Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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

@@ -1,89 +1,419 @@
 ---
-license: cc-by-4.0
-base_model: hon9kon9ize/bert-large-cantonese
 tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
 - generated_from_trainer
+- dataset_size:5749
+- loss:CosineSimilarityLoss
+base_model: hon9kon9ize/bert-large-cantonese-nli
+widget:
+- source_sentence: 有個男人彈緊豎琴。
+  sentences:
+  - 我鍾意將一心多用諗做快速轉換工作。
+  - 有個女人彈緊結他。
+  - 正如你原先個問題所講：維基百科嗰段嘢無話約瑟夫·P·甘迺迪買咗約翰·F·甘迺迪嘅勝選。
+- source_sentence: 一艘大型白色郵輪浮喺水上。
+  sentences:
+  - 有個女人喺台上唱歌。
+  - 有個男人吹緊笛。
+  - 一艘大型郵輪浮喺水上。
+- source_sentence: 個男人送緊蛋糕。
+  sentences:
+  - 有個女人剝緊蝦。
+  - 有個男人係度調味鵪鶉。
+  - 一架紅色雙層巴士喺一條擠迫嘅街道上。
+- source_sentence: 我哋相對宇宙共同靜止參考系嘅速度係……每秒大約 371 公里，方向係朝住獅子座。」
+  sentences:
+  - 間廳擺咗啲啡色嘅傢俬同埋一台平面電視。
+  - 冇一樣嘢係「靜止」嘅，除非係相對某啲其他物體先至係。
+  - 一個人喺水邊蹓狗。
+- source_sentence: 恆星喺恆星形成區形成，而恆星形成區本身係由分子雲演變而來。
+  sentences:
+  - 一個金毛小朋友喺屋企前面吹緊喇叭表演，佢細佬喺隔離睇緊。
+  - 一架四驅車泥濘路面度行緊。
+  - 「可能喺銀河系以外都存在好似我哋呢個太陽系嘅星系。」
+datasets:
+- hon9kon9ize/yue-stsb
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
 metrics:
-  - pearson_cosine
-  - spearman_cosine
-  - pearson_manhattan
-  - spearman_manhattan
-  - pearson_euclidean
-  - spearman_euclidean
-  - pearson_dot
-  - spearman_dot
-  - pearson_max
-  - spearman_max
+- pearson_cosine
+- spearman_cosine
 model-index:
-  - name: Cantonese Semantic Textual Similarity BERT based on hon9kon9ize/bert-large-cantonese-sts
-    results:
-      - task:
-          type: semantic-similarity
-          name: Semantic Similarity
-        dataset:
-          name: sts dev
-          type: sts-dev
-        metrics:
-          - type: pearson_cosine
-            value: 0.8195601142712411
-          - type: spearman_cosine
-            value: 0.8107244990045813
-          - type: pearson_manhattan
-            value: 0.8227349515965701
-          - type: spearman_manhattan
-            value: 0.8106624105549446
-          - type: pearson_euclidean
-            value: 0.8224444134336916
-          - type: spearman_euclidean
-            value: 0.810580167108645
-          - type: pearson_dot
-            value: 0.8197330940854836
-          - type: spearman_dot
-            value: 0.8107833210821748
+- name: SentenceTransformer based on hon9kon9ize/bert-large-cantonese-nli
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.825800689249711
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8262408727980405
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.7926469146205422
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.7911184368054363
+      name: Spearman Cosine
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# SentenceTransformer based on hon9kon9ize/bert-large-cantonese-nli
 
-# bert-large-cantonese-sts
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [hon9kon9ize/bert-large-cantonese-nli](https://huggingface.co/hon9kon9ize/bert-large-cantonese-nli) on the [yue-stsb](https://huggingface.co/datasets/hon9kon9ize/yue-stsb) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
-This model is a fine-tuned version of [hon9kon9ize/bert-large-cantonese](https://huggingface.co/hon9kon9ize/bert-large-cantonese) on the [hon9kon9ize/yue-sts](https://huggingface.co/datasets/hon9kon9ize/yue-sts) dataset.
+## Model Details
 
-## Model description
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [hon9kon9ize/bert-large-cantonese-nli](https://huggingface.co/hon9kon9ize/bert-large-cantonese-nli) <!-- at revision 140fca4e8ed46ca830b9ee0f9dec91c9c114bd5b -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [yue-stsb](https://huggingface.co/datasets/hon9kon9ize/yue-stsb)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
 
-More information needed
+### Model Sources
 
-## Intended uses & limitations
+- **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)
 
-More information needed
+### Full Model Architecture
 
-## Training and evaluation data
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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})
+)
+```
 
-More information needed
+## Usage
 
-## Training procedure
+### Direct Usage (Sentence Transformers)
 
-### Training hyperparameters
+First install the Sentence Transformers library:
 
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 64
-- total_train_batch_size: 1024
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
-- num_epochs: 10
+```bash
+pip install -U sentence-transformers
+```
 
-### Training results
+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 = [
+    '恆星喺恆星形成區形成，而恆星形成區本身係由分子雲演變而來。',
+    '「可能喺銀河系以外都存在好似我哋呢個太陽系嘅星系。」',
+    '一架四驅車泥濘路面度行緊。',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
 
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
 
-### Framework versions
+<!--
+### Direct Usage (Transformers)
 
-- Transformers 4.43.3
-- Pytorch 2.1.1+cu121
-- Datasets 2.15.0
-- Tokenizers 0.19.1
+<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
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev` and `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-dev    | sts-test   |
+|:--------------------|:-----------|:-----------|
+| pearson_cosine      | 0.8258     | 0.7926     |
+| **spearman_cosine** | **0.8262** | **0.7911** |
+
+<!--
+## 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
+
+#### yue-stsb
+
+* Dataset: [yue-stsb](https://huggingface.co/datasets/hon9kon9ize/yue-stsb) at [40cea5d](https://huggingface.co/datasets/hon9kon9ize/yue-stsb/tree/40cea5d8e9d1aeb1498816d90d1e417bafcc96a8)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 12.24 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 12.21 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                   | sentence2                           | score             |
+  |:----------------------------|:------------------------------------|:------------------|
+  | <code>架飛機正準備起飛。</code>      | <code>一架飛機正準備起飛。</code>             | <code>1.0</code>  |
+  | <code>有個男人吹緊一支好大嘅笛。</code>  | <code>有個男人吹緊笛。</code>               | <code>0.76</code> |
+  | <code>有個男人喺批薩上面灑碎芝士。</code> | <code>有個男人將磨碎嘅芝士灑落一塊未焗嘅批薩上面。</code> | <code>0.76</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### yue-stsb
+
+* Dataset: [yue-stsb](https://huggingface.co/datasets/hon9kon9ize/yue-stsb) at [40cea5d](https://huggingface.co/datasets/hon9kon9ize/yue-stsb/tree/40cea5d8e9d1aeb1498816d90d1e417bafcc96a8)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 19.76 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 19.65 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                    | sentence2                    | score             |
+  |:-----------------------------|:-----------------------------|:------------------|
+  | <code>有個戴住安全帽嘅男人喺度跳舞。</code> | <code>有個戴住安全帽嘅男人喺度跳舞。</code> | <code>1.0</code>  |
+  | <code>一個細路仔騎緊馬。</code>       | <code>個細路仔騎緊匹馬。</code>       | <code>0.95</code> |
+  | <code>有個男人餵老鼠畀條蛇食。</code>    | <code>個男人餵咗隻老鼠畀條蛇食。</code>   | <code>1.0</code>  |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `bf16`: 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`: 128
+- `per_device_eval_batch_size`: 128
+- `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`: 1.0
+- `num_train_epochs`: 4
+- `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`: True
+- `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`: False
+- `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
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|
+| 2.2222 | 100  | 0.0299        | 0.0312          | 0.8262                  | -                        |
+| 4.0    | 180  | -             | -               | -                       | 0.7911                   |
+
+
+### Framework Versions
+- Python: 3.11.2
+- Sentence Transformers: 3.3.1
+- Transformers: 4.46.1
+- PyTorch: 2.4.0+cu121
+- Accelerate: 1.0.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## 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",
+}
+```
+
+<!--
+## 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

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hon9kon9ize/bert-large-cantonese",
+  "_name_or_path": "hon9kon9ize/bert-large-cantonese-nli",
   "architectures": [
     "BertModel"
   ],
@@ -18,8 +18,8 @@
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.46.1",
   "type_vocab_size": 2,
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 21628
 }

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.46.1",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78387fed772b6da97ceb7be0791a2d5c51c59d2586b57c57174ff18f2f08f98
+oid sha256:9c1d5859a25e08b31120af6f1f2ababea81234d1ef546b566846773dc944d964
 size 1304182568

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": 512,
+  "do_lower_case": false
+}

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,