finiteautomata
commited on
Commit
•
7d0a074
1
Parent(s):
25bda70
Initial model
Browse files- README.md +12 -0
- added_tokens.json +1 -0
- config.json +44 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Emotion Analysis in Spanish
|
2 |
+
## beto-emotion-analysis
|
3 |
+
|
4 |
+
Repository: [https://github.com/finiteautomata/pysentimiento/](https://github.com/finiteautomata/pysentimiento/)
|
5 |
+
|
6 |
+
|
7 |
+
Model trained with TASS 2020 Task 2 corpus for Emotion detection in Spanish. Base model is [BETO](https://github.com/dccuchile/beto), a BERT model trained in Spanish.
|
8 |
+
|
9 |
+
|
10 |
+
**Coming soon**: a brief paper describing the model and training.
|
11 |
+
|
12 |
+
Enjoy! 🤗
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[EMOJI]": 31004, "[USER]": 31002, "[HASHTAG]": 31003}
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": [
|
12 |
+
"others",
|
13 |
+
"joy",
|
14 |
+
"sadness",
|
15 |
+
"anger",
|
16 |
+
"surprise",
|
17 |
+
"disgust",
|
18 |
+
"fear"
|
19 |
+
],
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"anger": 3,
|
24 |
+
"disgust": 5,
|
25 |
+
"fear": 6,
|
26 |
+
"joy": 1,
|
27 |
+
"others": 0,
|
28 |
+
"sadness": 2,
|
29 |
+
"surprise": 4
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-12,
|
32 |
+
"max_position_embeddings": 512,
|
33 |
+
"model_type": "bert",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_hidden_layers": 12,
|
36 |
+
"output_past": true,
|
37 |
+
"pad_token_id": 1,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"problem_type": "single_label_classification",
|
40 |
+
"transformers_version": "4.6.1",
|
41 |
+
"type_vocab_size": 2,
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 31005
|
44 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75706a6e461cc838f55e8961d8bdd4868185b57a2e431ae105c3420ce75f544c
|
3 |
+
size 439521165
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[USER]", "[HASHTAG]", "[EMOJI]"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "name_or_path": "dccuchile/bert-base-spanish-wwm-cased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/home/jmperez/.cache/huggingface/transformers/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|