Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,10 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,141 @@
----
-license: mit
----
+---
+language: 
+- multilingual
+- en
+- fr
+- es
+- de
+- el
+- bg
+- ru
+- tr
+- ar
+- vi
+- th
+- zh
+- hi
+- sw
+- ur
+tags:
+- text-classification
+- pytorch
+- tensorflow
+datasets:
+- multi_nli
+- xnli
+license: mit
+pipeline_tag: zero-shot-classification
+widget:
+- text: "За кого вы голосуете в 2020 году?"
+  candidate_labels: "politique étrangère, Europe, élections, affaires, politique"
+  multi_class: true
+- text: "لمن تصوت في 2020؟"
+  candidate_labels: "السياسة الخارجية, أوروبا, الانتخابات, الأعمال, السياسة"
+  multi_class: true
+- text: "2020'de kime oy vereceksiniz?"
+  candidate_labels: "dış politika, Avrupa, seçimler, ticaret, siyaset"
+  multi_class: true
+---
+
+# xlm-roberta-large-xnli
+
+## Model Description
+
+This model takes [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) and fine-tunes it on a combination of NLI data in 15 languages. It is intended to be used for zero-shot text classification, such as with the Hugging Face [ZeroShotClassificationPipeline](https://huggingface.co/transformers/master/main_classes/pipelines.html#transformers.ZeroShotClassificationPipeline).
+
+## Intended Usage
+
+This model is intended to be used for zero-shot text classification, especially in languages other than English. It is fine-tuned on XNLI, which is a multilingual NLI dataset. The model can therefore be used with any of the languages in the XNLI corpus:
+
+- English
+- French
+- Spanish
+- German
+- Greek
+- Bulgarian
+- Russian
+- Turkish
+- Arabic
+- Vietnamese
+- Thai
+- Chinese
+- Hindi
+- Swahili
+- Urdu
+
+Since the base model was pre-trained trained on 100 different languages, the
+model has shown some effectiveness in languages beyond those listed above as
+well. See the full list of pre-trained languages in appendix A of the
+[XLM Roberata paper](https://arxiv.org/abs/1911.02116)
+
+For English-only classification, it is recommended to use
+[bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) or
+[a distilled bart MNLI model](https://huggingface.co/models?filter=pipeline_tag%3Azero-shot-classification&search=valhalla).
+
+#### With the zero-shot classification pipeline
+
+The model can be loaded with the `zero-shot-classification` pipeline like so:
+
+```python
+from transformers import pipeline
+classifier = pipeline("zero-shot-classification",
+                      model="joeddav/xlm-roberta-large-xnli")
+```
+
+You can then classify in any of the above languages. You can even pass the labels in one language and the sequence to
+classify in another:
+
+```python
+# we will classify the Russian translation of, "Who are you voting for in 2020?"
+sequence_to_classify = "За кого вы голосуете в 2020 году?"
+# we can specify candidate labels in Russian or any other language above:
+candidate_labels = ["Europe", "public health", "politics"]
+classifier(sequence_to_classify, candidate_labels)
+# {'labels': ['politics', 'Europe', 'public health'],
+#  'scores': [0.9048484563827515, 0.05722189322113991, 0.03792969882488251],
+#  'sequence': 'За кого вы голосуете в 2020 году?'}
+```
+
+The default hypothesis template is the English, `This text is {}`. If you are working strictly within one language, it
+may be worthwhile to translate this to the language you are working with:
+
+```python
+sequence_to_classify = "¿A quién vas a votar en 2020?"
+candidate_labels = ["Europa", "salud pública", "política"]
+hypothesis_template = "Este ejemplo es {}."
+classifier(sequence_to_classify, candidate_labels, hypothesis_template=hypothesis_template)
+# {'labels': ['política', 'Europa', 'salud pública'],
+#  'scores': [0.9109585881233215, 0.05954807624220848, 0.029493311420083046],
+#  'sequence': '¿A quién vas a votar en 2020?'}
+```
+
+#### With manual PyTorch
+
+```python
+# pose sequence as a NLI premise and label as a hypothesis
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+nli_model = AutoModelForSequenceClassification.from_pretrained('joeddav/xlm-roberta-large-xnli')
+tokenizer = AutoTokenizer.from_pretrained('joeddav/xlm-roberta-large-xnli')
+
+premise = sequence
+hypothesis = f'This example is {label}.'
+
+# run through model pre-trained on MNLI
+x = tokenizer.encode(premise, hypothesis, return_tensors='pt',
+                     truncation_strategy='only_first')
+logits = nli_model(x.to(device))[0]
+
+# we throw away "neutral" (dim 1) and take the probability of
+# "entailment" (2) as the probability of the label being true 
+entail_contradiction_logits = logits[:,[0,2]]
+probs = entail_contradiction_logits.softmax(dim=1)
+prob_label_is_true = probs[:,1]
+```
+
+## Training
+
+This model was pre-trained on set of 100 languages, as described in
+[the original paper](https://arxiv.org/abs/1911.02116). It was then fine-tuned on the task of NLI on the concatenated
+MNLI train set and the XNLI validation and test sets. Finally, it was trained for one additional epoch on only XNLI
+data where the translations for the premise and hypothesis are shuffled such that the premise and hypothesis for
+each example come from the same original English example but the premise and hypothesis are of different languages.

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "contradiction",
+    "1": "neutral",
+    "2": "entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 0,
+    "entailment": 2,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "type_vocab_size": 1,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8869b0c99ad35ec8a8c92434b54383d2dfd7db8cd460e28b9944a407e3a423e4
+size 2243825580

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947e0cebe09808e3279f38ceeca58af60c1fcebefbdfa54642285f35a0f8ec57
+size 2243942751

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913bd557db7f4e2f85c4d94c4ba30b3342457f6d2d783a8be141ae4018f73325
+size 2244296816

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512}