Upload README.md with huggingface_hub

README.md

@@ -1,577 +1,201 @@
 ---
 base_model: colorfulscoop/sbert-base-ja
-library_name: sentence-transformers
-metrics:
-- cosine_accuracy
-- cosine_accuracy_threshold
-- cosine_f1
-- cosine_f1_threshold
-- cosine_precision
-- cosine_recall
-- cosine_ap
-- dot_accuracy
-- dot_accuracy_threshold
-- dot_f1
-- dot_f1_threshold
-- dot_precision
-- dot_recall
-- dot_ap
-- manhattan_accuracy
-- manhattan_accuracy_threshold
-- manhattan_f1
-- manhattan_f1_threshold
-- manhattan_precision
-- manhattan_recall
-- manhattan_ap
-- euclidean_accuracy
-- euclidean_accuracy_threshold
-- euclidean_f1
-- euclidean_f1_threshold
-- euclidean_precision
-- euclidean_recall
-- euclidean_ap
-- max_accuracy
-- max_accuracy_threshold
-- max_f1
-- max_f1_threshold
-- max_precision
-- max_recall
-- max_ap
-pipeline_tag: sentence-similarity
-tags:
-- sentence-transformers
-- sentence-similarity
-- feature-extraction
-- generated_from_trainer
-- dataset_size:5330
-- loss:CoSENTLoss
-widget:
-- source_sentence: 家族 は 日陰 の 公園 で 午後 を 楽しんで い ます 。
-  sentences:
-  - 家族 は 公園 で ピクニック を して い ます 。
-  - 人 が 会衆 に 説教 して い ます 。
-  - 青い シャツ を 着た 子供 は フリスビー を 投げ ます 。
-- source_sentence: 雪 が 溶けて 、 小さな 男の子 が 裏庭 で 犬 と 遊んで い ます 。
-  sentences:
-  - 男性 は スポーツ を 見て い ます 。
-  - 女性 は ビーチ サンダル を 運んで い ます 。
-  - 吹雪 の 雲 の 後ろ から 太陽 が 出た 後 、 小さな 男の子 と 彼 の 犬 が 外 で 遊ぶ 。
-- source_sentence: 日焼け した パンツ を 着た 男性 と 、 膝 ブレース を 着た 女性 。
-  sentences:
-  - 二 人 が 踊って い ます 。
-  - バック グラウンド に 空 の フィールド が あり ます 。
-  - ３ 人 の 若い 女の子 が そこ に 向かって いる 噴水 が あり ます 。
-- source_sentence: ３ 人 の 子供 が 映画 を 見て い ます 。
-  sentences:
-  - で歩いて いる 女性 を 見て 食品 ベンダー
-  - スケート ボード に 乗った 男 は 、 歓声 を 上げる 観客 に 手 の 込んだ ジャンプ を し ます 。
-  - 素晴らしい 映画 を 見て いる 人間 。
-- source_sentence: ２ 人 の 消防 士 が 消防 車 に 向かって 歩いて い ます 。
-  sentences:
-  - ２ 人 の 消防 士 が トラック に 行く
-  - 男 は 彼 の ｎｅ の 盗難 を 非難 し ます 。
-  - 岩 だらけ の 海岸 を 歩いて いる と 、 波 を 見て いる 男性 が い ます 。
-model-index:
-- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
-  results:
-  - task:
-      type: binary-classification
-      name: Binary Classification
-    dataset:
-      name: custom arc semantics data jp
-      type: custom-arc-semantics-data-jp
-    metrics:
-    - type: cosine_accuracy
-      value: 0.7196998123827392
-      name: Cosine Accuracy
-    - type: cosine_accuracy_threshold
-      value: 0.955563485622406
-      name: Cosine Accuracy Threshold
-    - type: cosine_f1
-      value: 0.8188111721174504
-      name: Cosine F1
-    - type: cosine_f1_threshold
-      value: 0.9209792017936707
-      name: Cosine F1 Threshold
-    - type: cosine_precision
-      value: 0.7104391052195526
-      name: Cosine Precision
-    - type: cosine_recall
-      value: 0.9661971830985916
-      name: Cosine Recall
-    - type: cosine_ap
-      value: 0.7547086304231496
-      name: Cosine Ap
-    - type: dot_accuracy
-      value: 0.7204502814258912
-      name: Dot Accuracy
-    - type: dot_accuracy_threshold
-      value: 611.2391357421875
-      name: Dot Accuracy Threshold
-    - type: dot_f1
-      value: 0.818549346016647
-      name: Dot F1
-    - type: dot_f1_threshold
-      value: 588.0654296875
-      name: Dot F1 Threshold
-    - type: dot_precision
-      value: 0.7082304526748971
-      name: Dot Precision
-    - type: dot_recall
-      value: 0.9695774647887324
-      name: Dot Recall
-    - type: dot_ap
-      value: 0.7795651338156695
-      name: Dot Ap
-    - type: manhattan_accuracy
-      value: 0.7193245778611632
-      name: Manhattan Accuracy
-    - type: manhattan_accuracy_threshold
-      value: 177.08966064453125
-      name: Manhattan Accuracy Threshold
-    - type: manhattan_f1
-      value: 0.8182469548602818
-      name: Manhattan F1
-    - type: manhattan_f1_threshold
-      value: 223.81216430664062
-      name: Manhattan F1 Threshold
-    - type: manhattan_precision
-      value: 0.7101990049751243
-      name: Manhattan Precision
-    - type: manhattan_recall
-      value: 0.9650704225352112
-      name: Manhattan Recall
-    - type: manhattan_ap
-      value: 0.7546997956004545
-      name: Manhattan Ap
-    - type: euclidean_accuracy
-      value: 0.7196998123827392
-      name: Euclidean Accuracy
-    - type: euclidean_accuracy_threshold
-      value: 7.550699710845947
-      name: Euclidean Accuracy Threshold
-    - type: euclidean_f1
-      value: 0.8188111721174504
-      name: Euclidean F1
-    - type: euclidean_f1_threshold
-      value: 10.068297386169434
-      name: Euclidean F1 Threshold
-    - type: euclidean_precision
-      value: 0.7104391052195526
-      name: Euclidean Precision
-    - type: euclidean_recall
-      value: 0.9661971830985916
-      name: Euclidean Recall
-    - type: euclidean_ap
-      value: 0.7545919416671392
-      name: Euclidean Ap
-    - type: max_accuracy
-      value: 0.7204502814258912
-      name: Max Accuracy
-    - type: max_accuracy_threshold
-      value: 611.2391357421875
-      name: Max Accuracy Threshold
-    - type: max_f1
-      value: 0.8188111721174504
-      name: Max F1
-    - type: max_f1_threshold
-      value: 588.0654296875
-      name: Max F1 Threshold
-    - type: max_precision
-      value: 0.7104391052195526
-      name: Max Precision
-    - type: max_recall
-      value: 0.9695774647887324
-      name: Max Recall
-    - type: max_ap
-      value: 0.7795651338156695
-      name: Max Ap
+language: ja
+license: cc-by-sa-4.0
+model_name: LeoChiuu/sbert-base-ja-arc
 ---
 
-# SentenceTransformer based on colorfulscoop/sbert-base-ja
+# Model Card for LeoChiuu/sbert-base-ja-arc
+
+<!-- Provide a quick summary of what the model is/does. -->
+
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. 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:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
-- **Maximum Sequence Length:** 512 tokens
-- **Output Dimensionality:** 768 tokens
-- **Similarity Function:** Cosine Similarity
-- **Training Dataset:**
-    - csv
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
 
-### Model Sources
+<!-- Provide a longer summary of what this model is. -->
 
-- **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)
+Generates similarity embeddings
 
-### Full Model Architecture
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** ja
+- **License:** cc-by-sa-4.0
+- **Finetuned from model [optional]:** colorfulscoop/sbert-base-ja
 
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (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})
-)
-```
+### Model Sources [optional]
 
-## Usage
+<!-- Provide the basic links for the model. -->
 
-### Direct Usage (Sentence Transformers)
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
 
-First install the Sentence Transformers library:
+## Uses
 
-```bash
-pip install -U sentence-transformers
-```
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-Then you can load this model and run inference.
-```python
-from sentence_transformers import SentenceTransformer
+### Direct Use
 
-# Download from the 🤗 Hub
-model = SentenceTransformer("sentence_transformers_model_id")
-# Run inference
-sentences = [
-    '２ 人 の 消防 士 が 消防 車 に 向かって 歩いて い ます 。',
-    '２ 人 の 消防 士 が トラック に 行く',
-    '岩 だらけ の 海岸 を 歩いて いる と 、 波 を 見て いる 男性 が い ます 。',
-]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 768]
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-# Get the similarity scores for the embeddings
-similarities = model.similarity(embeddings, embeddings)
-print(similarities.shape)
-# [3, 3]
-```
+[More Information Needed]
 
-<!--
-### Direct Usage (Transformers)
+### Downstream Use [optional]
 
-<details><summary>Click to see the direct usage in Transformers</summary>
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
-</details>
--->
+[More Information Needed]
 
-<!--
-### Downstream Usage (Sentence Transformers)
+### Out-of-Scope Use
 
-You can finetune this model on your own dataset.
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-<details><summary>Click to expand</summary>
+[More Information Needed]
 
-</details>
--->
+## Bias, Risks, and Limitations
 
-<!--
-### Out-of-Scope Use
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
+[More Information Needed]
 
-## Evaluation
-
-### Metrics
-
-#### Binary Classification
-* Dataset: `custom-arc-semantics-data-jp`
-* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
-
-| Metric                       | Value      |
-|:-----------------------------|:-----------|
-| cosine_accuracy              | 0.7197     |
-| cosine_accuracy_threshold    | 0.9556     |
-| cosine_f1                    | 0.8188     |
-| cosine_f1_threshold          | 0.921      |
-| cosine_precision             | 0.7104     |
-| cosine_recall                | 0.9662     |
-| cosine_ap                    | 0.7547     |
-| dot_accuracy                 | 0.7205     |
-| dot_accuracy_threshold       | 611.2391   |
-| dot_f1                       | 0.8185     |
-| dot_f1_threshold             | 588.0654   |
-| dot_precision                | 0.7082     |
-| dot_recall                   | 0.9696     |
-| dot_ap                       | 0.7796     |
-| manhattan_accuracy           | 0.7193     |
-| manhattan_accuracy_threshold | 177.0897   |
-| manhattan_f1                 | 0.8182     |
-| manhattan_f1_threshold       | 223.8122   |
-| manhattan_precision          | 0.7102     |
-| manhattan_recall             | 0.9651     |
-| manhattan_ap                 | 0.7547     |
-| euclidean_accuracy           | 0.7197     |
-| euclidean_accuracy_threshold | 7.5507     |
-| euclidean_f1                 | 0.8188     |
-| euclidean_f1_threshold       | 10.0683    |
-| euclidean_precision          | 0.7104     |
-| euclidean_recall             | 0.9662     |
-| euclidean_ap                 | 0.7546     |
-| max_accuracy                 | 0.7205     |
-| max_accuracy_threshold       | 611.2391   |
-| max_f1                       | 0.8188     |
-| max_f1_threshold             | 588.0654   |
-| max_precision                | 0.7104     |
-| max_recall                   | 0.9696     |
-| **max_ap**                   | **0.7796** |
-
-<!--
-## 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.*
--->
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
 
 ## Training Details
 
-### Training Dataset
-
-#### csv
-
-* Dataset: csv
-* Size: 5,330 training samples
-* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | text1                                                                               | text2                                                                             | label                                           |
-  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
-  | type    | string                                                                              | string                                                                            | int                                             |
-  | details | <ul><li>min: 12 tokens</li><li>mean: 35.93 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 22.72 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>0: ~32.50%</li><li>1: ~67.50%</li></ul> |
-* Samples:
-  | text1                                                                         | text2                                                          | label          |
-  |:------------------------------------------------------------------------------|:---------------------------------------------------------------|:---------------|
-  | <code>明るい 茶色 の 犬 は 、 フェンス で 囲ま れた エリア で 赤 茶色 の 犬 と ボール を プレー して い ます 。</code> | <code>犬 は フェンス で 囲ま れた エリア で ボール を プレー し ます</code>             | <code>0</code> |
-  | <code>青い 服 を 着た 人 が バイク に 乗って い ます 。</code>                                   | <code>その 人 は 、 地元 の 大学 で 授業 を 受ける ため に バイク に 乗って い ます 。</code> | <code>1</code> |
-  | <code>真っ白な 女性 が ピンク と 紫 の 花 の バナー の 前 に 買い物 袋 を 持って 立って い ます 。</code>         | <code>女性 は フットボール の 試合 で すべて 赤 を 着て い ます 。</code>              | <code>1</code> |
-* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
-  ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "pairwise_cos_sim"
-  }
-  ```
-
-### Evaluation Dataset
-
-#### csv
-
-* Dataset: csv
-* Size: 5,330 evaluation samples
-* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | text1                                                                               | text2                                                                             | label                                           |
-  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
-  | type    | string                                                                              | string                                                                            | int                                             |
-  | details | <ul><li>min: 11 tokens</li><li>mean: 35.77 tokens</li><li>max: 109 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 22.73 tokens</li><li>max: 67 tokens</li></ul> | <ul><li>0: ~32.60%</li><li>1: ~67.40%</li></ul> |
-* Samples:
-  | text1                                                                                                                             | text2                                            | label          |
-  |:----------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------|:---------------|
-  | <code>眼鏡 を かけた 男 は 、 「 ＦＲＥＥ ＷＯＲＤ 」 と いう 標識 を 持って い ます 。</code>                                                                    | <code>人 は 眼鏡 を 外して い ます 。</code>                 | <code>1</code> |
-  | <code>麦わら 帽子 を かぶった ２ 人 の 男 、 青い シャツ 、 日焼け した 帽子 の 男 、 赤い 格子 縞 の シャツ 、 両方 と も 前 に バスケット を 持って 、 未 舗装 の 道路 の 脇 に 座って い ます 。</code> | <code>帽子 を かぶった ２ 人 の 男 が 道路 の 脇 に 座って いる</code> | <code>0</code> |
-  | <code>傘 を 持って 歩く 女性 。</code>                                                                                                      | <code>女性 が 歩いて い ます 。</code>                     | <code>0</code> |
-* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
-  ```json
-  {
-      "scale": 20.0,
-      "similarity_fct": "pairwise_cos_sim"
-  }
-  ```
-
-### Training Hyperparameters
-#### Non-Default Hyperparameters
-
-- `eval_strategy`: epoch
-- `learning_rate`: 2e-05
-- `num_train_epochs`: 1
-- `warmup_ratio`: 0.4
-- `fp16`: True
-- `batch_sampler`: no_duplicates
-
-#### All Hyperparameters
-<details><summary>Click to expand</summary>
-
-- `overwrite_output_dir`: False
-- `do_predict`: False
-- `eval_strategy`: epoch
-- `prediction_loss_only`: True
-- `per_device_train_batch_size`: 8
-- `per_device_eval_batch_size`: 8
-- `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`: 2e-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`: 1
-- `max_steps`: -1
-- `lr_scheduler_type`: linear
-- `lr_scheduler_kwargs`: {}
-- `warmup_ratio`: 0.4
-- `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`: 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
-- `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
-- `eval_use_gather_object`: False
-- `batch_sampler`: no_duplicates
-- `multi_dataset_batch_sampler`: proportional
-
-</details>
-
-### Training Logs
-| Epoch | Step | Training Loss | loss   | custom-arc-semantics-data-jp_max_ap |
-|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
-| 1.0   | 334  | 3.415         | 2.3727 | 0.7796                              |
-
-
-### Framework Versions
-- Python: 3.10.14
-- Sentence Transformers: 3.1.0
-- Transformers: 4.44.2
-- PyTorch: 2.4.1+cu121
-- Accelerate: 0.34.2
-- Datasets: 2.20.0
-- Tokenizers: 0.19.1
-
-## 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",
-}
-```
-
-#### CoSENTLoss
-```bibtex
-@online{kexuefm-8847,
-    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
-    author={Su Jianlin},
-    year={2022},
-    month={Jan},
-    url={https://kexue.fm/archives/8847},
-}
-```
-
-<!--
-## 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.*
--->
-
-<!--
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
 ## Model Card Contact
 
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+[More Information Needed]