Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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
+}

README.md

@@ -1,3 +1,259 @@
----
-license: apache-2.0
----
+---
+tags:
+- setfit
+- sentence-transformers
+- text-classification
+- generated_from_setfit_trainer
+widget:
+- text: ya tengo mi trámite autorizado
+- text: que dijo
+- text: No se encuentra
+- text: deje su mensaje despues del tono.
+- text: Borren mi número
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: setfit
+inference: true
+base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+model-index:
+- name: SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: Unknown
+      type: unknown
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.7358490566037735
+      name: Accuracy
+---
+
+# SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+
+This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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 body:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2)
+- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
+- **Maximum Sequence Length:** 128 tokens
+- **Number of Classes:** 27 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)
+
+### Model Labels
+| Label | Examples                                                                                                                                                                  |
+|:------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 21    | <ul><li>'Por que tienen mi nombre'</li><li>'yo no le di mis datos ni nada a viraal'</li><li>'Como obtuvo mi informacion'</li></ul>                                        |
+| 12    | <ul><li>'Luego veo'</li><li>'Lo voy a pensar'</li><li>'Dejame checarlo'</li></ul>                                                                                         |
+| 18    | <ul><li>'Soy su hija'</li><li>'el no puede contestar ahorita'</li><li>'Soy su hijo'</li></ul>                                                                             |
+| 9     | <ul><li>'No quiero nada'</li><li>'No me interesa'</li><li>'No estoy interesado'</li></ul>                                                                                 |
+| 7     | <ul><li>'Estoy boletinado'</li><li>'Nadie me presta'</li><li>'Mi buro está rojo'</li></ul>                                                                                |
+| 5     | <ul><li>'no es mi numero'</li><li>'esta equivocada'</li><li>'no lo conozco'</li></ul>                                                                                     |
+| 24    | <ul><li>'Es rápido'</li><li>'En cuánto tiempo queda listo'</li><li>'Me urge el dinero, cuándo queda'</li></ul>                                                            |
+| 13    | <ul><li>'quien me busca'</li><li>'de parte de quien'</li><li>'no se quien eres'</li></ul>                                                                                 |
+| 15    | <ul><li>'La llamada se reenvio al buzon de voz,Graba tu mensaje despues del tono.'</li><li>'La llamada se reenvio al buzon de voz.'</li><li>'es el servicio de'</li></ul> |
+| 22    | <ul><li>'Requisitos para el credito'</li><li>'Piden buro de credito'</li><li>'Piden aval'</li></ul>                                                                       |
+| 17    | <ul><li>'Tienen oficinas físicas'</li><li>'Con que banco es el credito'</li><li>'quienes son ustedes'</li></ul>                                                           |
+| 20    | <ul><li>'sigue'</li><li>'bueno, bueno'</li><li>'habla'</li></ul>                                                                                                          |
+| 11    | <ul><li>'Márcame luego'</li><li>'Tengo prisa'</li><li>'Estoy trabajando'</li></ul>                                                                                        |
+| 25    | <ul><li>'Tengo credito con Credifiel'</li><li>'No tengo capacidad de credito'</li><li>'quiero bajar mi deuda actual'</li></ul>                                            |
+| 1     | <ul><li>'quiero la cotizacion'</li><li>'Sí, me interesa'</li><li>'A ver, cuentame más'</li></ul>                                                                          |
+| 23    | <ul><li>'La tasa es fija'</li><li>'Es muy caro el interes'</li><li>'Deme el porcentaje de interes'</li></ul>                                                              |
+| 6     | <ul><li>'Por el momento no'</li><li>'despues'</li><li>'Ahora no joven'</li></ul>                                                                                          |
+| 26    | <ul><li>'ya mande mis papeles'</li><li>'Me atendio otra señorita'</li><li>'ya estoy en proceso con ustedes'</li></ul>                                                     |
+| 14    | <ul><li>'quítenme de su lista'</li><li>'No necesito dinero, borren el número'</li><li>'No deseo recibir publicidad'</li></ul>                                             |
+| 0     | <ul><li>'No se, quizás'</li><li>'Mándalo a ver que tal'</li><li>'Dejame ver'</li></ul>                                                                                    |
+| 10    | <ul><li>'Estoy bien así'</li><li>'No quiero endeudarme'</li><li>'Tengo dinero'</li></ul>                                                                                  |
+| 2     | <ul><li>'Está enfermo'</li><li>'Está en el hospital'</li><li>'Tiene demencia'</li></ul>                                                                                   |
+| 19    | <ul><li>'no le oí bien'</li><li>'puede repetir por favor'</li><li>'me lo puede repetir por favor'</li></ul>                                                               |
+| 3     | <ul><li>'Es difunto'</li><li>'el ya no vive'</li><li>'Fallecio hace tiempo'</li></ul>                                                                                     |
+| 8     | <ul><li>'No uso banca movil'</li><li>'No se hacer pagos digitales'</li><li>'No le se al celular'</li></ul>                                                                |
+| 4     | <ul><li>'Anda fuera'</li><li>'Regresa más tarde'</li><li>'Salio'</li></ul>                                                                                                |
+| 16    | <ul><li>'Hay gastos ocultos'</li><li>'No doy dinero por adelantado'</li><li>'Tiene costo el trámite'</li></ul>                                                            |
+
+## Evaluation
+
+### Metrics
+| Label   | Accuracy |
+|:--------|:---------|
+| **all** | 0.7358   |
+
+## 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("que dijo")
+```
+
+<!--
+### 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   | 1   | 3.7644 | 13  |
+
+| Label | Training Sample Count |
+|:------|:----------------------|
+| 0     | 5                     |
+| 1     | 6                     |
+| 2     | 5                     |
+| 3     | 4                     |
+| 4     | 5                     |
+| 5     | 4                     |
+| 6     | 9                     |
+| 7     | 6                     |
+| 8     | 6                     |
+| 9     | 13                    |
+| 10    | 6                     |
+| 11    | 5                     |
+| 12    | 5                     |
+| 13    | 10                    |
+| 14    | 13                    |
+| 15    | 13                    |
+| 16    | 6                     |
+| 17    | 9                     |
+| 18    | 10                    |
+| 19    | 9                     |
+| 20    | 13                    |
+| 21    | 7                     |
+| 22    | 6                     |
+| 23    | 6                     |
+| 24    | 6                     |
+| 25    | 12                    |
+| 26    | 9                     |
+
+### Training Hyperparameters
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
+- max_steps: -1
+- sampling_strategy: oversampling
+- num_iterations: 20
+- body_learning_rate: (2e-05, 1e-05)
+- head_learning_rate: 0.01
+- loss: CosineSimilarityLoss
+- distance_metric: cosine_distance
+- margin: 0.25
+- end_to_end: False
+- use_amp: False
+- warmup_proportion: 0.1
+- l2_weight: 0.01
+- seed: 42
+- evaluation_strategy: epoch
+- eval_max_steps: -1
+- load_best_model_at_end: True
+
+### Training Results
+| Epoch  | Step | Training Loss | Validation Loss |
+|:------:|:----:|:-------------:|:---------------:|
+| 0.0019 | 1    | 0.1458        | -               |
+| 0.0962 | 50   | 0.1708        | -               |
+| 0.1923 | 100  | 0.1158        | -               |
+| 0.2885 | 150  | 0.059         | -               |
+| 0.3846 | 200  | 0.0494        | -               |
+| 0.4808 | 250  | 0.0337        | -               |
+| 0.5769 | 300  | 0.026         | -               |
+| 0.6731 | 350  | 0.0182        | -               |
+| 0.7692 | 400  | 0.0144        | -               |
+| 0.8654 | 450  | 0.0113        | -               |
+| 0.9615 | 500  | 0.0138        | -               |
+| 1.0    | 520  | -             | 0.0688          |
+
+### Framework Versions
+- Python: 3.12.12
+- SetFit: 1.1.3
+- Sentence Transformers: 5.2.0
+- Transformers: 4.57.3
+- PyTorch: 2.9.0+cpu
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## 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 +1,28 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.0+cpu"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

config_setfit.json

@@ -0,0 +1,4 @@
+{
+  "labels": null,
+  "normalize_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f09f5822fcb063607cfd4bdfbb8156e3dc617df0e5ae8eb5e41329d980d8f5d
+size 1112197096

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef061d1bdfb131a4d3b01f89b6cd90f887ecedb1100c18b4c9d6556b4e85af3
+size 167167

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}