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 +1,938 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+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:4894
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: "This Agreement shall be in force for 24 months after the Effective\
+ \ Date, unless terminated in advance by either Party with thirty (30) days’ written\
+ \ notice. However, the obligation of confidentiality and non-use shall survive\
+ \ the termination or expiration of this Agreement for five (5) years, with exception\
+ \ of trade secrets, which shall be confidential for an unlimited period of time.\
+ \ 4. Return and Destruction of Confidential Information 4.1. Recipient will at\
+ \ the written request of Discloser promptly return or destroy all the Confidential.\n\
+ \ Information and copies (save for one copy for record purposes and securely\
+ \ stored Confidential\n.\n Information that is created during automatic system\
+ \ back-up) to Discloser and immediately cease using\n the same. Recipient\
+ \ shall provide a written certification to Discloser regarding such destruction\
+ \ of\n\nRecipient agrees that Discloser will, in addition to any other remedies\
+ \ available to it at law or equity, be entitled to seek equitable relief, including\
+ \ injunctive relief and specific performance to enforce the terms hereof. 7.3.\
+ \ The terms and conditions herein constitute the entire agreement and understanding\
+ \ of the Parties and shall supersede all communications, negotiations, arrangements\
+ \ and agreements, either oral or written, with respect to the subject matter hereof.\
+ \ No amendments to or modifications of this Agree- ment shall be effective unless\
+ \ reduced to writing and executed by the Parties hereto."
+ sentences:
+ - Absolute Maximum Amount of Liability
+ - Termination for Convenience
+ - Third Party Beneficiary
+- source_sentence: " 19.7 Force Majeure. No liability hereunder shall result to\
+ \ a Party by reason of delay in\n performance caused by force majeure, that is\
+ \ circumstances beyond the reasonable control of\n the Party, including, without\
+ \ limitation, acts of God, fire, flood, war, terrorism, civil unrest, labor.\n\
+ \ unrest, or shortage of or inability to obtain material or equipment.\n.\n \
+ \ 19.8 Section and Paragraph Headings. The section and paragraph headings\
+ \ used in this\n into any interpretation of the Agreement..\n.\n 19.9\n \
+ \ Entire Agreement..The terms and conditions herein constitute the entire\n\
+ \n electronic, oral or written, between the Parties hereto with respect to the\
+ \ subject matter hereof.\n\nLICENSEE shall provide to BCM copies of certificates\
+ \ of insurance demonstrating its additional insured status within [***] days after\
+ \ execution of this Agreement. Upon request by BCM, LICENsEE shall provide to\
+ \ BCM copies of said policies of insurance. It is the intention of the Parties\
+ \ hereto that LiCENsEE shall throughout the Term of this Agreement, continuously\
+ \ and without interruption, maintain in force the required insurance coverages\
+ \ set forth in this -14- ------- of LICENSEE allowing BCM, at its option, to immediately\
+ \ terminate this Agreement. (ili) BcM reserves the right to request additional\
+ \ policies of insurance which are appropriate and reasonable in light of LICENSEE's\
+ \ business operations and availability of coverage..\n 17. WARRANTIES\n 17.1 Each\
+ \ of BCM and LICENsEE represents and warrants to the other that it has full authority\n\
+ \ to execute the license and undertake the obligations therein.\n.\n 17.2 Each\
+ \ of BcM and LICeNsEE represents and warrants to the other that the execution,\n\
+ \ delivery and performance of this Agreement by such Party does not create a breach\
+ \ or default\n under any other agreement to which it is a party or by which it\
+ \ is bound.\n.\n 17.3 bcM represents that Bcm is not aware of any claims pending,\
+ \ asserted, or threatened\n challenging BCM's ownership or control of the Patent\
+ \ Rights.\n"
+ sentences:
+ - Absolute Maximum Amount of Liability
+ - Absolute Maximum Amount of Liability
+ - Force Majeure
+- source_sentence: 'The liability of a party (''Party A") to the other party to this
+ Agreement ("Party B") in tort (including negligence), contract, statute or otherwise
+ for any loss, damage, cost or expense incurred by Party B or a third party in
+ connection with any act or omission by Party A: (a) is limited under or in relation
+ to this Agreement, to USD$500,000 per event or series of related events; and (b)
+ the aggregate liability of Party A to Party B under this Agreement for all such
+ claims by Party B which arise during each 12 month period (commencing on the Start
+ Date) is limited to USD$1,000,000.'
+ sentences:
+ - Absolute Maximum Amount of Liability
+ - Absolute Maximum Amount of Liability
+ - Governing Law
+- source_sentence: " WAIVER OF RIGHTS\n 21.9 A right created\
+ \ by this Agreement may only be waived in writing by the party giving the waiver,\
+ \ and the\n failure to exercise or any delay in exercising\
+ \ a right or remedy provided by this Agreement or by law\n \
+ \ does not waive the right or remedy.\n.\n 21.10 A waiver of a breach\
+ \ of this Agreement does not waive any other breach.\n.\n WARRANTIES\n\
+ \ 21.11 Each party warrants to the other that entering into and performing\
+ \ its obligations under this Agreement\n does not breach any\
+ \ of its contractual obligations to any other person.\n.\n 21.12 \
+ \ You warrant that you have not relied on any representations or warranties by\
+ \ us other than those in this\n Agreement.\n.\n ASSIGNMENT\
+ \ AND AGENCY\n 21.13 A party must not assign its rights or novate\
+ \ its obligations under this Agreement without the other\n \
+ \ party’s prior written consent, which must not be unreasonably withheld.\n.\n\
+ \ 21.14 You may appoint a third party to act on your behalf in relation\
+ \ to this Agreement with our prior written\n consent, which\
+ \ will not be unreasonably withheld. We may withdraw our consent on reasonable\n\
+ \ grounds relating to the conduct of the third party.\n\n \
+ \ 17.2 A party must not disclose the other party’s confidential information\
+ \ to any person except:\n TELSTRA CORPORATION LIMITED (ABN 33 051 775\
+ \ 556) | PAGE 6 OF 12\n\
+ DocuSign Envelope ID: 139730BE-3D26-4345-B2B4-0D606F8D4CEA\n \
+ \ (a) to its employees, professional advisors and our Personnel on a ‘need\
+ \ to know’ basis provided\n those persons first agree\
+ \ to observe the confidentiality of the information;\n (b)\
+ \ with the other party’s prior written consent;\n (c)\
+ \ if required by law, any regulatory authority or stock exchange; or\n \
+ \ (d) if it is in the public domain.\n"
+ sentences:
+ - Assignment
+ - Absolute Maximum Amount of Liability
+ - Third Party Beneficiary
+- source_sentence: "13.2 We accept liability to the extent arising from our negligence,\
+ \ breach of contract or nbn™ Activities: (a) for any personal injury or death\
+ \ to you or your Personnel resulting from the supply of the Services; (b) for\
+ \ any damage to your real or tangible property resulting from the supply of the\
+ \ Services, but we limit our liability to our choice of repairing or replacing\
+ \ the property or paying the cost of repairing or replacing it; or (c) unless\
+ \ clause 13.1 applies, for any other cost or expense you reasonably incur that\
+ \ is a direct result of and flows naturally from, our breach of contract, negligence\
+ \ or nbn™ Activities (but TELSTRA CORPORATION LIMITED (ABN 33 051 775 556) | PAGE\
+ \ 6 OF 25 DocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41 CONFIDENTIAL\
+ \ excluding loss of profits, revenue, business opportunities, likely savings and\
+ \ data), and our liability under this clause is limited for all claims in aggregate\
+ \ to the total amount payable to us under this Agreement during the first year\
+ \ of this Agreement.\n Intellectual Property Rights means\
+ \ all current and future registered rights in respect of copyright,\n \
+ \ designs, circuit layouts, trademarks, trade secrets, domain names,\
+ \ database rights, know-how and\n confidential information\
+ \ and any other intellectual property rights as defined by Article 2 of the World\n\
+ \ Intellectual Property Organisation Convention of July 1967,\
+ \ excluding patents.\n nbn™ means nbn co limited (ABN 86\
+ \ 136 533 741), as that company exists from time to time.\n \
+ \ nbn™ Activities means nbn™ Equipment and nbn™’s negligent or wilful acts\
+ \ or omissions in\n connection with the Services.\n \
+ \ nbn™ Equipment means any equipment that is owned, operated or\
+ \ controlled by nbn™.\n nbn™ Service means a Service that\
+ \ is supplied by or using nbn™ or nbn™ Equipment.\n.\n Our\
+ \ Customer Terms means the Standard Form of Agreement formulated by Telstra for\
+ \ the purposes\n of Part 23 of the Act, as amended by us\
+ \ from time to time in accordance with the Act.\n.\n Personnel\
+ \ means a person’s officers, employees, agents, contractors and sub-contractors\
+ \ and in our\n case includes our Related Bodies Corporate.\n\
+ .\n Planned Maintenance has the meaning in clause 10.1.\n\
+ .\n Related Bodies Corporate has the meaning given under\
+ \ the Corporations Act 2001 (Cth).\n.\n Service means a service\
+ \ under this Agreement set out or referred to in a Service Schedule or an\n \
+ \ agreed statement of work, and includes any individual service\
+ \ or component which constitutes the\n service.\n.\n \
+ \ Service Order Form means an agreed:\n \
+ \ (a) application or order form for a new Service or to vary, reconfigure,\
+ \ renew, reconfigure or\n cancel an existing\
+ \ Service; or\n (b) statement of work between the\
+ \ parties for services under a Service Schedule or otherwise.\n.\n TELSTRA\
+ \ CORPORATION LIMITED (ABN 33 051 775 556) | \
+ \ PAGE 10 OF 25\nDocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41\n\
+ \ \
+ \ CONFIDENTIAL\n \
+ \ Service Schedules means the Schedules attached or added to these Agreement\
+ \ Terms for a\n Service.\n"
+ sentences:
+ - Non Solicitation
+ - Late Payment Charges
+ - Absolute Maximum Amount of Liability
+model-index:
+- name: BGE base En v1.5 version 1
+ results:
+ - task:
+ type: information-retrieval
+ name: Information Retrieval
+ dataset:
+ name: dim 768
+ type: dim_768
+ metrics:
+ - type: cosine_accuracy@1
+ value: 0.006666666666666667
+ name: Cosine Accuracy@1
+ - type: cosine_accuracy@3
+ value: 0.02
+ name: Cosine Accuracy@3
+ - type: cosine_accuracy@5
+ value: 0.027777777777777776
+ name: Cosine Accuracy@5
+ - type: cosine_accuracy@10
+ value: 0.06222222222222222
+ name: Cosine Accuracy@10
+ - type: cosine_precision@1
+ value: 0.006666666666666667
+ name: Cosine Precision@1
+ - type: cosine_precision@3
+ value: 0.006666666666666667
+ name: Cosine Precision@3
+ - type: cosine_precision@5
+ value: 0.005555555555555556
+ name: Cosine Precision@5
+ - type: cosine_precision@10
+ value: 0.006222222222222223
+ name: Cosine Precision@10
+ - type: cosine_recall@1
+ value: 0.006666666666666667
+ name: Cosine Recall@1
+ - type: cosine_recall@3
+ value: 0.02
+ name: Cosine Recall@3
+ - type: cosine_recall@5
+ value: 0.027777777777777776
+ name: Cosine Recall@5
+ - type: cosine_recall@10
+ value: 0.06222222222222222
+ name: Cosine Recall@10
+ - type: cosine_ndcg@10
+ value: 0.028884112095227604
+ name: Cosine Ndcg@10
+ - type: cosine_mrr@10
+ value: 0.019000881834215163
+ name: Cosine Mrr@10
+ - type: cosine_map@100
+ value: 0.03210353835666393
+ name: Cosine Map@100
+ - task:
+ type: information-retrieval
+ name: Information Retrieval
+ dataset:
+ name: dim 512
+ type: dim_512
+ metrics:
+ - type: cosine_accuracy@1
+ value: 0.008888888888888889
+ name: Cosine Accuracy@1
+ - type: cosine_accuracy@3
+ value: 0.022222222222222223
+ name: Cosine Accuracy@3
+ - type: cosine_accuracy@5
+ value: 0.02666666666666667
+ name: Cosine Accuracy@5
+ - type: cosine_accuracy@10
+ value: 0.06555555555555556
+ name: Cosine Accuracy@10
+ - type: cosine_precision@1
+ value: 0.008888888888888889
+ name: Cosine Precision@1
+ - type: cosine_precision@3
+ value: 0.007407407407407407
+ name: Cosine Precision@3
+ - type: cosine_precision@5
+ value: 0.005333333333333333
+ name: Cosine Precision@5
+ - type: cosine_precision@10
+ value: 0.006555555555555556
+ name: Cosine Precision@10
+ - type: cosine_recall@1
+ value: 0.008888888888888889
+ name: Cosine Recall@1
+ - type: cosine_recall@3
+ value: 0.022222222222222223
+ name: Cosine Recall@3
+ - type: cosine_recall@5
+ value: 0.02666666666666667
+ name: Cosine Recall@5
+ - type: cosine_recall@10
+ value: 0.06555555555555556
+ name: Cosine Recall@10
+ - type: cosine_ndcg@10
+ value: 0.030776440813790534
+ name: Cosine Ndcg@10
+ - type: cosine_mrr@10
+ value: 0.020641975308641973
+ name: Cosine Mrr@10
+ - type: cosine_map@100
+ value: 0.033586608519897615
+ name: Cosine Map@100
+ - task:
+ type: information-retrieval
+ name: Information Retrieval
+ dataset:
+ name: dim 256
+ type: dim_256
+ metrics:
+ - type: cosine_accuracy@1
+ value: 0.005555555555555556
+ name: Cosine Accuracy@1
+ - type: cosine_accuracy@3
+ value: 0.016666666666666666
+ name: Cosine Accuracy@3
+ - type: cosine_accuracy@5
+ value: 0.028888888888888888
+ name: Cosine Accuracy@5
+ - type: cosine_accuracy@10
+ value: 0.058888888888888886
+ name: Cosine Accuracy@10
+ - type: cosine_precision@1
+ value: 0.005555555555555556
+ name: Cosine Precision@1
+ - type: cosine_precision@3
+ value: 0.005555555555555556
+ name: Cosine Precision@3
+ - type: cosine_precision@5
+ value: 0.005777777777777778
+ name: Cosine Precision@5
+ - type: cosine_precision@10
+ value: 0.005888888888888889
+ name: Cosine Precision@10
+ - type: cosine_recall@1
+ value: 0.005555555555555556
+ name: Cosine Recall@1
+ - type: cosine_recall@3
+ value: 0.016666666666666666
+ name: Cosine Recall@3
+ - type: cosine_recall@5
+ value: 0.028888888888888888
+ name: Cosine Recall@5
+ - type: cosine_recall@10
+ value: 0.058888888888888886
+ name: Cosine Recall@10
+ - type: cosine_ndcg@10
+ value: 0.02630259734836837
+ name: Cosine Ndcg@10
+ - type: cosine_mrr@10
+ value: 0.016666666666666663
+ name: Cosine Mrr@10
+ - type: cosine_map@100
+ value: 0.03062882281655914
+ name: Cosine Map@100
+ - task:
+ type: information-retrieval
+ name: Information Retrieval
+ dataset:
+ name: dim 128
+ type: dim_128
+ metrics:
+ - type: cosine_accuracy@1
+ value: 0.005555555555555556
+ name: Cosine Accuracy@1
+ - type: cosine_accuracy@3
+ value: 0.01888888888888889
+ name: Cosine Accuracy@3
+ - type: cosine_accuracy@5
+ value: 0.03222222222222222
+ name: Cosine Accuracy@5
+ - type: cosine_accuracy@10
+ value: 0.06111111111111111
+ name: Cosine Accuracy@10
+ - type: cosine_precision@1
+ value: 0.005555555555555556
+ name: Cosine Precision@1
+ - type: cosine_precision@3
+ value: 0.006296296296296296
+ name: Cosine Precision@3
+ - type: cosine_precision@5
+ value: 0.0064444444444444445
+ name: Cosine Precision@5
+ - type: cosine_precision@10
+ value: 0.006111111111111111
+ name: Cosine Precision@10
+ - type: cosine_recall@1
+ value: 0.005555555555555556
+ name: Cosine Recall@1
+ - type: cosine_recall@3
+ value: 0.01888888888888889
+ name: Cosine Recall@3
+ - type: cosine_recall@5
+ value: 0.03222222222222222
+ name: Cosine Recall@5
+ - type: cosine_recall@10
+ value: 0.06111111111111111
+ name: Cosine Recall@10
+ - type: cosine_ndcg@10
+ value: 0.028135521599685714
+ name: Cosine Ndcg@10
+ - type: cosine_mrr@10
+ value: 0.018347883597883592
+ name: Cosine Mrr@10
+ - type: cosine_map@100
+ value: 0.03242988165101947
+ name: Cosine Map@100
+ - task:
+ type: information-retrieval
+ name: Information Retrieval
+ dataset:
+ name: dim 64
+ type: dim_64
+ metrics:
+ - type: cosine_accuracy@1
+ value: 0.008888888888888889
+ name: Cosine Accuracy@1
+ - type: cosine_accuracy@3
+ value: 0.02
+ name: Cosine Accuracy@3
+ - type: cosine_accuracy@5
+ value: 0.03777777777777778
+ name: Cosine Accuracy@5
+ - type: cosine_accuracy@10
+ value: 0.06666666666666667
+ name: Cosine Accuracy@10
+ - type: cosine_precision@1
+ value: 0.008888888888888889
+ name: Cosine Precision@1
+ - type: cosine_precision@3
+ value: 0.006666666666666667
+ name: Cosine Precision@3
+ - type: cosine_precision@5
+ value: 0.007555555555555557
+ name: Cosine Precision@5
+ - type: cosine_precision@10
+ value: 0.006666666666666667
+ name: Cosine Precision@10
+ - type: cosine_recall@1
+ value: 0.008888888888888889
+ name: Cosine Recall@1
+ - type: cosine_recall@3
+ value: 0.02
+ name: Cosine Recall@3
+ - type: cosine_recall@5
+ value: 0.03777777777777778
+ name: Cosine Recall@5
+ - type: cosine_recall@10
+ value: 0.06666666666666667
+ name: Cosine Recall@10
+ - type: cosine_ndcg@10
+ value: 0.031856819250677085
+ name: Cosine Ndcg@10
+ - type: cosine_mrr@10
+ value: 0.02153174603174603
+ name: Cosine Mrr@10
+ - type: cosine_map@100
+ value: 0.035482035303672776
+ name: Cosine Map@100
+---
+
+# BGE base En v1.5 version 1
+
+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:** en
+- **License:** apache-2.0
+
+### 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("RishuD7/bge-base-en-v1.5-41-keys-phase-2-v1")
+# Run inference
+sentences = [
+ '13.2 We accept liability to the extent arising from our negligence, breach of contract or nbn™ Activities: (a) for any personal injury or death to you or your Personnel resulting from the supply of the Services; (b) for any damage to your real or tangible property resulting from the supply of the Services, but we limit our liability to our choice of repairing or replacing the property or paying the cost of repairing or replacing it; or (c) unless clause 13.1 applies, for any other cost or expense you reasonably incur that is a direct result of and flows naturally from, our breach of contract, negligence or nbn™ Activities (but TELSTRA CORPORATION LIMITED (ABN 33 051 775 556) | PAGE 6 OF 25 DocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41 CONFIDENTIAL excluding loss of profits, revenue, business opportunities, likely savings and data), and our liability under this clause is limited for all claims in aggregate to the total amount payable to us under this Agreement during the first year of this Agreement.\n Intellectual Property Rights means all current and future registered rights in respect of copyright,\n designs, circuit layouts, trademarks, trade secrets, domain names, database rights, know-how and\n confidential information and any other intellectual property rights as defined by Article 2 of the World\n Intellectual Property Organisation Convention of July 1967, excluding patents.\n nbn™ means nbn co limited (ABN 86 136 533 741), as that company exists from time to time.\n nbn™ Activities means nbn™ Equipment and nbn™’s negligent or wilful acts or omissions in\n connection with the Services.\n nbn™ Equipment means any equipment that is owned, operated or controlled by nbn™.\n nbn™ Service means a Service that is supplied by or using nbn™ or nbn™ Equipment.\n.\n Our Customer Terms means the Standard Form of Agreement formulated by Telstra for the purposes\n of Part 23 of the Act, as amended by us from time to time in accordance with the Act.\n.\n Personnel means a person’s officers, employees, agents, contractors and sub-contractors and in our\n case includes our Related Bodies Corporate.\n.\n Planned Maintenance has the meaning in clause 10.1.\n.\n Related Bodies Corporate has the meaning given under the Corporations Act 2001 (Cth).\n.\n Service means a service under this Agreement set out or referred to in a Service Schedule or an\n agreed statement of work, and includes any individual service or component which constitutes the\n service.\n.\n Service Order Form means an agreed:\n (a) application or order form for a new Service or to vary, reconfigure, renew, reconfigure or\n cancel an existing Service; or\n (b) statement of work between the parties for services under a Service Schedule or otherwise.\n.\n TELSTRA CORPORATION LIMITED (ABN 33 051 775 556) | PAGE 10 OF 25\nDocuSign Envelope ID: 3EE2487C-8AA0-42DB-8C95-FD658789EC41\n CONFIDENTIAL\n Service Schedules means the Schedules attached or added to these Agreement Terms for a\n Service.\n',
+ 'Absolute Maximum Amount of Liability',
+ 'Late Payment Charges',
+]
+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 | 0.0067 |
+| cosine_accuracy@3 | 0.02 |
+| cosine_accuracy@5 | 0.0278 |
+| cosine_accuracy@10 | 0.0622 |
+| cosine_precision@1 | 0.0067 |
+| cosine_precision@3 | 0.0067 |
+| cosine_precision@5 | 0.0056 |
+| cosine_precision@10 | 0.0062 |
+| cosine_recall@1 | 0.0067 |
+| cosine_recall@3 | 0.02 |
+| cosine_recall@5 | 0.0278 |
+| cosine_recall@10 | 0.0622 |
+| cosine_ndcg@10 | 0.0289 |
+| cosine_mrr@10 | 0.019 |
+| **cosine_map@100** | **0.0321** |
+
+#### 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 | 0.0089 |
+| cosine_accuracy@3 | 0.0222 |
+| cosine_accuracy@5 | 0.0267 |
+| cosine_accuracy@10 | 0.0656 |
+| cosine_precision@1 | 0.0089 |
+| cosine_precision@3 | 0.0074 |
+| cosine_precision@5 | 0.0053 |
+| cosine_precision@10 | 0.0066 |
+| cosine_recall@1 | 0.0089 |
+| cosine_recall@3 | 0.0222 |
+| cosine_recall@5 | 0.0267 |
+| cosine_recall@10 | 0.0656 |
+| cosine_ndcg@10 | 0.0308 |
+| cosine_mrr@10 | 0.0206 |
+| **cosine_map@100** | **0.0336** |
+
+#### 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 | 0.0056 |
+| cosine_accuracy@3 | 0.0167 |
+| cosine_accuracy@5 | 0.0289 |
+| cosine_accuracy@10 | 0.0589 |
+| cosine_precision@1 | 0.0056 |
+| cosine_precision@3 | 0.0056 |
+| cosine_precision@5 | 0.0058 |
+| cosine_precision@10 | 0.0059 |
+| cosine_recall@1 | 0.0056 |
+| cosine_recall@3 | 0.0167 |
+| cosine_recall@5 | 0.0289 |
+| cosine_recall@10 | 0.0589 |
+| cosine_ndcg@10 | 0.0263 |
+| cosine_mrr@10 | 0.0167 |
+| **cosine_map@100** | **0.0306** |
+
+#### 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 | 0.0056 |
+| cosine_accuracy@3 | 0.0189 |
+| cosine_accuracy@5 | 0.0322 |
+| cosine_accuracy@10 | 0.0611 |
+| cosine_precision@1 | 0.0056 |
+| cosine_precision@3 | 0.0063 |
+| cosine_precision@5 | 0.0064 |
+| cosine_precision@10 | 0.0061 |
+| cosine_recall@1 | 0.0056 |
+| cosine_recall@3 | 0.0189 |
+| cosine_recall@5 | 0.0322 |
+| cosine_recall@10 | 0.0611 |
+| cosine_ndcg@10 | 0.0281 |
+| cosine_mrr@10 | 0.0183 |
+| **cosine_map@100** | **0.0324** |
+
+#### 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 | 0.0089 |
+| cosine_accuracy@3 | 0.02 |
+| cosine_accuracy@5 | 0.0378 |
+| cosine_accuracy@10 | 0.0667 |
+| cosine_precision@1 | 0.0089 |
+| cosine_precision@3 | 0.0067 |
+| cosine_precision@5 | 0.0076 |
+| cosine_precision@10 | 0.0067 |
+| cosine_recall@1 | 0.0089 |
+| cosine_recall@3 | 0.02 |
+| cosine_recall@5 | 0.0378 |
+| cosine_recall@10 | 0.0667 |
+| cosine_ndcg@10 | 0.0319 |
+| cosine_mrr@10 | 0.0215 |
+| **cosine_map@100** | **0.0355** |
+
+<!--
+## 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: 4,894 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: 123 tokens</li><li>mean: 353.07 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.37 tokens</li><li>max: 8 tokens</li></ul> |
+* Samples:
+ | positive | anchor |
+ |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------|
+ | <code>In no event shall CBRE, Client, or their respective affiliates incur liability under this agreement or otherwise relating to the Services beyond the insurance proceeds available with respect to the particular matter under the Insurance Policies required to be carried by CBRE AND Client under Article 6 above including, if applicable, proceeds of self-insurance. Each party shall and shall cause its affiliates to look solely to such insurance proceeds (and any such proceeds paid through self-insurance) to satisfy its claims against the released parties and agrees that it shall have no right of recovery beyond such proceeds; provided, however, that if insurance proceeds under such policies are not paid because a party has failed to maintain such policies, comply with policy requirements or, in the case of self-insurance, unreasonably denied a claim, such party shall be liable for the amounts that otherwise would have been payable under such policies had such party maintained such policies, complied with the policy requirement or not unreasonably denied such claim, as the case may be.</code> | <code>Absolute Maximum Amount of Liability</code> |
+ | <code>4. Rent. <br>4.01 From and after the Commencement Date, Tenant shall pay Landlord, without any<br>setoff or deduction, unless expressly set forth in this Lease, all Base Rent and Additional Rent<br>due for the Term (collectively referred to as "Rent"). "Additional Rent" means all sums<br>(exclusive of Base Rent) that Tenant is required to pay Landlord under this Lease. Tenant shall<br>pay and be liable for all rental, sales and use taxes (but excluding income taxes), if any,<br>imposed upon or measured by Rent. Base Rent and recurring monthly charges of Additional<br>Rent shall be due and payable in advance on the first day of each calendar month without<br>notice or demand, provided that the installment of Base Rent attributable to the first (1st) full<br>calendar month of the Term following the Abatement Period shall be due concurrently with the<br>execution of this Lease by Tenant. All other items of Rent shall be due and payable on or<br>before thirty (30) days after billing by Landlord. Rent shall be made payable to the entity, and<br>sent to the address, that Landlord designates and shall be made by good and sufficient check or<br>by other means acceptable to Landlord. Landlord may return to Tenant, at any time within<br>fifteen (15) days after receiving same, any payment of Rent (a) made following any Default<br>(irrespective of whether Landlord has commenced the exercise of any remedy), or (b) that is<br>less than the amount due. Each such returned payment (whether made by returning Tenant's<br>actual check, or by issuing a refund in the event Tenant's check was deposited) shall be<br>conclusively presumed not to have been received or approved by Landlord. If Tenant does not<br>pay any Rent when due hereunder, Tenant shall pay Landlord an administration fee in the<br>amount of five percent (5%) of the past due amount. In addition, past due Rent shall accrue<br>interest at a rate equal to the lesser of (i) twelve percent (12%) per annum or (ii) the maximum<br>legal rate, and Tenant shall pay Landlord a fee for any checks returned by Tenant's bank for<br>any reason. Notwithstanding the foregoing, no such late charge or of interest shall be imposed<br>with respect to the first (1st) late payment in any calendar year, but not with respect to more<br>than three (3) such late payments during the initial Term of this Lease. </code> | <code>Late Payment Charges</code> |
+ | <code>Term This Agreement shall come into force and shall last unlimited from such date. Either Party may however terminate this Agreement at any time by giving upon thirty (30) days' written notice to the other Party. The Receiving Party's obligations contained in this Agreement to keep confidential and restrict use of the Disclosing Party's Confidential Information shall sur- vive for a period of five (5) years from the date of its termination for any reason whatsoever. lX. Contractual penalty<br>For the purposes of this Non-Disclosure Agreement, " Confidential Information" includes all technical and/or commercial and/or financial information in the field designated in section 1., which a contracting Party (hereinafter referred to as the "EQ€i1gPedy") makes, or has made, accessible to the other contracting Party (hereinafter referred to as the ".&eiyi!g Partv") in oral, written, tangible or other form (e.9. disk, data carrier) directly or indirectly, in- cluding but not limited to, drawings, models, components, and other material. Confidential In- formation is to be identified as such. Orally communicated or visually, information having been designated as confidential at the time of disclosure will be confirmed as such in writing by the Disclosing Party within 30 (thirty) days from such disclosure being understood thatlhe ./A information will be considered Confidential Information during that period of 30 (thirty) days. /L t'-4 PF 0233 (September 2016) page 1 of 5 ä =.<br> PFEIFFER F<br>.<br> F<br>.<br> VACUUM<br></code> | <code>Termination for Convenience</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`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 30
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `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`: 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`: 30
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `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`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `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
+- `batch_sampler`: no_duplicates
+- `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 |
+|:----------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 1.0458 | 10 | 11.285 | - | - | - | - | - |
+| 2.0915 | 20 | 2.1467 | - | - | - | - | - |
+| 3.1373 | 30 | 0.2715 | - | - | - | - | - |
+| 4.1830 | 40 | 0.0 | - | - | - | - | - |
+| 5.0196 | 48 | - | 0.0250 | 0.0238 | 0.0258 | 0.0234 | 0.0253 |
+| 1.1830 | 50 | 2.0636 | - | - | - | - | - |
+| 2.2288 | 60 | 5.6313 | - | - | - | - | - |
+| 3.2745 | 70 | 0.3035 | - | - | - | - | - |
+| 4.3203 | 80 | 0.0347 | - | - | - | - | - |
+| 5.3660 | 90 | 0.0 | - | - | - | - | - |
+| 5.9935 | 96 | - | 0.0293 | 0.0297 | 0.0304 | 0.0323 | 0.0297 |
+| 2.3660 | 100 | 2.3496 | - | - | - | - | - |
+| 3.4118 | 110 | 2.3024 | - | - | - | - | - |
+| 4.4575 | 120 | 0.0451 | - | - | - | - | - |
+| 5.5033 | 130 | 0.0021 | - | - | - | - | - |
+| 6.5490 | 140 | 0.0 | - | - | - | - | - |
+| **6.9673** | **144** | **-** | **0.0318** | **0.0308** | **0.0308** | **0.031** | **0.031** |
+| 3.5490 | 150 | 2.6928 | - | - | - | - | - |
+| 4.5948 | 160 | 1.0232 | - | - | - | - | - |
+| 5.6405 | 170 | 0.0082 | - | - | - | - | - |
+| 6.6863 | 180 | 0.0 | - | - | - | - | - |
+| 7.7320 | 190 | 0.0 | - | - | - | - | - |
+| 8.0458 | 193 | - | 0.0331 | 0.0319 | 0.0333 | 0.0315 | 0.0335 |
+| 4.7320 | 200 | 2.635 | - | - | - | - | - |
+| 5.7778 | 210 | 0.3362 | - | - | - | - | - |
+| 6.8235 | 220 | 0.0005 | - | - | - | - | - |
+| 7.8693 | 230 | 0.0 | - | - | - | - | - |
+| 8.9150 | 240 | 0.0 | - | - | - | - | - |
+| 9.0196 | 241 | - | 0.0311 | 0.0307 | 0.0322 | 0.0348 | 0.0324 |
+| 5.9150 | 250 | 2.7229 | - | - | - | - | - |
+| 6.9608 | 260 | 0.0297 | - | - | - | - | - |
+| 8.0065 | 270 | 0.0003 | 0.0324 | 0.0306 | 0.0336 | 0.0355 | 0.0321 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.19.1
+- 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": "4.41.2",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+ "__version__": {
+ "sentence_transformers": "3.1.1",
+ "transformers": "4.41.2",
+ "pytorch": "2.1.2+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 sha256:2dfadda68a81a5d63f4992ea94c6a0e4cdd41464f9bed72c254a46eea74f8930
+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]"
+}