Add new SentenceTransformer model

1_Pooling/config.json

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

README.md

@@ -0,0 +1,438 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:11347
+- loss:MultipleNegativesRankingLoss
+base_model: vinai/phobert-base
+widget:
+- source_sentence: "Beefsteak 123 la mot dia chi ban banh mi chao, beefsteak cuc ngon\
+    \ tai Can Tho ma ban nen mot gan ghe den. Khong gian quan rong rai, sach se, phuc\
+    \ vu nhanh nhen, gia ca hop ly. Banh mi chao duong Nguyen Van Troi noi tieng ban\
+    \ banh mi thom ngon, chat luong. Banh mi tai day chia ra lam 2 phan: co thit bo\
+    \ ma khong thit bo.\n\nQuan Beefsteak 123 la mot dia diem ly tuong cho nhung nguoi\
+    \ yeu thich thit bo va cac mon an ngon khac. Quan noi tieng voi su ket hop tuyet\
+    \ voi giua thit bo, pate va trung op la. Neu ban muon thu nhung mon khac, quan\
+    \ cung co san xuc xich, ca moi, cha lua va xiu mai. Menu cua quan duoc chia thanh\
+    \ tung phan da duoc ket hop san de ban de dang lua chon. Vi du nhu bo op la pate\
+    \ xuc xich hoac bo op la pate cha lua. Ban cung co the tao ra cac to hop rieng\
+    \ cua rieng minh nhu op la ca moi xiu mai.Mot dieu dac biet khi den quan la khi\
+    \ ban goi mot phan, ban se duoc tang mien phi mot dia xa lach tron. Day la cach\
+    \ hoan hao de ket hop khau vi cua ban voi cac loai rau song tuoi ngon.Voi khong\
+    \ gian thoai mai va phuc vu nhanh chong, quan Beefsteak 123 mang den cho ban trai\
+    \ nghiem am thuc doc dao va ngon mieng. Hay ghe tham quan de thuong thuc nhung\
+    \ mon an tuyet voi nay!\n\nTHONG TIN LIEN HE:\nDia chi: 9B Nguyen Van Troi, Phuong\
+    \ Xuan Khanh, Can Tho\nDien thoai: 0907 713 458\nGio mo cua: 06:00 - 14:00\nGia\
+    \ tham khao: 20.000d - 40.000d\nFanpage: https://www.facebook.com/Beefsteak-123-143170999350605/\n\
+    \n Goi dien"
+  sentences:
+  - Beefsteak 123 - Nguyen Van Troi
+  - Pho Ngon 37
+  - Khong tra no hay chi tien ngay Tet
+- source_sentence: 'KCC - Pho & Com Ga Xoi Mam la quan an duoc nhieu nguoi yeu thich
+    tai so 6 Ton That Thuyet, Nam Tu Liem, Ha Noi. Noi day voi khong gian am cung,
+    rat thich hop cho nhung bua an ben ban be, dong nghiep. Day la quan duoc nhieu
+    thuc khach danh gia cao ca dich vu lan chat luong do an. Den voi KCC - Pho & Com
+    Ga Xoi Mam ngoai pho la mon duoc yeu thich nhat ra, quan con co vo so cac mon
+    an hap dan nhu: com rang dui ga xoi mam, com rang dua bo, com rang cai bo, pho
+    xao bo, com nong dui ga xoi mam, mi xao bo, com nong cai bo, com nong dua bo.
+    Doc va la tu nhung hat com gion rum, cung voi do la huong vi cua nuoc sot dac
+    trung va bi truyen ngam sau vao tan ben trong.
+
+
+    Cac mon nay tuy binh di trong cach che bien nhung mang lai huong vi am thuc manh
+    me, du de lam to mo bat cu thuc khach nao khi thuong thuc. KCC - Pho & Com Ga
+    Xoi Mam cam ket mang den cho nguoi tieu dung nhung san pham ngon an toan, co loi
+    cho suc khoe voi gia rat hop ly. Ban dang o Ton That Thuyet, Ha Noi va dang ban
+    khoan khong biet dia chi an pho nao ngon thi hay ghe ngay quan an KCC nhe!
+
+
+    THONG TIN LIEN HE:  Dia chi:  6 Ton That Thuyet, Nam Tu Liem, Ha Noi Gio mo cua:  06:00
+    - 14:00 | 17:30 - 22:00
+
+    Dat mua ngay'
+  sentences:
+  - Nem Nuong Hai Anh
+  - Ca basa kho thom
+  - KCC - Pho & Com Ga Xoi Mam
+- source_sentence: Banh canh ca loc duoc lam tu bot gao va ca loc. Bot gao sau khi
+    duoc can mong thanh soi vua an thi duoc tha vao noi nuoc luoc Ca loc go lay phan
+    thit, uop chut gia vi cho dam vi. Phan xuong ca khong bi bo di ma duoc giu lai
+    gia nhuyen, loc lay phan nuoc ca roi do vao phan nuoc dung. Mon banh canh ca loc
+    ngon nhat la khi an con nong, vua chan vua hup vua xuyt xoa cai vi cay nong. Neu
+    an trong ngay dong thi qua tuyet voi roi phai khong nao. Mot to banh canh ca loc
+    chi co gia khoang 30.000 dong thoi cac ban nhe.
+  sentences:
+  - Banh canh ca loc
+  - Bun oc, bun oc chan
+  - Nha hang Trung Duong Marina
+- source_sentence: 'Nguyen lieu:Bap chuoi 1 cai Chanh 1 trai Bot chien gion 75 gr
+    Dau an 100 ml Nuoc mam 3 muong canh Bot ngot 1 muong ca phe Tuong ot 1 muong canh
+    Duong 1 muong canh Ot bot 1 muong ca pheCach che bien:So che bap chuoi: Dung tay
+    tach bap chuoi thanh nhung cong nho, sau do ngam bap chuoi vao trong thau nuoc
+    chanh pha loang de giup bap chuoi khong bi tham den. Tiep tuc go bo nhuy trong
+    bap chuoi roi rua sach lai voi nuoc.Nhung bot va chien bap chuoi: Bap chuoi sau
+    khi tach roi va rua sach ban cho bap chuoi ra to, do vao 75gr bot chien gion,
+    dao deu cho bot tham vao bap chuoi. Bac chao len bep cung voi 100ml dau an dun
+    soi (luong dau ngap bap chuoi), sau do cho bap chuoi da ao bot vao chien tren
+    lua vua khoang 5 - 10 phut cho bap chuoi chin vang deu thi vot ra de rao dau.Lam
+    bap chuoi chien nuoc mam: Bac mot cai chao khac cho vao 10ml dau an (tan dung
+    luong dau con du khi chien bap chuoi), roi cho vao 3 muong canh nuoc mam, 1 muong
+    ca phe bot ngot, 1 muong canh tuong ot, 1 muong canh duong, 1 muong ca phe ot
+    bot khuay tan hon hop cho sanh vang lai khoang 3 phut tren lua vua. Cuoi cung
+    ban cho bap chuoi da chien vang vao dao deu them 3 phut roi tat bep.Thanh pham:
+    Bap chuoi gion rum hoa quyen voi vi man man ngot ngot cua nuoc mam, an kem com
+    trang se cuc ki ngon mieng day. Mon an vo cung de lam nay se khien gia dinh ban
+    tam tac khen ngon.'
+  sentences:
+  - Nha Hang Ca Hoi Song Nhi
+  - Com nhoi thit hap ot chuong
+  - Hoa chuoi chien nuoc mam
+- source_sentence: "Noi tieng ve do lau doi va huong vi mon an nay o Ha Noi thi phai\
+    \ ke den hang Banh Duc Nong Thanh Tung. Banh o day hap dan o do deo dai cua bot,\
+    \ thit nam du day va nem nem vua mieng. Khi phuc vu, mon an nong sot toa ra mui\
+    \ huong thom lung tu bot, hanh phi, nuoc mam. Mon banh duc o day duoc chan ngap\
+    \ nuoc mam pha loang vi ngot, hoi man man, co thit bam voi nam meo va rat nhieu\
+    \ hanh kho da phi vang.Mon banh duc o Banh Duc Nong Thanh Tung duoc chan ngap\
+    \ nuoc mam pha loang vi ngot, hoi man man, co thit bam voi nam meo va rat nhieu\
+    \ hanh kho da phi vang. Cach an nay hoi giong voi mon banh gio chan nuoc mam thit\
+    \ bam o quan pho chua Lang Son gan cho Ban Co. La mon qua an nhe nhang, vua du\
+    \ lung lung bung, co ve dan da nen rat nhieu nguoi them them, nho nho. Banh duc\
+    \ nong Ha Noi o day khong bi pha them bot dau xanh nen van giu nguyen duoc huong\
+    \ vi dac trung. Dac biet, phan nhan con duoc tron them mot it cu dau xao tren\
+    \ ngon lua lon nen giu duoc do ngot gion.THONG TIN LIEN HE:Dia chi: 112 Truong\
+    \ Dinh, Quan Hai Ba Trung, Ha NoiGio mo cua: 10:00 - 21:00Dia diem chat luong:\
+    \ 4.7/5 (14 danh gia tren Google)\n Chi duong Danh gia Google"
+  sentences:
+  - Banh Duc
+  - Let's Eat Buffet
+  - Banh bi do
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on vinai/phobert-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [vinai/phobert-base](https://huggingface.co/vinai/phobert-base). 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.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [vinai/phobert-base](https://huggingface.co/vinai/phobert-base) <!-- at revision c1e37c5c86f918761049cef6fa216b4779d0d01d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **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: RobertaModel 
+  (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})
+)
+```
+
+## 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("trongvox/Phobert-Sentence-2")
+# Run inference
+sentences = [
+    'Noi tieng ve do lau doi va huong vi mon an nay o Ha Noi thi phai ke den hang Banh Duc Nong Thanh Tung. Banh o day hap dan o do deo dai cua bot, thit nam du day va nem nem vua mieng. Khi phuc vu, mon an nong sot toa ra mui huong thom lung tu bot, hanh phi, nuoc mam. Mon banh duc o day duoc chan ngap nuoc mam pha loang vi ngot, hoi man man, co thit bam voi nam meo va rat nhieu hanh kho da phi vang.Mon banh duc o Banh Duc Nong Thanh Tung duoc chan ngap nuoc mam pha loang vi ngot, hoi man man, co thit bam voi nam meo va rat nhieu hanh kho da phi vang. Cach an nay hoi giong voi mon banh gio chan nuoc mam thit bam o quan pho chua Lang Son gan cho Ban Co. La mon qua an nhe nhang, vua du lung lung bung, co ve dan da nen rat nhieu nguoi them them, nho nho. Banh duc nong Ha Noi o day khong bi pha them bot dau xanh nen van giu nguyen duoc huong vi dac trung. Dac biet, phan nhan con duoc tron them mot it cu dau xao tren ngon lua lon nen giu duoc do ngot gion.THONG TIN LIEN HE:Dia chi: 112 Truong Dinh, Quan Hai Ba Trung, Ha NoiGio mo cua: 10:00 - 21:00Dia diem chat luong: 4.7/5 (14 danh gia tren Google)\n Chi duong Danh gia Google',
+    'Banh Duc',
+    'Banh bi do',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# 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.*
+-->
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+
+* Size: 11,347 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                           | sentence_1                                                                      |
+  |:--------|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                          |
+  | details | <ul><li>min: 70 tokens</li><li>mean: 127.61 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 7.9 tokens</li><li>max: 20 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | sentence_1                      |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>Nhung cu ca rot tuoi ngon duoc tam uop mot lop gia vi chua chua, ngot ngot va dem nuong chung voi toi thom lung tao nen huong vi hap dan den kho long cuong lai, vi ngot tu nhien kich thich vi giac cua nguoi thuong thuc lam day. Ban co the lam mon ca rot nuong toi nay de an cung thit nuong hay dung lam mon an kem trong bua an rat tuyet nha.Cach che bien: Ban chi can mo lo nuong o 190 do C truoc 10 phut. Trong dau tron deu 1 muong dau olive, 2 muong bo va 2 muong giam Balsamic. Ca rot cat bo phan la xanh, giu nguyen vo, rua that sach, cat lam doi. Cho ca rot vao khay nuong, xep cho deu. Toi lot vo, bao mong. Sau do ruoi hon hop dau olive da chuan bi len ca rot. Sau do cho toi bao mong len cung voi ngo tay, muoi va tieu, tron deu len. Cho khay ca rot vao lo nuong 30 phut la ca rot chin. Lay ra dia va thuong thuc.</code>                                                                                                                                                                                          | <code>Ca rot nuong</code>       |
+  | <code>Banh chung Bo Dau la mot trong nhung mon ngon noi tieng nhat cua Thai Nguyen. Lang banh chung Bo Dau thuoc xa Co Lung, huyen Phu Luong duoc coi la noi luu giu mon banh mang tinh hoa am thuc Viet. "Banh chung luoc nuoc gieng than, thom ngon mui vi co phan troi cho", co le cau ca dao nay da tu lau tro thanh niem tu hao cua nguoi dan noi day - mot trong 5 lang lam banh chung noi tieng nhat mien Bac.<br><br>Banh chung Bo Dau phai duoc lam tu gao nep nuong thom ngon Dinh Hoa, thit lon sach cua nguoi dan toc va la dong rung duoc hai tai Na Ry, Bac Kan. Voi ban tay kheo leo day dan kinh nghiem lanh nghe cho ra nhung chiec banh dep mat. Co le vi the ma huong vi banh chung Bo Dau khong the tron lan voi cac loai khac. Do la thu dac san quanh nam khong chi dip Tet moi co, da keo chan biet bao du khach tu moi mien den thuong thuc. Huong vi cua troi dat, thien nhien va con nguoi giao hoa, hoa quyen va duoc ket tinh thanh thuc qua dac san noi tieng cua manh dat Thai Nguyen - banh chung Bo Dau.</code>             | <code>Banh chung Bo Dau</code>  |
+  | <code>Mi Ramen la mot trong nhung mon an ngon nuc tieng ma nguoi Nhat rat ua chuong va tu hao. Tham chi, nguoi Nhat da mo han mot bao tang mi Ramen voi rat nhieu nhung hien vat trung bay ve lich su ra doi, phat trien cua mon an nay. Phan mi cua Ramen thuong duoc lam tu lua mi, muoi va kansui, co mau vang sam rat hap dan. Linh hon cua mon mi Ramen chac han la phan nuoc dung chu yeu duoc ham tu xuong heo hoac xuong ga trong it nhat 10 tieng tao nen vi ngon ngot, dam da. Va khi thuong thuc, ban se an kem voi thit heo thai lat mong, rong bien, trung, cha ca Nhat, ngo va bap cai de huong vi tro nen hoan hao nhat. Vay con chan chu gi ma khong ghe ngay Nha Hang Tho Tuyet de co ngay mon mi ngon kho cuong nay nao!<br>Nha Hang Tho Tuyet da tro thanh moi ruot cua nhieu thuc khach boi gia rat phai chang, menu khong co qua nhieu mon nhu may cho khac nhung hau nhu thu mon nao cung ngon. Mon Ramen Tho Tuyet Special ngon tuyet voi chac chan ban khong the bo lo. Trong do, an tuong nhat co le chinh la phan nuoc ...</code> | <code>Nha Hang Tho Tuyet</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
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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`: False
+- `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`: False
+- `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
+- `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
+- `dispatch_batches`: None
+- `split_batches`: 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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.7042 | 500  | 0.9125        |
+| 1.4085 | 1000 | 0.2277        |
+| 2.1127 | 1500 | 0.1527        |
+| 2.8169 | 2000 | 0.1009        |
+| 0.7042 | 500  | 0.1098        |
+| 1.4085 | 1000 | 0.0842        |
+| 2.1127 | 1500 | 0.0553        |
+| 2.8169 | 2000 | 0.0356        |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "vinai/phobert-base",
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.1",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a83a0c1ffae201bce06d87e9091367e388d3c812464ccc6cdadb66c5995d68
+size 540015464

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 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}