DavidAU commited on
Commit
d01b17e
·
verified ·
1 Parent(s): 1e4eb09

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # DeepHermes-3-Llama-3-8B-Preview-exp40-3
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the passthrough merge method.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * D:/DeepHermes-3-Llama-3-8B-Preview
22
+
23
+ ### Configuration
24
+
25
+ The following YAML configuration was used to produce this model:
26
+
27
+ ```yaml
28
+ # Six splits plus "end game
29
+ # "D" starts at plus .1 VS D/O proj.
30
+ # 40 plus.
31
+
32
+ slices:
33
+ - sources:
34
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
35
+ layer_range: [0, 31]
36
+
37
+ # conc layers
38
+ # split 1
39
+
40
+ - sources:
41
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
42
+ layer_range: [31,32]
43
+ parameters:
44
+ scale:
45
+ - filter: o_proj
46
+ value: 0.01
47
+ - filter: down_proj
48
+ value: 0.01
49
+ - value: 0.11
50
+ - sources:
51
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
52
+ layer_range: [31,32]
53
+ parameters:
54
+ scale:
55
+ - filter: o_proj
56
+ value: 0.02
57
+ - filter: down_proj
58
+ value: 0.02
59
+ - value: 0.12
60
+ - sources:
61
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
62
+ layer_range: [31,32]
63
+ parameters:
64
+ scale:
65
+ - filter: o_proj
66
+ value: 0.03
67
+ - filter: down_proj
68
+ value: 0.03
69
+ - value: 0.13
70
+
71
+ - sources:
72
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
73
+ layer_range: [31,32]
74
+ parameters:
75
+ scale:
76
+ - filter: o_proj
77
+ value: 0.04
78
+ - filter: down_proj
79
+ value: 0.04
80
+ - value: 0.61
81
+
82
+ # split 2, SURGE D THEN D drop .46, continues @ D .15 (from .13)
83
+
84
+ - sources:
85
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
86
+ layer_range: [31,32]
87
+ parameters:
88
+ scale:
89
+ - filter: o_proj
90
+ value: 0.05
91
+ - filter: down_proj
92
+ value: 0.05
93
+ - value: 0.15
94
+ - sources:
95
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
96
+ layer_range: [31,32]
97
+ parameters:
98
+ scale:
99
+ - filter: o_proj
100
+ value: 0.06
101
+ - filter: down_proj
102
+ value: 0.06
103
+ - value: 0.16
104
+ - sources:
105
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
106
+ layer_range: [31,32]
107
+ parameters:
108
+ scale:
109
+ - filter: o_proj
110
+ value: 0.07
111
+ - filter: down_proj
112
+ value: 0.07
113
+ - value: 0.17
114
+ - sources:
115
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
116
+ layer_range: [31,32]
117
+ parameters:
118
+ scale:
119
+ - filter: o_proj
120
+ value: 0.08
121
+ - filter: down_proj
122
+ value: 0.08
123
+ - value: 0.41
124
+
125
+ # split 3, SURGE D to .41, D drop .21 ... follows .17 previous
126
+
127
+ - sources:
128
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
129
+ layer_range: [31,32]
130
+ parameters:
131
+ scale:
132
+ - filter: o_proj
133
+ value: 0.09
134
+ - filter: down_proj
135
+ value: 0.09
136
+ - value: 0.19
137
+ - sources:
138
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
139
+ layer_range: [31,32]
140
+ parameters:
141
+ scale:
142
+ - filter: o_proj
143
+ value: 0.10
144
+ - filter: down_proj
145
+ value: 0.10
146
+ - value: 0.20
147
+ - sources:
148
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
149
+ layer_range: [31,32]
150
+ parameters:
151
+ scale:
152
+ - filter: o_proj
153
+ value: 0.11
154
+ - filter: down_proj
155
+ value: 0.11
156
+ - value: .22
157
+ - sources:
158
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
159
+ layer_range: [31,32]
160
+ parameters:
161
+ scale:
162
+ - filter: o_proj
163
+ value: 0.12
164
+ - filter: down_proj
165
+ value: 0.12
166
+ - value: .24
167
+ - sources:
168
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
169
+ layer_range: [31,32]
170
+ parameters:
171
+ scale:
172
+ - filter: o_proj
173
+ value: 0.13
174
+ - filter: down_proj
175
+ value: 0.13
176
+ - value: .26
177
+ - sources:
178
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
179
+ layer_range: [31,32]
180
+ parameters:
181
+ scale:
182
+ - filter: o_proj
183
+ value: 0.14
184
+ - filter: down_proj
185
+ value: 0.14
186
+ - value: .28
187
+ - sources:
188
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
189
+ layer_range: [31,32]
190
+ parameters:
191
+ scale:
192
+ - filter: o_proj
193
+ value: 0.15
194
+ - filter: down_proj
195
+ value: 0.15
196
+ - value: .30
197
+ - sources:
198
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
199
+ layer_range: [31,32]
200
+ parameters:
201
+ scale:
202
+ - filter: o_proj
203
+ value: 0.16
204
+ - filter: down_proj
205
+ value: 0.16
206
+ - value: .31
207
+ - sources:
208
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
209
+ layer_range: [31,32]
210
+ parameters:
211
+ scale:
212
+ - filter: o_proj
213
+ value: 0.20
214
+ - filter: down_proj
215
+ value: 0.20
216
+ - value: .32
217
+ - sources:
218
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
219
+ layer_range: [31,32]
220
+ parameters:
221
+ scale:
222
+ - filter: o_proj
223
+ value: 0.21
224
+ - filter: down_proj
225
+ value: 0.21
226
+ - value: .33
227
+ - sources:
228
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
229
+ layer_range: [31,32]
230
+ parameters:
231
+ scale:
232
+ - filter: o_proj
233
+ value: 0.22
234
+ - filter: down_proj
235
+ value: 0.22
236
+ - value: .34
237
+ - sources:
238
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
239
+ layer_range: [31,32]
240
+ parameters:
241
+ scale:
242
+ - filter: o_proj
243
+ value: 0.23
244
+ - filter: down_proj
245
+ value: 0.23
246
+ - value: .35
247
+
248
+ # split 4 , NO SURGE D, "D" down drop of .24 ; reverts to .11 (the very first "D" setting )
249
+
250
+ - sources:
251
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
252
+ layer_range: [31,32]
253
+ parameters:
254
+ scale:
255
+ - filter: o_proj
256
+ value: 0.24
257
+ - filter: down_proj
258
+ value: 0.24
259
+ - value: 0.11
260
+ - sources:
261
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
262
+ layer_range: [31,32]
263
+ parameters:
264
+ scale:
265
+ - filter: o_proj
266
+ value: 0.241
267
+ - filter: down_proj
268
+ value: 0.241
269
+ - value: 0.12
270
+ - sources:
271
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
272
+ layer_range: [31,32]
273
+ parameters:
274
+ scale:
275
+ - filter: o_proj
276
+ value: 0.242
277
+ - filter: down_proj
278
+ value: 0.243
279
+ - value: 0.13
280
+ - sources:
281
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
282
+ layer_range: [31,32]
283
+ parameters:
284
+ scale:
285
+ - filter: o_proj
286
+ value: 0.244
287
+ - filter: down_proj
288
+ value: 0.244
289
+ - value: 0.61
290
+
291
+ # split 5, D Surge to .61, drop to .15 (following .13)
292
+
293
+ - sources:
294
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
295
+ layer_range: [31,32]
296
+ parameters:
297
+ scale:
298
+ - filter: o_proj
299
+ value: 0.245
300
+ - filter: down_proj
301
+ value: 0.245
302
+ - value: 0.15
303
+ - sources:
304
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
305
+ layer_range: [31,32]
306
+ parameters:
307
+ scale:
308
+ - filter: o_proj
309
+ value: 0.246
310
+ - filter: down_proj
311
+ value: 0.246
312
+ - value: 0.16
313
+ - sources:
314
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
315
+ layer_range: [31,32]
316
+ parameters:
317
+ scale:
318
+ - filter: o_proj
319
+ value: 0.247
320
+ - filter: down_proj
321
+ value: 0.247
322
+ - value: 0.17
323
+ - sources:
324
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
325
+ layer_range: [31,32]
326
+ parameters:
327
+ scale:
328
+ - filter: o_proj
329
+ value: 0.248
330
+ - filter: down_proj
331
+ value: 0.248
332
+ - value: 0.41
333
+
334
+ # split 6, D surge to .41 , then follows .17
335
+
336
+ - sources:
337
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
338
+ layer_range: [31,32]
339
+ parameters:
340
+ scale:
341
+ - filter: o_proj
342
+ value: 0.249
343
+ - filter: down_proj
344
+ value: 0.249
345
+ - value: 0.19
346
+ - sources:
347
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
348
+ layer_range: [31,32]
349
+ parameters:
350
+ scale:
351
+ - filter: o_proj
352
+ value: 0.250
353
+ - filter: down_proj
354
+ value: 0.250
355
+ - value: 0.20
356
+ - sources:
357
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
358
+ layer_range: [31,32]
359
+ parameters:
360
+ scale:
361
+ - filter: o_proj
362
+ value: 0.251
363
+ - filter: down_proj
364
+ value: 0.251
365
+ - value: .22
366
+ - sources:
367
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
368
+ layer_range: [31,32]
369
+ parameters:
370
+ scale:
371
+ - filter: o_proj
372
+ value: 0.252
373
+ - filter: down_proj
374
+ value: 0.252
375
+ - value: .24
376
+ - sources:
377
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
378
+ layer_range: [31,32]
379
+ parameters:
380
+ scale:
381
+ - filter: o_proj
382
+ value: 0.253
383
+ - filter: down_proj
384
+ value: 0.254
385
+ - value: .26
386
+ - sources:
387
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
388
+ layer_range: [31,32]
389
+ parameters:
390
+ scale:
391
+ - filter: o_proj
392
+ value: 0.255
393
+ - filter: down_proj
394
+ value: 0.255
395
+ - value: .28
396
+ - sources:
397
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
398
+ layer_range: [31,32]
399
+ parameters:
400
+ scale:
401
+ - filter: o_proj
402
+ value: 0.256
403
+ - filter: down_proj
404
+ value: 0.256
405
+ - value: .30
406
+
407
+ # O PROJ, DPROJ to .3333 /
408
+ # end game
409
+
410
+ - sources:
411
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
412
+ layer_range: [31,32]
413
+ parameters:
414
+ scale:
415
+ - filter: o_proj
416
+ value: 0.3333333333333
417
+ - filter: down_proj
418
+ value: 0.3333333333333
419
+ - value: 0.3333333333333
420
+ - sources:
421
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
422
+ layer_range: [31,32]
423
+ parameters:
424
+ scale:
425
+ - filter: o_proj
426
+ value: 0.4444444444444
427
+ - filter: down_proj
428
+ value: 0.4444444444444
429
+ - value: 0.4444444444444
430
+ - sources:
431
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
432
+ layer_range: [31,32]
433
+ parameters:
434
+ scale:
435
+ - filter: o_proj
436
+ value: 0.5555555555555
437
+ - filter: down_proj
438
+ value: 0.5555555555555
439
+ - value: 0.5555555555555
440
+ - sources:
441
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
442
+ layer_range: [31,32]
443
+ parameters:
444
+ scale:
445
+ - filter: o_proj
446
+ value: 0.6666666666666
447
+ - filter: down_proj
448
+ value: 0.6666666666666
449
+ - value: 0.6666666666666
450
+ - sources:
451
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
452
+ layer_range: [31,32]
453
+ parameters:
454
+ scale:
455
+ - filter: o_proj
456
+ value: 0.777777777777
457
+ - filter: down_proj
458
+ value: 0.777777777777
459
+ - value: 0.888888888888
460
+ merge_method: passthrough
461
+ dtype: bfloat16
462
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "D:/DeepHermes-3-Llama-3-8B-Preview",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 71,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128004,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.2",
35
+ "unsloth_fixed": true,
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Six splits plus "end game
2
+ # "D" starts at plus .1 VS D/O proj.
3
+ # 40 plus.
4
+
5
+ slices:
6
+ - sources:
7
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
8
+ layer_range: [0, 31]
9
+
10
+ # conc layers
11
+ # split 1
12
+
13
+ - sources:
14
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
15
+ layer_range: [31,32]
16
+ parameters:
17
+ scale:
18
+ - filter: o_proj
19
+ value: 0.01
20
+ - filter: down_proj
21
+ value: 0.01
22
+ - value: 0.11
23
+ - sources:
24
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
25
+ layer_range: [31,32]
26
+ parameters:
27
+ scale:
28
+ - filter: o_proj
29
+ value: 0.02
30
+ - filter: down_proj
31
+ value: 0.02
32
+ - value: 0.12
33
+ - sources:
34
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
35
+ layer_range: [31,32]
36
+ parameters:
37
+ scale:
38
+ - filter: o_proj
39
+ value: 0.03
40
+ - filter: down_proj
41
+ value: 0.03
42
+ - value: 0.13
43
+
44
+ - sources:
45
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
46
+ layer_range: [31,32]
47
+ parameters:
48
+ scale:
49
+ - filter: o_proj
50
+ value: 0.04
51
+ - filter: down_proj
52
+ value: 0.04
53
+ - value: 0.61
54
+
55
+ # split 2, SURGE D THEN D drop .46, continues @ D .15 (from .13)
56
+
57
+ - sources:
58
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
59
+ layer_range: [31,32]
60
+ parameters:
61
+ scale:
62
+ - filter: o_proj
63
+ value: 0.05
64
+ - filter: down_proj
65
+ value: 0.05
66
+ - value: 0.15
67
+ - sources:
68
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
69
+ layer_range: [31,32]
70
+ parameters:
71
+ scale:
72
+ - filter: o_proj
73
+ value: 0.06
74
+ - filter: down_proj
75
+ value: 0.06
76
+ - value: 0.16
77
+ - sources:
78
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
79
+ layer_range: [31,32]
80
+ parameters:
81
+ scale:
82
+ - filter: o_proj
83
+ value: 0.07
84
+ - filter: down_proj
85
+ value: 0.07
86
+ - value: 0.17
87
+ - sources:
88
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
89
+ layer_range: [31,32]
90
+ parameters:
91
+ scale:
92
+ - filter: o_proj
93
+ value: 0.08
94
+ - filter: down_proj
95
+ value: 0.08
96
+ - value: 0.41
97
+
98
+ # split 3, SURGE D to .41, D drop .21 ... follows .17 previous
99
+
100
+ - sources:
101
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
102
+ layer_range: [31,32]
103
+ parameters:
104
+ scale:
105
+ - filter: o_proj
106
+ value: 0.09
107
+ - filter: down_proj
108
+ value: 0.09
109
+ - value: 0.19
110
+ - sources:
111
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
112
+ layer_range: [31,32]
113
+ parameters:
114
+ scale:
115
+ - filter: o_proj
116
+ value: 0.10
117
+ - filter: down_proj
118
+ value: 0.10
119
+ - value: 0.20
120
+ - sources:
121
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
122
+ layer_range: [31,32]
123
+ parameters:
124
+ scale:
125
+ - filter: o_proj
126
+ value: 0.11
127
+ - filter: down_proj
128
+ value: 0.11
129
+ - value: .22
130
+ - sources:
131
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
132
+ layer_range: [31,32]
133
+ parameters:
134
+ scale:
135
+ - filter: o_proj
136
+ value: 0.12
137
+ - filter: down_proj
138
+ value: 0.12
139
+ - value: .24
140
+ - sources:
141
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
142
+ layer_range: [31,32]
143
+ parameters:
144
+ scale:
145
+ - filter: o_proj
146
+ value: 0.13
147
+ - filter: down_proj
148
+ value: 0.13
149
+ - value: .26
150
+ - sources:
151
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
152
+ layer_range: [31,32]
153
+ parameters:
154
+ scale:
155
+ - filter: o_proj
156
+ value: 0.14
157
+ - filter: down_proj
158
+ value: 0.14
159
+ - value: .28
160
+ - sources:
161
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
162
+ layer_range: [31,32]
163
+ parameters:
164
+ scale:
165
+ - filter: o_proj
166
+ value: 0.15
167
+ - filter: down_proj
168
+ value: 0.15
169
+ - value: .30
170
+ - sources:
171
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
172
+ layer_range: [31,32]
173
+ parameters:
174
+ scale:
175
+ - filter: o_proj
176
+ value: 0.16
177
+ - filter: down_proj
178
+ value: 0.16
179
+ - value: .31
180
+ - sources:
181
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
182
+ layer_range: [31,32]
183
+ parameters:
184
+ scale:
185
+ - filter: o_proj
186
+ value: 0.20
187
+ - filter: down_proj
188
+ value: 0.20
189
+ - value: .32
190
+ - sources:
191
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
192
+ layer_range: [31,32]
193
+ parameters:
194
+ scale:
195
+ - filter: o_proj
196
+ value: 0.21
197
+ - filter: down_proj
198
+ value: 0.21
199
+ - value: .33
200
+ - sources:
201
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
202
+ layer_range: [31,32]
203
+ parameters:
204
+ scale:
205
+ - filter: o_proj
206
+ value: 0.22
207
+ - filter: down_proj
208
+ value: 0.22
209
+ - value: .34
210
+ - sources:
211
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
212
+ layer_range: [31,32]
213
+ parameters:
214
+ scale:
215
+ - filter: o_proj
216
+ value: 0.23
217
+ - filter: down_proj
218
+ value: 0.23
219
+ - value: .35
220
+
221
+ # split 4 , NO SURGE D, "D" down drop of .24 ; reverts to .11 (the very first "D" setting )
222
+
223
+ - sources:
224
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
225
+ layer_range: [31,32]
226
+ parameters:
227
+ scale:
228
+ - filter: o_proj
229
+ value: 0.24
230
+ - filter: down_proj
231
+ value: 0.24
232
+ - value: 0.11
233
+ - sources:
234
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
235
+ layer_range: [31,32]
236
+ parameters:
237
+ scale:
238
+ - filter: o_proj
239
+ value: 0.241
240
+ - filter: down_proj
241
+ value: 0.241
242
+ - value: 0.12
243
+ - sources:
244
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
245
+ layer_range: [31,32]
246
+ parameters:
247
+ scale:
248
+ - filter: o_proj
249
+ value: 0.242
250
+ - filter: down_proj
251
+ value: 0.243
252
+ - value: 0.13
253
+ - sources:
254
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
255
+ layer_range: [31,32]
256
+ parameters:
257
+ scale:
258
+ - filter: o_proj
259
+ value: 0.244
260
+ - filter: down_proj
261
+ value: 0.244
262
+ - value: 0.61
263
+
264
+ # split 5, D Surge to .61, drop to .15 (following .13)
265
+
266
+ - sources:
267
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
268
+ layer_range: [31,32]
269
+ parameters:
270
+ scale:
271
+ - filter: o_proj
272
+ value: 0.245
273
+ - filter: down_proj
274
+ value: 0.245
275
+ - value: 0.15
276
+ - sources:
277
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
278
+ layer_range: [31,32]
279
+ parameters:
280
+ scale:
281
+ - filter: o_proj
282
+ value: 0.246
283
+ - filter: down_proj
284
+ value: 0.246
285
+ - value: 0.16
286
+ - sources:
287
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
288
+ layer_range: [31,32]
289
+ parameters:
290
+ scale:
291
+ - filter: o_proj
292
+ value: 0.247
293
+ - filter: down_proj
294
+ value: 0.247
295
+ - value: 0.17
296
+ - sources:
297
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
298
+ layer_range: [31,32]
299
+ parameters:
300
+ scale:
301
+ - filter: o_proj
302
+ value: 0.248
303
+ - filter: down_proj
304
+ value: 0.248
305
+ - value: 0.41
306
+
307
+ # split 6, D surge to .41 , then follows .17
308
+
309
+ - sources:
310
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
311
+ layer_range: [31,32]
312
+ parameters:
313
+ scale:
314
+ - filter: o_proj
315
+ value: 0.249
316
+ - filter: down_proj
317
+ value: 0.249
318
+ - value: 0.19
319
+ - sources:
320
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
321
+ layer_range: [31,32]
322
+ parameters:
323
+ scale:
324
+ - filter: o_proj
325
+ value: 0.250
326
+ - filter: down_proj
327
+ value: 0.250
328
+ - value: 0.20
329
+ - sources:
330
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
331
+ layer_range: [31,32]
332
+ parameters:
333
+ scale:
334
+ - filter: o_proj
335
+ value: 0.251
336
+ - filter: down_proj
337
+ value: 0.251
338
+ - value: .22
339
+ - sources:
340
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
341
+ layer_range: [31,32]
342
+ parameters:
343
+ scale:
344
+ - filter: o_proj
345
+ value: 0.252
346
+ - filter: down_proj
347
+ value: 0.252
348
+ - value: .24
349
+ - sources:
350
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
351
+ layer_range: [31,32]
352
+ parameters:
353
+ scale:
354
+ - filter: o_proj
355
+ value: 0.253
356
+ - filter: down_proj
357
+ value: 0.254
358
+ - value: .26
359
+ - sources:
360
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
361
+ layer_range: [31,32]
362
+ parameters:
363
+ scale:
364
+ - filter: o_proj
365
+ value: 0.255
366
+ - filter: down_proj
367
+ value: 0.255
368
+ - value: .28
369
+ - sources:
370
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
371
+ layer_range: [31,32]
372
+ parameters:
373
+ scale:
374
+ - filter: o_proj
375
+ value: 0.256
376
+ - filter: down_proj
377
+ value: 0.256
378
+ - value: .30
379
+
380
+ # O PROJ, DPROJ to .3333 /
381
+ # end game
382
+
383
+ - sources:
384
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
385
+ layer_range: [31,32]
386
+ parameters:
387
+ scale:
388
+ - filter: o_proj
389
+ value: 0.3333333333333
390
+ - filter: down_proj
391
+ value: 0.3333333333333
392
+ - value: 0.3333333333333
393
+ - sources:
394
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
395
+ layer_range: [31,32]
396
+ parameters:
397
+ scale:
398
+ - filter: o_proj
399
+ value: 0.4444444444444
400
+ - filter: down_proj
401
+ value: 0.4444444444444
402
+ - value: 0.4444444444444
403
+ - sources:
404
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
405
+ layer_range: [31,32]
406
+ parameters:
407
+ scale:
408
+ - filter: o_proj
409
+ value: 0.5555555555555
410
+ - filter: down_proj
411
+ value: 0.5555555555555
412
+ - value: 0.5555555555555
413
+ - sources:
414
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
415
+ layer_range: [31,32]
416
+ parameters:
417
+ scale:
418
+ - filter: o_proj
419
+ value: 0.6666666666666
420
+ - filter: down_proj
421
+ value: 0.6666666666666
422
+ - value: 0.6666666666666
423
+ - sources:
424
+ - model: D:/DeepHermes-3-Llama-3-8B-Preview
425
+ layer_range: [31,32]
426
+ parameters:
427
+ scale:
428
+ - filter: o_proj
429
+ value: 0.777777777777
430
+ - filter: down_proj
431
+ value: 0.777777777777
432
+ - value: 0.888888888888
433
+ merge_method: passthrough
434
+ dtype: bfloat16
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.2", "total_size": 33073258496}, "weight_map": {"lm_head.weight": "model-00001-of-00035.safetensors", "model.embed_tokens.weight": "model-00002-of-00035.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00035.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00035.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00035.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00035.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00035.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00035.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00035.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00035.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00035.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00035.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00035.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00035.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00035.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00035.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00035.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00035.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00035.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00035.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00035.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00035.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00035.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00035.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00035.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00035.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00035.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00035.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00035.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00035.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00035.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00035.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00035.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00035.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00035.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00035.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00035.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00035.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00035.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00035.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00035.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00035.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00035.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00035.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00035.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00035.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00035.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00035.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00035.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00035.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00035.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00035.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00035.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00035.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00035.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00035.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00035.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00035.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00035.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00035.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00035.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00035.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00035.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00035.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00035.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00035.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00035.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00035.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00035.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00035.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00035.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00035.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00035.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00035.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00035.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00035.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00035.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00035.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00035.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00035.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00035.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00035.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00035.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00035.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00035.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00035.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00035.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00035.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00035.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00035.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00035.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00035.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00011-of-00035.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00035.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00035.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00035.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00035.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00035.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00035.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00035.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00035.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00035.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00011-of-00035.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00035.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00035.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00035.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00035.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00035.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00035.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00035.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00035.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00035.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00035.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00035.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00035.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00035.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00035.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00035.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00035.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00035.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00035.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00013-of-00035.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00035.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00035.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00035.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00035.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00035.safetensors", "model.layers.70.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.69.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.68.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.67.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.66.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.65.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.64.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.63.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.62.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.61.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.60.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.59.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.58.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.57.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.56.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.55.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.54.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.53.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.52.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.51.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.50.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.49.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.48.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.47.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.46.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.45.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.44.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.33.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00035.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00014-of-00035.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00015-of-00035.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00016-of-00035.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00035.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00018-of-00035.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00019-of-00035.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00019-of-00035.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00020-of-00035.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00021-of-00035.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00022-of-00035.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00035.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00024-of-00035.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00035.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00025-of-00035.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00026-of-00035.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00027-of-00035.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00028-of-00035.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00029-of-00035.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00029-of-00035.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00029-of-00035.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00029-of-00035.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00030-of-00035.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00030-of-00035.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00030-of-00035.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00030-of-00035.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00030-of-00035.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00030-of-00035.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00031-of-00035.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.input_layernorm.weight": "model-00032-of-00035.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00032-of-00035.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00032-of-00035.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00032-of-00035.safetensors", "model.layers.5.input_layernorm.weight": "model-00032-of-00035.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00033-of-00035.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00033-of-00035.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00033-of-00035.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00033-of-00035.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00033-of-00035.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00033-of-00035.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.input_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00033-of-00035.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00033-of-00035.safetensors", "model.layers.7.input_layernorm.weight": "model-00033-of-00035.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00033-of-00035.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00034-of-00035.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00034-of-00035.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00034-of-00035.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00034-of-00035.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00034-of-00035.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00034-of-00035.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.input_layernorm.weight": "model-00034-of-00035.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00034-of-00035.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00034-of-00035.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00034-of-00035.safetensors", "model.layers.9.input_layernorm.weight": "model-00034-of-00035.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00034-of-00035.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00034-of-00035.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00035-of-00035.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00035-of-00035.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00035-of-00035.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00035-of-00035.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00035-of-00035.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00035-of-00035.safetensors", "model.norm.weight": "model-00035-of-00035.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "chat_template": [
2055
+ {
2056
+ "name": "default",
2057
+ "template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
2058
+ },
2059
+ {
2060
+ "name": "tool_use",
2061
+ "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": \"' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\n\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\n Returns:\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- for tool_call in message.tool_calls %}\n {{- '\n<tool_call>\n' }} {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '{' }}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"' }}\n {{- ', '}}\n {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments|tojson }}\n {%- endif %}\n {%- endif %}\n {{- '}' }}\n {{- '\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\n' }}\n {%- endif %}\n {{- '<tool_response>\n' }}\n {{- message.content }}\n {%- if not loop.last %}\n {{- '\n</tool_response>\n' }}\n {%- else %}\n {{- '\n</tool_response>' }}\n {%- endif %}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
2062
+ }
2063
+ ],
2064
+
2065
+ "clean_up_tokenization_spaces": true,
2066
+ "eos_token": "<|eot_id|>",
2067
+ "extra_special_tokens": {},
2068
+ "model_input_names": [
2069
+ "input_ids",
2070
+ "attention_mask"
2071
+ ],
2072
+ "model_max_length": 131072,
2073
+ "pad_token": "<|end_of_text|>",
2074
+ "padding_side": "left",
2075
+ "tokenizer_class": "PreTrainedTokenizerFast",
2076
+ "unk_token": null
2077
+ }