Upload folder using huggingface_hub
Browse files- README.md +70 -50
- config.json +3 -2
- config_sentence_transformers.json +1 -1
- config_setfit.json +2 -2
- model.safetensors +1 -1
- model_head.pkl +2 -2
- tokenizer_config.json +1 -2
README.md
CHANGED
|
@@ -5,11 +5,11 @@ tags:
|
|
| 5 |
- text-classification
|
| 6 |
- generated_from_setfit_trainer
|
| 7 |
widget:
|
| 8 |
-
- text:
|
| 9 |
-
- text:
|
| 10 |
-
- text: se
|
| 11 |
-
- text:
|
| 12 |
-
- text:
|
| 13 |
metrics:
|
| 14 |
- accuracy
|
| 15 |
pipeline_tag: text-classification
|
|
@@ -28,7 +28,7 @@ model-index:
|
|
| 28 |
split: test
|
| 29 |
metrics:
|
| 30 |
- type: accuracy
|
| 31 |
-
value: 0.
|
| 32 |
name: Accuracy
|
| 33 |
---
|
| 34 |
|
|
@@ -48,7 +48,7 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 48 |
- **Sentence Transformer body:** [hiiamsid/sentence_similarity_spanish_es](https://huggingface.co/hiiamsid/sentence_similarity_spanish_es)
|
| 49 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 50 |
- **Maximum Sequence Length:** 512 tokens
|
| 51 |
-
- **Number of Classes:**
|
| 52 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 53 |
<!-- - **Language:** Unknown -->
|
| 54 |
<!-- - **License:** Unknown -->
|
|
@@ -60,28 +60,33 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 60 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 61 |
|
| 62 |
### Model Labels
|
| 63 |
-
| Label | Examples
|
| 64 |
-
|:------|:--------------------------------------------------------------------------------------------------------------------------|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
| 7 | <ul><li>'
|
| 69 |
-
|
|
| 70 |
-
| 10 | <ul><li>'
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
| 3 | <ul><li>'
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
|
| 79 |
## Evaluation
|
| 80 |
|
| 81 |
### Metrics
|
| 82 |
| Label | Accuracy |
|
| 83 |
|:--------|:---------|
|
| 84 |
-
| **all** | 0.
|
| 85 |
|
| 86 |
## Uses
|
| 87 |
|
|
@@ -101,7 +106,7 @@ from setfit import SetFitModel
|
|
| 101 |
# Download from the 🤗 Hub
|
| 102 |
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 103 |
# Run inference
|
| 104 |
-
preds = model("
|
| 105 |
```
|
| 106 |
|
| 107 |
<!--
|
|
@@ -133,23 +138,28 @@ preds = model("se nos murio")
|
|
| 133 |
### Training Set Metrics
|
| 134 |
| Training set | Min | Median | Max |
|
| 135 |
|:-------------|:----|:-------|:----|
|
| 136 |
-
| Word count | 1 | 3.
|
| 137 |
|
| 138 |
| Label | Training Sample Count |
|
| 139 |
|:------|:----------------------|
|
| 140 |
-
| 0 |
|
| 141 |
-
| 1 |
|
| 142 |
-
| 2 |
|
| 143 |
-
| 3 |
|
| 144 |
-
| 4 |
|
| 145 |
-
| 5 |
|
| 146 |
-
| 6 |
|
| 147 |
-
| 7 |
|
| 148 |
-
| 8 |
|
| 149 |
-
| 9 |
|
| 150 |
-
| 10 |
|
| 151 |
| 11 | 13 |
|
| 152 |
-
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
|
| 154 |
### Training Hyperparameters
|
| 155 |
- batch_size: (16, 16)
|
|
@@ -174,26 +184,36 @@ preds = model("se nos murio")
|
|
| 174 |
### Training Results
|
| 175 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 176 |
|:------:|:----:|:-------------:|:---------------:|
|
| 177 |
-
| 0.
|
| 178 |
-
| 0.
|
| 179 |
-
| 0.
|
| 180 |
-
| 0.
|
| 181 |
-
| 0.
|
| 182 |
-
| 0.
|
| 183 |
-
| 0.
|
| 184 |
-
| 0.
|
| 185 |
-
| 0.
|
| 186 |
-
| 0.
|
| 187 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
|
| 189 |
### Framework Versions
|
| 190 |
- Python: 3.12.12
|
| 191 |
- SetFit: 1.1.3
|
| 192 |
- Sentence Transformers: 5.2.2
|
| 193 |
-
- Transformers: 4.
|
| 194 |
- PyTorch: 2.9.0+cu126
|
| 195 |
- Datasets: 4.0.0
|
| 196 |
-
- Tokenizers: 0.
|
| 197 |
|
| 198 |
## Citation
|
| 199 |
|
|
|
|
| 5 |
- text-classification
|
| 6 |
- generated_from_setfit_trainer
|
| 7 |
widget:
|
| 8 |
+
- text: soy quien busca
|
| 9 |
+
- text: adios, buenas tardes
|
| 10 |
+
- text: no se encuentra
|
| 11 |
+
- text: yo le puedo pasar el mensaje
|
| 12 |
+
- text: quizas funcione
|
| 13 |
metrics:
|
| 14 |
- accuracy
|
| 15 |
pipeline_tag: text-classification
|
|
|
|
| 28 |
split: test
|
| 29 |
metrics:
|
| 30 |
- type: accuracy
|
| 31 |
+
value: 0.9111111111111111
|
| 32 |
name: Accuracy
|
| 33 |
---
|
| 34 |
|
|
|
|
| 48 |
- **Sentence Transformer body:** [hiiamsid/sentence_similarity_spanish_es](https://huggingface.co/hiiamsid/sentence_similarity_spanish_es)
|
| 49 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 50 |
- **Maximum Sequence Length:** 512 tokens
|
| 51 |
+
- **Number of Classes:** 18 classes
|
| 52 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 53 |
<!-- - **Language:** Unknown -->
|
| 54 |
<!-- - **License:** Unknown -->
|
|
|
|
| 60 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 61 |
|
| 62 |
### Model Labels
|
| 63 |
+
| Label | Examples |
|
| 64 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------|
|
| 65 |
+
| 14 | <ul><li>'tengo otro prestamo activo'</li><li>'mi historial esta mal'</li><li>'tengo credito con otra financiera'</li></ul> |
|
| 66 |
+
| 11 | <ul><li>'hable mas fuerte'</li><li>'se oye muy lejos'</li><li>'se corta'</li></ul> |
|
| 67 |
+
| 15 | <ul><li>'ahorita voy manejando, hablame luego'</li><li>'ahorita no puedo atenderte, estoy ocupado'</li><li>'voy manejando'</li></ul> |
|
| 68 |
+
| 7 | <ul><li>'ya fallecio'</li><li>'ya no esta con nosotros'</li><li>'el ya no vive'</li></ul> |
|
| 69 |
+
| 4 | <ul><li>'adios, buenas noches'</li><li>'bueno, gracias, adios'</li><li>'listo, hasta luego'</li></ul> |
|
| 70 |
+
| 10 | <ul><li>'si, quiero saber'</li><li>'si, digame rapido'</li><li>'te escucho'</li></ul> |
|
| 71 |
+
| 12 | <ul><li>'no, joven, muchas gracias'</li><li>'no, oiga, gracias'</li><li>'no, por ahora paso, gracias'</li></ul> |
|
| 72 |
+
| 17 | <ul><li>'bueno, diga'</li><li>'si'</li><li>'si, diga'</li></ul> |
|
| 73 |
+
| 3 | <ul><li>'si, a ver de que se trata'</li><li>'tal vez si'</li><li>'esta bien, envialo'</li></ul> |
|
| 74 |
+
| 5 | <ul><li>'no corresponde ese numero'</li><li>'esta llamando al numero equivocado'</li><li>'aqui no vive esa persona'</li></ul> |
|
| 75 |
+
| 8 | <ul><li>'¿me da la direccion de sus oficinas?'</li><li>'yo no les di mi telefono'</li><li>'yo no le di mis datos a nadie'</li></ul> |
|
| 76 |
+
| 0 | <ul><li>'soy su hermana'</li><li>'esta bajo tratamiento'</li><li>'se siente mal'</li></ul> |
|
| 77 |
+
| 16 | <ul><li>'¿quien me llama?'</li><li>'¿de que empresa llaman?'</li><li>'¿quien es?'</li></ul> |
|
| 78 |
+
| 1 | <ul><li>'habla el senor'</li><li>'con ella habla'</li><li>'si aqui habla'</li></ul> |
|
| 79 |
+
| 6 | <ul><li>'un momento por favor'</li><li>'deja le hablo'</li><li>'permiteme un segundo, no me cuelgues'</li></ul> |
|
| 80 |
+
| 2 | <ul><li>'¿con quien quiere hablar?'</li><li>'¿quien busca?'</li><li>'¿a quien esta buscando?'</li></ul> |
|
| 81 |
+
| 9 | <ul><li>'no esten chingando'</li><li>'es la quinta vez que me marcan hoy'</li><li>'¡que no entiendes que no!'</li></ul> |
|
| 82 |
+
| 13 | <ul><li>'salio a la tienda, no tarda'</li><li>'ahorita no esta, anda de viaje'</li><li>'anda trabajando'</li></ul> |
|
| 83 |
|
| 84 |
## Evaluation
|
| 85 |
|
| 86 |
### Metrics
|
| 87 |
| Label | Accuracy |
|
| 88 |
|:--------|:---------|
|
| 89 |
+
| **all** | 0.9111 |
|
| 90 |
|
| 91 |
## Uses
|
| 92 |
|
|
|
|
| 106 |
# Download from the 🤗 Hub
|
| 107 |
model = SetFitModel.from_pretrained("setfit_model_id")
|
| 108 |
# Run inference
|
| 109 |
+
preds = model("soy quien busca")
|
| 110 |
```
|
| 111 |
|
| 112 |
<!--
|
|
|
|
| 138 |
### Training Set Metrics
|
| 139 |
| Training set | Min | Median | Max |
|
| 140 |
|:-------------|:----|:-------|:----|
|
| 141 |
+
| Word count | 1 | 3.9018 | 11 |
|
| 142 |
|
| 143 |
| Label | Training Sample Count |
|
| 144 |
|:------|:----------------------|
|
| 145 |
+
| 0 | 32 |
|
| 146 |
+
| 1 | 18 |
|
| 147 |
+
| 2 | 11 |
|
| 148 |
+
| 3 | 18 |
|
| 149 |
+
| 4 | 18 |
|
| 150 |
+
| 5 | 22 |
|
| 151 |
+
| 6 | 9 |
|
| 152 |
+
| 7 | 12 |
|
| 153 |
+
| 8 | 40 |
|
| 154 |
+
| 9 | 11 |
|
| 155 |
+
| 10 | 33 |
|
| 156 |
| 11 | 13 |
|
| 157 |
+
| 12 | 48 |
|
| 158 |
+
| 13 | 8 |
|
| 159 |
+
| 14 | 36 |
|
| 160 |
+
| 15 | 13 |
|
| 161 |
+
| 16 | 18 |
|
| 162 |
+
| 17 | 37 |
|
| 163 |
|
| 164 |
### Training Hyperparameters
|
| 165 |
- batch_size: (16, 16)
|
|
|
|
| 184 |
### Training Results
|
| 185 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 186 |
|:------:|:----:|:-------------:|:---------------:|
|
| 187 |
+
| 0.0010 | 1 | 0.3888 | - |
|
| 188 |
+
| 0.0504 | 50 | 0.211 | - |
|
| 189 |
+
| 0.1007 | 100 | 0.1344 | - |
|
| 190 |
+
| 0.1511 | 150 | 0.0742 | - |
|
| 191 |
+
| 0.2014 | 200 | 0.0484 | - |
|
| 192 |
+
| 0.2518 | 250 | 0.0387 | - |
|
| 193 |
+
| 0.3021 | 300 | 0.0264 | - |
|
| 194 |
+
| 0.3525 | 350 | 0.0183 | - |
|
| 195 |
+
| 0.4028 | 400 | 0.0135 | - |
|
| 196 |
+
| 0.4532 | 450 | 0.0115 | - |
|
| 197 |
+
| 0.5035 | 500 | 0.0082 | - |
|
| 198 |
+
| 0.5539 | 550 | 0.0083 | - |
|
| 199 |
+
| 0.6042 | 600 | 0.0073 | - |
|
| 200 |
+
| 0.6546 | 650 | 0.009 | - |
|
| 201 |
+
| 0.7049 | 700 | 0.0067 | - |
|
| 202 |
+
| 0.7553 | 750 | 0.0075 | - |
|
| 203 |
+
| 0.8056 | 800 | 0.0085 | - |
|
| 204 |
+
| 0.8560 | 850 | 0.0073 | - |
|
| 205 |
+
| 0.9063 | 900 | 0.0065 | - |
|
| 206 |
+
| 0.9567 | 950 | 0.0076 | - |
|
| 207 |
+
| 1.0 | 993 | - | 0.0437 |
|
| 208 |
|
| 209 |
### Framework Versions
|
| 210 |
- Python: 3.12.12
|
| 211 |
- SetFit: 1.1.3
|
| 212 |
- Sentence Transformers: 5.2.2
|
| 213 |
+
- Transformers: 4.44.2
|
| 214 |
- PyTorch: 2.9.0+cu126
|
| 215 |
- Datasets: 4.0.0
|
| 216 |
+
- Tokenizers: 0.19.1
|
| 217 |
|
| 218 |
## Citation
|
| 219 |
|
config.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"BertModel"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
"classifier_dropout": null,
|
| 7 |
-
"dtype": "float32",
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
|
@@ -19,7 +19,8 @@
|
|
| 19 |
"output_past": true,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
-
"
|
|
|
|
| 23 |
"type_vocab_size": 2,
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 31002
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "hiiamsid/sentence_similarity_spanish_es",
|
| 3 |
"architectures": [
|
| 4 |
"BertModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
|
|
|
| 19 |
"output_past": true,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.44.2",
|
| 24 |
"type_vocab_size": 2,
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 31002
|
config_sentence_transformers.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"__version__": {
|
| 3 |
"sentence_transformers": "5.2.2",
|
| 4 |
-
"transformers": "4.
|
| 5 |
"pytorch": "2.9.0+cu126"
|
| 6 |
},
|
| 7 |
"model_type": "SentenceTransformer",
|
|
|
|
| 1 |
{
|
| 2 |
"__version__": {
|
| 3 |
"sentence_transformers": "5.2.2",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
"pytorch": "2.9.0+cu126"
|
| 6 |
},
|
| 7 |
"model_type": "SentenceTransformer",
|
config_setfit.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"labels": null,
|
| 3 |
+
"normalize_embeddings": false
|
| 4 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 439425888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69618ae50cf5d9badf705bfa0d831bafedcfe359c65440434d337da90ae5caff
|
| 3 |
size 439425888
|
model_head.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:546fe46dd5fed7c63dfe7f1ca36775a3710f7f6b3c9ed2b93bdaa3aa461e94ad
|
| 3 |
+
size 111719
|
tokenizer_config.json
CHANGED
|
@@ -41,11 +41,10 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"clean_up_tokenization_spaces":
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
| 48 |
-
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"max_length": 512,
|
| 51 |
"model_max_length": 512,
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": false,
|
|
|
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"max_length": 512,
|
| 50 |
"model_max_length": 512,
|