Full models v2.0

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* 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
+lm.* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,18 @@
+---
+language:
+  - en
+  - pt
+  - multilingual
+license: cc-by-sa-4.0
+tags:
+  - bicleaner-ai
+tasks:
+  - text-classification
+---
+
+# Bicleaner AI full model for en-pt
+Bicleaner AI is a tool that aims at detecting noisy sentence pairs in a parallel corpus. It
+indicates the likelihood of a pair of sentences being mutual translations (with a value near to 1) or not (with a value near to 0).
+Sentence pairs considered very noisy are scored with 0.
+
+Find out at our repository for further instructions on how to use it: https://github.com/bitextor/bicleaner-ai

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bitextor/bicleaner-ai-full-en-pt",
+  "architectures": [
+    "XLMRBicleanerAI"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "head_activation": "relu",
+  "head_dropout": 0.1,
+  "head_hidden_size": 2048,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

lm.en

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d01d7d41d87c46183d8c4d41b6a180bebf5caca4ad6ce669c685633e475955
+size 202685013

lm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1486cb795ee76ad21074e98b774167a5d6ed755360f78aeada84d39cde6875b4
+size 187325239

metadata.yaml

@@ -0,0 +1,31 @@
+bicleaner_ai_version: 2.1.0
+precision_score: 0.887
+recall_score: 0.915
+f1_score: 0.901
+matthews_corr_coef: 0.890
+source_lang: en
+target_lang: pt
+porn_removal_file: porn_removal.ftz
+porn_removal_side: sl
+source_lm: lm.en
+target_lm: lm.pt
+lm_type: CHARACTER
+clean_mean_perp: -1.0385617878337767
+clean_stddev_perp: 0.16396083880979564
+noisy_mean_perp: -3.9983609024726428
+noisy_stddev_perp: 0.15078200001769357
+classifier_type: xlmr
+classifier_settings:
+    activation: relu
+    base_model: jplu/tf-xlm-roberta-base
+    batch_size: 96
+    calibration_params: [8.20400524, -3.08755279]
+    epochs: 15
+    loss: binary_crossentropy
+    maxlen: 150
+    model_name: bitextor/bicleaner-ai-full-en-pt
+    n_classes: 2
+    n_hidden: 2048
+    patience: 3
+    steps_per_epoch: 3000
+    warmup_steps: 1000

porn_removal.ftz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34cb84b95408b1d7cfb09919ccc979b43edd89ff4629786c0433ce4e4071db6
+size 1213624

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5277c1f907ffad5afcf891d816f167106f6b08c65894f7e0a08778ac367190bb
+size 1116401536

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672b5602c725cafd47011e4e49d4b211fd746d0de2e8e187549f0324685987d0
+size 17098332

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "jplu/tf-xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}