Add new SparseEncoder model

README.md

@@ -0,0 +1,880 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sparse-encoder
+- sparse
+- asymmetric
+- inference-free
+- splade
+- generated_from_trainer
+- dataset_size:99000
+- loss:SpladeLoss
+- loss:SparseMultipleNegativesRankingLoss
+- loss:FlopsLoss
+widget:
+- text: Rollin' (Limp Bizkit song) The music video was filmed atop the South Tower
+    of the former World Trade Center in New York City. The introduction features Ben
+    Stiller and Stephen Dorff mistaking Fred Durst for the valet and giving him the
+    keys to their Bentley Azure. Also making a cameo is break dancer Mr. Wiggles.
+    The rest of the video has several cuts to Durst and his bandmates hanging out
+    of the Bentley as they drive about Manhattan. The song Ben Stiller is playing
+    at the beginning is "My Generation" from the same album. The video also features
+    scenes of Fred Durst with five girls dancing in a room. The video was filmed around
+    the same time as the film Zoolander, which explains Stiller and Dorff's appearance.
+    Fred Durst has a small cameo in that film.
+- text: who played the dj in the movie the warriors
+- text: Lionel Messi Born and raised in central Argentina, Messi was diagnosed with
+    a growth hormone deficiency as a child. At age 13, he relocated to Spain to join
+    Barcelona, who agreed to pay for his medical treatment. After a fast progression
+    through Barcelona's youth academy, Messi made his competitive debut aged 17 in
+    October 2004. Despite being injury-prone during his early career, he established
+    himself as an integral player for the club within the next three years, finishing
+    2007 as a finalist for both the Ballon d'Or and FIFA World Player of the Year
+    award, a feat he repeated the following year. His first uninterrupted campaign
+    came in the 2008–09 season, during which he helped Barcelona achieve the first
+    treble in Spanish football. At 22 years old, Messi won the Ballon d'Or and FIFA
+    World Player of the Year award by record voting margins.
+- text: 'Send In the Clowns "Send In the Clowns" is a song written by Stephen Sondheim
+    for the 1973 musical A Little Night Music, an adaptation of Ingmar Bergman''s
+    film Smiles of a Summer Night. It is a ballad from Act Two, in which the character
+    Desirée reflects on the ironies and disappointments of her life. Among other things,
+    she looks back on an affair years earlier with the lawyer Fredrik, who was deeply
+    in love with her but whose marriage proposals she had rejected. Meeting him after
+    so long, she realizes she is in love with him and finally ready to marry him,
+    but now it is he who rejects her: he is in an unconsummated marriage with a much
+    younger woman. Desirée proposes marriage to rescue him from this situation, but
+    he declines, citing his dedication to his bride. Reacting to his rejection, Desirée
+    sings this song. The song is later reprised as a coda after Fredrik''s young wife
+    runs away with his son, and Fredrik is finally free to accept Desirée''s offer.[1]'
+datasets:
+- sentence-transformers/natural-questions
+pipeline_tag: feature-extraction
+library_name: sentence-transformers
+metrics:
+- dot_accuracy@1
+- dot_accuracy@3
+- dot_accuracy@5
+- dot_accuracy@10
+- dot_precision@1
+- dot_precision@3
+- dot_precision@5
+- dot_precision@10
+- dot_recall@1
+- dot_recall@3
+- dot_recall@5
+- dot_recall@10
+- dot_ndcg@10
+- dot_mrr@10
+- dot_map@100
+- query_active_dims
+- query_sparsity_ratio
+- corpus_active_dims
+- corpus_sparsity_ratio
+co2_eq_emissions:
+  emissions: 0.08091219208784432
+  energy_consumed: 0.03403649566911146
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.1
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: Inference-free SPLADE BERT-tiny trained on Natural-Questions tuples
+  results:
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: NanoMSMARCO
+      type: NanoMSMARCO
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.28
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.48
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.54
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.68
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.28
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.15999999999999998
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.10800000000000003
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.068
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.28
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.48
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.54
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.68
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.4712098455669033
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.4061269841269841
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.42140578268075485
+      name: Dot Map@100
+    - type: query_active_dims
+      value: 7.360000133514404
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.9997588624554906
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 182.14356994628906
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.9940323841836612
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: NanoNFCorpus
+      type: NanoNFCorpus
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.46
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.6
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.64
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.7
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.46
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.38
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.34
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.264
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.04441960931285628
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.07834808274816461
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.11501385338572513
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.13826891393122565
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.3362315857787886
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.5348571428571429
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.1428111004748431
+      name: Dot Map@100
+    - type: query_active_dims
+      value: 5.739999771118164
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.9998119389367958
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 268.686767578125
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.9911969475270912
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-information-retrieval
+      name: Sparse Information Retrieval
+    dataset:
+      name: NanoNQ
+      type: NanoNQ
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.3
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.56
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.7
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.7
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.3
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.18666666666666665
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.14
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.07200000000000001
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.3
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.54
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.66
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.67
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.4962070267718764
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.44433333333333325
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.44473112450804114
+      name: Dot Map@100
+    - type: query_active_dims
+      value: 10.420000076293945
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.999658606903994
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 156.8834228515625
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.9948599887670676
+      name: Corpus Sparsity Ratio
+  - task:
+      type: sparse-nano-beir
+      name: Sparse Nano BEIR
+    dataset:
+      name: NanoBEIR mean
+      type: NanoBEIR_mean
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.3466666666666667
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.5466666666666667
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.6266666666666667
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.6933333333333334
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.3466666666666667
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.24222222222222223
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.19600000000000004
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.13466666666666668
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.20813986977095209
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.36611602758272155
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.43833795112857504
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.4960896379770752
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.4345494860391894
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.4617724867724868
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.33631600255454636
+      name: Dot Map@100
+    - type: query_active_dims
+      value: 7.839999993642171
+      name: Query Active Dims
+    - type: query_sparsity_ratio
+      value: 0.9997431360987601
+      name: Query Sparsity Ratio
+    - type: corpus_active_dims
+      value: 191.99524840418664
+      name: Corpus Active Dims
+    - type: corpus_sparsity_ratio
+      value: 0.993709611152474
+      name: Corpus Sparsity Ratio
+---
+
+# Inference-free SPLADE BERT-tiny trained on Natural-Questions tuples
+
+This is a [Asymmetric Inference-free SPLADE Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model trained on the [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space   and can be used for semantic search and sparse retrieval.
+## Model Details
+
+### Model Description
+- **Model Type:** Asymmetric Inference-free SPLADE Sparse Encoder
+<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 30522 dimensions
+- **Similarity Function:** Dot Product
+- **Training Dataset:**
+    - [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions)
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Documentation:** [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder)
+
+### Full Model Architecture
+
+```
+SparseEncoder(
+  (0): Router(
+    (query_0_IDF): IDF ({'frozen': False}, dim:30522, tokenizer: BertTokenizerFast)
+    (document_0_MLMTransformer): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False}) with MLMTransformer model: BertForMaskedLM 
+    (document_1_SpladePooling): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
+  )
+)
+```
+
+## 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 SparseEncoder
+
+# Download from the 🤗 Hub
+model = SparseEncoder("tomaarsen/inference-free-splade-bert-tiny-nq")
+# Run inference
+sentences = [
+    'is send in the clowns from a musical',
+    'Send In the Clowns "Send In the Clowns" is a song written by Stephen Sondheim for the 1973 musical A Little Night Music, an adaptation of Ingmar Bergman\'s film Smiles of a Summer Night. It is a ballad from Act Two, in which the character Desirée reflects on the ironies and disappointments of her life. Among other things, she looks back on an affair years earlier with the lawyer Fredrik, who was deeply in love with her but whose marriage proposals she had rejected. Meeting him after so long, she realizes she is in love with him and finally ready to marry him, but now it is he who rejects her: he is in an unconsummated marriage with a much younger woman. Desirée proposes marriage to rescue him from this situation, but he declines, citing his dedication to his bride. Reacting to his rejection, Desirée sings this song. The song is later reprised as a coda after Fredrik\'s young wife runs away with his son, and Fredrik is finally free to accept Desirée\'s offer.[1]',
+    'who played the dj in the movie the warriors',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# (3, 30522)
+
+# 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
+
+#### Sparse Information Retrieval
+
+* Datasets: `NanoMSMARCO`, `NanoNFCorpus` and `NanoNQ`
+* Evaluated with [<code>SparseInformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator)
+
+| Metric                | NanoMSMARCO | NanoNFCorpus | NanoNQ     |
+|:----------------------|:------------|:-------------|:-----------|
+| dot_accuracy@1        | 0.28        | 0.46         | 0.3        |
+| dot_accuracy@3        | 0.48        | 0.6          | 0.56       |
+| dot_accuracy@5        | 0.54        | 0.64         | 0.7        |
+| dot_accuracy@10       | 0.68        | 0.7          | 0.7        |
+| dot_precision@1       | 0.28        | 0.46         | 0.3        |
+| dot_precision@3       | 0.16        | 0.38         | 0.1867     |
+| dot_precision@5       | 0.108       | 0.34         | 0.14       |
+| dot_precision@10      | 0.068       | 0.264        | 0.072      |
+| dot_recall@1          | 0.28        | 0.0444       | 0.3        |
+| dot_recall@3          | 0.48        | 0.0783       | 0.54       |
+| dot_recall@5          | 0.54        | 0.115        | 0.66       |
+| dot_recall@10         | 0.68        | 0.1383       | 0.67       |
+| **dot_ndcg@10**       | **0.4712**  | **0.3362**   | **0.4962** |
+| dot_mrr@10            | 0.4061      | 0.5349       | 0.4443     |
+| dot_map@100           | 0.4214      | 0.1428       | 0.4447     |
+| query_active_dims     | 7.36        | 5.74         | 10.42      |
+| query_sparsity_ratio  | 0.9998      | 0.9998       | 0.9997     |
+| corpus_active_dims    | 182.1436    | 268.6868     | 156.8834   |
+| corpus_sparsity_ratio | 0.994       | 0.9912       | 0.9949     |
+
+#### Sparse Nano BEIR
+
+* Dataset: `NanoBEIR_mean`
+* Evaluated with [<code>SparseNanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters:
+  ```json
+  {
+      "dataset_names": [
+          "msmarco",
+          "nfcorpus",
+          "nq"
+      ]
+  }
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| dot_accuracy@1        | 0.3467     |
+| dot_accuracy@3        | 0.5467     |
+| dot_accuracy@5        | 0.6267     |
+| dot_accuracy@10       | 0.6933     |
+| dot_precision@1       | 0.3467     |
+| dot_precision@3       | 0.2422     |
+| dot_precision@5       | 0.196      |
+| dot_precision@10      | 0.1347     |
+| dot_recall@1          | 0.2081     |
+| dot_recall@3          | 0.3661     |
+| dot_recall@5          | 0.4383     |
+| dot_recall@10         | 0.4961     |
+| **dot_ndcg@10**       | **0.4345** |
+| dot_mrr@10            | 0.4618     |
+| dot_map@100           | 0.3363     |
+| query_active_dims     | 7.84       |
+| query_sparsity_ratio  | 0.9997     |
+| corpus_active_dims    | 191.9952   |
+| corpus_sparsity_ratio | 0.9937     |
+
+<!--
+## 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
+
+#### natural-questions
+
+* Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
+* Size: 99,000 training samples
+* Columns: <code>query</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | answer                                                                              |
+  |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                              |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 11.71 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 131.81 tokens</li><li>max: 450 tokens</li></ul> |
+* Samples:
+  | query                                                         | answer                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+  |:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>who played the father in papa don't preach</code>       | <code>Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.</code>                                                                                                                                                                                                                                                                                                                                                     |
+  | <code>where was the location of the battle of hastings</code> | <code>Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory.</code> |
+  | <code>how many puppies can a dog give birth to</code>         | <code>Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22]</code>                                                                                                                                                                                                                                                      |
+* Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters:
+  ```json
+  {
+      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
+      "lambda_corpus": 0.03,
+      "lambda_query": 0
+  }
+  ```
+
+### Evaluation Dataset
+
+#### natural-questions
+
+* Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17)
+* Size: 1,000 evaluation samples
+* Columns: <code>query</code> and <code>answer</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | answer                                                                               |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 11.69 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 134.01 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                                                  | answer                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+  |:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>where is the tiber river located in italy</code> | <code>Tiber The Tiber (/ˈtaɪbər/, Latin: Tiberis,[1] Italian: Tevere [ˈteːvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252 mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709 sq mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks.</code> |
+  | <code>what kind of car does jay gatsby drive</code>    | <code>Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry.</code>                                       |
+  | <code>who sings if i can dream about you</code>        | <code>I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1]</code>                                                                                                                                                                                                                   |
+* Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters:
+  ```json
+  {
+      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
+      "lambda_corpus": 0.03,
+      "lambda_query": 0
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `batch_sampler`: no_duplicates
+- `router_mapping`: ['query', 'document']
+- `learning_rate_mapping`: {'IDF\\.weight': 0.001}
+
+#### 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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 0.1
+- `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`: 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
+- `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`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: ['query', 'document']
+- `learning_rate_mapping`: {'IDF\\.weight': 0.001}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | NanoMSMARCO_dot_ndcg@10 | NanoNFCorpus_dot_ndcg@10 | NanoNQ_dot_ndcg@10 | NanoBEIR_mean_dot_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|:------------------:|:-------------------------:|
+| 0.0129 | 20   | 1.8729        | -               | -                       | -                        | -                  | -                         |
+| 0.0259 | 40   | 4.3293        | -               | -                       | -                        | -                  | -                         |
+| 0.0388 | 60   | 7.3159        | -               | -                       | -                        | -                  | -                         |
+| 0.0517 | 80   | 7.3727        | -               | -                       | -                        | -                  | -                         |
+| 0.0646 | 100  | 5.1717        | -               | -                       | -                        | -                  | -                         |
+| 0.0776 | 120  | 3.5122        | -               | -                       | -                        | -                  | -                         |
+| 0.0905 | 140  | 2.6885        | -               | -                       | -                        | -                  | -                         |
+| 0.1034 | 160  | 2.2643        | -               | -                       | -                        | -                  | -                         |
+| 0.1164 | 180  | 1.9245        | -               | -                       | -                        | -                  | -                         |
+| 0.1293 | 200  | 1.671         | 1.2606          | 0.3849                  | 0.3159                   | 0.3992             | 0.3667                    |
+| 0.1422 | 220  | 1.4991        | -               | -                       | -                        | -                  | -                         |
+| 0.1551 | 240  | 1.3325        | -               | -                       | -                        | -                  | -                         |
+| 0.1681 | 260  | 1.2823        | -               | -                       | -                        | -                  | -                         |
+| 0.1810 | 280  | 1.1572        | -               | -                       | -                        | -                  | -                         |
+| 0.1939 | 300  | 1.0759        | -               | -                       | -                        | -                  | -                         |
+| 0.2069 | 320  | 1.0124        | -               | -                       | -                        | -                  | -                         |
+| 0.2198 | 340  | 0.9672        | -               | -                       | -                        | -                  | -                         |
+| 0.2327 | 360  | 0.9361        | -               | -                       | -                        | -                  | -                         |
+| 0.2456 | 380  | 0.8801        | -               | -                       | -                        | -                  | -                         |
+| 0.2586 | 400  | 0.8114        | 0.7099          | 0.4201                  | 0.3166                   | 0.4655             | 0.4007                    |
+| 0.2715 | 420  | 0.7889        | -               | -                       | -                        | -                  | -                         |
+| 0.2844 | 440  | 0.8081        | -               | -                       | -                        | -                  | -                         |
+| 0.2973 | 460  | 0.7586        | -               | -                       | -                        | -                  | -                         |
+| 0.3103 | 480  | 0.7705        | -               | -                       | -                        | -                  | -                         |
+| 0.3232 | 500  | 0.7696        | -               | -                       | -                        | -                  | -                         |
+| 0.3361 | 520  | 0.7469        | -               | -                       | -                        | -                  | -                         |
+| 0.3491 | 540  | 0.7132        | -               | -                       | -                        | -                  | -                         |
+| 0.3620 | 560  | 0.7656        | -               | -                       | -                        | -                  | -                         |
+| 0.3749 | 580  | 0.6988        | -               | -                       | -                        | -                  | -                         |
+| 0.3878 | 600  | 0.758         | 0.6141          | 0.4342                  | 0.3205                   | 0.4905             | 0.4151                    |
+| 0.4008 | 620  | 0.7029        | -               | -                       | -                        | -                  | -                         |
+| 0.4137 | 640  | 0.6143        | -               | -                       | -                        | -                  | -                         |
+| 0.4266 | 660  | 0.6392        | -               | -                       | -                        | -                  | -                         |
+| 0.4396 | 680  | 0.6761        | -               | -                       | -                        | -                  | -                         |
+| 0.4525 | 700  | 0.658         | -               | -                       | -                        | -                  | -                         |
+| 0.4654 | 720  | 0.5961        | -               | -                       | -                        | -                  | -                         |
+| 0.4783 | 740  | 0.6261        | -               | -                       | -                        | -                  | -                         |
+| 0.4913 | 760  | 0.6035        | -               | -                       | -                        | -                  | -                         |
+| 0.5042 | 780  | 0.5663        | -               | -                       | -                        | -                  | -                         |
+| 0.5171 | 800  | 0.609         | 0.5503          | 0.4427                  | 0.3284                   | 0.4805             | 0.4172                    |
+| 0.5301 | 820  | 0.6068        | -               | -                       | -                        | -                  | -                         |
+| 0.5430 | 840  | 0.5911        | -               | -                       | -                        | -                  | -                         |
+| 0.5559 | 860  | 0.6082        | -               | -                       | -                        | -                  | -                         |
+| 0.5688 | 880  | 0.5738        | -               | -                       | -                        | -                  | -                         |
+| 0.5818 | 900  | 0.5727        | -               | -                       | -                        | -                  | -                         |
+| 0.5947 | 920  | 0.563         | -               | -                       | -                        | -                  | -                         |
+| 0.6076 | 940  | 0.5438        | -               | -                       | -                        | -                  | -                         |
+| 0.6206 | 960  | 0.5583        | -               | -                       | -                        | -                  | -                         |
+| 0.6335 | 980  | 0.5972        | -               | -                       | -                        | -                  | -                         |
+| 0.6464 | 1000 | 0.5212        | 0.5208          | 0.4493                  | 0.3320                   | 0.4957             | 0.4256                    |
+| 0.6593 | 1020 | 0.5487        | -               | -                       | -                        | -                  | -                         |
+| 0.6723 | 1040 | 0.5313        | -               | -                       | -                        | -                  | -                         |
+| 0.6852 | 1060 | 0.5471        | -               | -                       | -                        | -                  | -                         |
+| 0.6981 | 1080 | 0.5754        | -               | -                       | -                        | -                  | -                         |
+| 0.7111 | 1100 | 0.5558        | -               | -                       | -                        | -                  | -                         |
+| 0.7240 | 1120 | 0.5334        | -               | -                       | -                        | -                  | -                         |
+| 0.7369 | 1140 | 0.5589        | -               | -                       | -                        | -                  | -                         |
+| 0.7498 | 1160 | 0.5341        | -               | -                       | -                        | -                  | -                         |
+| 0.7628 | 1180 | 0.5516        | -               | -                       | -                        | -                  | -                         |
+| 0.7757 | 1200 | 0.558         | 0.5028          | 0.4633                  | 0.3320                   | 0.4983             | 0.4312                    |
+| 0.7886 | 1220 | 0.5373        | -               | -                       | -                        | -                  | -                         |
+| 0.8016 | 1240 | 0.5483        | -               | -                       | -                        | -                  | -                         |
+| 0.8145 | 1260 | 0.5265        | -               | -                       | -                        | -                  | -                         |
+| 0.8274 | 1280 | 0.543         | -               | -                       | -                        | -                  | -                         |
+| 0.8403 | 1300 | 0.5616        | -               | -                       | -                        | -                  | -                         |
+| 0.8533 | 1320 | 0.5377        | -               | -                       | -                        | -                  | -                         |
+| 0.8662 | 1340 | 0.5295        | -               | -                       | -                        | -                  | -                         |
+| 0.8791 | 1360 | 0.5266        | -               | -                       | -                        | -                  | -                         |
+| 0.8920 | 1380 | 0.5328        | -               | -                       | -                        | -                  | -                         |
+| 0.9050 | 1400 | 0.5187        | 0.4932          | 0.4720                  | 0.3343                   | 0.4972             | 0.4345                    |
+| 0.9179 | 1420 | 0.5219        | -               | -                       | -                        | -                  | -                         |
+| 0.9308 | 1440 | 0.4934        | -               | -                       | -                        | -                  | -                         |
+| 0.9438 | 1460 | 0.5452        | -               | -                       | -                        | -                  | -                         |
+| 0.9567 | 1480 | 0.5216        | -               | -                       | -                        | -                  | -                         |
+| 0.9696 | 1500 | 0.5311        | -               | -                       | -                        | -                  | -                         |
+| 0.9825 | 1520 | 0.5303        | -               | -                       | -                        | -                  | -                         |
+| 0.9955 | 1540 | 0.5299        | -               | -                       | -                        | -                  | -                         |
+| -1     | -1   | -             | -               | 0.4712                  | 0.3362                   | 0.4962             | 0.4345                    |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.034 kWh
+- **Carbon Emitted**: 0.000 kg of CO2
+- **Hours Used**: 0.1 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 4.2.0.dev0
+- Transformers: 4.52.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.1
+- Datasets: 2.21.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### SpladeLoss
+```bibtex
+@misc{formal2022distillationhardnegativesampling,
+      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
+      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
+      year={2022},
+      eprint={2205.04733},
+      archivePrefix={arXiv},
+      primaryClass={cs.IR},
+      url={https://arxiv.org/abs/2205.04733},
+}
+```
+
+#### SparseMultipleNegativesRankingLoss
+```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}
+}
+```
+
+#### FlopsLoss
+```bibtex
+@article{paria2020minimizing,
+    title={Minimizing flops to learn efficient sparse representations},
+    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
+    journal={arXiv preprint arXiv:2004.05665},
+    year={2020}
+    }
+```
+
+<!--
+## 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 +1,19 @@
+{
+  "types": {
+    "query_0_IDF": "sentence_transformers.sparse_encoder.models.IDF",
+    "document_0_MLMTransformer": "sentence_transformers.sparse_encoder.models.MLMTransformer",
+    "document_1_SpladePooling": "sentence_transformers.sparse_encoder.models.SpladePooling"
+  },
+  "structure": {
+    "query": [
+      "query_0_IDF"
+    ],
+    "document": [
+      "document_0_MLMTransformer",
+      "document_1_SpladePooling"
+    ]
+  },
+  "parameters": {
+    "allow_empty_key": true
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SparseEncoder",
+  "__version__": {
+    "sentence_transformers": "4.2.0.dev0",
+    "transformers": "4.52.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "dot"
+}

document_0_MLMTransformer/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

document_0_MLMTransformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84656012ba3a3e310168b0c07bbfc99314d23f184c62f07ab0d7102683c16f12
+size 17671560

document_0_MLMTransformer/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

document_0_MLMTransformer/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

document_0_MLMTransformer/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

document_1_SpladePooling/config.json

@@ -0,0 +1,5 @@
+{
+    "pooling_strategy": "max",
+    "activation_function": "relu",
+    "word_embedding_dimension": 30522
+}

modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Asym"
+  }
+]

query_0_IDF/config.json

@@ -0,0 +1,3 @@
+{
+    "frozen": false
+}

query_0_IDF/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd58ea1d4475f9557440a6feabafd8bfe9dc44e8cc6817ac931b8f8692b12c72
+size 122168

query_0_IDF/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

query_0_IDF/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}