First commit

README.md

@@ -0,0 +1,56 @@
+---
+
+pipeline_tag: text-classification
+inference: false
+language: en
+tags:
+- transformers
+
+---
+
+# Prompsit/paraphrase-roberta-es
+
+This model allows to evaluate paraphrases for a given phrase.  
+
+We have fine-tuned this model from pretrained "PlanTL-GOB-ES/roberta-base-bne".
+
+Model built under a TSI-100905-2019-4 project, co-financed by Ministry of Economic Affairs and Digital Transformation from the Government of Spain.
+
+# How to use it
+
+The model answer the following question: Is "phrase B" a paraphrase of "phrase A".
+
+Please note that we're considering phrases instead of sentences. Therefore, we must take into account that the model doesn't expect to find punctuation marks or long pieces of text.
+
+Resulting probabilities correspond to classes:  
+
+* 0: Not a paraphrase
+* 1: It's a paraphrase
+
+So, considering the phrase "se buscarán acuerdos" and a candidate paraphrase like "se deberá obtener el acuerdo", you can use the model like this:
+
+```
+
+import torch
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+tokenizer = AutoTokenizer.from_pretrained("Prompsit/paraphrase-roberta-es")
+model = AutoModelForSequenceClassification.from_pretrained("Prompsit/paraphrase-roberta-es")
+
+input = tokenizer('se buscarán acuerdos','se deberá obtener el acuerdo',return_tensors='pt')
+logits = model(**input).logits
+soft = torch.nn.Softmax(dim=1)
+print(soft(logits))
+
+```
+
+Code output is:
+
+ ``` 
+
+ tensor([[0.2266, 0.7734]], grad_fn=<SoftmaxBackward>)
+
+ ```
+
+As the probability of 1 (=It's a paraphrase) is 0.77 and the probability of 0 (=It is not a paraphrase) is 0.22, we can conclude, for our previous example, that "se deberá obtener el acuerdo" is a paraphrase of "se buscarán acuerdos".
+

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Not Paraphrase",
+    "1": "Paraphrase"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Not Paraphrase": 0,
+    "Paraphrase": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c73c5e6e7e2a1856d003f044ad44a463017df3ce54d2c58878f5abe42616eb
+size 498664877

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "PlanTL-GOB-ES/roberta-base-bne", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a5bc90de40c0c9489ac705d5176d0991e203c34e0c667b2630a0bdcdffe6854
+size 2799