Instructions to use hucruz/consejo-ner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hucruz/consejo-ner with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="hucruz/consejo-ner")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("hucruz/consejo-ner") model = AutoModelForTokenClassification.from_pretrained("hucruz/consejo-ner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +78 -0
- pytorch_model.bin +3 -0
- runs/Feb21_17-44-44_082f89abe8f1/1677001498.5592074/events.out.tfevents.1677001498.082f89abe8f1.235.1 +3 -0
- runs/Feb21_17-44-44_082f89abe8f1/events.out.tfevents.1677001498.082f89abe8f1.235.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-911",
|
| 14 |
+
"2": "I-911",
|
| 15 |
+
"3": "B-alcaldia",
|
| 16 |
+
"4": "I-alcaldia",
|
| 17 |
+
"5": "B-chat_confianza",
|
| 18 |
+
"6": "I-chat_confianza",
|
| 19 |
+
"7": "B-ciberacoso",
|
| 20 |
+
"8": "I-ciberacoso",
|
| 21 |
+
"9": "B-extorsion",
|
| 22 |
+
"10": "I-extorsion",
|
| 23 |
+
"11": "B-maltrato_animal",
|
| 24 |
+
"12": "I-maltrato_animal",
|
| 25 |
+
"13": "B-maltrato_infantil",
|
| 26 |
+
"14": "I-maltrato_infantil",
|
| 27 |
+
"15": "B-pais",
|
| 28 |
+
"16": "I-pais",
|
| 29 |
+
"17": "B-robo",
|
| 30 |
+
"18": "I-robo",
|
| 31 |
+
"19": "B-secuestro",
|
| 32 |
+
"20": "I-secuestro",
|
| 33 |
+
"21": "B-trata_personas",
|
| 34 |
+
"22": "I-trata_personas",
|
| 35 |
+
"23": "B-violencia_familiar",
|
| 36 |
+
"24": "I-violencia_familiar"
|
| 37 |
+
},
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"B-911": 1,
|
| 41 |
+
"B-alcaldia": 3,
|
| 42 |
+
"B-chat_confianza": 5,
|
| 43 |
+
"B-ciberacoso": 7,
|
| 44 |
+
"B-extorsion": 9,
|
| 45 |
+
"B-maltrato_animal": 11,
|
| 46 |
+
"B-maltrato_infantil": 13,
|
| 47 |
+
"B-pais": 15,
|
| 48 |
+
"B-robo": 17,
|
| 49 |
+
"B-secuestro": 19,
|
| 50 |
+
"B-trata_personas": 21,
|
| 51 |
+
"B-violencia_familiar": 23,
|
| 52 |
+
"I-911": 2,
|
| 53 |
+
"I-alcaldia": 4,
|
| 54 |
+
"I-chat_confianza": 6,
|
| 55 |
+
"I-ciberacoso": 8,
|
| 56 |
+
"I-extorsion": 10,
|
| 57 |
+
"I-maltrato_animal": 12,
|
| 58 |
+
"I-maltrato_infantil": 14,
|
| 59 |
+
"I-pais": 16,
|
| 60 |
+
"I-robo": 18,
|
| 61 |
+
"I-secuestro": 20,
|
| 62 |
+
"I-trata_personas": 22,
|
| 63 |
+
"I-violencia_familiar": 24,
|
| 64 |
+
"O": 0
|
| 65 |
+
},
|
| 66 |
+
"max_position_embeddings": 512,
|
| 67 |
+
"model_type": "distilbert",
|
| 68 |
+
"n_heads": 12,
|
| 69 |
+
"n_layers": 6,
|
| 70 |
+
"pad_token_id": 0,
|
| 71 |
+
"qa_dropout": 0.1,
|
| 72 |
+
"seq_classif_dropout": 0.2,
|
| 73 |
+
"sinusoidal_pos_embds": true,
|
| 74 |
+
"tie_weights_": true,
|
| 75 |
+
"torch_dtype": "float32",
|
| 76 |
+
"transformers_version": "4.26.1",
|
| 77 |
+
"vocab_size": 31002
|
| 78 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8a3a9393881c456f80e5a94e81d0da3a3b835c6018581f99570767bfc19fd22
|
| 3 |
+
size 267037797
|
runs/Feb21_17-44-44_082f89abe8f1/1677001498.5592074/events.out.tfevents.1677001498.082f89abe8f1.235.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef6a5faf7d772f1cfeaaf33aadbde0cdc77aa5f892ba791abdd819ecbc43d902
|
| 3 |
+
size 5655
|
runs/Feb21_17-44-44_082f89abe8f1/events.out.tfevents.1677001498.082f89abe8f1.235.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:851816cc96ec185c788b2b0fda354e5c1a6301b1378bd09ddecb56c82b0fe984
|
| 3 |
+
size 5460
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "dccuchile/distilbert-base-spanish-uncased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": false,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bdc7f7bfa50f9ef851f46664d1214a93c9ab8d9de98d56e5b1382a4804dcc30
|
| 3 |
+
size 3515
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|