cre-bge-small-marco

SentenceTransformer based on anishgillella/cre-bge-small-tsdae

This is a sentence-transformers model finetuned from anishgillella/cre-bge-small-tsdae. It maps sentences & paragraphs to a 384-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: anishgillella/cre-bge-small-tsdae <!-- at revision 6ecdb18b93306383e47103cbf66dce0d088c0740 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("anishgillella/cre-bge-small-marco")
# Run inference
sentences = [
    'H-E-B grocery in TX',
    "Sentinel=[DOC]; Asset=Ridge Road Towne Center; Location=Rockwall TX; Anchor=single_tenant; TenantFamily=grocery; Structure=nnn; Body: a New Buyer Ability to Convert to Triple Net (NNN) Leases in the Next 18 Months, Providing For a Secure Investment in a Rapidly Growing Market. OFFERING SUMMARY Cap Rate: 6.29% NOI: $1,130,949 Price / SF: $329.69 Occupancy: 97.8% BUILDING INFORMATION Street Address: 2435-2455 Ridge Road City, State, Zip: Rockwall, TX 75087 County: Rockwall Building Size: 54,521 SF Lot Size: 7.68 Acres Year Built: 2005 Year Last Renovated: 2022 R I D G E R O A D T O W N E C E N T E R E XECUTIVE S UMMA RY Investment Overview 6 PROPERTY HIGHLIGHTS Texas is an Income Tax Free State Strong Mix of National, Regional and Local Tenants Including: Children's Health, Geico Insurance, The House of Gyros, Papa Murphy’s, Wing Stop, Kid to Kid, HotWorx and X Golf Sport Bar 13% of Leases Are Gross Leases Allowing a New Buyer Ability to Convert to Triple Net (NNN) Leases in the Next 18 Months Existing Tenants Are Paying Below Market Rents at an Average of $22 PSF - Market Rental Rate is at $26.65 PSF with a 1.7% Vacancy Rate Property Consists of Two Buildings, Offering the Opportunity to Convert the Front Building to Single Tenant or Sell as Outparcel New Roof as of 2022 22 Tenants Can Provide For a Diversified Mix of Rental Increases/More Stability Top MSA - Dallas is the #4 Ranked Metropolitan Statistical Area in the Country Strong Demographics with an Average Household Income of $122,500 Within a 5-Mile Radius 1-Mile Population Growth Over the Next Five Years is 27.22% Easy Access - Multiple Points of Entry; On a Hard Corner R I D G E R O A D T O W N E C E N T E R IN VESTME N T H IGHLIGHT S Financial Overview 8 Lease Dates Tenant Stretch Zone 30 Brunch House Lakes Regional Community The House of Gyros T's Ice Cream Papa Murphy's XGolf Sports Dr. Paul Field HotWorx Cure Nail Spa Geico Insurance Small Cakes Divas & Darling Bouঞque Chiloso's Kid to Kid Dr. Waller Chiropracঞc Wingstop Rockwall Wellness Center Juvanew Medspa Our Children's House Vacant My Computer Guy Total/Average Base Rent 54,251 Rent Escalaঞon Unit 100 101 101B 109 110 111B 115 117 120 123 125 127 129 135 143 147 149 151 & 155 157 200 205 251 7.4 Years SF 1,343 2,760 4,455 1,200 1,187 1,200 6,056 2,975 2,058 1,625 1,930 1,170 2,140 3,500 3,291 1,205 2,000 2,984 4,022 3,454 1,180 2,516 3.6 Years % of SF 2.48% 5.09% 8.21% 2.21% 2.19% 2.21% 11.16% 5.48% 3.79% 3.00% 3.56% 2.16% 3.94% 6.45% 6.07% 2.22% 3.69% 5.50% 7.41% 6.37% 2.18% 4.64% $1,195,002 Start Mar 2023 Oct 2022 May 2014 Aug 2016 Jan 2023 Dec 2015 Dec 2022 Jul 2016 Dec 2022 Dec 2005 May 2022 Apr 2022 Jan 2019 Sep 2005 Feb 2018 Mar 2015 Dec 2014 Jan 2008 Jun 2013 Sep 2006 - Dec 2018 $22.03 End Jul 2030 Jan 2028 Apr 2026 Nov 2026 Dec 2029 Apr 2024 Mar 2030 Sep 2026 Dec 2032 Jun 2028 Oct 2027 Jun 2027 Mar",
    'Sentinel=[DOC]; Asset=Pasadena Center (2024); Location=Pasadena TX; TenantFamily=grocery; Structure=nnn; Body: landlord canceling the next extended term at least 180 days prior. CAM PAYMENTS: Tenant shall reimburse Landlord its pro rata share of CAM expenses. The increase in controllable CAM expenses is capped 5% of previous year expenses. INSURANCE PAYMENTS: Tenant shall reimburse Landlord its pro rata share of Insurance expenses. RE TAX PAYMENTS: Tenant shall reimburse Landlord its pro rata share of Real Estate Tax expenses. UTILITIES: Tenant shall pay all charges for utilities used in the premises. Pasadena Shopping Center | 17 LEASE ABSTRACT TENANT MAINTENANCE: Tenant shall maintain and repair all interior, non-structural portions of the leased premises. LANDLORD MAINTENANCE: Landlord shall maintain and keep in good repair the exterior portions of the leased premises, including the roof, exterior walls, canopy, gutters, downspouts, all structural portions, fire sprinkler system, exterior plumbing and electrical lines. PERCENTAGE RENT: N/A BREAKPOINT: N/A GUARANTOR: N/A ASSIGNEE: Family Dollar Stores, Inc CO-TENANCY/TERMINATION: N/A EXCLUSIVES / RESTRICTIONS: Landlord shall not lease any space in the shopping center to any variety store, variety discount store, discount department store, dollar store, liquidation or close-out store, thrift store, any store selling used clothing or any store similar to tenant in operation or merchandising. ESTOPPEL CERTIFICATE: Tenant shall provide an estoppel certificate within 30 days upon written request by the Landlord. ADDITIONAL INFORMATION: N/A Pasadena Shopping Center | 19 POPULATION: 30,503,301 NO STATE INCOME TAX 2ND FASTEST GROWING ECONOMY IN THE US #1 STATE FOR JOB GROWTH: 407,000+ JOBS CREATED IN 2023 BEST STATE FOR BUSINESS 19 CONSECUTIVE YEARS CHIEF EXECUTIVE MAGAZINE FASTEST GROWING STATE IN THE US 4.8 MILLION+ NEW TEXANS SINCE 2010 THE WORLD’S 8TH LARGEST ECONOMY LEADS THE NATION WITH 55 FORTUNE 500 COMPANIES WINNER OF THE GOVERNER’S CUP 11 YEARS IN A ROW Texas Overview Major Metros: HOUSTON: #2 Top U.S. Metros for Job Growth #2 Metros with Most Corporate Headquarters DALLAS: #1 Fastest Growing MSA #5 Best Performing Cities in U.S. FORT WORTH: Top 20 Large U.S. Cities to Start a Business AUSTIN: #1 Best Place to Start a business in U.S. #3 Best Performing Cities In U.S. SAN ANTONIO: #1 Best City for Veterans #1 Pasadena Shopping Center | 19 Pasadena Shopping Center | 20 4TH LARGEST CITY IN THE U.S. POPULATION: 7,300,000+ $490 BILLION REGIONAL GDP TOP 10 CITIES FOR JOB GROWTH Houston Overview TEXAS MEDICAL CENTER MD ANDERSON LARGEST MEDICAL CENTER 2ND LARGEST CANCER CENTER PORT OF HOUSTON RANKED #1 IN FOREIGN TONNAGE 2ND LARGEST PORT IN THE U.S. & THE LARGEST PORT ON THE GULF ENERGY CAPITAL OF THE WORLD HOME TO 44 OF THE LARGEST PUBLICLY TRADED OIL & GAS FIRMS RETAIL MARKET OVER $126 BILLION 207 MILLION SF GROSS ANNUAL RETAIL SALES #4 MOST AFFORDABLE CITY TO LIVE IN WITH A COST OF LIVING AT 28% BELOW AVERAGE MOST DIVERSE CITY 1 IN 4 HOUSTONIANS ARE FOREIGN BORN 1.2 MILLION SF UNDER CONSTRUCTION TOTAL INVENTORY 93.5% OCCUPANCY RATE 2.3% INCREASE IN AVG ASKING RENT 26 FORTUNE 500 COMPANIES BASED IN HOUSTON TOP 10 LARGEST EMPLOYERS: 20,000 + EMPLOYEES 10,000 + EMPLOYEES H-E-B Methodist Memorial Hermann MD Anderson Walmart ExxonMobil',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6789, 0.6729],
#         [0.6789, 1.0000, 0.9932],
#         [0.6729, 0.9932, 1.0000]])

<!-- ### 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.* --> <!-- ## 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: 1,025 training samples
• Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	sentence_2
  type	string	string	string
  details	<ul><li>min: 5 tokens</li><li>mean: 12.73 tokens</li><li>max: 40 tokens</li></ul>	<ul><li>min: 233 tokens</li><li>mean: 494.63 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 233 tokens</li><li>mean: 510.33 tokens</li><li>max: 512 tokens</li></ul>

• Samples:

  sentence_0	sentence_1	sentence_2
  <code>Walmart big box nnn in Bonham, TX</code>	<code>Sentinel=[DOC]; Asset=Retail Shops B; Location=San Marcos TX; TenantFamily=big_box; Structure=nnn; Body: Springtown Plaza OFFERING MEMORANDUM The Lyndon at Springtown - Retail Shops B San Marcos, TX (Austin MSA) www.preservewestcapital.com This property is listed in conjunction with Texas-licensed real estate broker Delta Commercial. VIEW PROPERTY VIDEO Preserve West Capital (“Broker”) has been retained on an exclusive basis to market the property described herein (“Property”). Broker has been authorized by the Seller of the Property (“Seller”) to prepare and distribute the enclosed information (“Material”) for the purpose of soliciting offers to purchase from interested parties. More detailed financial, title and tenant lease information may be made available upon request following the mutual execution of a letter of intent or contract to purchase between the Seller and a prospective purchaser. You are invited to review this opportunity and make an offer to purchase based upon your an...</code>	<code>Sentinel=[DOC]; Asset=Northbelt Plaza; Location=Humble TX; Body: For Sale Northbelt Plaza 14925 & 14929 Old Humble Road, Humble, TX 77396 Hunington Properties, Inc. 3773 Richmond Ave., Suite 800 Houston, Texas 77046 713-623-6944 hpiproperties.com The information contained herein while based upon data supplied by sources deemed reliable, is subject to errors or omissions and is not in any way, warranted by Hunington Properties or by any agent, independent associate, subsidiary or employee of Hunington Properties. This information is subject to change. For Sale NORTHBELT PLAZA 14925 & 14929 Old Humble Road, Humble, TX 77396 Property Details Sale Price $3,985,000.00 NOI $264,501.02 CAP Rate 6.64% Net Rentable Area 16,262 SF Lot Size 1.71 AC Occupancy 100% Year Built 2008 Property Highlights • Within a block of the Sam Houston Tollway (Beltway 8) • High traffic and dense demographics within a one mile radius. • Retail property comprised of one freestanding retail building and a second buil...</code>
  <code>service in Houston, TX</code>	<code>Sentinel=[DOC]; Asset=Sports Village Plaza; Location=Frisco TX; Anchor=multi_tenant; TenantFamily=service; Structure=nnn; Body: performance, or comparable rents for the area. Returns are not guaranteed; the tenant and any guarantors may fail to pay the lease rent or property taxes, or may fail to comply with other material terms of the lease; cash flow may be interrupted in part or in whole due to market, economic, environmental or other conditions. Regardless of tenant history and lease guarantees, Buyer is responsible for conducting his/her own investigation of all matters affecting the intrinsic value of the property and the value of any long-term lease, including the likelihood of locating a replacement tenant fit the current tenant should default or abandon the property, and the lease terms that Buyer may be able to negotiate with a potential replacement tenant considering the location of the property, and Buyer's legal ability to make alternate use of the property. B y a c c e p ...</code>	<code>Sentinel=[DOC]; Asset=Ridge Road Towne Center; Location=Rockwall TX; Anchor=single_tenant; TenantFamily=grocery; Structure=nnn; Body: RIDGE ROAD TOW NE CE N T E R 2435-2455 Ridge Road - Rockwall, TX 75087 In Cooperaঞon With Sands Investment Group Ausঞn, LLC - Lic. #9004706 BoR: Max Freedman - Lic. TX #644481 www.SIGnnn.com Sands Investment Group // 2009 S. Capital of Texas, Suite 210 // Westlake Hills, TX 78746 www.SIGnnn.com JUSTIN WALKER 754.255.6989 | DIRECT [email protected] FL #SL3384090 KAYLAN KNITOWSKI 954.902.5247 | DIRECT [email protected] FL #SL3557957 MARK HEBERT 754.255.6993 | DIRECT [email protected] FL #SL3547657 In Cooperaঞon With Sands Investment Group Ausঞn, LLC - Lic. #9004706 BoR: Max Freedman - Lic. TX #644481 R I D G E R O A D T O W N E C E N T E R E XCLUS IVE LY MA RK E T E D BY CONFIDENTIALITY & DISCLAIMER © 2023 Sands Investment Group (SIG). The information contained in this ‘Offering Memorandum’, has been obtained from sources believed to be reliable. Sands I...</code>
  <code>Lowe’s multi tenant grocery nnn in Bastrop, TX</code>	<code>Sentinel=[DOC]; Asset=Ridge Road Towne Center; Location=Rockwall TX; Anchor=single_tenant; TenantFamily=grocery; Structure=nnn; Body: RIDGE ROAD TOW NE CE N T E R 2435-2455 Ridge Road - Rockwall, TX 75087 In Cooperaঞon With Sands Investment Group Ausঞn, LLC - Lic. #9004706 BoR: Max Freedman - Lic. TX #644481 www.SIGnnn.com Sands Investment Group // 2009 S. Capital of Texas, Suite 210 // Westlake Hills, TX 78746 www.SIGnnn.com JUSTIN WALKER 754.255.6989 | DIRECT [email protected] FL #SL3384090 KAYLAN KNITOWSKI 954.902.5247 | DIRECT [email protected] FL #SL3557957 MARK HEBERT 754.255.6993 | DIRECT [email protected] FL #SL3547657 In Cooperaঞon With Sands Investment Group Ausঞn, LLC - Lic. #9004706 BoR: Max Freedman - Lic. TX #644481 R I D G E R O A D T O W N E C E N T E R E XCLUS IVE LY MA RK E T E D BY CONFIDENTIALITY & DISCLAIMER © 2023 Sands Investment Group (SIG). The information contained in this ‘Offering Memorandum’, has been obtained from sources believed to be reliable. Sands I...</code>	<code>Sentinel=[DOC]; Asset=Rose-Rich Shopping Center; Location=Rosenberg TX; TenantFamily=financial; Structure=nnn; Body: Hunington Properties, Inc. 3773 Richmond Ave., Suite 800 Houston, Texas 77046 713-623-6944 hpiproperties.com For Sale Rose-Rich Center 5100 - 5198 Avenue H (US Highway 90) Rosenberg, Texas 77471 For More Information Todd Carlson Director/Investment Sales [email protected] For More Information ROSE-RICH CENTER 5100-5197 Avenue H (US Highway 90), Rosenberg, Texas 77051 PROPERTY INFORMATION Sale Pricet $10,000,000 CAP Rate 8.31% Net Operating Income $830,587.46 Occupancy 93% Lease Type NNN Net Rentable Area 101,639 SF Lot Size 8.6 Acres Year Built 1955/2016 PROPERTY HIGHLIGHTS • Long Term National Tenancy • Low Rent & Operating Expenses • Great Visibility • High Traffic Location on US Hwy 90 • Ample Parking DEMOGRAPHICS Population 1 mi. - 8,991 3 mi. - 56,376 5 mi. - 107,426 Average Household Income 1 mi. - $52,634 3 mi. - $78,768 5 mi. - $94,221 Traffic Count US 90: 3...</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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
• bf16: False
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: 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
• project: huggingface
• trackio_space_id: trackio
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Framework Versions

• Python: 3.11.12
• Sentence Transformers: 5.1.1
• Transformers: 4.57.0
• PyTorch: 2.8.0+cu128
• Accelerate: 1.10.1
• Datasets: 4.1.1
• Tokenizers: 0.22.1

Citation

BibTeX

Sentence Transformers

@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",
}

MultipleNegativesRankingLoss

@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.* -->