jhuertas
commited on
Commit
•
eb95d6d
1
Parent(s):
9ec4fb7
First commit
Browse files- README.md +26 -0
- config.json +38 -0
- pytorch_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-classification
|
| 3 |
+
tags:
|
| 4 |
+
- natural-language-inference
|
| 5 |
+
- misogyny
|
| 6 |
+
language: en
|
| 7 |
+
license: apache-2.0
|
| 8 |
+
widget:
|
| 9 |
+
- text: "Las mascarillas causan hipoxia. Wearing masks is harmful to human health"
|
| 10 |
+
example_title: "Natural Language Inference"
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# bertweet-base-multi-mami
|
| 14 |
+
This is a finetuned XLM-RoBERTA model for natural language inference. It has been trained with a massive ammount of data following the ANLI pipeline training. We include data from:
|
| 15 |
+
- [mnli-mt](https://github.com/facebookresearch/XNLI) {train}
|
| 16 |
+
- [snli](https://nlp.stanford.edu/projects/snli/) {train, dev and test}
|
| 17 |
+
- [xnli](https://github.com/facebookresearch/XNLI) {dev and test}
|
| 18 |
+
- [fever](https://fever.ai/resources.html) {train, dev and test}
|
| 19 |
+
- [anli](https://github.com/facebookresearch/anli) {train}
|
| 20 |
+
|
| 21 |
+
# Multilabels
|
| 22 |
+
label2id={
|
| 23 |
+
"contradiction": 0,
|
| 24 |
+
"entailment": 1,
|
| 25 |
+
"neutral": 2,
|
| 26 |
+
},
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0,
|
| 22 |
+
"LABEL_1": 1,
|
| 23 |
+
"LABEL_2": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "xlm-roberta",
|
| 28 |
+
"num_attention_heads": 16,
|
| 29 |
+
"num_hidden_layers": 24,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.12.3",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 250002
|
| 38 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52b89fff0f487510c63887a17701b2130aa45dec797bed608b935029b0c24762
|
| 3 |
+
size 2239738157
|