vicgalle commited on
Commit
a48caa7
1 Parent(s): 17e4ad4

initial model

Browse files
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: multilingual
3
+ tags:
4
+ - zero-shot-classification
5
+ - nli
6
+ - pytorch
7
+ datasets:
8
+ - mnli
9
+ - xnli
10
+ - anli
11
+ license: mit
12
+ pipeline_tag: zero-shot-classification
13
+ widget:
14
+ - text: "La película empezaba bien pero terminó siendo un desastre."
15
+ labels: "positivo, negativo, neutral"
16
+ - text: "¿A quién vas a votar en 2020?"
17
+ labels: "Europa, elecciones, política, ciencia, deportes"
18
+ ---
19
+
20
+ ### XLM-RoBERTa-large-XNLI-ANLI
21
+
22
+ XLM-RoBERTa-large model finetunned over several NLI datasets, ready to use for zero-shot classification.
23
+
24
+ Here are the accuracies for several test datasets:
25
+
26
+ | | XNLI-es | XNLI-fr | ANLI-R1 | ANLI-R2 | ANLI-R3 |
27
+ |-----------------------------|---------|---------|---------|---------|---------|
28
+ | xlm-roberta-large-xnli-anli | 93.7% | 93.2% | 68.5% | 53.6% | 49.0% |
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "contradiction",
14
+ "1": "neutral",
15
+ "2": "entailment"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "contradiction": 0,
21
+ "entailment": 2,
22
+ "neutral": 1
23
+ },
24
+ "layer_norm_eps": 1e-05,
25
+ "max_position_embeddings": 514,
26
+ "model_type": "xlm-roberta",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "output_past": true,
30
+ "pad_token_id": 1,
31
+ "type_vocab_size": 1,
32
+ "vocab_size": 250002
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f5d4fa3552fe9a4a1395dd30c7fd19d62fbc3d101bae31aa2e931fa5b08803
3
+ size 2239747529
sentencepiece.bpe.model ADDED
Binary file (5.07 MB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 512}