Hugging Face's logo

yahyaabd
/
allstats-search-mini-v1-2

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:967831
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files Community
yahyaabd commited on
Commit
bd03a8d
·
verified ·
1 Parent(s): cd7be9c

Add new SentenceTransformer model

Browse files
Files changed (12) hide show
  1. .gitattributes +2 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +646 -0
  4. config.json +26 -0
  5. config_sentence_transformers.json +10 -0
  6. model.safetensors +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +65 -0
  12. unigram.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ unigram.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,646 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:967831
8
+ - loss:MultipleNegativesRankingLoss
9
+ base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
10
+ widget:
11
+ - source_sentence: Gaji pekerja berdasarkan jenis pekerjaan dan umur, 2016
12
+ sentences:
13
+ - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Kelompok Umur
14
+ dan Jenis Pekerjaan (Rupiah), 2016
15
+ - '[Seri 2010] PDRB Triwulanan Atas Dasar Harga Berlaku Menurut Lapangan Usaha di
16
+ Provinsi Seluruh Indonesia (Miliar Rupiah), 2010-2024'
17
+ - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Pendidikan Tertinggi
18
+ yang Ditamatkan, 2019
19
+ - source_sentence: Ke negara mana saja ekspor tanaman obat Indonesia tahun 2018?
20
+ sentences:
21
+ - Jumlah Rumah Tangga Perikanan Tangkap Menurut Provinsi dan Jenis Penangkapan,
22
+ 2000-2016
23
+ - Perolehan Suara dan Kursi Dewan Perwakilan Rakyat (DPR) Menurut Partai Politik
24
+ Hasil Pemilu Tahun 2009 dan 2014
25
+ - Ekspor Tanaman Obat, Aromatik, dan Rempah-Rempah menurut Negara Tujuan Utama,
26
+ 2012-2023
27
+ - source_sentence: Negara asal impor soybean 2023
28
+ sentences:
29
+ - Ringkasan Neraca Arus Dana, Triwulan III, 2010, (Miliar Rupiah)
30
+ - Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Kelompok Umur
31
+ (ribu rupiah), 2018
32
+ - Impor Kedelai menurut Negara Asal Utama, 2017-2023
33
+ - source_sentence: Cek penghasilan bersih rata-rata yang didapat wiraswasta di Indonesia
34
+ tahun 2021, bedakan per provinsi dan ijazah terakhir
35
+ sentences:
36
+ - Rata-rata Pendapatan bersih Berusaha Sendiri menurut Provinsi dan Pendidikan yang
37
+ Ditamatkan, 2021
38
+ - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan
39
+ dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Sumatera Selatan, 2018-2023
40
+ - Impor Daging Sejenis Lembu menurut Negara Asal Utama, 2018-2023
41
+ - source_sentence: Status pernikahan penduduk (10+) tiap provinsi, data 2012
42
+ sentences:
43
+ - Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)
44
+ - Ekspor Batu Bara Menurut Negara Tujuan Utama, 2012-2023
45
+ - Persentase Penduduk Berumur 10 Tahun ke Atas menurut Provinsi, Jenis Kelamin,
46
+ dan Status Perkawinan, 2009-2018
47
+ datasets:
48
+ - yahyaabd/statictable-triplets-all
49
+ pipeline_tag: sentence-similarity
50
+ library_name: sentence-transformers
51
+ metrics:
52
+ - cosine_accuracy@1
53
+ - cosine_accuracy@3
54
+ - cosine_accuracy@5
55
+ - cosine_accuracy@10
56
+ - cosine_precision@1
57
+ - cosine_precision@3
58
+ - cosine_precision@5
59
+ - cosine_precision@10
60
+ - cosine_recall@1
61
+ - cosine_recall@3
62
+ - cosine_recall@5
63
+ - cosine_recall@10
64
+ - cosine_ndcg@10
65
+ - cosine_mrr@10
66
+ - cosine_map@100
67
+ model-index:
68
+ - name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
69
+ results:
70
+ - task:
71
+ type: information-retrieval
72
+ name: Information Retrieval
73
+ dataset:
74
+ name: bps statictable ir
75
+ type: bps-statictable-ir
76
+ metrics:
77
+ - type: cosine_accuracy@1
78
+ value: 0.8990228013029316
79
+ name: Cosine Accuracy@1
80
+ - type: cosine_accuracy@3
81
+ value: 0.9739413680781759
82
+ name: Cosine Accuracy@3
83
+ - type: cosine_accuracy@5
84
+ value: 0.9804560260586319
85
+ name: Cosine Accuracy@5
86
+ - type: cosine_accuracy@10
87
+ value: 0.9869706840390879
88
+ name: Cosine Accuracy@10
89
+ - type: cosine_precision@1
90
+ value: 0.8990228013029316
91
+ name: Cosine Precision@1
92
+ - type: cosine_precision@3
93
+ value: 0.3517915309446254
94
+ name: Cosine Precision@3
95
+ - type: cosine_precision@5
96
+ value: 0.2299674267100977
97
+ name: Cosine Precision@5
98
+ - type: cosine_precision@10
99
+ value: 0.13420195439739416
100
+ name: Cosine Precision@10
101
+ - type: cosine_recall@1
102
+ value: 0.7037534704802675
103
+ name: Cosine Recall@1
104
+ - type: cosine_recall@3
105
+ value: 0.777408879373005
106
+ name: Cosine Recall@3
107
+ - type: cosine_recall@5
108
+ value: 0.7896378239472596
109
+ name: Cosine Recall@5
110
+ - type: cosine_recall@10
111
+ value: 0.8147874661605627
112
+ name: Cosine Recall@10
113
+ - type: cosine_ndcg@10
114
+ value: 0.8242104501990923
115
+ name: Cosine Ndcg@10
116
+ - type: cosine_mrr@10
117
+ value: 0.9361834961997827
118
+ name: Cosine Mrr@10
119
+ - type: cosine_map@100
120
+ value: 0.7641191235697605
121
+ name: Cosine Map@100
122
+ ---
123
+
124
+ # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
125
+
126
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) on the [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
127
+
128
+ ## Model Details
129
+
130
+ ### Model Description
131
+ - **Model Type:** Sentence Transformer
132
+ - **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
133
+ - **Maximum Sequence Length:** 128 tokens
134
+ - **Output Dimensionality:** 384 dimensions
135
+ - **Similarity Function:** Cosine Similarity
136
+ - **Training Dataset:**
137
+ - [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all)
138
+ <!-- - **Language:** Unknown -->
139
+ <!-- - **License:** Unknown -->
140
+
141
+ ### Model Sources
142
+
143
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
144
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
145
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
146
+
147
+ ### Full Model Architecture
148
+
149
+ ```
150
+ SentenceTransformer(
151
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
152
+ (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
153
+ )
154
+ ```
155
+
156
+ ## Usage
157
+
158
+ ### Direct Usage (Sentence Transformers)
159
+
160
+ First install the Sentence Transformers library:
161
+
162
+ ```bash
163
+ pip install -U sentence-transformers
164
+ ```
165
+
166
+ Then you can load this model and run inference.
167
+ ```python
168
+ from sentence_transformers import SentenceTransformer
169
+
170
+ # Download from the 🤗 Hub
171
+ model = SentenceTransformer("yahyaabd/allstats-search-mini-v1-2")
172
+ # Run inference
173
+ sentences = [
174
+ 'Status pernikahan penduduk (10+) tiap provinsi, data 2012',
175
+ 'Persentase Penduduk Berumur 10 Tahun ke Atas menurut Provinsi, Jenis Kelamin, dan Status Perkawinan, 2009-2018',
176
+ 'Ekspor Batu Bara Menurut Negara Tujuan Utama, 2012-2023',
177
+ ]
178
+ embeddings = model.encode(sentences)
179
+ print(embeddings.shape)
180
+ # [3, 384]
181
+
182
+ # Get the similarity scores for the embeddings
183
+ similarities = model.similarity(embeddings, embeddings)
184
+ print(similarities.shape)
185
+ # [3, 3]
186
+ ```
187
+
188
+ <!--
189
+ ### Direct Usage (Transformers)
190
+
191
+ <details><summary>Click to see the direct usage in Transformers</summary>
192
+
193
+ </details>
194
+ -->
195
+
196
+ <!--
197
+ ### Downstream Usage (Sentence Transformers)
198
+
199
+ You can finetune this model on your own dataset.
200
+
201
+ <details><summary>Click to expand</summary>
202
+
203
+ </details>
204
+ -->
205
+
206
+ <!--
207
+ ### Out-of-Scope Use
208
+
209
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
210
+ -->
211
+
212
+ ## Evaluation
213
+
214
+ ### Metrics
215
+
216
+ #### Information Retrieval
217
+
218
+ * Dataset: `bps-statictable-ir`
219
+ * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
220
+
221
+ | Metric | Value |
222
+ |:--------------------|:-----------|
223
+ | cosine_accuracy@1 | 0.899 |
224
+ | cosine_accuracy@3 | 0.9739 |
225
+ | cosine_accuracy@5 | 0.9805 |
226
+ | cosine_accuracy@10 | 0.987 |
227
+ | cosine_precision@1 | 0.899 |
228
+ | cosine_precision@3 | 0.3518 |
229
+ | cosine_precision@5 | 0.23 |
230
+ | cosine_precision@10 | 0.1342 |
231
+ | cosine_recall@1 | 0.7038 |
232
+ | cosine_recall@3 | 0.7774 |
233
+ | cosine_recall@5 | 0.7896 |
234
+ | cosine_recall@10 | 0.8148 |
235
+ | **cosine_ndcg@10** | **0.8242** |
236
+ | cosine_mrr@10 | 0.9362 |
237
+ | cosine_map@100 | 0.7641 |
238
+
239
+ <!--
240
+ ## Bias, Risks and Limitations
241
+
242
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
243
+ -->
244
+
245
+ <!--
246
+ ### Recommendations
247
+
248
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
249
+ -->
250
+
251
+ ## Training Details
252
+
253
+ ### Training Dataset
254
+
255
+ #### statictable-triplets-all
256
+
257
+ * Dataset: [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) at [24979b4](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all/tree/24979b4f0d8269377aca975e20d52e69c3b5a030)
258
+ * Size: 967,831 training samples
259
+ * Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
260
+ * Approximate statistics based on the first 1000 samples:
261
+ | | query | pos | neg |
262
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
263
+ | type | string | string | string |
264
+ | details | <ul><li>min: 5 tokens</li><li>mean: 18.35 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.22 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.78 tokens</li><li>max: 58 tokens</li></ul> |
265
+ * Samples:
266
+ | query | pos | neg |
267
+ |:---------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------|
268
+ | <code>Jumlah bank dan kantor bank di Indonesia, 2010-2017</code> | <code>Bank dan Kantor Bank, 2010-2017</code> | <code>Rata-Rata Pengeluaran per Kapita Sebulan Menurut Kelompok Barang (rupiah), 1998-2012</code> |
269
+ | <code>Konsumsi makanan mingguan per orang di Sulteng: beda tingkat pengeluaran (2021)</code> | <code>Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Sulawesi Selatan, 2018-2023</code> | <code>IHK, Upah Nominal, Indeks Upah Nominal dan Riil Buruh Industri Berstatus di bawah Mandor Menurut Wilayah, 2008-2014 (2007=100)</code> |
270
+ | <code>Impor semen Indonesia, negara asal utama, 2021</code> | <code>Impor Semen Menurut Negara Asal Utama, 2017-2023</code> | <code>Penerimaan dari Wisatawan Mancanegara Menurut Negara Tempat Tinggal (juta US$), 2000-2014</code> |
271
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
272
+ ```json
273
+ {
274
+ "scale": 20.0,
275
+ "similarity_fct": "cos_sim"
276
+ }
277
+ ```
278
+
279
+ ### Evaluation Dataset
280
+
281
+ #### statictable-triplets-all
282
+
283
+ * Dataset: [statictable-triplets-all](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all) at [24979b4](https://huggingface.co/datasets/yahyaabd/statictable-triplets-all/tree/24979b4f0d8269377aca975e20d52e69c3b5a030)
284
+ * Size: 967,831 evaluation samples
285
+ * Columns: <code>query</code>, <code>pos</code>, and <code>neg</code>
286
+ * Approximate statistics based on the first 1000 samples:
287
+ | | query | pos | neg |
288
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
289
+ | type | string | string | string |
290
+ | details | <ul><li>min: 5 tokens</li><li>mean: 18.39 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.22 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.33 tokens</li><li>max: 58 tokens</li></ul> |
291
+ * Samples:
292
+ | query | pos | neg |
293
+ |:----------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------|
294
+ | <code>Bagaimana hubungan antara bidang pekerjaan utama dan pendidikan pekerja 15+ di minggu lalu (tahun 2016)?</code> | <code>Penduduk Berumur 15 Tahun Ke Atas yang Bekerja Selama Seminggu yang Lalu Menurut Lapangan Pekerjaan Utama dan Pendidikan Tertinggi yang Ditamatkan, 2008 - 2024</code> | <code>Bank dan Kantor Bank, 2010-2017</code> |
295
+ | <code>Tren indikator kondisi perumahan, 2001</code> | <code>Indikator Perumahan 1993-2023</code> | <code>Banyaknya Desa/Kelurahan Menurut Keberadaan Kelompok Pertokoan, Pasar, dan Kios Sarana Produksi Pertanian (Saprotan), 2014 & 2018</code> |
296
+ | <code>Gaji bersih rata-rata: Per pendidikan & lapangan kerja utama, Indonesia, 2021</code> | <code>Rata-rata Upah/Gaji Bersih sebulan Buruh/Karyawan Pegawai Menurut Pendidikan Tertinggi dan Lapangan Pekerjaan Utama, 2021</code> | <code>[Seri 2000] Laju Pertumbuhan Kumulatif PDB Menurut Lapangan Usaha (Persen), 2001-2014</code> |
297
+ * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
298
+ ```json
299
+ {
300
+ "scale": 20.0,
301
+ "similarity_fct": "cos_sim"
302
+ }
303
+ ```
304
+
305
+ ### Training Hyperparameters
306
+ #### Non-Default Hyperparameters
307
+
308
+ - `eval_strategy`: steps
309
+ - `per_device_train_batch_size`: 16
310
+ - `per_device_eval_batch_size`: 16
311
+ - `num_train_epochs`: 1
312
+ - `warmup_ratio`: 0.1
313
+ - `fp16`: True
314
+ - `load_best_model_at_end`: True
315
+ - `eval_on_start`: True
316
+ - `batch_sampler`: no_duplicates
317
+
318
+ #### All Hyperparameters
319
+ <details><summary>Click to expand</summary>
320
+
321
+ - `overwrite_output_dir`: False
322
+ - `do_predict`: False
323
+ - `eval_strategy`: steps
324
+ - `prediction_loss_only`: True
325
+ - `per_device_train_batch_size`: 16
326
+ - `per_device_eval_batch_size`: 16
327
+ - `per_gpu_train_batch_size`: None
328
+ - `per_gpu_eval_batch_size`: None
329
+ - `gradient_accumulation_steps`: 1
330
+ - `eval_accumulation_steps`: None
331
+ - `torch_empty_cache_steps`: None
332
+ - `learning_rate`: 5e-05
333
+ - `weight_decay`: 0.0
334
+ - `adam_beta1`: 0.9
335
+ - `adam_beta2`: 0.999
336
+ - `adam_epsilon`: 1e-08
337
+ - `max_grad_norm`: 1.0
338
+ - `num_train_epochs`: 1
339
+ - `max_steps`: -1
340
+ - `lr_scheduler_type`: linear
341
+ - `lr_scheduler_kwargs`: {}
342
+ - `warmup_ratio`: 0.1
343
+ - `warmup_steps`: 0
344
+ - `log_level`: passive
345
+ - `log_level_replica`: warning
346
+ - `log_on_each_node`: True
347
+ - `logging_nan_inf_filter`: True
348
+ - `save_safetensors`: True
349
+ - `save_on_each_node`: False
350
+ - `save_only_model`: False
351
+ - `restore_callback_states_from_checkpoint`: False
352
+ - `no_cuda`: False
353
+ - `use_cpu`: False
354
+ - `use_mps_device`: False
355
+ - `seed`: 42
356
+ - `data_seed`: None
357
+ - `jit_mode_eval`: False
358
+ - `use_ipex`: False
359
+ - `bf16`: False
360
+ - `fp16`: True
361
+ - `fp16_opt_level`: O1
362
+ - `half_precision_backend`: auto
363
+ - `bf16_full_eval`: False
364
+ - `fp16_full_eval`: False
365
+ - `tf32`: None
366
+ - `local_rank`: 0
367
+ - `ddp_backend`: None
368
+ - `tpu_num_cores`: None
369
+ - `tpu_metrics_debug`: False
370
+ - `debug`: []
371
+ - `dataloader_drop_last`: False
372
+ - `dataloader_num_workers`: 0
373
+ - `dataloader_prefetch_factor`: None
374
+ - `past_index`: -1
375
+ - `disable_tqdm`: False
376
+ - `remove_unused_columns`: True
377
+ - `label_names`: None
378
+ - `load_best_model_at_end`: True
379
+ - `ignore_data_skip`: False
380
+ - `fsdp`: []
381
+ - `fsdp_min_num_params`: 0
382
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
383
+ - `fsdp_transformer_layer_cls_to_wrap`: None
384
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
385
+ - `deepspeed`: None
386
+ - `label_smoothing_factor`: 0.0
387
+ - `optim`: adamw_torch
388
+ - `optim_args`: None
389
+ - `adafactor`: False
390
+ - `group_by_length`: False
391
+ - `length_column_name`: length
392
+ - `ddp_find_unused_parameters`: None
393
+ - `ddp_bucket_cap_mb`: None
394
+ - `ddp_broadcast_buffers`: False
395
+ - `dataloader_pin_memory`: True
396
+ - `dataloader_persistent_workers`: False
397
+ - `skip_memory_metrics`: True
398
+ - `use_legacy_prediction_loop`: False
399
+ - `push_to_hub`: False
400
+ - `resume_from_checkpoint`: None
401
+ - `hub_model_id`: None
402
+ - `hub_strategy`: every_save
403
+ - `hub_private_repo`: None
404
+ - `hub_always_push`: False
405
+ - `gradient_checkpointing`: False
406
+ - `gradient_checkpointing_kwargs`: None
407
+ - `include_inputs_for_metrics`: False
408
+ - `include_for_metrics`: []
409
+ - `eval_do_concat_batches`: True
410
+ - `fp16_backend`: auto
411
+ - `push_to_hub_model_id`: None
412
+ - `push_to_hub_organization`: None
413
+ - `mp_parameters`:
414
+ - `auto_find_batch_size`: False
415
+ - `full_determinism`: False
416
+ - `torchdynamo`: None
417
+ - `ray_scope`: last
418
+ - `ddp_timeout`: 1800
419
+ - `torch_compile`: False
420
+ - `torch_compile_backend`: None
421
+ - `torch_compile_mode`: None
422
+ - `dispatch_batches`: None
423
+ - `split_batches`: None
424
+ - `include_tokens_per_second`: False
425
+ - `include_num_input_tokens_seen`: False
426
+ - `neftune_noise_alpha`: None
427
+ - `optim_target_modules`: None
428
+ - `batch_eval_metrics`: False
429
+ - `eval_on_start`: True
430
+ - `use_liger_kernel`: False
431
+ - `eval_use_gather_object`: False
432
+ - `average_tokens_across_devices`: False
433
+ - `prompts`: None
434
+ - `batch_sampler`: no_duplicates
435
+ - `multi_dataset_batch_sampler`: proportional
436
+
437
+ </details>
438
+
439
+ ### Training Logs
440
+ <details><summary>Click to expand</summary>
441
+
442
+ | Epoch | Step | Training Loss | Validation Loss | bps-statictable-ir_cosine_ndcg@10 |
443
+ |:----------:|:--------:|:-------------:|:---------------:|:---------------------------------:|
444
+ | 0 | 0 | - | 1.1084 | 0.4644 |
445
+ | 0.0070 | 20 | 1.0801 | 0.8303 | 0.5117 |
446
+ | 0.0139 | 40 | 0.6994 | 0.4459 | 0.6310 |
447
+ | 0.0209 | 60 | 0.3674 | 0.2510 | 0.7155 |
448
+ | 0.0278 | 80 | 0.2814 | 0.1829 | 0.7521 |
449
+ | 0.0348 | 100 | 0.1746 | 0.1303 | 0.7751 |
450
+ | 0.0418 | 120 | 0.1867 | 0.1001 | 0.7772 |
451
+ | 0.0487 | 140 | 0.1047 | 0.0819 | 0.7857 |
452
+ | 0.0557 | 160 | 0.1032 | 0.0739 | 0.7960 |
453
+ | 0.0626 | 180 | 0.0783 | 0.0645 | 0.7861 |
454
+ | 0.0696 | 200 | 0.0575 | 0.0567 | 0.7849 |
455
+ | 0.0765 | 220 | 0.0969 | 0.0454 | 0.7945 |
456
+ | 0.0835 | 240 | 0.0769 | 0.0433 | 0.7890 |
457
+ | 0.0905 | 260 | 0.0864 | 0.0507 | 0.7848 |
458
+ | 0.0974 | 280 | 0.0495 | 0.0347 | 0.8052 |
459
+ | 0.1044 | 300 | 0.0429 | 0.0398 | 0.7955 |
460
+ | 0.1113 | 320 | 0.0432 | 0.0343 | 0.7915 |
461
+ | 0.1183 | 340 | 0.0392 | 0.0295 | 0.8177 |
462
+ | 0.1253 | 360 | 0.0211 | 0.0298 | 0.8052 |
463
+ | 0.1322 | 380 | 0.043 | 0.0339 | 0.8052 |
464
+ | 0.1392 | 400 | 0.0453 | 0.0322 | 0.8050 |
465
+ | 0.1461 | 420 | 0.0309 | 0.0286 | 0.8120 |
466
+ | 0.1531 | 440 | 0.0147 | 0.0321 | 0.8181 |
467
+ | 0.1601 | 460 | 0.0491 | 0.0273 | 0.8178 |
468
+ | 0.1670 | 480 | 0.0229 | 0.0232 | 0.8176 |
469
+ | 0.1740 | 500 | 0.0317 | 0.0210 | 0.8198 |
470
+ | 0.1809 | 520 | 0.0193 | 0.0207 | 0.8159 |
471
+ | 0.1879 | 540 | 0.034 | 0.0175 | 0.8191 |
472
+ | 0.1949 | 560 | 0.0292 | 0.0168 | 0.8166 |
473
+ | 0.2018 | 580 | 0.0431 | 0.0184 | 0.8228 |
474
+ | 0.2088 | 600 | 0.0306 | 0.0183 | 0.7963 |
475
+ | 0.2157 | 620 | 0.0134 | 0.0147 | 0.8216 |
476
+ | 0.2227 | 640 | 0.0155 | 0.0161 | 0.8166 |
477
+ | 0.2296 | 660 | 0.0201 | 0.0187 | 0.8170 |
478
+ | 0.2366 | 680 | 0.0301 | 0.0133 | 0.8272 |
479
+ | 0.2436 | 700 | 0.0164 | 0.0119 | 0.8274 |
480
+ | 0.2505 | 720 | 0.0254 | 0.0119 | 0.8223 |
481
+ | 0.2575 | 740 | 0.0129 | 0.0146 | 0.8165 |
482
+ | 0.2644 | 760 | 0.0208 | 0.0136 | 0.8162 |
483
+ | 0.2714 | 780 | 0.0157 | 0.0138 | 0.8120 |
484
+ | 0.2784 | 800 | 0.0169 | 0.0143 | 0.8248 |
485
+ | 0.2853 | 820 | 0.0158 | 0.0119 | 0.8166 |
486
+ | 0.2923 | 840 | 0.0227 | 0.0115 | 0.8153 |
487
+ | 0.2992 | 860 | 0.0196 | 0.0117 | 0.8163 |
488
+ | 0.3062 | 880 | 0.0137 | 0.0112 | 0.8225 |
489
+ | 0.3132 | 900 | 0.0299 | 0.0090 | 0.8155 |
490
+ | 0.3201 | 920 | 0.0073 | 0.0106 | 0.8157 |
491
+ | 0.3271 | 940 | 0.0248 | 0.0088 | 0.8174 |
492
+ | 0.3340 | 960 | 0.0179 | 0.0087 | 0.8215 |
493
+ | 0.3410 | 980 | 0.0171 | 0.0077 | 0.8285 |
494
+ | 0.3479 | 1000 | 0.0123 | 0.0096 | 0.8175 |
495
+ | 0.3549 | 1020 | 0.0081 | 0.0098 | 0.8152 |
496
+ | 0.3619 | 1040 | 0.0097 | 0.0094 | 0.8139 |
497
+ | 0.3688 | 1060 | 0.0379 | 0.0107 | 0.8236 |
498
+ | 0.3758 | 1080 | 0.0104 | 0.0078 | 0.8208 |
499
+ | 0.3827 | 1100 | 0.0067 | 0.0065 | 0.8189 |
500
+ | 0.3897 | 1120 | 0.0128 | 0.0080 | 0.8221 |
501
+ | 0.3967 | 1140 | 0.0049 | 0.0078 | 0.8181 |
502
+ | 0.4036 | 1160 | 0.0084 | 0.0092 | 0.8218 |
503
+ | 0.4106 | 1180 | 0.0173 | 0.0081 | 0.8248 |
504
+ | 0.4175 | 1200 | 0.0144 | 0.0080 | 0.8272 |
505
+ | 0.4245 | 1220 | 0.0025 | 0.0077 | 0.8260 |
506
+ | 0.4315 | 1240 | 0.0086 | 0.0072 | 0.8312 |
507
+ | 0.4384 | 1260 | 0.0114 | 0.0073 | 0.8242 |
508
+ | 0.4454 | 1280 | 0.0065 | 0.0067 | 0.8245 |
509
+ | 0.4523 | 1300 | 0.0132 | 0.0069 | 0.8248 |
510
+ | 0.4593 | 1320 | 0.003 | 0.0066 | 0.8233 |
511
+ | 0.4662 | 1340 | 0.0125 | 0.0066 | 0.8245 |
512
+ | 0.4732 | 1360 | 0.0016 | 0.0070 | 0.8281 |
513
+ | 0.4802 | 1380 | 0.0041 | 0.0066 | 0.8418 |
514
+ | 0.4871 | 1400 | 0.0117 | 0.0073 | 0.8361 |
515
+ | 0.4941 | 1420 | 0.0095 | 0.0073 | 0.8337 |
516
+ | 0.5010 | 1440 | 0.0184 | 0.0071 | 0.8282 |
517
+ | 0.5080 | 1460 | 0.0042 | 0.0069 | 0.8259 |
518
+ | 0.5150 | 1480 | 0.0077 | 0.0065 | 0.8235 |
519
+ | 0.5219 | 1500 | 0.0213 | 0.0059 | 0.8209 |
520
+ | 0.5289 | 1520 | 0.0037 | 0.0059 | 0.8277 |
521
+ | 0.5358 | 1540 | 0.0053 | 0.0053 | 0.8186 |
522
+ | 0.5428 | 1560 | 0.0045 | 0.0071 | 0.8238 |
523
+ | 0.5498 | 1580 | 0.0013 | 0.0101 | 0.8257 |
524
+ | 0.5567 | 1600 | 0.017 | 0.0051 | 0.8292 |
525
+ | 0.5637 | 1620 | 0.0053 | 0.0045 | 0.8234 |
526
+ | 0.5706 | 1640 | 0.0077 | 0.0044 | 0.8235 |
527
+ | 0.5776 | 1660 | 0.0135 | 0.0046 | 0.8200 |
528
+ | 0.5846 | 1680 | 0.0013 | 0.0045 | 0.8242 |
529
+ | 0.5915 | 1700 | 0.0067 | 0.0048 | 0.8266 |
530
+ | 0.5985 | 1720 | 0.0154 | 0.0049 | 0.8232 |
531
+ | 0.6054 | 1740 | 0.0037 | 0.0048 | 0.8222 |
532
+ | 0.6124 | 1760 | 0.0012 | 0.0049 | 0.8232 |
533
+ | 0.6193 | 1780 | 0.0112 | 0.0051 | 0.8212 |
534
+ | 0.6263 | 1800 | 0.0173 | 0.0056 | 0.8228 |
535
+ | 0.6333 | 1820 | 0.0044 | 0.0059 | 0.8177 |
536
+ | 0.6402 | 1840 | 0.0193 | 0.0059 | 0.8197 |
537
+ | 0.6472 | 1860 | 0.0028 | 0.0060 | 0.8203 |
538
+ | 0.6541 | 1880 | 0.005 | 0.0054 | 0.8278 |
539
+ | 0.6611 | 1900 | 0.0077 | 0.0049 | 0.8227 |
540
+ | 0.6681 | 1920 | 0.0126 | 0.0040 | 0.8267 |
541
+ | 0.6750 | 1940 | 0.008 | 0.0039 | 0.8258 |
542
+ | 0.6820 | 1960 | 0.0131 | 0.0039 | 0.8251 |
543
+ | 0.6889 | 1980 | 0.0114 | 0.0042 | 0.8310 |
544
+ | 0.6959 | 2000 | 0.0083 | 0.0041 | 0.8314 |
545
+ | 0.7029 | 2020 | 0.006 | 0.0037 | 0.8303 |
546
+ | 0.7098 | 2040 | 0.0048 | 0.0036 | 0.8269 |
547
+ | 0.7168 | 2060 | 0.0165 | 0.0040 | 0.8262 |
548
+ | 0.7237 | 2080 | 0.0093 | 0.0035 | 0.8158 |
549
+ | 0.7307 | 2100 | 0.007 | 0.0031 | 0.8167 |
550
+ | 0.7376 | 2120 | 0.0065 | 0.0030 | 0.8248 |
551
+ | 0.7446 | 2140 | 0.0042 | 0.0029 | 0.8274 |
552
+ | 0.7516 | 2160 | 0.0111 | 0.0026 | 0.8258 |
553
+ | 0.7585 | 2180 | 0.0066 | 0.0028 | 0.8249 |
554
+ | 0.7655 | 2200 | 0.0034 | 0.0034 | 0.8244 |
555
+ | 0.7724 | 2220 | 0.0013 | 0.0033 | 0.8238 |
556
+ | 0.7794 | 2240 | 0.0025 | 0.0034 | 0.8253 |
557
+ | 0.7864 | 2260 | 0.0065 | 0.0034 | 0.8240 |
558
+ | 0.7933 | 2280 | 0.0049 | 0.0035 | 0.8258 |
559
+ | 0.8003 | 2300 | 0.0007 | 0.0035 | 0.8277 |
560
+ | 0.8072 | 2320 | 0.004 | 0.0034 | 0.8298 |
561
+ | 0.8142 | 2340 | 0.0013 | 0.0033 | 0.8293 |
562
+ | 0.8212 | 2360 | 0.0122 | 0.0032 | 0.8300 |
563
+ | 0.8281 | 2380 | 0.0008 | 0.0033 | 0.8285 |
564
+ | 0.8351 | 2400 | 0.0019 | 0.0032 | 0.8266 |
565
+ | 0.8420 | 2420 | 0.0033 | 0.0032 | 0.8266 |
566
+ | 0.8490 | 2440 | 0.0078 | 0.0024 | 0.8284 |
567
+ | 0.8559 | 2460 | 0.0087 | 0.0022 | 0.8272 |
568
+ | 0.8629 | 2480 | 0.003 | 0.0021 | 0.8255 |
569
+ | 0.8699 | 2500 | 0.0039 | 0.0021 | 0.8232 |
570
+ | 0.8768 | 2520 | 0.0054 | 0.0021 | 0.8225 |
571
+ | **0.8838** | **2540** | **0.0015** | **0.0021** | **0.8236** |
572
+ | 0.8907 | 2560 | 0.0043 | 0.0021 | 0.8245 |
573
+ | 0.8977 | 2580 | 0.0083 | 0.0022 | 0.8237 |
574
+ | 0.9047 | 2600 | 0.0029 | 0.0024 | 0.8233 |
575
+ | 0.9116 | 2620 | 0.0095 | 0.0025 | 0.8257 |
576
+ | 0.9186 | 2640 | 0.0013 | 0.0025 | 0.8263 |
577
+ | 0.9255 | 2660 | 0.0025 | 0.0025 | 0.8268 |
578
+ | 0.9325 | 2680 | 0.006 | 0.0025 | 0.8264 |
579
+ | 0.9395 | 2700 | 0.0078 | 0.0026 | 0.8247 |
580
+ | 0.9464 | 2720 | 0.0061 | 0.0025 | 0.8248 |
581
+ | 0.9534 | 2740 | 0.001 | 0.0025 | 0.8238 |
582
+ | 0.9603 | 2760 | 0.0041 | 0.0025 | 0.8233 |
583
+ | 0.9673 | 2780 | 0.0157 | 0.0024 | 0.8249 |
584
+ | 0.9743 | 2800 | 0.0039 | 0.0024 | 0.8248 |
585
+ | 0.9812 | 2820 | 0.0047 | 0.0024 | 0.8242 |
586
+ | 0.9882 | 2840 | 0.0058 | 0.0024 | 0.8243 |
587
+ | 0.9951 | 2860 | 0.0018 | 0.0024 | 0.8242 |
588
+
589
+ * The bold row denotes the saved checkpoint.
590
+ </details>
591
+
592
+ ### Framework Versions
593
+ - Python: 3.10.12
594
+ - Sentence Transformers: 3.4.0
595
+ - Transformers: 4.48.1
596
+ - PyTorch: 2.5.1+cu124
597
+ - Accelerate: 1.3.0
598
+ - Datasets: 3.2.0
599
+ - Tokenizers: 0.21.0
600
+
601
+ ## Citation
602
+
603
+ ### BibTeX
604
+
605
+ #### Sentence Transformers
606
+ ```bibtex
607
+ @inproceedings{reimers-2019-sentence-bert,
608
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
609
+ author = "Reimers, Nils and Gurevych, Iryna",
610
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
611
+ month = "11",
612
+ year = "2019",
613
+ publisher = "Association for Computational Linguistics",
614
+ url = "https://arxiv.org/abs/1908.10084",
615
+ }
616
+ ```
617
+
618
+ #### MultipleNegativesRankingLoss
619
+ ```bibtex
620
+ @misc{henderson2017efficient,
621
+ title={Efficient Natural Language Response Suggestion for Smart Reply},
622
+ author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
623
+ year={2017},
624
+ eprint={1705.00652},
625
+ archivePrefix={arXiv},
626
+ primaryClass={cs.CL}
627
+ }
628
+ ```
629
+
630
+ <!--
631
+ ## Glossary
632
+
633
+ *Clearly define terms in order to be accessible across audiences.*
634
+ -->
635
+
636
+ <!--
637
+ ## Model Card Authors
638
+
639
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
640
+ -->
641
+
642
+ <!--
643
+ ## Model Card Contact
644
+
645
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
646
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-multilingual-miniLM-L12-V2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.48.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 250037
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.0",
4
+ "transformers": "4.48.1",
5
+ "pytorch": "2.5.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f4db58c67240e0c9d52bea87c1fb60edac45b2817fc40a8f2e97f261fb69b3
3
+ size 470637416
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
3
+ size 17082987
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "do_lower_case": true,
48
+ "eos_token": "</s>",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "<mask>",
51
+ "max_length": 128,
52
+ "model_max_length": 128,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "<unk>"
65
+ }
unigram.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
3
+ size 14763260