
+ "model.decoder.layers.4.final_layer_norm.bias": "model-00005-of-00007.safetensors",
264
+ "model.decoder.layers.4.final_layer_norm.weight": "model-00005-of-00007.safetensors",
265
+ "model.decoder.layers.4.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
266
+ "model.decoder.layers.4.self_attn.out_proj.bias": "model-00005-of-00007.safetensors",
267
+ "model.decoder.layers.4.self_attn.out_proj.weight": "model-00005-of-00007.safetensors",
268
+ "model.decoder.layers.4.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
269
+ "model.decoder.layers.4.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
270
+ "model.decoder.layers.4.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
271
+ "model.decoder.layers.4.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
272
+ "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
273
+ "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
274
+ "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00005-of-00007.safetensors",
275
+ "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00005-of-00007.safetensors",
276
+ "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00005-of-00007.safetensors",
277
+ "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00005-of-00007.safetensors",
278
+ "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00005-of-00007.safetensors",
279
+ "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00005-of-00007.safetensors",
280
+ "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00005-of-00007.safetensors",
281
+ "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
282
+ "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
283
+ "model.decoder.layers.5.fc1.bias": "model-00005-of-00007.safetensors",
284
+ "model.decoder.layers.5.fc1.weight": "model-00005-of-00007.safetensors",
285
+ "model.decoder.layers.5.fc2.bias": "model-00005-of-00007.safetensors",
286
+ "model.decoder.layers.5.fc2.weight": "model-00005-of-00007.safetensors",
287
+ "model.decoder.layers.5.final_layer_norm.bias": "model-00005-of-00007.safetensors",
288
+ "model.decoder.layers.5.final_layer_norm.weight": "model-00005-of-00007.safetensors",
289
+ "model.decoder.layers.5.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
290
+ "model.decoder.layers.5.self_attn.out_proj.bias": "model-00005-of-00007.safetensors",
291
+ "model.decoder.layers.5.self_attn.out_proj.weight": "model-00005-of-00007.safetensors",
292
+ "model.decoder.layers.5.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
293
+ "model.decoder.layers.5.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
294
+ "model.decoder.layers.5.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
295
+ "model.decoder.layers.5.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
296
+ "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
297
+ "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
298
+ "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00005-of-00007.safetensors",
299
+ "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00005-of-00007.safetensors",
300
+ "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00005-of-00007.safetensors",
301
+ "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00005-of-00007.safetensors",
302
+ "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00005-of-00007.safetensors",
303
+ "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00005-of-00007.safetensors",
304
+ "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00005-of-00007.safetensors",
305
+ "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
306
+ "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
307
+ "model.decoder.layers.6.fc1.bias": "model-00005-of-00007.safetensors",
308
+ "model.decoder.layers.6.fc1.weight": "model-00005-of-00007.safetensors",
309
+ "model.decoder.layers.6.fc2.bias": "model-00006-of-00007.safetensors",
310
+ "model.decoder.layers.6.fc2.weight": "model-00006-of-00007.safetensors",
311
+ "model.decoder.layers.6.final_layer_norm.bias": "model-00006-of-00007.safetensors",
312
+ "model.decoder.layers.6.final_layer_norm.weight": "model-00006-of-00007.safetensors",
313
+ "model.decoder.layers.6.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
314
+ "model.decoder.layers.6.self_attn.out_proj.bias": "model-00005-of-00007.safetensors",
315
+ "model.decoder.layers.6.self_attn.out_proj.weight": "model-00005-of-00007.safetensors",
316
+ "model.decoder.layers.6.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
317
+ "model.decoder.layers.6.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
318
+ "model.decoder.layers.6.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
319
+ "model.decoder.layers.6.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
320
+ "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00005-of-00007.safetensors",
321
+ "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00005-of-00007.safetensors",
322
+ "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00006-of-00007.safetensors",
323
+ "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00006-of-00007.safetensors",
324
+ "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00006-of-00007.safetensors",
325
+ "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00006-of-00007.safetensors",
326
+ "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00006-of-00007.safetensors",
327
+ "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00006-of-00007.safetensors",
328
+ "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00006-of-00007.safetensors",
329
+ "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
330
+ "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
331
+ "model.decoder.layers.7.fc1.bias": "model-00006-of-00007.safetensors",
332
+ "model.decoder.layers.7.fc1.weight": "model-00006-of-00007.safetensors",
333
+ "model.decoder.layers.7.fc2.bias": "model-00006-of-00007.safetensors",
334
+ "model.decoder.layers.7.fc2.weight": "model-00006-of-00007.safetensors",
335
+ "model.decoder.layers.7.final_layer_norm.bias": "model-00006-of-00007.safetensors",
336
+ "model.decoder.layers.7.final_layer_norm.weight": "model-00006-of-00007.safetensors",
337
+ "model.decoder.layers.7.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
338
+ "model.decoder.layers.7.self_attn.out_proj.bias": "model-00006-of-00007.safetensors",
339
+ "model.decoder.layers.7.self_attn.out_proj.weight": "model-00006-of-00007.safetensors",
340
+ "model.decoder.layers.7.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
341
+ "model.decoder.layers.7.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
342
+ "model.decoder.layers.7.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
343
+ "model.decoder.layers.7.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
344
+ "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
345
+ "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
346
+ "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00006-of-00007.safetensors",
347
+ "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00006-of-00007.safetensors",
348
+ "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00006-of-00007.safetensors",
349
+ "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00006-of-00007.safetensors",
350
+ "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00006-of-00007.safetensors",
351
+ "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00006-of-00007.safetensors",
352
+ "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00006-of-00007.safetensors",
353
+ "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
354
+ "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
355
+ "model.decoder.layers.8.fc1.bias": "model-00006-of-00007.safetensors",
356
+ "model.decoder.layers.8.fc1.weight": "model-00006-of-00007.safetensors",
357
+ "model.decoder.layers.8.fc2.bias": "model-00006-of-00007.safetensors",
358
+ "model.decoder.layers.8.fc2.weight": "model-00006-of-00007.safetensors",
359
+ "model.decoder.layers.8.final_layer_norm.bias": "model-00006-of-00007.safetensors",
360
+ "model.decoder.layers.8.final_layer_norm.weight": "model-00006-of-00007.safetensors",
361
+ "model.decoder.layers.8.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
362
+ "model.decoder.layers.8.self_attn.out_proj.bias": "model-00006-of-00007.safetensors",
363
+ "model.decoder.layers.8.self_attn.out_proj.weight": "model-00006-of-00007.safetensors",
364
+ "model.decoder.layers.8.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
365
+ "model.decoder.layers.8.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
366
+ "model.decoder.layers.8.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
367
+ "model.decoder.layers.8.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
368
+ "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
369
+ "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
370
+ "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00006-of-00007.safetensors",
371
+ "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00006-of-00007.safetensors",
372
+ "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00006-of-00007.safetensors",
373
+ "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00006-of-00007.safetensors",
374
+ "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00006-of-00007.safetensors",
375
+ "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00006-of-00007.safetensors",
376
+ "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00006-of-00007.safetensors",
377
+ "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
378
+ "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
379
+ "model.decoder.layers.9.fc1.bias": "model-00006-of-00007.safetensors",
380
+ "model.decoder.layers.9.fc1.weight": "model-00006-of-00007.safetensors",
381
+ "model.decoder.layers.9.fc2.bias": "model-00006-of-00007.safetensors",
382
+ "model.decoder.layers.9.fc2.weight": "model-00006-of-00007.safetensors",
383
+ "model.decoder.layers.9.final_layer_norm.bias": "model-00006-of-00007.safetensors",
384
+ "model.decoder.layers.9.final_layer_norm.weight": "model-00006-of-00007.safetensors",
385
+ "model.decoder.layers.9.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
386
+ "model.decoder.layers.9.self_attn.out_proj.bias": "model-00006-of-00007.safetensors",
387
+ "model.decoder.layers.9.self_attn.out_proj.weight": "model-00006-of-00007.safetensors",
388
+ "model.decoder.layers.9.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
389
+ "model.decoder.layers.9.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
390
+ "model.decoder.layers.9.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
391
+ "model.decoder.layers.9.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
392
+ "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00006-of-00007.safetensors",
393
+ "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00006-of-00007.safetensors",
394
+ "model.encoder.conv1.bias": "model-00001-of-00007.safetensors",
395
+ "model.encoder.conv1.weight": "model-00001-of-00007.safetensors",
396
+ "model.encoder.conv2.bias": "model-00001-of-00007.safetensors",
397
+ "model.encoder.conv2.weight": "model-00001-of-00007.safetensors",
398
+ "model.encoder.embed_positions.weight": "model-00001-of-00007.safetensors",
399
+ "model.encoder.layer_norm.bias": "model-00003-of-00007.safetensors",
400
+ "model.encoder.layer_norm.weight": "model-00003-of-00007.safetensors",
401
+ "model.encoder.layers.0.fc1.bias": "model-00001-of-00007.safetensors",
402
+ "model.encoder.layers.0.fc1.weight": "model-00001-of-00007.safetensors",
403
+ "model.encoder.layers.0.fc2.bias": "model-00001-of-00007.safetensors",
404
+ "model.encoder.layers.0.fc2.weight": "model-00001-of-00007.safetensors",
405
+ "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00007.safetensors",
406
+ "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00007.safetensors",
407
+ "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
408
+ "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
409
+ "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
410
+ "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
411
+ "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
412
+ "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
413
+ "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
414
+ "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
415
+ "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
416
+ "model.encoder.layers.1.fc1.bias": "model-00001-of-00007.safetensors",
417
+ "model.encoder.layers.1.fc1.weight": "model-00001-of-00007.safetensors",
418
+ "model.encoder.layers.1.fc2.bias": "model-00001-of-00007.safetensors",
419
+ "model.encoder.layers.1.fc2.weight": "model-00001-of-00007.safetensors",
420
+ "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00007.safetensors",
421
+ "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00007.safetensors",
422
+ "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
423
+ "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
424
+ "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
425
+ "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
426
+ "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
427
+ "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
428
+ "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
429
+ "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
430
+ "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
431
+ "model.encoder.layers.10.fc1.bias": "model-00002-of-00007.safetensors",
432
+ "model.encoder.layers.10.fc1.weight": "model-00002-of-00007.safetensors",
433
+ "model.encoder.layers.10.fc2.bias": "model-00002-of-00007.safetensors",
434
+ "model.encoder.layers.10.fc2.weight": "model-00002-of-00007.safetensors",
435
+ "model.encoder.layers.10.final_layer_norm.bias": "model-00002-of-00007.safetensors",
436
+ "model.encoder.layers.10.final_layer_norm.weight": "model-00002-of-00007.safetensors",
437
+ "model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
438
+ "model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00007.safetensors",
439
+ "model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00007.safetensors",
440
+ "model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
441
+ "model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
442
+ "model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
443
+ "model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
444
+ "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00007.safetensors",
445
+ "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00007.safetensors",
446
+ "model.encoder.layers.11.fc1.bias": "model-00002-of-00007.safetensors",
447
+ "model.encoder.layers.11.fc1.weight": "model-00002-of-00007.safetensors",
448
+ "model.encoder.layers.11.fc2.bias": "model-00002-of-00007.safetensors",
449
+ "model.encoder.layers.11.fc2.weight": "model-00002-of-00007.safetensors",
450
+ "model.encoder.layers.11.final_layer_norm.bias": "model-00002-of-00007.safetensors",
451
+ "model.encoder.layers.11.final_layer_norm.weight": "model-00002-of-00007.safetensors",
452
+ "model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
453
+ "model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00007.safetensors",
454
+ "model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00007.safetensors",
455
+ "model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
456
+ "model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
457
+ "model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
458
+ "model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
459
+ "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00007.safetensors",
460
+ "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00007.safetensors",
461
+ "model.encoder.layers.12.fc1.bias": "model-00003-of-00007.safetensors",
462
+ "model.encoder.layers.12.fc1.weight": "model-00003-of-00007.safetensors",
463
+ "model.encoder.layers.12.fc2.bias": "model-00003-of-00007.safetensors",
464
+ "model.encoder.layers.12.fc2.weight": "model-00003-of-00007.safetensors",
465
+ "model.encoder.layers.12.final_layer_norm.bias": "model-00003-of-00007.safetensors",
466
+ "model.encoder.layers.12.final_layer_norm.weight": "model-00003-of-00007.safetensors",
467
+ "model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
468
+ "model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00007.safetensors",
469
+ "model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00007.safetensors",
470
+ "model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
471
+ "model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
472
+ "model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
473
+ "model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
474
+ "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00007.safetensors",
475
+ "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00007.safetensors",
476
+ "model.encoder.layers.13.fc1.bias": "model-00003-of-00007.safetensors",
477
+ "model.encoder.layers.13.fc1.weight": "model-00003-of-00007.safetensors",
478
+ "model.encoder.layers.13.fc2.bias": "model-00003-of-00007.safetensors",
479
+ "model.encoder.layers.13.fc2.weight": "model-00003-of-00007.safetensors",
480
+ "model.encoder.layers.13.final_layer_norm.bias": "model-00003-of-00007.safetensors",
481
+ "model.encoder.layers.13.final_layer_norm.weight": "model-00003-of-00007.safetensors",
482
+ "model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
483
+ "model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00007.safetensors",
484
+ "model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00007.safetensors",
485
+ "model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
486
+ "model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
487
+ "model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
488
+ "model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
489
+ "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00007.safetensors",
490
+ "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00007.safetensors",
491
+ "model.encoder.layers.14.fc1.bias": "model-00003-of-00007.safetensors",
492
+ "model.encoder.layers.14.fc1.weight": "model-00003-of-00007.safetensors",
493
+ "model.encoder.layers.14.fc2.bias": "model-00003-of-00007.safetensors",
494
+ "model.encoder.layers.14.fc2.weight": "model-00003-of-00007.safetensors",
495
+ "model.encoder.layers.14.final_layer_norm.bias": "model-00003-of-00007.safetensors",
496
+ "model.encoder.layers.14.final_layer_norm.weight": "model-00003-of-00007.safetensors",
497
+ "model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
498
+ "model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00007.safetensors",
499
+ "model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00007.safetensors",
500
+ "model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
501
+ "model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
502
+ "model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
503
+ "model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
504
+ "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00007.safetensors",
505
+ "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00007.safetensors",
506
+ "model.encoder.layers.15.fc1.bias": "model-00003-of-00007.safetensors",
507
+ "model.encoder.layers.15.fc1.weight": "model-00003-of-00007.safetensors",
508
+ "model.encoder.layers.15.fc2.bias": "model-00003-of-00007.safetensors",
509
+ "model.encoder.layers.15.fc2.weight": "model-00003-of-00007.safetensors",
510
+ "model.encoder.layers.15.final_layer_norm.bias": "model-00003-of-00007.safetensors",
511
+ "model.encoder.layers.15.final_layer_norm.weight": "model-00003-of-00007.safetensors",
512
+ "model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
513
+ "model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00007.safetensors",
514
+ "model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00007.safetensors",
515
+ "model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
516
+ "model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
517
+ "model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
518
+ "model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
519
+ "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00007.safetensors",
520
+ "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00007.safetensors",
521
+ "model.encoder.layers.2.fc1.bias": "model-00001-of-00007.safetensors",
522
+ "model.encoder.layers.2.fc1.weight": "model-00001-of-00007.safetensors",
523
+ "model.encoder.layers.2.fc2.bias": "model-00001-of-00007.safetensors",
524
+ "model.encoder.layers.2.fc2.weight": "model-00001-of-00007.safetensors",
525
+ "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00007.safetensors",
526
+ "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00007.safetensors",
527
+ "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
528
+ "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
529
+ "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
530
+ "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
531
+ "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
532
+ "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
533
+ "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
534
+ "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
535
+ "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
536
+ "model.encoder.layers.3.fc1.bias": "model-00001-of-00007.safetensors",
537
+ "model.encoder.layers.3.fc1.weight": "model-00001-of-00007.safetensors",
538
+ "model.encoder.layers.3.fc2.bias": "model-00001-of-00007.safetensors",
539
+ "model.encoder.layers.3.fc2.weight": "model-00001-of-00007.safetensors",
540
+ "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00007.safetensors",
541
+ "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00007.safetensors",
542
+ "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
543
+ "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
544
+ "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
545
+ "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
546
+ "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
547
+ "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
548
+ "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
549
+ "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
550
+ "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
551
+ "model.encoder.layers.4.fc1.bias": "model-00001-of-00007.safetensors",
552
+ "model.encoder.layers.4.fc1.weight": "model-00001-of-00007.safetensors",
553
+ "model.encoder.layers.4.fc2.bias": "model-00001-of-00007.safetensors",
554
+ "model.encoder.layers.4.fc2.weight": "model-00001-of-00007.safetensors",
555
+ "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00007.safetensors",
556
+ "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00007.safetensors",
557
+ "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
558
+ "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
559
+ "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
560
+ "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
561
+ "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
562
+ "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
563
+ "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
564
+ "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
565
+ "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
566
+ "model.encoder.layers.5.fc1.bias": "model-00001-of-00007.safetensors",
567
+ "model.encoder.layers.5.fc1.weight": "model-00001-of-00007.safetensors",
568
+ "model.encoder.layers.5.fc2.bias": "model-00002-of-00007.safetensors",
569
+ "model.encoder.layers.5.fc2.weight": "model-00002-of-00007.safetensors",
570
+ "model.encoder.layers.5.final_layer_norm.bias": "model-00002-of-00007.safetensors",
571
+ "model.encoder.layers.5.final_layer_norm.weight": "model-00002-of-00007.safetensors",
572
+ "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
573
+ "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00007.safetensors",
574
+ "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00007.safetensors",
575
+ "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
576
+ "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
577
+ "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
578
+ "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
579
+ "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00007.safetensors",
580
+ "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00007.safetensors",
581
+ "model.encoder.layers.6.fc1.bias": "model-00002-of-00007.safetensors",
582
+ "model.encoder.layers.6.fc1.weight": "model-00002-of-00007.safetensors",
583
+ "model.encoder.layers.6.fc2.bias": "model-00002-of-00007.safetensors",
584
+ "model.encoder.layers.6.fc2.weight": "model-00002-of-00007.safetensors",
585
+ "model.encoder.layers.6.final_layer_norm.bias": "model-00002-of-00007.safetensors",
586
+ "model.encoder.layers.6.final_layer_norm.weight": "model-00002-of-00007.safetensors",
587
+ "model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
588
+ "model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00007.safetensors",
589
+ "model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00007.safetensors",
590
+ "model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
591
+ "model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
592
+ "model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
593
+ "model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
594
+ "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00007.safetensors",
595
+ "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00007.safetensors",
596
+ "model.encoder.layers.7.fc1.bias": "model-00002-of-00007.safetensors",
597
+ "model.encoder.layers.7.fc1.weight": "model-00002-of-00007.safetensors",
598
+ "model.encoder.layers.7.fc2.bias": "model-00002-of-00007.safetensors",
599
+ "model.encoder.layers.7.fc2.weight": "model-00002-of-00007.safetensors",
600
+ "model.encoder.layers.7.final_layer_norm.bias": "model-00002-of-00007.safetensors",
601
+ "model.encoder.layers.7.final_layer_norm.weight": "model-00002-of-00007.safetensors",
602
+ "model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
603
+ "model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00007.safetensors",
604
+ "model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00007.safetensors",
605
+ "model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
606
+ "model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
607
+ "model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
608
+ "model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
609
+ "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00007.safetensors",
610
+ "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00007.safetensors",
611
+ "model.encoder.layers.8.fc1.bias": "model-00002-of-00007.safetensors",
612
+ "model.encoder.layers.8.fc1.weight": "model-00002-of-00007.safetensors",
613
+ "model.encoder.layers.8.fc2.bias": "model-00002-of-00007.safetensors",
614
+ "model.encoder.layers.8.fc2.weight": "model-00002-of-00007.safetensors",
615
+ "model.encoder.layers.8.final_layer_norm.bias": "model-00002-of-00007.safetensors",
616
+ "model.encoder.layers.8.final_layer_norm.weight": "model-00002-of-00007.safetensors",
617
+ "model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
618
+ "model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00007.safetensors",
619
+ "model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00007.safetensors",
620
+ "model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
621
+ "model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
622
+ "model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
623
+ "model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
624
+ "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00007.safetensors",
625
+ "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00007.safetensors",
626
+ "model.encoder.layers.9.fc1.bias": "model-00002-of-00007.safetensors",
627
+ "model.encoder.layers.9.fc1.weight": "model-00002-of-00007.safetensors",
628
+ "model.encoder.layers.9.fc2.bias": "model-00002-of-00007.safetensors",
629
+ "model.encoder.layers.9.fc2.weight": "model-00002-of-00007.safetensors",
630
+ "model.encoder.layers.9.final_layer_norm.bias": "model-00002-of-00007.safetensors",
631
+ "model.encoder.layers.9.final_layer_norm.weight": "model-00002-of-00007.safetensors",
632
+ "model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
633
+ "model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00007.safetensors",
634
+ "model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00007.safetensors",
635
+ "model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
636
+ "model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
637
+ "model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
638
+ "model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
639
+ "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00007.safetensors",
640
+ "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00007.safetensors"
641
+ }
642
+ }