Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,852 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+language: []
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:76
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: ply C Tris  pH8.0 Dextran Trehalose dNTPS Na2 SO4 Triton X-100
+  sentences:
+  - NE
+  - Assignee
+  - ID  NO
+- source_sentence: Certain  isothermal  amplification  methods  are  able  to amplify
+    a target nucleic  acid from  trace levels to  very high  25 and  detectable  levels  within  a  matter  of  minutes.  Such
+    isothermal  methods,  e.g.,  Nicking  and  Extension Amplifi cation Reaction  (NEAR),  allow
+    users  to  detect  a  particular nucleotide  sequence in trace  amounts,  facilitating
+    point-of care  testing  and  increasing  the  accessibility  and  speed  of diagnostics.
+    Streptococcus pyogenes is  the causative agent of group A streptococcal  (GAS)  infections  such  as  pharyngitis,  impe
+    tigo,  and  life-threatening  necrotizing  fasciitis  and  sepsis. The  most  common  GAS  infection,  pharyngitis,  can  be
+    diagnosed by collecting a throat swab sample from a patient and culturing the
+    sample under conditions that would enable bacterial,  specifically S.  pyogenes,  growth,
+    which takes 2-3 days.  Culturing  S.  pyogenes  is  an  accurate  and  reliable
+    method of diagnosing GAS,  but it  is  slow. A 2-3  day delay in prescribing appropriate  antibiotic
+    treatment can result in unnecessary patient suffering and potentially the onset
+    oflife threatening conditions such as rheumatic fever.  In the recent past, biochemical
+    methods have been developed to detect S. pyogenes,  but these  methods  do  not  provide  the  necessary
+    characteristics  to  be  deployed  in  the  point-of-care  setting, either due  to  a  lack
+    of sensitivity  or time to  result  (speed). Accordingly, a highly sensitive and
+    rapid qualitative assay for the detection and diagnosis of a S.  pyogenes infection
+    is desired.
+  sentences:
+  - ABSTRACT
+  - TACTGTTCCTGTTTGA
+  - BACKGROUND
+- source_sentence: W02010/141940 12/2010 CA (US)
+  sentences:
+  - WO
+  - DESCRIPTION OF  DRAWINGS
+  - SUMMARY
+- source_sentence: 9 6 nucleotide sequence at least 80,  85  or 95%  identity to  SEQ
+  sentences:
+  - '2'
+  - NEAR
+  - Ph.  Dissertation published Jan.  1,  2008.  (Year
+- source_sentence: One potential inhibitor of the NEAR technology is human gDNA.  When  a  throat  swab  sample  is  collected  from  a
+    patient  symptomatic  for  GAS  infection,  it  is  possible  that human gDNA
+    is  also  collected on the  swab  (from immune cells such as white blood cells
+    or from local epithelial cells). In order to  assess the  impact that human gDNA
+    has on the GAS  assay,  a  study  was  performed  using  three  different levels  of
+    GAS  gDNA  (25,  250  and  1000  copies)  in  the presence of 0,  10,  50,  100,  250,  500  or  1000
+    ng  of human gDNA. As  shown in FIG.  6,  the presence of human gDNA does  have  an  impact  on
+    GAS  assay  performance,  and  the impact is  GAS  target concentration dependent.  When
+    there is  a low copy number of target GAS present in the reaction, 10  ng  of
+    human  gDNA  or  more  significantly  inhibits  the assay. At 250 copies  of GAS
+    target,  the impact of 10 ng of 60  human gDNA is  less, and at 1,000 copies of
+    GAS target, the effect of 10 ng of human gDNA on the assay is  significantly less.  In
+    fact,  when  1,000  copies  of target  is  present  in the assay, up to  100 ng
+    of human gDNA can be tolerated, albeit with a slower amplification speed and reduced
+    fluorescence signal.  Testing  of the  501  (IC  only)  mix  showed  a  more robust  response  to  human  gDNA.  When  the  501  mix  was
+    tested in the presence of O copies  of target  GAS  and up  to US  10,329,601  B2
+    23 1,000 ng of human gDNA, the assay still produced a clearly positive signal
+    at 500 ng of human gDNA (even at 1,000 ng of human  gDNA  the  fluorescence  signal  was  still  above
+    background). Other Embodiments It  is  to  be understood  that  while  the  invention
+    has  been described  in  conjunction  with  the  detailed  description 24 thereof,  the  foregoing  description  is  intended  to  illustrate
+    and not limit the scope of the invention, which is  defined by the scope of the
+    appended claims. Other aspects, advantages, and  modifications  are  within  the  scope  of
+    the  following claims.
+  sentences:
+  - '75'
+  - TGTAGCTGACACCACCAAGCTACA
+  - Impact  of Human Genomic  DNA (gDNA)  on GAS Assay
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.875
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29166666666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.875
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8202007889556063
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7604166666666666
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7604166666666666
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.875
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.875
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29166666666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17500000000000002
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.875
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.875
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.810892117584935
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.75
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.75
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.625
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.875
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.875
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.625
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29166666666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17500000000000002
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.625
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.875
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.875
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8057993287946483
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7447916666666666
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7447916666666666
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.75
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.875
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.75
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29166666666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.75
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.875
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8608566009043177
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8166666666666667
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8166666666666667
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.75
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.875
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 1.0
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 1.0
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.75
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29166666666666663
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.2
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.1
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.75
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.875
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 1.0
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 1.0
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8608566009043177
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8166666666666667
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8166666666666667
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("kr-manish/fine-tuned-bge-base-raw_pdf-v1")
+# Run inference
+sentences = [
+    'One potential inhibitor of the NEAR technology is human gDNA.  When  a  throat  swab  sample  is  collected  from  a patient  symptomatic  for  GAS  infection,  it  is  possible  that human gDNA is  also  collected on the  swab  (from immune cells such as white blood cells or from local epithelial cells). In order to  assess the  impact that human gDNA has on the GAS  assay,  a  study  was  performed  using  three  different levels  of GAS  gDNA  (25,  250  and  1000  copies)  in  the presence of 0,  10,  50,  100,  250,  500  or  1000 ng  of human gDNA. As  shown in FIG.  6,  the presence of human gDNA does  have  an  impact  on GAS  assay  performance,  and  the impact is  GAS  target concentration dependent.  When there is  a low copy number of target GAS present in the reaction, 10  ng  of human  gDNA  or  more  significantly  inhibits  the assay. At 250 copies  of GAS target,  the impact of 10 ng of 60  human gDNA is  less, and at 1,000 copies of GAS target, the effect of 10 ng of human gDNA on the assay is  significantly less.  In fact,  when  1,000  copies  of target  is  present  in the assay, up to  100 ng of human gDNA can be tolerated, albeit with a slower amplification speed and reduced fluorescence signal.  Testing  of the  501  (IC  only)  mix  showed  a  more robust  response  to  human  gDNA.  When  the  501  mix  was tested in the presence of O copies  of target  GAS  and up  to US  10,329,601  B2 23 1,000 ng of human gDNA, the assay still produced a clearly positive signal at 500 ng of human gDNA (even at 1,000 ng of human  gDNA  the  fluorescence  signal  was  still  above background). Other Embodiments It  is  to  be understood  that  while  the  invention has  been described  in  conjunction  with  the  detailed  description 24 thereof,  the  foregoing  description  is  intended  to  illustrate and not limit the scope of the invention, which is  defined by the scope of the appended claims. Other aspects, advantages, and  modifications  are  within  the  scope  of the  following claims.',
+    'Impact  of Human Genomic  DNA (gDNA)  on GAS Assay',
+    'TGTAGCTGACACCACCAAGCTACA',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.625      |
+| cosine_accuracy@3   | 0.875      |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.625      |
+| cosine_precision@3  | 0.2917     |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.625      |
+| cosine_recall@3     | 0.875      |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8202     |
+| cosine_mrr@10       | 0.7604     |
+| **cosine_map@100**  | **0.7604** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value    |
+|:--------------------|:---------|
+| cosine_accuracy@1   | 0.625    |
+| cosine_accuracy@3   | 0.875    |
+| cosine_accuracy@5   | 0.875    |
+| cosine_accuracy@10  | 1.0      |
+| cosine_precision@1  | 0.625    |
+| cosine_precision@3  | 0.2917   |
+| cosine_precision@5  | 0.175    |
+| cosine_precision@10 | 0.1      |
+| cosine_recall@1     | 0.625    |
+| cosine_recall@3     | 0.875    |
+| cosine_recall@5     | 0.875    |
+| cosine_recall@10    | 1.0      |
+| cosine_ndcg@10      | 0.8109   |
+| cosine_mrr@10       | 0.75     |
+| **cosine_map@100**  | **0.75** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.625      |
+| cosine_accuracy@3   | 0.875      |
+| cosine_accuracy@5   | 0.875      |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.625      |
+| cosine_precision@3  | 0.2917     |
+| cosine_precision@5  | 0.175      |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.625      |
+| cosine_recall@3     | 0.875      |
+| cosine_recall@5     | 0.875      |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8058     |
+| cosine_mrr@10       | 0.7448     |
+| **cosine_map@100**  | **0.7448** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 0.875      |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.2917     |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 0.875      |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8609     |
+| cosine_mrr@10       | 0.8167     |
+| **cosine_map@100**  | **0.8167** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.75       |
+| cosine_accuracy@3   | 0.875      |
+| cosine_accuracy@5   | 1.0        |
+| cosine_accuracy@10  | 1.0        |
+| cosine_precision@1  | 0.75       |
+| cosine_precision@3  | 0.2917     |
+| cosine_precision@5  | 0.2        |
+| cosine_precision@10 | 0.1        |
+| cosine_recall@1     | 0.75       |
+| cosine_recall@3     | 0.875      |
+| cosine_recall@5     | 1.0        |
+| cosine_recall@10    | 1.0        |
+| cosine_ndcg@10      | 0.8609     |
+| cosine_mrr@10       | 0.8167     |
+| **cosine_map@100**  | **0.8167** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 76 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                            | anchor                                                                           |
+  |:--------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                           |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 148.89 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 6.54 tokens</li><li>max: 18 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | anchor                                                          |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------|
+  | <code>1  (AGACTCCATATGGAGTCTAGC CAAACAGGAACA);  a  reverse  template  comprising  a nucleotide  sequence having at  least 80,  85  or 95%  identity  55 (CGACTCCATATGGAGTC to GAAAGCAATCTGAGGA);  and  a  probe  oligonucleotide comprising  a  nucleotide  sequence  at  least  80,  85  or  95%</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | <code>to  SEQ  ID  NO</code>                                    |
+  | <code>One potential inhibitor of the NEAR technology is human gDNA.  When  a  throat  swab  sample  is  collected  from  a patient  symptomatic  for  GAS  infection,  it  is  possible  that human gDNA is  also  collected on the  swab  (from immune cells such as white blood cells or from local epithelial cells). In order to  assess the  impact that human gDNA has on the GAS  assay,  a  study  was  performed  using  three  different levels  of GAS  gDNA  (25,  250  and  1000  copies)  in  the presence of 0,  10,  50,  100,  250,  500  or  1000 ng  of human gDNA. As  shown in FIG.  6,  the presence of human gDNA does  have  an  impact  on GAS  assay  performance,  and  the impact is  GAS  target concentration dependent.  When there is  a low copy number of target GAS present in the reaction, 10  ng  of human  gDNA  or  more  significantly  inhibits  the assay. At 250 copies  of GAS target,  the impact of 10 ng of 60  human gDNA is  less, and at 1,000 copies of GAS target, the effect of 10 ng of human gDNA on the assay is  significantly less.  In fact,  when  1,000  copies  of target  is  present  in the assay, up to  100 ng of human gDNA can be tolerated, albeit with a slower amplification speed and reduced fluorescence signal.  Testing  of the  501  (IC  only)  mix  showed  a  more robust  response  to  human  gDNA.  When  the  501  mix  was tested in the presence of O copies  of target  GAS  and up  to US  10,329,601  B2 23 1,000 ng of human gDNA, the assay still produced a clearly positive signal at 500 ng of human gDNA (even at 1,000 ng of human  gDNA  the  fluorescence  signal  was  still  above background). Other Embodiments It  is  to  be understood  that  while  the  invention has  been described  in  conjunction  with  the  detailed  description 24 thereof,  the  foregoing  description  is  intended  to  illustrate and not limit the scope of the invention, which is  defined by the scope of the appended claims. Other aspects, advantages, and  modifications  are  within  the  scope  of the  following claims.</code>                                                                                                                                                                                                                                                                                      | <code>Impact  of Human Genomic  DNA (gDNA)  on GAS Assay</code> |
+  | <code>25C-4x  lyophilization  mix,  single tube assay format;  50C-2x lyophilization mix,  single tube assay  format;  25T-4x  lyophilization  mix,  target  assay only;  50T-2x lyophilization mix,  target assay only;  25I- 4x lyophilization mix, IC assay only; 50I-2x lyophilization mix,  internal  control  (IC)  assay  only. The  GAS  NEAR  assay  can  be  run  on  an  appropriate platform. For example, the GAS NEAR assay can be run on an Al ere i platform (www.alere.com/ww/en/product-details/ alere-i-strep-a.html). AnA!ere i system consists of an instru ment  which  provides  heating,  mixing  and  fluorescence detection with automated result output,  and a set  of dispos ables,  consisting  of the  sample receiver  (where  the elution buffer  is  stored),  a  test  base  ( containing  two  tubes  of lyophilized NEAR reagents) and a transfer device ( designed to  transfer 100 µI  aliquots of eluted sample from the sample receiver  to  each  of the  two  tubes  containing  lyophilized NEAR  reagents  located  in  the  test  base).  Suitable  dispos ables for use with the Alere i GAS NEAR test include those 60  described in,  for example U.S.  application Ser.  No.  13/242, 999,  incorporated herein by reference  in its  entirety. In addition to containing the reagents necessary for driv ing  the  GAS  NEAR  assay,  the  lyophilized  material  also contains the lytic agent for GAS, the protein plyC; therefore, 65  GAS  lysis  does  not  occur until  the  lyophilized  material  is re-suspended.  In some  cases,  the  lyophilized material  does not  contain  a  lytic  agent  for  GAS,  for  example,  in  some US  10,329,601  B2 19 examples,  the  lyophilized  material  does  not  contain  the protein plyC.  The elution buffer was  designed to  allow  for the  rapid  release  of GAS  organisms  from  clinical  sample throat  swabs  as  well  as  to  provide  the  necessary  salts  for driving the NEAR assay (both MgSO4 and (NH4)2SO4), in  5 a  slightly basic environment.  In some examples, the elution buffer also  includes  an anti-microbial  agent or preservative (e.g.,  ProClin®  950). For the present examples, GAS assay was performed as  a two tube assay-a GAS target specific assay in one tube, and an internal control (IC) assay in a second tube (tested side by side  on the Alere  i).</code> | <code>annotated  as  follows</code>                             |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 3e-05
+- `num_train_epochs`: 40
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.2
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+
+#### 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`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 3e-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`: 40
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.2
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `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
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch    | Step   | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:--------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0        | 0      | -             | 0.2103                 | 0.1702                 | 0.1888                 | 0.1783                | 0.1815                 |
+| 1.0      | 1      | -             | 0.2102                 | 0.1702                 | 0.1888                 | 0.1783                | 0.1815                 |
+| 2.0      | 2      | -             | 0.2104                 | 0.1705                 | 0.1890                 | 0.1797                | 0.1815                 |
+| 3.0      | 3      | -             | 0.2841                 | 0.1733                 | 0.2524                 | 0.1997                | 0.2465                 |
+| 4.0      | 5      | -             | 0.3285                 | 0.2747                 | 0.2865                 | 0.3281                | 0.2901                 |
+| 5.0      | 6      | -             | 0.3311                 | 0.3045                 | 0.2996                 | 0.3930                | 0.3001                 |
+| 6.0      | 7      | -             | 0.3948                 | 0.3808                 | 0.3193                 | 0.4576                | 0.3147                 |
+| 7.0      | 9      | -             | 0.5308                 | 0.4366                 | 0.4222                 | 0.5445                | 0.4367                 |
+| 8.0      | 10     | 3.233         | 0.5352                 | 0.5240                 | 0.5224                 | 0.5867                | 0.4591                 |
+| 9.0      | 11     | -             | 0.5438                 | 0.5864                 | 0.5228                 | 0.6519                | 0.6475                 |
+| 10.0     | 13     | -             | 0.6540                 | 0.5906                 | 0.6554                 | 0.6684                | 0.6511                 |
+| 11.0     | 14     | -             | 0.6585                 | 0.6020                 | 0.6684                 | 0.6857                | 0.6621                 |
+| 12.0     | 15     | -             | 0.6632                 | 0.6661                 | 0.6798                 | 0.7063                | 0.6685                 |
+| 13.0     | 17     | -             | 0.7292                 | 0.7210                 | 0.6971                 | 0.7396                | 0.7062                 |
+| 14.0     | 18     | -             | 0.7396                 | 0.7375                 | 0.7229                 | 0.8333                | 0.7068                 |
+| 15.0     | 19     | -             | 0.75                   | 0.7438                 | 0.7021                 | 0.8333                | 0.7083                 |
+| 16.0     | 20     | 1.4113        | 0.7604                 | 0.7292                 | 0.7042                 | 0.8229                | 0.7104                 |
+| 17.0     | 21     | -             | 0.7542                 | 0.7262                 | 0.7095                 | 0.8229                | 0.7158                 |
+| 18.0     | 22     | -             | 0.7438                 | 0.7344                 | 0.7054                 | 0.8167                | 0.7188                 |
+| 19.0     | 23     | -             | 0.8063                 | 0.7344                 | 0.7125                 | 0.8125                | 0.7021                 |
+| 20.0     | 25     | -             | 0.7958                 | 0.7344                 | 0.7262                 | 0.8125                | 0.7333                 |
+| 21.0     | 26     | -             | 0.8021                 | 0.7344                 | 0.7470                 | 0.8095                | 0.7333                 |
+| 22.0     | 27     | -             | 0.8021                 | 0.7344                 | 0.7470                 | 0.8095                | 0.7333                 |
+| 23.0     | 29     | -             | 0.8021                 | 0.7344                 | 0.7470                 | 0.8095                | 0.7438                 |
+| 24.0     | 30     | 0.6643        | 0.8021                 | 0.7448                 | 0.7470                 | 0.8125                | 0.7438                 |
+| 25.0     | 31     | -             | 0.8125                 | 0.7448                 | 0.7470                 | 0.8125                | 0.7604                 |
+| 26.0     | 33     | -             | 0.8125                 | 0.7448                 | 0.75                   | 0.8167                | 0.7604                 |
+| 27.0     | 34     | -             | 0.8125                 | 0.7448                 | 0.75                   | 0.8167                | 0.7604                 |
+| 28.0     | 35     | -             | 0.8125                 | 0.7448                 | 0.75                   | 0.8167                | 0.7604                 |
+| **29.0** | **37** | **-**         | **0.8167**             | **0.7448**             | **0.75**               | **0.8167**            | **0.7604**             |
+| 30.0     | 38     | -             | 0.8167                 | 0.7448                 | 0.75                   | 0.8167                | 0.7604                 |
+| 31.0     | 39     | -             | 0.8167                 | 0.7448                 | 0.75                   | 0.8167                | 0.7604                 |
+| 32.0     | 40     | 0.4648        | 0.8167                 | 0.7448                 | 0.75                   | 0.8167                | 0.7604                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5474f2ec91b59854d751112c7183d66e397a6d6a5fd0c4606f7d84989e8005
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

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

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}