Upload model from local path: models\paraphrase-multilingual-miniLM-L12-v2-finetuned-bps-all

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,473 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:350
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Data pengeluaran bulanan rumah tangga pedesaan untuk konsumsi makanan
+    dan non-makanan per provinsi, tahun berapa saja tersedia?
+  sentences:
+  - Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 (84 x 84)
+  - Persentase RataRata Pengeluaran per Kapita Sebulan Untuk Makanan dan Bukan Makanan
+    di Daerah Perdesaan Menurut Provinsi, 2007-2024
+  - Nilai Impor Jawa Madura Menurut Pelabuhan Impor di Pulau Jawa Madura Tahun 2009
+    - 2013 (Juta US $) 1)
+- source_sentence: Asal impor gula Indonesia periode 2017 hingga 2023
+  sentences:
+  - Banyaknya Anggota Kadinda Menurut Kabupaten/Kota di Provinsi Jawa Tengah, 2019
+  - Impor Gula menurut Negara Asal Utama, 2017-2023
+  - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Kelompok Umur,
+    2023
+- source_sentence: Laju kehilangan hutan Indonesia dalam dan luar kawasan hutan 2013-2022.
+  sentences:
+  - Institusi Pemerintah Neraca Institusi Terintegrasi (Triliun Rupiah), 2016 2023
+  - Angka Deforestasi (Netto) Indonesia di Dalam dan di Luar Kawasan Hutan Tahun 2013-2022
+    (Ha/Th)
+  - Produksi Perkebunan Menurut Kabupaten/Kota dan Jenis Tanaman di Provinsi Jawa
+    Tengah (ton), 2021 dan 2022
+- source_sentence: Kemana saja lada putih Indonesia diekspor pada periode 2012 sampai
+    2023?
+  sentences:
+  - Rata-rata Pendapatan Bersih Pekerja Bebas Menurut Provinsi dan Kelompok Umur,
+    2022-2023
+  - Ekspor Lada Putih menurut Negara Tujuan Utama, 2012-2023
+  - Angka Kelahiran Kasar (Crude Birth Rate) Hasil Long Form SP2020 Menurut Provinsi/Kabupaten/Kota,
+    2020
+- source_sentence: data gaji bersih pegawai per bulan tahun 2023 berdasarkan pendidikan
+    dan jenis pekerjaan utama
+  sentences:
+  - Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Pendidikan Tertinggi
+    yang Ditamatkan dan Jenis Pekerjaan Utama, 2023
+  - Banyaknya Kunjungan Kapal Melalui Pelabuhan Jepara Menurut Jenis Pelayaran Tahun
+    2009 - 2013
+  - Ekspor Sarang Burung menurut Negara Tujuan Utama, 2012-2023
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: bps val mfd all
+      type: bps-val-mfd-all
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9861111111111112
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9861111111111112
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9861111111111112
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9861111111111112
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9861111111111112
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.9351851851851851
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.9055555555555554
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.8333333333333334
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.016151592322246593
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.0425075387306992
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.06836160354671791
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.11202747994449548
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8706665539282586
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9861111111111112
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.44673547368787836
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+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 csv 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.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - csv
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'data gaji bersih pegawai per bulan tahun 2023 berdasarkan pendidikan dan jenis pekerjaan utama',
+    'Rata-rata Upah/Gaji Bersih Sebulan Buruh/Karyawan/Pegawai Menurut Pendidikan Tertinggi yang Ditamatkan dan Jenis Pekerjaan Utama, 2023',
+    'Banyaknya Kunjungan Kapal Melalui Pelabuhan Jepara Menurut Jenis Pelayaran Tahun 2009 - 2013',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `bps-val-mfd-all`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9861     |
+| cosine_accuracy@3   | 0.9861     |
+| cosine_accuracy@5   | 0.9861     |
+| cosine_accuracy@10  | 0.9861     |
+| cosine_precision@1  | 0.9861     |
+| cosine_precision@3  | 0.9352     |
+| cosine_precision@5  | 0.9056     |
+| cosine_precision@10 | 0.8333     |
+| cosine_recall@1     | 0.0162     |
+| cosine_recall@3     | 0.0425     |
+| cosine_recall@5     | 0.0684     |
+| cosine_recall@10    | 0.112      |
+| **cosine_ndcg@10**  | **0.8707** |
+| cosine_mrr@10       | 0.9861     |
+| cosine_map@100      | 0.4467     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### csv
+
+* Dataset: csv
+* Size: 350 training samples
+* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 350 samples:
+  |         | query                                                                             | positive                                                                         | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 16.16 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 23.2 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 27.02 tokens</li><li>max: 59 tokens</li></ul> |
+* Samples:
+  | query                                                                                                         | positive                                                                                            | negative                                                                                                      |
+  |:--------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------|
+  | <code>Bagaimana pengeluaran rumah tangga per orang di Indonesia berubah dari 2010 sampai 2024?</code>         | <code>Distribusi Pembagian Pengeluaran per Kapita dan Indeks Gini, 2010-2024</code>                 | <code>Proyeksi Beban Pencemaran Udara Menurut Industri di Jawa Tengah Tahun 2020 (Ton/Tahun)</code>           |
+  | <code>Data kesenjangan pendapatan di Indonesia tahun 2010-2024: indeks Gini dan pengeluaran rata-rata.</code> | <code>Distribusi Pembagian Pengeluaran per Kapita dan Indeks Gini, 2010-2024</code>                 | <code>Banyaknya Mahasiswa dan Dosen Pada Perguruan Tinggi Agama Islam Swasta di Jawa Tengah, 2018/2019</code> |
+  | <code>Berapa konsumsi makanan pokok per orang per minggu di Indonesia tahun 2007-2024?</code>                 | <code>Rata-Rata Konsumsi per Kapita Seminggu Beberapa Macam Bahan Makanan Penting, 2007-2024</code> | <code>Rekapitulasi Industri Non Formal Yang Baru Menurut Kabupaten/kota 2012</code>                           |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `weight_decay`: 0.01
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | bps-val-mfd-all_cosine_ndcg@10 |
+|:----------:|:------:|:------------------------------:|
+| 0.9091     | 10     | 0.8300                         |
+| **1.8182** | **20** | **0.8736**                     |
+| 2.7273     | 30     | 0.8707                         |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.11
+- Sentence Transformers: 3.4.0
+- Transformers: 4.53.1
+- PyTorch: 2.7.1+cpu
+- Accelerate: 1.8.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    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},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0",
+    "transformers": "4.53.1",
+    "pytorch": "2.7.1+cpu"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befcc36fc7d5417bd784bd3acdee9493f4a75e4f57f46da41930b7186d09a78c
+size 470637416

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a815d88d776679933dd177bf05b8e549b01abede23e0d6669bd39afc3a22dc0
+size 6033

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260