pritamdeka commited on
Commit
17a7d2f
1 Parent(s): 1a9f0d3

Add new SentenceTransformer model.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
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 +1,455 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1
3
+ datasets: []
4
+ language: []
5
+ library_name: sentence-transformers
6
+ metrics:
7
+ - pearson_cosine
8
+ - spearman_cosine
9
+ - pearson_manhattan
10
+ - spearman_manhattan
11
+ - pearson_euclidean
12
+ - spearman_euclidean
13
+ - pearson_dot
14
+ - spearman_dot
15
+ - pearson_max
16
+ - spearman_max
17
+ pipeline_tag: sentence-similarity
18
+ tags:
19
+ - sentence-transformers
20
+ - sentence-similarity
21
+ - feature-extraction
22
+ - generated_from_trainer
23
+ - dataset_size:5749
24
+ - loss:CosineSimilarityLoss
25
+ widget:
26
+ - source_sentence: আমি "... comoving মহাজাগতিক বিশ্ৰাম ফ্ৰেমৰ তুলনাত ... সিংহ নক্ষত্ৰমণ্ডলৰ
27
+ ফালে কিছু 371 কিলোমিটাৰ প্ৰতি ছেকেণ্ডত" আগবাঢ়িছো.
28
+ sentences:
29
+ - বাস্কেটবল খেলুৱৈগৰাকীয়ে নিজৰ দলৰ হৈ পইণ্ট লাভ কৰিবলৈ ওলাইছে।
30
+ - আন কোনো বস্তুৰ লগত আপেক্ষিক নহোৱা কোনো ‘ষ্টিল’ নাই।
31
+ - এজনী ছোৱালীয়ে বতাহ বাদ্যযন্ত্ৰ বজায়।
32
+ - source_sentence: চাৰিটা ল’ৰা-ছোৱালীয়ে ভঁৰালৰ জীৱ-জন্তুবোৰলৈ চাই আছে।
33
+ sentences:
34
+ - ডাইনিং টেবুল এখনৰ চাৰিওফালে বৃদ্ধৰ দল এটাই পোজ দিছে।
35
+ - বিকিনি পিন্ধা চাৰিগৰাকী মহিলাই বিলত ভলীবল খেলি আছে।
36
+ - ল’ৰা-ছোৱালীয়ে ভেড়া চাই।
37
+ - source_sentence: ডালত বহি থকা দুটা টান ঈগল।
38
+ sentences:
39
+ - জাতৰ জেব্ৰা ডানিঅ’ অত্যন্ত কঠোৰ মাছ, ইহঁতক হত্যা কৰাটো প্ৰায় কঠিন।
40
+ - এটা ডালত দুটা ঈগল বহি আছে।
41
+ - নূন্যতম মজুৰিৰ আইনসমূহে কম দক্ষ, কম উৎপাদনশীল লোকক আটাইতকৈ বেছি আঘাত দিয়ে।
42
+ - source_sentence: '"মই আচলতে যি বিচাৰিছো সেয়া হৈছে মুছলমান জনসংখ্যাৰ এটা অনুমান..."
43
+ @ThanosK আৰু @T.E.D., এটা সামগ্ৰিক, সাধাৰণ জনসংখ্যাৰ অনুমান f.e.'
44
+ sentences:
45
+ - এগৰাকী মহিলাই সেউজীয়া পিঁয়াজ কাটি আছে।
46
+ - তলত দিয়া কথাখিনি মোৰ কুকুৰ কাণৰ দৰে কপিৰ পৰা লোৱা হৈছে নিউ পেংগুইন এটলাছ অৱ মেডিভেল
47
+ হিষ্ট্ৰীৰ।
48
+ - আমাৰ দৰে সৌৰজগতৰ কোনো তাৰকাৰাজ্যৰ বাহিৰত থকাটো সম্ভৱ হ’ব পাৰে।
49
+ - source_sentence: ইণ্টাৰনেট কেমেৰাৰ জৰিয়তে এগৰাকী ছোৱালীৰ লগত কথা পাতিলে মানুহজনে।
50
+ sentences:
51
+ - গছৰ শাৰী এটাৰ সন্মুখত পথাৰত ভেড়া চৰিছে।
52
+ - এজন মানুহে গীটাৰ বজাই আছে।
53
+ - ৱেবকেমৰ জৰিয়তে এগৰাকী ছোৱালীৰ সৈতে কথা পাতিছে এজন কিশোৰে।
54
+ model-index:
55
+ - name: SentenceTransformer based on pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1
56
+ results:
57
+ - task:
58
+ type: semantic-similarity
59
+ name: Semantic Similarity
60
+ dataset:
61
+ name: pritamdeka/stsb assamese translated dev
62
+ type: pritamdeka/stsb-assamese-translated-dev
63
+ metrics:
64
+ - type: pearson_cosine
65
+ value: 0.8525258323169252
66
+ name: Pearson Cosine
67
+ - type: spearman_cosine
68
+ value: 0.8506593647943235
69
+ name: Spearman Cosine
70
+ - type: pearson_manhattan
71
+ value: 0.8334889460288037
72
+ name: Pearson Manhattan
73
+ - type: spearman_manhattan
74
+ value: 0.843042040822402
75
+ name: Spearman Manhattan
76
+ - type: pearson_euclidean
77
+ value: 0.8351723933495433
78
+ name: Pearson Euclidean
79
+ - type: spearman_euclidean
80
+ value: 0.8450734552112781
81
+ name: Spearman Euclidean
82
+ - type: pearson_dot
83
+ value: 0.8273071926204811
84
+ name: Pearson Dot
85
+ - type: spearman_dot
86
+ value: 0.8277520425148079
87
+ name: Spearman Dot
88
+ - type: pearson_max
89
+ value: 0.8525258323169252
90
+ name: Pearson Max
91
+ - type: spearman_max
92
+ value: 0.8506593647943235
93
+ name: Spearman Max
94
+ - task:
95
+ type: semantic-similarity
96
+ name: Semantic Similarity
97
+ dataset:
98
+ name: pritamdeka/stsb assamese translated test
99
+ type: pritamdeka/stsb-assamese-translated-test
100
+ metrics:
101
+ - type: pearson_cosine
102
+ value: 0.8138083526567048
103
+ name: Pearson Cosine
104
+ - type: spearman_cosine
105
+ value: 0.8119367763029309
106
+ name: Spearman Cosine
107
+ - type: pearson_manhattan
108
+ value: 0.8044112753419641
109
+ name: Pearson Manhattan
110
+ - type: spearman_manhattan
111
+ value: 0.8073243490029997
112
+ name: Spearman Manhattan
113
+ - type: pearson_euclidean
114
+ value: 0.805728285628756
115
+ name: Pearson Euclidean
116
+ - type: spearman_euclidean
117
+ value: 0.8086070843216111
118
+ name: Spearman Euclidean
119
+ - type: pearson_dot
120
+ value: 0.7754575809083841
121
+ name: Pearson Dot
122
+ - type: spearman_dot
123
+ value: 0.7720173359758135
124
+ name: Spearman Dot
125
+ - type: pearson_max
126
+ value: 0.8138083526567048
127
+ name: Pearson Max
128
+ - type: spearman_max
129
+ value: 0.8119367763029309
130
+ name: Spearman Max
131
+ ---
132
+
133
+ # SentenceTransformer based on pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1
134
+
135
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1](https://huggingface.co/pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
136
+
137
+ ## Model Details
138
+
139
+ ### Model Description
140
+ - **Model Type:** Sentence Transformer
141
+ - **Base model:** [pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1](https://huggingface.co/pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1) <!-- at revision ec876d6ec1d2030ad233470e574f1d3d3fe56c74 -->
142
+ - **Maximum Sequence Length:** 512 tokens
143
+ - **Output Dimensionality:** 768 tokens
144
+ - **Similarity Function:** Cosine Similarity
145
+ <!-- - **Training Dataset:** Unknown -->
146
+ <!-- - **Language:** Unknown -->
147
+ <!-- - **License:** Unknown -->
148
+
149
+ ### Model Sources
150
+
151
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
152
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
153
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
154
+
155
+ ### Full Model Architecture
156
+
157
+ ```
158
+ SentenceTransformer(
159
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
160
+ (1): Pooling({'word_embedding_dimension': 768, '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})
161
+ )
162
+ ```
163
+
164
+ ## Usage
165
+
166
+ ### Direct Usage (Sentence Transformers)
167
+
168
+ First install the Sentence Transformers library:
169
+
170
+ ```bash
171
+ pip install -U sentence-transformers
172
+ ```
173
+
174
+ Then you can load this model and run inference.
175
+ ```python
176
+ from sentence_transformers import SentenceTransformer
177
+
178
+ # Download from the 🤗 Hub
179
+ model = SentenceTransformer("pritamdeka/muril-base-cased-assamese-indicxnli-random-negatives-v1-sts")
180
+ # Run inference
181
+ sentences = [
182
+ 'ইণ্টাৰনেট কেমেৰাৰ জৰিয়তে এগৰাকী ছোৱালীৰ লগত কথা পাতিলে মানুহজনে।',
183
+ 'ৱেবকেমৰ জৰিয়তে এগৰাকী ছোৱালীৰ সৈতে কথা পাতিছে এজন কিশোৰে।',
184
+ 'এজন মানুহে গীটাৰ বজাই আছে।',
185
+ ]
186
+ embeddings = model.encode(sentences)
187
+ print(embeddings.shape)
188
+ # [3, 768]
189
+
190
+ # Get the similarity scores for the embeddings
191
+ similarities = model.similarity(embeddings, embeddings)
192
+ print(similarities.shape)
193
+ # [3, 3]
194
+ ```
195
+
196
+ <!--
197
+ ### Direct Usage (Transformers)
198
+
199
+ <details><summary>Click to see the direct usage in Transformers</summary>
200
+
201
+ </details>
202
+ -->
203
+
204
+ <!--
205
+ ### Downstream Usage (Sentence Transformers)
206
+
207
+ You can finetune this model on your own dataset.
208
+
209
+ <details><summary>Click to expand</summary>
210
+
211
+ </details>
212
+ -->
213
+
214
+ <!--
215
+ ### Out-of-Scope Use
216
+
217
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
218
+ -->
219
+
220
+ ## Evaluation
221
+
222
+ ### Metrics
223
+
224
+ #### Semantic Similarity
225
+ * Dataset: `pritamdeka/stsb-assamese-translated-dev`
226
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
227
+
228
+ | Metric | Value |
229
+ |:--------------------|:-----------|
230
+ | pearson_cosine | 0.8525 |
231
+ | **spearman_cosine** | **0.8507** |
232
+ | pearson_manhattan | 0.8335 |
233
+ | spearman_manhattan | 0.843 |
234
+ | pearson_euclidean | 0.8352 |
235
+ | spearman_euclidean | 0.8451 |
236
+ | pearson_dot | 0.8273 |
237
+ | spearman_dot | 0.8278 |
238
+ | pearson_max | 0.8525 |
239
+ | spearman_max | 0.8507 |
240
+
241
+ #### Semantic Similarity
242
+ * Dataset: `pritamdeka/stsb-assamese-translated-test`
243
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
244
+
245
+ | Metric | Value |
246
+ |:--------------------|:-----------|
247
+ | pearson_cosine | 0.8138 |
248
+ | **spearman_cosine** | **0.8119** |
249
+ | pearson_manhattan | 0.8044 |
250
+ | spearman_manhattan | 0.8073 |
251
+ | pearson_euclidean | 0.8057 |
252
+ | spearman_euclidean | 0.8086 |
253
+ | pearson_dot | 0.7755 |
254
+ | spearman_dot | 0.772 |
255
+ | pearson_max | 0.8138 |
256
+ | spearman_max | 0.8119 |
257
+
258
+ <!--
259
+ ## Bias, Risks and Limitations
260
+
261
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
262
+ -->
263
+
264
+ <!--
265
+ ### Recommendations
266
+
267
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
268
+ -->
269
+
270
+ ## Training Details
271
+
272
+ ### Training Hyperparameters
273
+ #### Non-Default Hyperparameters
274
+
275
+ - `eval_strategy`: steps
276
+ - `per_device_train_batch_size`: 64
277
+ - `per_device_eval_batch_size`: 64
278
+ - `num_train_epochs`: 10
279
+ - `warmup_ratio`: 0.1
280
+ - `fp16`: True
281
+ - `load_best_model_at_end`: True
282
+
283
+ #### All Hyperparameters
284
+ <details><summary>Click to expand</summary>
285
+
286
+ - `overwrite_output_dir`: False
287
+ - `do_predict`: False
288
+ - `eval_strategy`: steps
289
+ - `prediction_loss_only`: True
290
+ - `per_device_train_batch_size`: 64
291
+ - `per_device_eval_batch_size`: 64
292
+ - `per_gpu_train_batch_size`: None
293
+ - `per_gpu_eval_batch_size`: None
294
+ - `gradient_accumulation_steps`: 1
295
+ - `eval_accumulation_steps`: None
296
+ - `learning_rate`: 5e-05
297
+ - `weight_decay`: 0.0
298
+ - `adam_beta1`: 0.9
299
+ - `adam_beta2`: 0.999
300
+ - `adam_epsilon`: 1e-08
301
+ - `max_grad_norm`: 1.0
302
+ - `num_train_epochs`: 10
303
+ - `max_steps`: -1
304
+ - `lr_scheduler_type`: linear
305
+ - `lr_scheduler_kwargs`: {}
306
+ - `warmup_ratio`: 0.1
307
+ - `warmup_steps`: 0
308
+ - `log_level`: passive
309
+ - `log_level_replica`: warning
310
+ - `log_on_each_node`: True
311
+ - `logging_nan_inf_filter`: True
312
+ - `save_safetensors`: True
313
+ - `save_on_each_node`: False
314
+ - `save_only_model`: False
315
+ - `restore_callback_states_from_checkpoint`: False
316
+ - `no_cuda`: False
317
+ - `use_cpu`: False
318
+ - `use_mps_device`: False
319
+ - `seed`: 42
320
+ - `data_seed`: None
321
+ - `jit_mode_eval`: False
322
+ - `use_ipex`: False
323
+ - `bf16`: False
324
+ - `fp16`: True
325
+ - `fp16_opt_level`: O1
326
+ - `half_precision_backend`: auto
327
+ - `bf16_full_eval`: False
328
+ - `fp16_full_eval`: False
329
+ - `tf32`: None
330
+ - `local_rank`: 0
331
+ - `ddp_backend`: None
332
+ - `tpu_num_cores`: None
333
+ - `tpu_metrics_debug`: False
334
+ - `debug`: []
335
+ - `dataloader_drop_last`: False
336
+ - `dataloader_num_workers`: 0
337
+ - `dataloader_prefetch_factor`: None
338
+ - `past_index`: -1
339
+ - `disable_tqdm`: False
340
+ - `remove_unused_columns`: True
341
+ - `label_names`: None
342
+ - `load_best_model_at_end`: True
343
+ - `ignore_data_skip`: False
344
+ - `fsdp`: []
345
+ - `fsdp_min_num_params`: 0
346
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
347
+ - `fsdp_transformer_layer_cls_to_wrap`: None
348
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
349
+ - `deepspeed`: None
350
+ - `label_smoothing_factor`: 0.0
351
+ - `optim`: adamw_torch
352
+ - `optim_args`: None
353
+ - `adafactor`: False
354
+ - `group_by_length`: False
355
+ - `length_column_name`: length
356
+ - `ddp_find_unused_parameters`: None
357
+ - `ddp_bucket_cap_mb`: None
358
+ - `ddp_broadcast_buffers`: False
359
+ - `dataloader_pin_memory`: True
360
+ - `dataloader_persistent_workers`: False
361
+ - `skip_memory_metrics`: True
362
+ - `use_legacy_prediction_loop`: False
363
+ - `push_to_hub`: False
364
+ - `resume_from_checkpoint`: None
365
+ - `hub_model_id`: None
366
+ - `hub_strategy`: every_save
367
+ - `hub_private_repo`: False
368
+ - `hub_always_push`: False
369
+ - `gradient_checkpointing`: False
370
+ - `gradient_checkpointing_kwargs`: None
371
+ - `include_inputs_for_metrics`: False
372
+ - `eval_do_concat_batches`: True
373
+ - `fp16_backend`: auto
374
+ - `push_to_hub_model_id`: None
375
+ - `push_to_hub_organization`: None
376
+ - `mp_parameters`:
377
+ - `auto_find_batch_size`: False
378
+ - `full_determinism`: False
379
+ - `torchdynamo`: None
380
+ - `ray_scope`: last
381
+ - `ddp_timeout`: 1800
382
+ - `torch_compile`: False
383
+ - `torch_compile_backend`: None
384
+ - `torch_compile_mode`: None
385
+ - `dispatch_batches`: None
386
+ - `split_batches`: None
387
+ - `include_tokens_per_second`: False
388
+ - `include_num_input_tokens_seen`: False
389
+ - `neftune_noise_alpha`: None
390
+ - `optim_target_modules`: None
391
+ - `batch_eval_metrics`: False
392
+ - `eval_on_start`: False
393
+ - `batch_sampler`: batch_sampler
394
+ - `multi_dataset_batch_sampler`: proportional
395
+
396
+ </details>
397
+
398
+ ### Training Logs
399
+ | Epoch | Step | Training Loss | loss | pritamdeka/stsb-assamese-translated-dev_spearman_cosine | pritamdeka/stsb-assamese-translated-test_spearman_cosine |
400
+ |:----------:|:-------:|:-------------:|:----------:|:-------------------------------------------------------:|:--------------------------------------------------------:|
401
+ | 1.1111 | 100 | 0.0331 | 0.0259 | 0.8482 | - |
402
+ | **2.2222** | **200** | **0.0176** | **0.0253** | **0.8515** | **-** |
403
+ | 3.3333 | 300 | 0.011 | 0.0253 | 0.8513 | - |
404
+ | 4.4444 | 400 | 0.0066 | 0.0259 | 0.8492 | - |
405
+ | 5.5556 | 500 | 0.0048 | 0.0255 | 0.8511 | - |
406
+ | 6.6667 | 600 | 0.0037 | 0.0256 | 0.8508 | - |
407
+ | 7.7778 | 700 | 0.0033 | 0.0254 | 0.8515 | - |
408
+ | 8.8889 | 800 | 0.0029 | 0.0255 | 0.8512 | - |
409
+ | 10.0 | 900 | 0.0027 | 0.0257 | 0.8507 | 0.8119 |
410
+
411
+ * The bold row denotes the saved checkpoint.
412
+
413
+ ### Framework Versions
414
+ - Python: 3.10.12
415
+ - Sentence Transformers: 3.0.1
416
+ - Transformers: 4.42.4
417
+ - PyTorch: 2.3.1+cu121
418
+ - Accelerate: 0.32.1
419
+ - Datasets: 2.20.0
420
+ - Tokenizers: 0.19.1
421
+
422
+ ## Citation
423
+
424
+ ### BibTeX
425
+
426
+ #### Sentence Transformers
427
+ ```bibtex
428
+ @inproceedings{reimers-2019-sentence-bert,
429
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
430
+ author = "Reimers, Nils and Gurevych, Iryna",
431
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
432
+ month = "11",
433
+ year = "2019",
434
+ publisher = "Association for Computational Linguistics",
435
+ url = "https://arxiv.org/abs/1908.10084",
436
+ }
437
+ ```
438
+
439
+ <!--
440
+ ## Glossary
441
+
442
+ *Clearly define terms in order to be accessible across audiences.*
443
+ -->
444
+
445
+ <!--
446
+ ## Model Card Authors
447
+
448
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
449
+ -->
450
+
451
+ <!--
452
+ ## Model Card Contact
453
+
454
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
455
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output/training_stsbenchmark_pritamdeka-muril-base-cased-assamese-indicxnli-random-negatives-v1-2024-07-17_18-57-25/final",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
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": "4.42.4",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 197285
26
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.42.4",
5
+ "pytorch": "2.3.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd6cb1d692d0c34cc3bf3907a77988d854096788095631d2d852af13ae4fcf12
3
+ size 950247272
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": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "103": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "105": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "lowercase": false,
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": false,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff