Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,240 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: 'hasAdditionalInformation: Large Square - 48" x 48" Daily Fundamentals - Vinyl
+    for Concrete, hasCreatedDate: 2024-08-12, hasCustomerHomeCountry: United States,
+    hasCustomerID: 38262, hasCustomerName: Architecture Products Group (APG)(Architecture
+    Products Group (APG) (USA)), hasCutting: Trim to size, hasElementID: 3448379,
+    hasElementTitle: Large Square - 48" x 48" Daily Fundamentals - Vinyl for Concrete,
+    hasFinishedSizeHeight: 48, hasFinishedSizeWidth: 48, hasFscPaperBeenSpecified:
+    No, hasInternalID: ca0cb75e-c8ba-4447-9a73-2f4f31ac1fde, hasMaterialCategory:
+    Paper, hasMaterialDescription: Vinyl for Concrete, hasMaterialRecycledPercentage:
+    0%, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure: Pounds (lbs),
+    hasNumberOfVersions: 1, hasPrice: 95.04 USD, hasPrintedSides: Not printed, hasProductCategory:
+    Indoor/Outdoor Signage, hasProofType: PDF digital proof, hasQuantity: 2, hasRecycledContentBeenOffered:
+    N/A, hasSupplierName: Firehouse Image Center(Firehouse Image Center  - 12168 -
+    HHGSP), hasUnitOfMeasure: Inches (in), '
+- text: 'hasCreatedDate: 2024-11-20, hasCustomerHomeCountry: United States, hasCustomerID:
+    14347, hasCustomerName: Lowe''s Companies Inc.(Lowe''s USD), hasCutting: Trim
+    to size, hasElementID: 3646411, hasElementTitle: RESET00002 PT BRITTEN, hasFinishedSizeHeight:
+    1, hasFinishedSizeWidth: 1, hasFlatSizeHeight: 1, hasFlatSizeWidth: 1, hasFscPaperBeenSpecified:
+    No, hasInternalID: 47920581-39d1-4737-aa2e-32fdddebe3c3, hasMaterialCategory:
+    Other, hasMaterialDescription: Other, hasMaterialType: Other, hasNumberOfVersions:
+    1, hasPrice: 0 USD, hasPrintedSides: Single sided, hasProofType: No proof required,
+    hasQuantity: 1, hasRecycledContentBeenOffered: N/A, hasSupplierName: BRITTEN BANNERS(Britten
+    Inc  - 38859 - HHGSP), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), '
+- text: 'hasArtworkDoubleSidedStatus: Double Sided Same, hasCreatedDate: 2024-06-21,
+    hasCustomerHomeCountry: United Kingdom, hasCustomerID: 37535, hasCustomerName:
+    Musgrave Retail Partners NI Ltd. | Centra NI (Musgrave Retail Partners NI Ltd.
+    | Centra NI ), hasCutting: Cut to shape, hasElementID: 3360484, hasElementTitle:
+    SKU.21 - Indoor Bunting 5m Summer POS , hasFinishedSizeHeight: 297, hasFinishedSizeWidth:
+    210, hasFscPaperBeenSpecified: No, hasInternalID: 62b006eb-1c4e-4d6e-adbf-9ac9543daa86,
+    hasMaterialCategory: Paper, hasMaterialDescription: Art, hasMaterialThicknessOrWeight:
+    300, hasMaterialType: Paper, hasMaterialUnitOfMeasure: GSM, hasNumberOfVersions:
+    1, hasPackingRequirements: Indoor Bunting 5m. A4 pennants. 4/4 onto 300grm art.
+    Matt Lam and Die Cut to shape., hasPrice: 45 GBP, hasPrintedSides: Double sided,
+    hasProofType: PDF digital proof, hasQuantity: 6, hasQuantityPerVersion: 1, hasRecycledContentBeenOffered:
+    No, hasSupplierName: McGowans(McGowans), hasTotalColours: 4, hasTotalColoursFace:
+    4, hasUnitOfMeasure: Millimetres (mm), '
+- text: 'hasAdditionalInformation: Title, hasCreatedDate: 2024-08-20, hasCustomerHomeCountry:
+    United Kingdom, hasCustomerID: 49021, hasCustomerName: LONDON EYE(MERLIN - EYE
+    - LONDON), hasCutting: Trim to size, hasElementID: 3461182, hasElementTitle: 2731
+    LE Gift Shop A0 Banners, hasFinishedSizeHeight: 1189, hasFinishedSizeWidth: 841,
+    hasFscPaperBeenSpecified: No, hasHandFinishing: Yes, hasHandFinishingDetails:
+    hem and eyelet, hasInternalID: b7ec9eab-be07-41d6-b977-191abb1b573f, hasMaterialCategory:
+    Plastic, hasMaterialDescription: PVC, hasMaterialThicknessOrWeight: 440, hasMaterialType:
+    PVC, hasMaterialUnitOfMeasure: Microns, hasMinimumRecycledContent: 0%, hasNumberOfVersions:
+    1, hasPrice: 50 GBP, hasPrintedSides: Single sided, hasProductCategory: Loose
+    Print, hasProofType: PDF digital proof, hasQuantity: 2, hasQuantityPerVersion:
+    2, hasRecycledContentBeenRequested: No, hasSendToDetails: Simona Bottiglia (she/her)
+    Senior Retail Manager      The London Eye, County Hall, Westminster Bridge Road,
+    London, SE1 7PB, hasSupplierName: Design X-Press Limited(Design X-Press Limited),
+    hasTotalColours: 4, hasUnitOfMeasure: Millimetres (mm), '
+- text: 'hasArtworkDoubleSidedStatus: Double Sided Different, hasCreatedDate: 2024-09-17,
+    hasCustomerHomeCountry: United States, hasCustomerID: 39021, hasCustomerName:
+    Pulte Homes Corporation(PulteGroup | Mid-Atlantic - 1038), hasCutting: Trim to
+    size, hasElementID: 3512114, hasElementTitle: MidAtlantic - Cattail Run - Bifolds
+    17x11 folded to 8.5x11 (Summerfield) (300 QTY), hasFinishedSizeHeight: 11, hasFinishedSizeWidth:
+    8.5, hasFlatSizeHeight: 11, hasFlatSizeWidth: 17, hasFscPaperBeenSpecified: No,
+    hasInternalID: 14a905f8-9a6a-4ea9-a0e4-7299704feeb0, hasMachineFinishing: Yes,
+    hasMachineFinishingDetails: Half Fold, hasMaterialCategory: Paper, hasMaterialDescription:
+    Gloss/Text, Substrate Grade #2, bleached(white), bleed, hasMaterialThicknessOrWeight:
+    80, hasMaterialType: Paper, hasMaterialUnitOfMeasure: Pounds (lbs), hasNumberOfVersions:
+    1, hasPackingRequirements: Shrink wrap in packs of 100  Deliver to, hasPrice:
+    200.68 USD, hasPrintedSides: Double sided, hasProofType: PDF digital proof, hasQuantity:
+    300, hasQuantityPerVersion: 300, hasRecycledContentBeenOffered: N/A, hasSupplierName:
+    Team Concept Printing (Team Concept Printing  - HHGSP - PI), hasTotalColours:
+    4, hasTotalColoursFace: 4, hasUnitOfMeasure: Inches (in), '
+metrics:
+- f1_micro
+- f1_macro
+- f1_weighted
+- precision
+- accuracy
+- recall
+pipeline_tag: text-classification
+library_name: setfit
+inference: false
+model-index:
+- name: SetFit
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: f1_micro
+      value: 0.8504854368932039
+      name: F1_Micro
+    - type: f1_macro
+      value: 0.35725054393071265
+      name: F1_Macro
+    - type: f1_weighted
+      value: 0.7613078250339776
+      name: F1_Weighted
+    - type: precision
+      value: 0.9125000238418579
+      name: Precision
+    - type: accuracy
+      value: 0.879687488079071
+      name: Accuracy
+    - type: recall
+      value: 0.7963636517524719
+      name: Recall
+---
+
+# SetFit
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. A OneVsRestClassifier instance is used for classification.
+
+The model has been trained using an efficient few-shot learning technique that involves:
+
+1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
+2. Training a classification head with features from the fine-tuned Sentence Transformer.
+
+## Model Details
+
+### Model Description
+- **Model Type:** SetFit
+<!-- - **Sentence Transformer:** [Unknown](https://huggingface.co/unknown) -->
+- **Classification head:** a OneVsRestClassifier instance
+- **Maximum Sequence Length:** 512 tokens
+- **Number of Classes:** 8 classes
+<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
+- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
+- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
+
+## Evaluation
+
+### Metrics
+| Label   | F1_Micro | F1_Macro | F1_Weighted | Precision | Accuracy | Recall |
+|:--------|:---------|:---------|:------------|:----------|:---------|:-------|
+| **all** | 0.8505   | 0.3573   | 0.7613      | 0.9125    | 0.8797   | 0.7964 |
+
+## Uses
+
+### Direct Use for Inference
+
+First install the SetFit library:
+
+```bash
+pip install setfit
+```
+
+Then you can load this model and run inference.
+
+```python
+from setfit import SetFitModel
+
+# Download from the 🤗 Hub
+model = SetFitModel.from_pretrained("setfit_model_id")
+# Run inference
+preds = model("hasCreatedDate: 2024-11-20, hasCustomerHomeCountry: United States, hasCustomerID: 14347, hasCustomerName: Lowe's Companies Inc.(Lowe's USD), hasCutting: Trim to size, hasElementID: 3646411, hasElementTitle: RESET00002 PT BRITTEN, hasFinishedSizeHeight: 1, hasFinishedSizeWidth: 1, hasFlatSizeHeight: 1, hasFlatSizeWidth: 1, hasFscPaperBeenSpecified: No, hasInternalID: 47920581-39d1-4737-aa2e-32fdddebe3c3, hasMaterialCategory: Other, hasMaterialDescription: Other, hasMaterialType: Other, hasNumberOfVersions: 1, hasPrice: 0 USD, hasPrintedSides: Single sided, hasProofType: No proof required, hasQuantity: 1, hasRecycledContentBeenOffered: N/A, hasSupplierName: BRITTEN BANNERS(Britten Inc  - 38859 - HHGSP), hasTotalColours: 4, hasUnitOfMeasure: Inches (in), ")
+```
+
+<!--
+### Downstream Use
+
+*List how someone could finetune this model on their own dataset.*
+-->
+
+<!--
+### 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 Set Metrics
+| Training set | Min | Median   | Max |
+|:-------------|:----|:---------|:----|
+| Word count   | 69  | 111.6031 | 313 |
+
+### Framework Versions
+- Python: 3.10.16
+- SetFit: 1.1.1
+- Sentence Transformers: 3.4.1
+- Transformers: 4.49.0
+- PyTorch: 2.6.0+cu124
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+    doi = {10.48550/ARXIV.2209.11055},
+    url = {https://arxiv.org/abs/2209.11055},
+    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
+    title = {Efficient Few-Shot Learning Without Prompts},
+    publisher = {arXiv},
+    year = {2022},
+    copyright = {Creative Commons Attribution 4.0 International}
+}
+```
+
+<!--
+## 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 +1,31 @@
+{
+  "_name_or_path": "avsolatorio/GIST-small-Embedding-v0",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

config_setfit.json

@@ -0,0 +1,13 @@
+{
+  "labels": [
+    "http://example.com/domain#ManufacturingDomain",
+    "http://example.com/domain#ProductDomain",
+    "http://example.com/domain#AssemblyDomain",
+    "http://example.com/domain#SupplierDomain",
+    "http://example.com/domain#MaterialDomain",
+    "http://example.com/domain#MeasurementDomain",
+    "http://example.com/domain#FeatureDomain",
+    "http://example.com/domain#ShippingAndHandlingDomain"
+  ],
+  "normalize_embeddings": false
+}

heads/domain-router.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d3d2dee16136f590aad71f365f7eb48cf7118e9667abada200996002635dd9
+size 28404

heads/head_metadata.json

@@ -0,0 +1,17 @@
+[
+    {
+        "name": "domain-router",
+        "dataset_name": "Northell/ros-classifiers-domains-routing",
+        "dataset_revision": null,
+        "num_classes": 8,
+        "metrics": {
+            "f1_micro": 0.8504854368932039,
+            "f1_macro": 0.35725054393071265,
+            "f1_weighted": 0.7613078250339776,
+            "precision": 0.9125000238418579,
+            "accuracy": 0.879687488079071,
+            "recall": 0.7963636517524719
+        },
+        "pkl_cache": null
+    }
+]

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa751a822b7eb0a7db5d0167b6e38ffd6ad1978e71de205d7c0efedcc18bf2a
+size 133462128

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92197e97e8ca99ea116a8ecf46a0c475a21605c75b28ef89d27d0bfda7e4ca3a
+size 28404

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "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]"
+}