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 +1,252 @@
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: 'hasAdditionalInformation: TFP10-73Pepsi Max X 264 TFP10-174 BAT Velo X 353,
+    hasColourDetails: 1pp - Face Print, hasCreatedDate: 2024-06-12, hasCustomerHomeCountry:
+    United Kingdom, hasCustomerID: 25892, hasCustomerName: Co-operative Group Limited.(Co-operative
+    Group Limited (Co-op Food)), hasCutting: Cut to shape, hasElementID: 3343462,
+    hasElementTitle: POS028 SECURITY SHROUD, hasFinishedSizeHeight: 1540, hasFinishedSizeWidth:
+    600, hasFlatSizeHeight: 3080, hasFlatSizeWidth: 600, hasFscPaperBeenSpecified:
+    No, hasInternalID: 354d490a-f709-4034-af56-3e0b28ee34ba, hasMachineFinishing:
+    Yes, hasMachineFinishingDetails: Trimmed to Size, Fold in Half, Weld Long Edges
+    Only with 2 x PP Eyelets Positioned as Template - Fold Twice (to 600x515 approx)
+    for Flat Packing Pack in 2''s, hasMaterialCategory: Plastic, hasMaterialDescription:
+    180gsm White/White Woven PE, hasMaterialThicknessOrWeight: 180, hasMaterialType:
+    Polypropylene, hasMaterialUnitOfMeasure: GSM, hasNumberOfVersions: 2, hasPackingRequirements:
+    Delivery to K Displays, Smith Way Ossett, FAO Dean Newbold. Delivery required
+    Friday 21st June.  Please book in 48hrs in advance and mark all pallets on boxes
+    with code, qty and P10 2024 Co-op Campaign, hasPrice: 3513.22 GBP, hasPrintedSides:
+    Single sided, hasProofType: PDF digital proof, hasQuantity: 617, hasRecycledContentBeenOffered:
+    No, hasSupplierName: Dominion Print Limited(Dominion Print Limited), hasTotalColours:
+    4, hasUnitOfMeasure: Millimetres (mm), '
+- text: 'hasAdditionalInformation: Mailed First Class, hasArtworkDoubleSidedStatus:
+    Double Sided Different, hasCreatedDate: 2024-03-21, hasCustomerHomeCountry: United
+    States, hasCustomerID: 32065, hasCustomerName: Republic Services, Inc(Republic
+    Services), hasCutting: Trim to size, hasElementID: 3192439, hasElementTitle: Crockett
+    Residental PC Mailer 2024, hasFinishedSizeHeight: 4, hasFinishedSizeWidth: 6,
+    hasFscPaperBeenSpecified: No, hasInternalID: a63ca51f-99e2-4479-abb8-3e1f48c385e8,
+    hasMaterialCategory: Paper, hasMaterialDescription: Uncoated Cover, hasMaterialThicknessOrWeight:
+    100, hasMaterialType: Paper, hasMaterialUnitOfMeasure: Pounds (lbs), hasNumberOfVersions:
+    1, hasPaperType: Cover, hasPrice: 302.6 USD, hasPrintedSides: Double sided, hasProofType:
+    PDF digital proof, hasQuantity: 1200, hasRecycledContentBeenOffered: N/A, hasSendToDetails:
+    [email protected], hasSupplierName: United Printing and Mail
+    - HHG Strategic Partner (United Printing and Mail  - 48084 - HHGSP - US Only),
+    hasTotalColours: 4, hasTotalColoursFace: 4, hasUnitOfMeasure: Inches (in), '
+- text: 'hasAdditionalInformation: US-89839_AIRSUPRA HCP Discover Leave behind Qt
+    150,000 8.5”x11” flat/finished 80# Chorus Art Coated Cover 6/0 (CMYK + 2PMS) +
+    Satin AQ S/W in 25s, hasColourDetails: 6/0 (CMYK + 2PMS) + Satin AQ, hasCreatedDate:
+    2024-07-11, hasCustomerHomeCountry: United States, hasCustomerID: 31753, hasCustomerName:
+    AstraZeneca Pharmaceuticals LP(AstraZeneca - US - BBU), hasCutting: Trim to size,
+    hasElementID: 3394425, hasElementTitle: US-89839_AIRSUPRA HCP Discover Leave behind,
+    hasFinishedSizeHeight: 11, hasFinishedSizeWidth: 8.5, hasFlatSizeHeight: 11, hasFlatSizeWidth:
+    8.5, hasFscPaperBeenSpecified: Yes, hasInternalID: 91a64b08-cb2a-4d8e-b11d-b3908f11f2cd,
+    hasMachineFinishing: Yes, hasMachineFinishingDetails: S/W in 25s, hasMaterialCategory:
+    Paper, hasMaterialDescription: 80# Chorus Art Coated Cover, hasMaterialRecycledPercentage:
+    30%, hasMaterialThicknessOrWeight: 80, hasMaterialType: Paper and board, hasMaterialUnitOfMeasure:
+    Pounds (lbs), hasNumberOfVersions: 1, hasPackingRequirements: S/W in 25s, hasPaperType:
+    Cover, hasPrice: 13847.67 USD, hasPrintedSides: Single sided, hasProductCategory:
+    Loose Print, hasProofType: PDF digital proof,Colour contract proof, hasQuantity:
+    150000, hasQuantityPerVersion: 150000, hasRecycledContentBeenOffered: Yes, hasSupplierName:
+    Phoenix Lithographing Corporation(Phoenix Lithographing Corp - HHGSP - PI), hasTotalColours:
+    6, hasUnitOfMeasure: Inches (in), '
+- text: 'hasAdditionalInformation: US-82104_AIRSUPRA HCP Clinical Leave Behind Qt
+    650,000 (4pg Bi-fold) 17"x11" flat 8.5"x11" finished 80# Coated Cover 6/6 (CMYK
+    + 2PMS) + GLOSS AQ Trim / Score / Bi-Fold S/W in 25s, hasArtworkDoubleSidedStatus:
+    Double Sided Different, hasColourDetails: 6/6 (CMYK + 2PMS) + GLOSS AQ, hasCreatedDate:
+    2024-01-18, hasCustomerHomeCountry: United States, hasCustomerID: 31753, hasCustomerName:
+    AstraZeneca Pharmaceuticals LP(AstraZeneca - US - BBU), hasCutting: Trim to size,
+    hasElementID: 3071417, hasElementTitle: US-82104_AIRSUPRA HCP Clinical Leave Behind,
+    hasFinishedSizeHeight: 11, hasFinishedSizeWidth: 8.5, hasFlatSizeHeight: 11, hasFlatSizeWidth:
+    17, hasFscPaperBeenSpecified: Yes, hasInternalID: a8e77a84-d6af-4478-b83a-a54ea515b6f0,
+    hasMachineFinishing: Yes, hasMachineFinishingDetails: Trim / Score / Bi-Fold S/W
+    in 25s, hasMaterialCategory: Paper, hasMaterialDescription: 80# Coated Cover,
+    hasMaterialRecycledPercentage: 0%, hasMaterialThicknessOrWeight: 80, hasMaterialType:
+    Paper and board, hasMaterialUnitOfMeasure: Pounds (lbs), hasNumberOfVersions:
+    1, hasPackingRequirements: S/W in 25s, hasPaperType: Cover, hasPrice: 118754 USD,
+    hasPrintedSides: Double sided, hasProductCategory: Booklets & Brochures, hasProofType:
+    Colour contract proof,PDF digital proof, hasQuantity: 650000, hasQuantityPerVersion:
+    650000, hasRecycledContentBeenOffered: Yes, hasSupplierName: Graphic Arts Incorporated(Graphic
+    Arts Inc  - 56170 - HHGSP), hasTotalColours: 6, hasUnitOfMeasure: Inches (in), '
+- text: 'hasCreatedDate: 2024-01-04, hasCustomerHomeCountry: United States, hasCustomerID:
+    14458, hasCustomerName: Lowe''s Companies Inc(Lowe''s FVS), hasCutting: Trim to
+    size, hasElementID: 3044623, hasElementTitle: G284515 Commodity Moulding Profile
+    Card 110911, hasFinishedSizeHeight: 6.875, hasFinishedSizeWidth: 3, hasFlatSizeHeight:
+    6.875, hasFlatSizeWidth: 3, hasFscPaperBeenSpecified: No, hasInternalID: c88f6dd9-5470-4870-a971-6d88eafb768d,
+    hasMaterialCategory: Other, hasMaterialDescription: 8PT _C1S Cover, hasMaterialType:
+    Other, hasNumberOfVersions: 1, hasPrice: 0.01 USD, hasPrintedSides: Single sided,
+    hasProofType: PDF digital proof, hasQuantity: 1, hasRecycledContentBeenOffered:
+    N/A, hasSupplierName: HH IC Content Production + Development(HH IC Content Production
+    + Development), hasTotalColours: 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: Northell/ros-classifiers-materials-flat
+      type: unknown
+      split: test
+    metrics:
+    - type: f1_micro
+      value: 0.4888472352389878
+      name: F1_Micro
+    - type: f1_macro
+      value: 0.07490145637740193
+      name: F1_Macro
+    - type: f1_weighted
+      value: 0.45529275569713784
+      name: F1_Weighted
+    - type: precision
+      value: 0.8907103538513184
+      name: Precision
+    - type: accuracy
+      value: 0.9836170077323914
+      name: Accuracy
+    - type: recall
+      value: 0.33686384558677673
+      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:** 43 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** | 0.4888   | 0.0749   | 0.4553      | 0.8907    | 0.9836   | 0.3369 |
+
+## 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: 2024-01-04, hasCustomerHomeCountry: United States, hasCustomerID: 14458, hasCustomerName: Lowe's Companies Inc(Lowe's FVS), hasCutting: Trim to size, hasElementID: 3044623, hasElementTitle: G284515 Commodity Moulding Profile Card 110911, hasFinishedSizeHeight: 6.875, hasFinishedSizeWidth: 3, hasFlatSizeHeight: 6.875, hasFlatSizeWidth: 3, hasFscPaperBeenSpecified: No, hasInternalID: c88f6dd9-5470-4870-a971-6d88eafb768d, hasMaterialCategory: Other, hasMaterialDescription: 8PT _C1S Cover, hasMaterialType: Other, hasNumberOfVersions: 1, hasPrice: 0.01 USD, hasPrintedSides: Single sided, hasProofType: PDF digital proof, hasQuantity: 1, hasRecycledContentBeenOffered: N/A, hasSupplierName: HH IC Content Production + Development(HH IC Content Production + Development), 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   | 61  | 109.9881 | 766 |
+
+### 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: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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 +1,48 @@
+{
+  "labels": [
+    "https://www.northell.com/taxonomies/MaterialTypes/TextilesCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/Artboard",
+    "https://www.northell.com/taxonomies/MaterialTypes/Leather",
+    "https://www.northell.com/taxonomies/MaterialTypes/FabricCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/Softwood",
+    "https://www.northell.com/taxonomies/MaterialTypes/PVC",
+    "https://www.northell.com/taxonomies/MaterialTypes/Hardwood",
+    "https://www.northell.com/taxonomies/MaterialTypes/Nylon",
+    "https://www.northell.com/taxonomies/MaterialTypes/Particleboard",
+    "https://www.northell.com/taxonomies/MaterialTypes/PLABioplastic",
+    "https://www.northell.com/taxonomies/MaterialTypes/Paper",
+    "https://www.northell.com/taxonomies/MaterialTypes/Polyurethane",
+    "https://www.northell.com/taxonomies/MaterialTypes/FoamBoard",
+    "https://www.northell.com/taxonomies/MaterialTypes/Medium-densityfibreboardMDF",
+    "https://www.northell.com/taxonomies/MaterialTypes/PlasticCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/Bamboo",
+    "https://www.northell.com/taxonomies/MaterialTypes/Aluminium",
+    "https://www.northell.com/taxonomies/MaterialTypes/Tinplate",
+    "https://www.northell.com/taxonomies/MaterialTypes/Displayboard",
+    "https://www.northell.com/taxonomies/MaterialTypes/LDPE",
+    "https://www.northell.com/taxonomies/MaterialTypes/MetalsCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/MaterialTypeScheme",
+    "https://www.northell.com/taxonomies/MaterialTypes/ABS",
+    "https://www.northell.com/taxonomies/MaterialTypes/PaperCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/Corrugated",
+    "https://www.northell.com/taxonomies/MaterialTypes/Paperandboard",
+    "https://www.northell.com/taxonomies/MaterialTypes/WoodCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/Steel",
+    "https://www.northell.com/taxonomies/MaterialTypes/Polystyrol",
+    "https://www.northell.com/taxonomies/MaterialTypes/Acrylics",
+    "https://www.northell.com/taxonomies/MaterialTypes/Polypropylene",
+    "https://www.northell.com/taxonomies/MaterialTypes/Polystyrene",
+    "https://www.northell.com/taxonomies/MaterialTypes/HDPE",
+    "https://www.northell.com/taxonomies/MaterialTypes/PET",
+    "https://www.northell.com/taxonomies/MaterialTypes/Polycarbonate",
+    "https://www.northell.com/taxonomies/MaterialTypes/Wool",
+    "https://www.northell.com/taxonomies/MaterialTypes/Cotton",
+    "https://www.northell.com/taxonomies/MaterialTypes/Polyester",
+    "https://www.northell.com/taxonomies/MaterialTypes/Fabric",
+    "https://www.northell.com/taxonomies/MaterialTypes/Iron",
+    "https://www.northell.com/taxonomies/MaterialTypes/OtherCategory",
+    "https://www.northell.com/taxonomies/MaterialTypes/Other",
+    "https://www.northell.com/taxonomies/MaterialTypes/AcrylicsPolymethylmethacrylate"
+  ],
+  "normalize_embeddings": false
+}

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:d4e093ed8471559d53424417b7ce370af389102c3d2e5d6eff0d6ba2df9212cb
+size 104996

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]"
+}