Init commit-

README.md

@@ -0,0 +1,47 @@
+---
+language: 
+  - ar
+  - bg
+  - de
+  - el
+  - en
+  - es
+  - fr
+  - ru
+  - th
+  - tr
+  - ur
+  - vn
+  - zh
+datasets:
+- SNLI
+- MNLI
+- ANLI
+- XNLI
+tags:
+- zero-shot-classification
+---
+
+
+A cross attention NLI model trained for zero-shot and few-shot text classification.
+
+The base model is [xlm-roberta-base](https://huggingface.co/xlm-roberta-base), trained with the code from [here](https://github.com/facebookresearch/anli).
+on [SNLI](https://nlp.stanford.edu/projects/snli/) and [MNLI](https://cims.nyu.edu/~sbowman/multinli/), [ANLI](https://github.com/facebookresearch/anli) and [XNLI](https://github.com/facebookresearch/XNLI).
+
+Usage:
+
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import numpy as np
+
+model = AutoModelForSequenceClassification.from_pretrained("symanto/xlm-roberta-base-snli-mnli-anli-xnli")
+tokenizer = AutoTokenizer.from_pretrained("symanto/xlm-roberta-base-snli-mnli-anli-xnli")
+
+input_pairs = [("I like this pizza.", "The sentence is positive."), ("I like this pizza.", "The sentence is negative.")]
+inputs = tokenizer(["</s></s>".join(input_pair) for input_pair in input_pairs], return_tensors="pt")
+logits = model(**inputs).logits
+probs =  torch.softmax(logits, dim=1).tolist()
+print("probs", probs)
+np.testing.assert_almost_equal(probs, [[0.86, 0.14, 0.00], [0.16, 0.15, 0.69]], decimal=2)
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "symanto/xlm-roberta-base-snli-mnli-anli-xnli",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ENTAILMENT",
+    "1": "NEUTRAL",
+    "2": "CONTRADICTION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ENTAILMENT": 0,
+    "NEUTRAL": 1,
+    "CONTRADICTION": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c9f77c1df291bb64322f179bbc3cbc26e98a3d17ddf38dccd1df204216d02f
+size 1112266413

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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/mpnet-base", "tokenizer_class": "MPNetTokenizer"}