Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "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 +1,692 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: Snowflake/snowflake-arctic-embed-l
+widget:
+- source_sentence: How many full-time staff members are employed at 787 Market & Cafe?
+  sentences:
+  - 'STORE ANALYSIS: 787 Market & Cafe (7858724)
+
+    Location: 6105 Memphis Ave, Cleveland
+
+
+    Store 7858724 - 787 Market & Cafe operates as a Open Store Supermarket-Conventional
+    establishment at 6105 Memphis Ave, Cleveland, OH 441442252 (FIPS 39-35). Geographically
+    precise at coordinates 41.4399,-81.7293 (Geocoded to specific address), this location
+    generates $2,028,000 in annual sales ($2,000,001 to $4,000,000) from its 2000.0
+    square foot space. The operation employs 23 full-time staff across 3 checkout
+    lanes, yielding a sales density of $1,014.00/sqft. Owned by Independent (Family
+    ID: 99999) as part of a 1 Store-location network, the store sources inventory
+    through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its
+    position in the Grocery sector''s Supermarket-Conventional segment.'
+  - 'STORE ANALYSIS: 128 Teresa Grocery (729684)
+
+    Location: 128 Audubon Ave, New York
+
+
+    Store 729684 - 128 Teresa Grocery operates as a Open Store Superette establishment
+    at 128 Audubon Ave, New York, NY 100322109 (FIPS 36-61). Geographically precise
+    at coordinates 40.8427,-73.9369 (Geocoded to specific address), this location
+    generates $1,560,000 in annual sales ($1,500,001 to $2,000,000) from its 2000.0
+    square foot space. The operation employs 7 full-time staff across 1 checkout lanes,
+    yielding a sales density of $780.00/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+  - 'STORE ANALYSIS: 2 Star Grocery (1818510)
+
+    Location: 1123 Dellwood Ave, Memphis
+
+
+    Store 1818510 - 2 Star Grocery operates as a Open Store Superette establishment
+    at 1123 Dellwood Ave, Memphis, TN 381277761 (FIPS 47-157). Geographically precise
+    at coordinates 35.2105,-90.0267 (Geocoded to specific address), this location
+    generates $1,664,000 in annual sales ($1,500,001 to $2,000,000) from its 1000.0
+    square foot space. The operation employs 7 full-time staff across 2 checkout lanes,
+    yielding a sales density of $1,664.00/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+- source_sentence: What is the annual sales figure for the 2031 Webster Food Court
+    supermarket?
+  sentences:
+  - 'STORE ANALYSIS: 2031 Webster Food Court (2192571)
+
+    Location: 2031 Webster Ave, Bronx
+
+
+    Store 2192571 - 2031 Webster Food Court operates as a Open Store Supermarket-Conventional
+    establishment at 2031 Webster Ave, Bronx, NY 104572411 (FIPS 36-5). Geographically
+    precise at coordinates 40.8509,-73.8992 (Geocoded to specific address), this location
+    generates $2,028,000 in annual sales ($2,000,001 to $4,000,000) from its 1000.0
+    square foot space. The operation employs 14 full-time staff across 1 checkout
+    lanes, yielding a sales density of $2,028.00/sqft. Owned by Independent (Family
+    ID: 99999) as part of a 1 Store-location network, the store sources inventory
+    through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its
+    position in the Grocery sector''s Supermarket-Conventional segment.'
+  - 'STORE ANALYSIS: 4M Foods (1483149)
+
+    Location: 6349 Macarthur Blvd, Oakland
+
+
+    Store 1483149 - 4M Foods operates as a Open Store Superette establishment at 6349
+    Macarthur Blvd, Oakland, CA 946051635 (FIPS 6-1). Geographically precise at coordinates
+    37.7741,-122.1801 (Geocoded to specific address), this location generates $1,560,000
+    in annual sales ($1,500,001 to $2,000,000) from its 2000.0 square foot space.
+    The operation employs 7 full-time staff across 2 checkout lanes, yielding a sales
+    density of $780.00/sqft. Owned by Independent (Family ID: 99999) as part of a
+    1 Store-location network, the store sources inventory through Small Supplier (Supplier
+    ID: 888888, Family ID: 88888) to maintain its position in the Grocery sector''s
+    Superette segment.'
+  - 'STORE ANALYSIS: 16th Food Max (701011)
+
+    Location: 9901 N 16th St, Tampa
+
+
+    Store 701011 - 16th Food Max operates as a Open Store Superette establishment
+    at 9901 N 16th St, Tampa, FL 336128233 (FIPS 12-57). Geographically precise at
+    coordinates 28.0393,-82.4415 (Geocoded to specific address), this location generates
+    $1,196,000 in annual sales ($1,000,001 to $1,500,000) from its 1000.0 square foot
+    space. The operation employs 6 full-time staff across 2 checkout lanes, yielding
+    a sales density of $1,196.00/sqft. Owned by Independent (Family ID: 99999) as
+    part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+- source_sentence: What is the annual sales figure for 103 Deli & Grocery located
+    at 148 E 103rd St, New York?
+  sentences:
+  - 'STORE ANALYSIS: 103 Deli & Grocery (970062)
+
+    Location: 148 E 103rd St, New York
+
+
+    Store 970062 - 103 Deli & Grocery operates as a Open Store Superette establishment
+    at 148 E 103rd St, New York, NY 100295334 (FIPS 36-61). Geographically precise
+    at coordinates 40.7902,-73.9476 (Geocoded to specific address), this location
+    generates $1,352,000 in annual sales ($1,000,001 to $1,500,000) from its 1000.0
+    square foot space. The operation employs 6 full-time staff across 1 checkout lanes,
+    yielding a sales density of $1,352.00/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+  - 'STORE ANALYSIS: 1158 Grocery & Deli (1666158)
+
+    Location: 1158 Saint Lawrence Ave, Bronx
+
+
+    Store 1666158 - 1158 Grocery & Deli operates as a Open Store Superette establishment
+    at 1158 Saint Lawrence Ave, Bronx, NY 104724612 (FIPS 36-5). Geographically precise
+    at coordinates 40.8295,-73.8666 (Geocoded to specific address), this location
+    generates $1,352,000 in annual sales ($1,000,001 to $1,500,000) from its 1000.0
+    square foot space. The operation employs 6 full-time staff across 2 checkout lanes,
+    yielding a sales density of $1,352.00/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+  - 'STORE ANALYSIS: A & A Grocery (7345282)
+
+    Location: 6776 Biggers Reyno Rd, Reyno
+
+
+    Store 7345282 - A & A Grocery operates as a Open Store Supermarket-Conventional
+    establishment at 6776 Biggers Reyno Rd, Reyno, AR 72462 (FIPS 5-121). Geographically
+    precise at coordinates 36.3629,-90.7534 (Geocoded to specific address), this location
+    generates $4,160,000 in annual sales ($4,000,001 to $6,000,000) from its 2000.0
+    square foot space. The operation employs 16 full-time staff across 2 checkout
+    lanes, yielding a sales density of $2,080.00/sqft. Owned by Independent (Family
+    ID: 99999) as part of a 1 Store-location network, the store sources inventory
+    through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its
+    position in the Grocery sector''s Supermarket-Conventional segment.'
+- source_sentence: What is the annual sales figure for 12th St Mike Gourmet Deli?
+  sentences:
+  - 'STORE ANALYSIS: 8 Brothers Grocery Store (1639326)
+
+    Location: 2120 N 29th St, Philadelphia
+
+
+    Store 1639326 - 8 Brothers Grocery Store operates as a Open Store Superette establishment
+    at 2120 N 29th St, Philadelphia, PA 191211234 (FIPS 42-101). Geographically precise
+    at coordinates 39.9886,-75.1805 (Geocoded to specific address), this location
+    generates $1,820,000 in annual sales ($1,500,001 to $2,000,000) from its 3000.0
+    square foot space. The operation employs 9 full-time staff across 1 checkout lanes,
+    yielding a sales density of $606.67/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+  - 'STORE ANALYSIS: 12th St Mike Gourmet Deli (879406)
+
+    Location: 1203 40th Ave, Long Island City
+
+
+    Store 879406 - 12th St Mike Gourmet Deli operates as a Open Store Superette establishment
+    at 1203 40th Ave, Long Island City, NY 111016107 (FIPS 36-81). Geographically
+    precise at coordinates 40.7561,-73.9425 (Geocoded to specific address), this location
+    generates $1,508,000 in annual sales ($1,500,001 to $2,000,000) from its 1000.0
+    square foot space. The operation employs 6 full-time staff across 1 checkout lanes,
+    yielding a sales density of $1,508.00/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Harold
+    Levinson Associates (Supplier ID: 195994, Family ID: 2213) to maintain its position
+    in the Grocery sector''s Superette segment.'
+  - 'STORE ANALYSIS: A & B Naturals (5551436)
+
+    Location: 101 Cottage St, Bar Harbor
+
+
+    Store 5551436 - A & B Naturals operates as a Open Store Supermarket-Natural/Gourmet
+    Foods establishment at 101 Cottage St, Bar Harbor, ME 46091442 (FIPS 23-9). Geographically
+    precise at coordinates 44.389,-68.2121 (Geocoded to specific address), this location
+    generates $3,640,000 in annual sales ($2,000,001 to $4,000,000) from its 3000.0
+    square foot space. The operation employs 15 full-time staff across 2 checkout
+    lanes, yielding a sales density of $1,213.33/sqft. Owned by Independent (Family
+    ID: 99999) as part of a 1 Store-location network, the store sources inventory
+    through United Natural Foods/Dist Ctr (Supplier ID: 74258, Family ID: 10540) to
+    maintain its position in the Grocery sector''s Supermarket-Natural/Gourmet Foods
+    segment.'
+- source_sentence: How many full-time staff members are employed at the 54 Royal Market?
+  sentences:
+  - 'STORE ANALYSIS: 114th Gourmet Deli & Grill (805951)
+
+    Location: 11321 Jamaica Ave, Richmond Hill
+
+
+    Store 805951 - 114th Gourmet Deli & Grill operates as a Open Store Superette establishment
+    at 11321 Jamaica Ave, Richmond Hill, NY 114182441 (FIPS 36-81). Geographically
+    precise at coordinates 40.6983,-73.835 (Geocoded to specific address), this location
+    generates $1,820,000 in annual sales ($1,500,001 to $2,000,000) from its 1000.0
+    square foot space. The operation employs 11 full-time staff across 1 checkout
+    lanes, yielding a sales density of $1,820.00/sqft. Owned by Independent (Family
+    ID: 99999) as part of a 1 Store-location network, the store sources inventory
+    through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its
+    position in the Grocery sector''s Superette segment.'
+  - 'STORE ANALYSIS: 54 Royal Market (728885)
+
+    Location: 817 9th Ave, New York
+
+
+    Store 728885 - 54 Royal Market operates as a Open Store Superette establishment
+    at 817 9th Ave, New York, NY 100194401 (FIPS 36-61). Geographically precise at
+    coordinates 40.7662,-73.9872 (Geocoded to specific address), this location generates
+    $1,768,000 in annual sales ($1,500,001 to $2,000,000) from its 2000.0 square foot
+    space. The operation employs 11 full-time staff across 3 checkout lanes, yielding
+    a sales density of $884.00/sqft. Owned by Independent (Family ID: 99999) as part
+    of a 1 Store-location network, the store sources inventory through Small Supplier
+    (Supplier ID: 888888, Family ID: 88888) to maintain its position in the Grocery
+    sector''s Superette segment.'
+  - 'STORE ANALYSIS: 1683 Jimmy Deli Grocery (1816263)
+
+    Location: 1683 Woodbine St, Ridgewood
+
+
+    Store 1816263 - 1683 Jimmy Deli Grocery operates as a Open Store Superette establishment
+    at 1683 Woodbine St, Ridgewood, NY 113853546 (FIPS 36-81). Geographically precise
+    at coordinates 40.7012,-73.9083 (Geocoded to specific address), this location
+    generates $1,456,000 in annual sales ($1,000,001 to $1,500,000) from its 1000.0
+    square foot space. The operation employs 8 full-time staff across 2 checkout lanes,
+    yielding a sales density of $1,456.00/sqft. Owned by Independent (Family ID: 99999)
+    as part of a 1 Store-location network, the store sources inventory through Small
+    Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the
+    Grocery sector''s Superette segment.'
+pipeline_tag: sentence-similarity
+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
+model-index:
+- name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.85
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.93
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.96
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.98
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.85
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.30999999999999994
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19199999999999995
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09799999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.85
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.93
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.96
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.98
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9172332496525142
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8967619047619046
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8976413373860181
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l). It maps sentences & paragraphs to a 1024-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:** [Snowflake/snowflake-arctic-embed-l](https://huggingface.co/Snowflake/snowflake-arctic-embed-l) <!-- at revision d8fb21ca8d905d2832ee8b96c894d3298964346b -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **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': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 1024, '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("philocifer/banner-flip-arctic-embed-l")
+# Run inference
+sentences = [
+    'How many full-time staff members are employed at the 54 Royal Market?',
+    "STORE ANALYSIS: 54 Royal Market (728885)\nLocation: 817 9th Ave, New York\n\nStore 728885 - 54 Royal Market operates as a Open Store Superette establishment at 817 9th Ave, New York, NY 100194401 (FIPS 36-61). Geographically precise at coordinates 40.7662,-73.9872 (Geocoded to specific address), this location generates $1,768,000 in annual sales ($1,500,001 to $2,000,000) from its 2000.0 square foot space. The operation employs 11 full-time staff across 3 checkout lanes, yielding a sales density of $884.00/sqft. Owned by Independent (Family ID: 99999) as part of a 1 Store-location network, the store sources inventory through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the Grocery sector's Superette segment.",
+    "STORE ANALYSIS: 1683 Jimmy Deli Grocery (1816263)\nLocation: 1683 Woodbine St, Ridgewood\n\nStore 1816263 - 1683 Jimmy Deli Grocery operates as a Open Store Superette establishment at 1683 Woodbine St, Ridgewood, NY 113853546 (FIPS 36-81). Geographically precise at coordinates 40.7012,-73.9083 (Geocoded to specific address), this location generates $1,456,000 in annual sales ($1,000,001 to $1,500,000) from its 1000.0 square foot space. The operation employs 8 full-time staff across 2 checkout lanes, yielding a sales density of $1,456.00/sqft. Owned by Independent (Family ID: 99999) as part of a 1 Store-location network, the store sources inventory through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the Grocery sector's Superette segment.",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.85       |
+| cosine_accuracy@3   | 0.93       |
+| cosine_accuracy@5   | 0.96       |
+| cosine_accuracy@10  | 0.98       |
+| cosine_precision@1  | 0.85       |
+| cosine_precision@3  | 0.31       |
+| cosine_precision@5  | 0.192      |
+| cosine_precision@10 | 0.098      |
+| cosine_recall@1     | 0.85       |
+| cosine_recall@3     | 0.93       |
+| cosine_recall@5     | 0.96       |
+| cosine_recall@10    | 0.98       |
+| **cosine_ndcg@10**  | **0.9172** |
+| cosine_mrr@10       | 0.8968     |
+| cosine_map@100      | 0.8976     |
+
+<!--
+## 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: 300 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 300 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                                |
+  | details | <ul><li>min: 13 tokens</li><li>mean: 19.23 tokens</li><li>max: 29 tokens</li></ul> | <ul><li>min: 200 tokens</li><li>mean: 215.01 tokens</li><li>max: 232 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                 | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+  |:-------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>How many full-time staff members are employed at 3 Rivers Grocery Market?</code>     | <code>STORE ANALYSIS: 3 Rivers Grocery Market (432489)<br>Location: 9400 US Highway 60 W, Kevil<br><br>Store 432489 - 3 Rivers Grocery Market operates as a Open Store Supermarket-Conventional establishment at 9400 US Highway 60 W, Kevil, KY 420539678 (FIPS 21-145). Geographically precise at coordinates 37.0624,-88.8028 (Geocoded to specific address), this location generates $4,160,000 in annual sales ($4,000,001 to $6,000,000) from its 13000.0 square foot space. The operation employs 18 full-time staff across 4 checkout lanes, yielding a sales density of $320.00/sqft. Owned by Independent (Family ID: 99999) as part of a 1 Store-location network, the store sources inventory through Assoc Wholesale/Nashville Div (Supplier ID: 12115, Family ID: 4110) to maintain its position in the Grocery sector's Supermarket-Conventional segment.</code> |
+  | <code>How many full-time staff members are employed at the 28th Street Supermarket?</code> | <code>STORE ANALYSIS: 28th Street Supermarket (737932)<br>Location: 2747 Cedar Ave, Cleveland<br><br>Store 737932 - 28th Street Supermarket operates as a Open Store Superette establishment at 2747 Cedar Ave, Cleveland, OH 441152908 (FIPS 39-35). Geographically precise at coordinates 41.4988,-81.6687 (Geocoded to specific address), this location generates $1,404,000 in annual sales ($1,000,001 to $1,500,000) from its 1000.0 square foot space. The operation employs 4 full-time staff across 3 checkout lanes, yielding a sales density of $1,404.00/sqft. Owned by Independent (Family ID: 99999) as part of a 1 Store-location network, the store sources inventory through H T Hackney Co/Dist Ctr (Supplier ID: 36166, Family ID: 41880) to maintain its position in the Grocery sector's Superette segment.</code>                                         |
+  | <code>How many full-time staff members are employed at the 4th Street Market?</code>       | <code>STORE ANALYSIS: 4th Street Market (772013)<br>Location: 301 4th St, Richmond<br><br>Store 772013 - 4th Street Market operates as a Open Store Superette establishment at 301 4th St, Richmond, CA 948013001 (FIPS 6-13). Geographically precise at coordinates 37.9362,-122.3657 (Geocoded to specific address), this location generates $1,560,000 in annual sales ($1,500,001 to $2,000,000) from its 1000.0 square foot space. The operation employs 7 full-time staff across 2 checkout lanes, yielding a sales density of $1,560.00/sqft. Owned by Independent (Family ID: 99999) as part of a 1 Store-location network, the store sources inventory through Small Supplier (Supplier ID: 888888, Family ID: 88888) to maintain its position in the Grocery sector's Superette segment.</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`: steps
+- `per_device_train_batch_size`: 10
+- `per_device_eval_batch_size`: 10
+- `num_train_epochs`: 10
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 10
+- `per_device_eval_batch_size`: 10
+- `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`: 10
+- `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
+- `use_ipex`: 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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | cosine_ndcg@10 |
+|:------:|:----:|:--------------:|
+| 1.0    | 30   | 0.9111         |
+| 1.6667 | 50   | 0.9106         |
+| 2.0    | 60   | 0.9058         |
+| 3.0    | 90   | 0.9149         |
+| 3.3333 | 100  | 0.9199         |
+| 4.0    | 120  | 0.9185         |
+| 5.0    | 150  | 0.9208         |
+| 6.0    | 180  | 0.9172         |
+| 6.6667 | 200  | 0.9172         |
+| 7.0    | 210  | 0.9172         |
+| 8.0    | 240  | 0.9172         |
+| 8.3333 | 250  | 0.9172         |
+| 9.0    | 270  | 0.9172         |
+| 10.0   | 300  | 0.9172         |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## 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 +1,25 @@
+{
+  "_name_or_path": "Snowflake/snowflake-arctic-embed-l",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {
+    "query": "Represent this sentence for searching relevant passages: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5b181bf06b9084809506bc81610b3ceabe292b778ebffa7652530b14346510
+size 1336413848

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": false
+}

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 +1,63 @@
+{
+  "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_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}