Hugging Face's logo

nicolasembleton
/
gliner2.5-multi-v1-onnx

Token Classification
ONNX
GLiNER2
gliner2.5
boundary
webgpu
text-classification
relation-extraction
Model card Files
xet
 Community
nicolasembleton commited on
Commit
5e55e26
·
verified ·
1 Parent(s): 2bdb079

v2 export: pair reranker in graph; verified decode parity

Browse files
Files changed (5) hide show
  1. README.md +69 -15
  2. export_config.json +8 -3
  3. onnx/model.onnx +2 -2
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +8 -932
README.md CHANGED
@@ -4,24 +4,27 @@ license: apache-2.0
4
  pipeline_tag: token-classification
5
  base_model: fastino/gliner2.5-multi-v1
6
  tags:
7
- - onnx
8
- - gliner2
9
- - boundary
10
- - webgpu
11
- - token-classification
 
12
  ---
13
 
14
  # gliner2.5-multi-v1-onnx
15
 
16
- ONNX export of [fastino/gliner2.5-multi-v1](https://huggingface.co/fastino/gliner2.5-multi-v1) (GLiNER 2.5 `BoundaryExtractor`) for onnxruntime / WebGPU.
17
 
18
- This is **not** a drop-in `AutoExtractor` graph. The ONNX file runs:
19
 
20
- 1. DeBERTa encoder on packed `input_ids`
21
  2. Gather of word states and query-marker states
22
- 3. Boundary start/end logits `[batch, queries, words+1]`
 
 
23
 
24
- Schema packing (entity-type markers) and span decode stay on the host, same split as GLiNER.js.
25
 
26
  ## Inputs
27
 
@@ -36,16 +39,67 @@ Schema packing (entity-type markers) and span decode stay on the host, same spli
36
 
37
  ## Outputs
38
 
39
- | Name | Shape |
40
- |------|-------|
41
- | start_logits | [B, Q, L+1] |
42
- | end_logits | [B, Q, L+1] |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
 
44
  ## Python check
45
 
46
  ```python
47
  import onnxruntime as ort
48
  sess = ort.InferenceSession("onnx/model.onnx")
 
 
49
  ```
50
 
51
- WebGPU: load `onnx/model.onnx` with `onnxruntime-web` `webgpu` execution provider. Int64 inputs are required; some browsers need the WASM backend as fallback.
 
 
 
 
 
 
 
 
 
4
  pipeline_tag: token-classification
5
  base_model: fastino/gliner2.5-multi-v1
6
  tags:
7
+ - onnx
8
+ - gliner2
9
+ - gliner2.5
10
+ - boundary
11
+ - webgpu
12
+ - token-classification
13
  ---
14
 
15
  # gliner2.5-multi-v1-onnx
16
 
17
+ ONNX export of [fastino/gliner2.5-multi-v1](https://huggingface.co/fastino/gliner2.5-multi-v1) (GLiNER 2.5 `BoundaryExtractor`) for onnxruntime-web / WebGPU. **Revision 2: the graph now contains the full candidate path — sparse proposer, shared candidate pool, and pair reranker — not just the boundary marginals.** Host-side decode is a threshold on the reranked pair scores, matching the Python `AutoExtractor` pipeline (verified to 4 decimals).
18
 
19
+ ## What the graph runs
20
 
21
+ 1. DeBERTa encoder over packed `input_ids` (schema + `[SEP_TEXT]` + words)
22
  2. Gather of word states and query-marker states
23
+ 3. Boundary encoder + boundary marginals
24
+ 4. Document candidate pool (top-k endpoints, Cartesian pairing, learned compatibility)
25
+ 5. Pair reranker (endpoint compatibility + length features + inside evidence + FiLM-conditioned scoring)
26
 
27
+ Schema packing (entity-type markers) stays on the host; span decode is a host-side threshold.
28
 
29
  ## Inputs
30
 
 
39
 
40
  ## Outputs
41
 
42
+ | Name | Shape | Dtype | Meaning |
43
+ |------|-------|-------|---------|
44
+ | start_logits | [B, Q, L+1] | float32 | boundary start marginals |
45
+ | end_logits | [B, Q, L+1] | float32 | boundary end marginals |
46
+ | pair_indices | [B, Q, C, 2] | int64 | candidate spans, half-open word boundaries (s,e), s<e≤L; C=192 |
47
+ | pair_logits | [B, Q, C] | float32 | reranked span logits |
48
+ | pair_valid | [B, Q, C] | uint8 | 1 = real candidate (duplicate (s,e) keys can occur; dedupe on the host) |
49
+
50
+ ## Host decode (any language)
51
+
52
+ ```
53
+ probs = sigmoid(pair_logits / pair_temperature) # pair_temperature = 1.0
54
+ keep candidates where pair_valid == 1 and probs >= threshold # 0.5 default
55
+ dedupe by (start, end) keeping the max prob
56
+ resolve overlaps per label (e.g. max-total-score interval scheduling)
57
+ char span = words[s].start .. words[e-1].end
58
+ ```
59
+
60
+ Boundary i sits before word i; boundary L sits after the last word. Pair (s, e) covers words s..e-1.
61
+
62
+ ## Verified decode parity
63
+
64
+ JavaScript decode of this graph (ONNX Runtime Web) vs Python `AutoExtractor` on
65
+ `"Apple CEO Tim Cook announced iPhone 15 in Cupertino yesterday."` with labels
66
+ company/person/product/location:
67
+
68
+ | Entity | ONNX-web JS | Python AutoExtractor |
69
+ |---|---|---|
70
+ | Apple | 0.9966 | 0.9966 |
71
+ | Tim Cook | 0.9987 | 0.9987 |
72
+ | iPhone 15 | 0.9905 | 0.9905 |
73
+ | Cupertino | 0.9988 | 0.9988 |
74
+
75
+ Confidences match to 4 decimals. Reference runtime: [Pastel-Org/gliner2.5-onnx-webgpu](https://github.com/Pastel-Org/gliner2.5-onnx-webgpu) (live demo: [gliner25-onnx-webgpu.pages.dev](https://gliner25-onnx-webgpu.pages.dev)).
76
+
77
+ ## Revision 2 changes
78
+
79
+ - Graph now ends at the pair reranker instead of the marginals. The previous
80
+ revision required a `min(sigmoid(start), sigmoid(end))` proxy that cost
81
+ precision at low thresholds (0.45 P at 0.3 on our 26-sample suite); this
82
+ revision holds ≥0.77 P across the whole 0.3–0.7 range with flat F1.
83
+ - `export_mode="vectorized"` proposer; sort/scatter_reduce internals replaced
84
+ with opset-17-safe `topk` + sentinel padding (constant-k for any input
85
+ length; duplicate candidates possible and deduped on the host).
86
+ - Decode parity with the Python pipeline added to the export validation.
87
 
88
  ## Python check
89
 
90
  ```python
91
  import onnxruntime as ort
92
  sess = ort.InferenceSession("onnx/model.onnx")
93
+ print([o.name for o in sess.get_outputs()])
94
+ # ['start_logits', 'end_logits', 'pair_indices', 'pair_logits', 'pair_valid']
95
  ```
96
 
97
+ WebGPU: load `onnx/model.onnx` with `onnxruntime-web` (`webgpu` execution
98
+ provider; WASM fallback where WebGPU is unavailable). Int64 inputs are
99
+ required.
100
+
101
+ ## Credits
102
+
103
+ - Base checkpoints and the GLiNER2 reference implementation by
104
+ [Fastino](https://fastino.ai) — Apache-2.0.
105
+ - ONNX export + host protocol by [Pastel-Cloud OÜ](https://github.com/Pastel-Org).
export_config.json CHANGED
@@ -1,7 +1,9 @@
1
  {
2
  "architecture": "boundary",
 
3
  "base_model": "fastino/gliner2.5-multi-v1",
4
- "hidden_size": 768,
 
5
  "opset": 17,
6
  "inputs": [
7
  "input_ids",
@@ -13,7 +15,10 @@
13
  ],
14
  "outputs": [
15
  "start_logits",
16
- "end_logits"
 
 
 
17
  ],
18
- "notes": "Host must pack schema markers into input_ids and pass word/query gather indices. Decode spans from start/end logits in JS."
19
  }
 
1
  {
2
  "architecture": "boundary",
3
+ "export_version": 2,
4
  "base_model": "fastino/gliner2.5-multi-v1",
5
+ "candidate_budget": 192,
6
+ "pair_temperature": 1.0,
7
  "opset": 17,
8
  "inputs": [
9
  "input_ids",
 
15
  ],
16
  "outputs": [
17
  "start_logits",
18
+ "end_logits",
19
+ "pair_indices",
20
+ "pair_logits",
21
+ "pair_valid"
22
  ],
23
+ "notes": "v2 graph: proposer + shared pool + pair reranker included. Host decode: keep pair_valid candidates with sigmoid(pair_logits / pair_temperature) >= threshold, dedupe (start,end), resolve overlaps per label, boundaries are word indices (s,e) half-open over words."
24
  }
onnx/model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ca83f1aaf71a9a79698ce020cceeb0fc2e367bd2855c9d94c6bbafe05d344c
3
- size 1113924155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8e3313d123c19e6ad4d29ddca3c3021f095c9237da850a830f66f454a8741a
3
+ size 1115957710
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b107e2e5998e7429491aaae7807d8b0815ff3e06fcb5ba95bc6a35c9b93185c5
3
- size 16020605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62446df87ae18ec98b133f8f84fc449a07cc89bbf8ef192a4cb5f9c53777a7a
3
+ size 16035853
tokenizer_config.json CHANGED
@@ -1,928 +1,11 @@
1
  {
2
  "add_prefix_space": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "[PAD]",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "[CLS]",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "[SEP]",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "[UNK]",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "250001": {
37
- "content": "▁<extra_id_99>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": false
43
- },
44
- "250002": {
45
- "content": "▁<extra_id_98>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": false
51
- },
52
- "250003": {
53
- "content": "▁<extra_id_97>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": false
59
- },
60
- "250004": {
61
- "content": "▁<extra_id_96>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": false
67
- },
68
- "250005": {
69
- "content": "▁<extra_id_95>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": false
75
- },
76
- "250006": {
77
- "content": "▁<extra_id_94>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": false
83
- },
84
- "250007": {
85
- "content": "▁<extra_id_93>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": false
91
- },
92
- "250008": {
93
- "content": "▁<extra_id_92>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": false
99
- },
100
- "250009": {
101
- "content": "▁<extra_id_91>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": false
107
- },
108
- "250010": {
109
- "content": "▁<extra_id_90>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": false
115
- },
116
- "250011": {
117
- "content": "▁<extra_id_89>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": false
123
- },
124
- "250012": {
125
- "content": "▁<extra_id_88>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": false
131
- },
132
- "250013": {
133
- "content": "▁<extra_id_87>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": false
139
- },
140
- "250014": {
141
- "content": "▁<extra_id_86>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": false
147
- },
148
- "250015": {
149
- "content": "▁<extra_id_85>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": false
155
- },
156
- "250016": {
157
- "content": "▁<extra_id_84>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": false
163
- },
164
- "250017": {
165
- "content": "▁<extra_id_83>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": false
171
- },
172
- "250018": {
173
- "content": "▁<extra_id_82>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": false
179
- },
180
- "250019": {
181
- "content": "▁<extra_id_81>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": false
187
- },
188
- "250020": {
189
- "content": "▁<extra_id_80>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": false
195
- },
196
- "250021": {
197
- "content": "▁<extra_id_79>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": false
203
- },
204
- "250022": {
205
- "content": "▁<extra_id_78>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": false
211
- },
212
- "250023": {
213
- "content": "▁<extra_id_77>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": false
219
- },
220
- "250024": {
221
- "content": "▁<extra_id_76>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": false
227
- },
228
- "250025": {
229
- "content": "▁<extra_id_75>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": false
235
- },
236
- "250026": {
237
- "content": "▁<extra_id_74>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": false
243
- },
244
- "250027": {
245
- "content": "▁<extra_id_73>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": false
251
- },
252
- "250028": {
253
- "content": "▁<extra_id_72>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": false
259
- },
260
- "250029": {
261
- "content": "▁<extra_id_71>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": false
267
- },
268
- "250030": {
269
- "content": "▁<extra_id_70>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": false
275
- },
276
- "250031": {
277
- "content": "▁<extra_id_69>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": false
283
- },
284
- "250032": {
285
- "content": "▁<extra_id_68>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": false
291
- },
292
- "250033": {
293
- "content": "▁<extra_id_67>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": false
299
- },
300
- "250034": {
301
- "content": "▁<extra_id_66>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": false
307
- },
308
- "250035": {
309
- "content": "▁<extra_id_65>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": false
315
- },
316
- "250036": {
317
- "content": "▁<extra_id_64>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": false
323
- },
324
- "250037": {
325
- "content": "▁<extra_id_63>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": false
331
- },
332
- "250038": {
333
- "content": "▁<extra_id_62>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": false
339
- },
340
- "250039": {
341
- "content": "▁<extra_id_61>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": false
347
- },
348
- "250040": {
349
- "content": "▁<extra_id_60>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": false
355
- },
356
- "250041": {
357
- "content": "▁<extra_id_59>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": false
363
- },
364
- "250042": {
365
- "content": "▁<extra_id_58>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": false
371
- },
372
- "250043": {
373
- "content": "▁<extra_id_57>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": false
379
- },
380
- "250044": {
381
- "content": "▁<extra_id_56>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": false
387
- },
388
- "250045": {
389
- "content": "▁<extra_id_55>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": false
395
- },
396
- "250046": {
397
- "content": "▁<extra_id_54>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": false
403
- },
404
- "250047": {
405
- "content": "▁<extra_id_53>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": false
411
- },
412
- "250048": {
413
- "content": "▁<extra_id_52>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": false
419
- },
420
- "250049": {
421
- "content": "▁<extra_id_51>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": false
427
- },
428
- "250050": {
429
- "content": "▁<extra_id_50>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": false
435
- },
436
- "250051": {
437
- "content": "▁<extra_id_49>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": false
443
- },
444
- "250052": {
445
- "content": "▁<extra_id_48>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": false
451
- },
452
- "250053": {
453
- "content": "▁<extra_id_47>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": false
459
- },
460
- "250054": {
461
- "content": "▁<extra_id_46>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": false
467
- },
468
- "250055": {
469
- "content": "▁<extra_id_45>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": false
475
- },
476
- "250056": {
477
- "content": "▁<extra_id_44>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": false
483
- },
484
- "250057": {
485
- "content": "▁<extra_id_43>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": false
491
- },
492
- "250058": {
493
- "content": "▁<extra_id_42>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": false
499
- },
500
- "250059": {
501
- "content": "▁<extra_id_41>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": false
507
- },
508
- "250060": {
509
- "content": "▁<extra_id_40>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": false
515
- },
516
- "250061": {
517
- "content": "▁<extra_id_39>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": false
523
- },
524
- "250062": {
525
- "content": "▁<extra_id_38>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": false
531
- },
532
- "250063": {
533
- "content": "▁<extra_id_37>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": false
539
- },
540
- "250064": {
541
- "content": "▁<extra_id_36>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": false
547
- },
548
- "250065": {
549
- "content": "▁<extra_id_35>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": false
555
- },
556
- "250066": {
557
- "content": "▁<extra_id_34>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": false
563
- },
564
- "250067": {
565
- "content": "▁<extra_id_33>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": false
571
- },
572
- "250068": {
573
- "content": "▁<extra_id_32>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": false
579
- },
580
- "250069": {
581
- "content": "▁<extra_id_31>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": false
587
- },
588
- "250070": {
589
- "content": "▁<extra_id_30>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": false
595
- },
596
- "250071": {
597
- "content": "▁<extra_id_29>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": false
603
- },
604
- "250072": {
605
- "content": "▁<extra_id_28>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": false
611
- },
612
- "250073": {
613
- "content": "▁<extra_id_27>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": false
619
- },
620
- "250074": {
621
- "content": "▁<extra_id_26>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": false
627
- },
628
- "250075": {
629
- "content": "▁<extra_id_25>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": false
635
- },
636
- "250076": {
637
- "content": "▁<extra_id_24>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": false
643
- },
644
- "250077": {
645
- "content": "▁<extra_id_23>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": false
651
- },
652
- "250078": {
653
- "content": "▁<extra_id_22>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": false
659
- },
660
- "250079": {
661
- "content": "▁<extra_id_21>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": false
667
- },
668
- "250080": {
669
- "content": "▁<extra_id_20>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": false
675
- },
676
- "250081": {
677
- "content": "▁<extra_id_19>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": false
683
- },
684
- "250082": {
685
- "content": "▁<extra_id_18>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": false
691
- },
692
- "250083": {
693
- "content": "▁<extra_id_17>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": false
699
- },
700
- "250084": {
701
- "content": "▁<extra_id_16>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": false
707
- },
708
- "250085": {
709
- "content": "▁<extra_id_15>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": false
715
- },
716
- "250086": {
717
- "content": "▁<extra_id_14>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": false
723
- },
724
- "250087": {
725
- "content": "▁<extra_id_13>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": false
731
- },
732
- "250088": {
733
- "content": "▁<extra_id_12>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": false
739
- },
740
- "250089": {
741
- "content": "▁<extra_id_11>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": false
747
- },
748
- "250090": {
749
- "content": "▁<extra_id_10>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": false
755
- },
756
- "250091": {
757
- "content": "▁<extra_id_9>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": false
763
- },
764
- "250092": {
765
- "content": "▁<extra_id_8>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": false
771
- },
772
- "250093": {
773
- "content": "▁<extra_id_7>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": false
779
- },
780
- "250094": {
781
- "content": "▁<extra_id_6>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": false
787
- },
788
- "250095": {
789
- "content": "▁<extra_id_5>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": false
795
- },
796
- "250096": {
797
- "content": "▁<extra_id_4>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": false
803
- },
804
- "250097": {
805
- "content": "▁<extra_id_3>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": false
811
- },
812
- "250098": {
813
- "content": "▁<extra_id_2>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": false
819
- },
820
- "250099": {
821
- "content": "▁<extra_id_1>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": false
827
- },
828
- "250100": {
829
- "content": "▁<extra_id_0>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": false
835
- },
836
- "250101": {
837
- "content": "[MASK]",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": true
843
- },
844
- "250102": {
845
- "content": "[SEP_STRUCT]",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": true
851
- },
852
- "250103": {
853
- "content": "[SEP_TEXT]",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "250104": {
861
- "content": "[P]",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "250105": {
869
- "content": "[C]",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": true
875
- },
876
- "250106": {
877
- "content": "[E]",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": true
883
- },
884
- "250107": {
885
- "content": "[R]",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": true
891
- },
892
- "250108": {
893
- "content": "[L]",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": true
899
- },
900
- "250109": {
901
- "content": "[EXAMPLE]",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": true
907
- },
908
- "250110": {
909
- "content": "[OUTPUT]",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": true
915
- },
916
- "250111": {
917
- "content": "[DESCRIPTION]",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": true
923
- }
924
- },
925
- "additional_special_tokens": [
926
  "[SEP_STRUCT]",
927
  "[SEP_TEXT]",
928
  "[P]",
@@ -934,21 +17,14 @@
934
  "[OUTPUT]",
935
  "[DESCRIPTION]"
936
  ],
937
- "backend": "tokenizers",
938
- "bos_token": "[CLS]",
939
- "clean_up_tokenization_spaces": false,
940
- "cls_token": "[CLS]",
941
- "do_lower_case": false,
942
- "eos_token": "[SEP]",
943
- "extra_special_tokens": {},
944
- "is_local": true,
945
  "local_files_only": false,
946
  "mask_token": "[MASK]",
947
  "model_max_length": 1000000000000000019884624838656,
948
  "pad_token": "[PAD]",
949
  "sep_token": "[SEP]",
950
  "split_by_punct": false,
951
- "tokenizer_class": "DebertaV2TokenizerFast",
952
  "unk_id": 3,
953
  "unk_token": "[UNK]",
954
  "vocab_type": "spm"
 
1
  {
2
  "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "[SEP_STRUCT]",
10
  "[SEP_TEXT]",
11
  "[P]",
 
17
  "[OUTPUT]",
18
  "[DESCRIPTION]"
19
  ],
20
+ "is_local": false,
 
 
 
 
 
 
 
21
  "local_files_only": false,
22
  "mask_token": "[MASK]",
23
  "model_max_length": 1000000000000000019884624838656,
24
  "pad_token": "[PAD]",
25
  "sep_token": "[SEP]",
26
  "split_by_punct": false,
27
+ "tokenizer_class": "DebertaV2Tokenizer",
28
  "unk_id": 3,
29
  "unk_token": "[UNK]",
30
  "vocab_type": "spm"