Upload folder using huggingface_hub
Browse files- README.md +38 -3
- config.json +24 -0
- metrics.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,38 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Modelo de Análisis de Sentimiento IMDb - DistilBERT
|
2 |
+
|
3 |
+
Este modelo ha sido entrenado para la tarea de análisis de sentimiento sobre reseñas de películas del dataset IMDb.
|
4 |
+
|
5 |
+
## Arquitectura
|
6 |
+
- **Modelo base:** distilbert-base-uncased (de Hugging Face Transformers)
|
7 |
+
- **Tarea:** Clasificación binaria (positivo/negativo)
|
8 |
+
- **Tokenizador:** DistilBERT uncased
|
9 |
+
|
10 |
+
## Datos de entrenamiento
|
11 |
+
- **Dataset:** IMDb (25,000 reseñas de películas)
|
12 |
+
- **Split:** 60% entrenamiento, 40% validación
|
13 |
+
- **Test:** 25,000 ejemplos (conjunto original de test)
|
14 |
+
|
15 |
+
## Proceso de entrenamiento
|
16 |
+
- **Épocas:** 3
|
17 |
+
- **Batch size:** 16
|
18 |
+
- **Optimización:** AdamW, weight decay 0.01
|
19 |
+
- **Warmup steps:** 500
|
20 |
+
- **Métricas:** Accuracy, F1, Precision, Recall
|
21 |
+
- **Hardware:** Entrenado en GPU (NVIDIA GeForce GTX 960M)
|
22 |
+
|
23 |
+
## Uso
|
24 |
+
Puedes cargar este modelo con Hugging Face Transformers:
|
25 |
+
|
26 |
+
```python
|
27 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
28 |
+
|
29 |
+
tokenizer = AutoTokenizer.from_pretrained("juancmamacias/jd-jcms")
|
30 |
+
model = AutoModelForSequenceClassification.from_pretrained("juancmamacias/jd-jcms")
|
31 |
+
```
|
32 |
+
|
33 |
+
## Autor
|
34 |
+
- Juan C. Macías
|
35 |
+
|
36 |
+
## Notas
|
37 |
+
- El modelo es adecuado para tareas de análisis de sentimiento en inglés.
|
38 |
+
- Entrenado con el script `train_sentiment_model.py` incluido en este repositorio.
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"DistilBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"dim": 768,
|
8 |
+
"dropout": 0.1,
|
9 |
+
"hidden_dim": 3072,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"max_position_embeddings": 512,
|
12 |
+
"model_type": "distilbert",
|
13 |
+
"n_heads": 12,
|
14 |
+
"n_layers": 6,
|
15 |
+
"pad_token_id": 0,
|
16 |
+
"problem_type": "single_label_classification",
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.53.3",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
metrics.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_loss": 0.33,
|
3 |
+
"eval_accuracy": 0.93,
|
4 |
+
"eval_f1": 0.93,
|
5 |
+
"eval_precision": 0.93,
|
6 |
+
"eval_recall": 0.93
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0eebe4d70159be4a2bef6f4adc687e66654160c652a1f34865e513419632435
|
3 |
+
size 267832560
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87f990c6acfaf2521f08c43efacc759614b5acbb9cca5401ab6ab197bb66dca8
|
3 |
+
size 5649
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|