Full model 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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "bitextor/bicleaner-ai-full-en-bg",
+  "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": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

lm.bg

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f0a70020b21e56481c825f4df62a4c3051016a26d860e6f9d24f40f8612307
+size 174558658

lm.en

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc416b4b62efe5495e7e2963636b5591a808abeabd914c7886881a9695f53fcc
+size 152177167

metadata.yaml

@@ -0,0 +1,31 @@
+bicleaner_ai_version: 2.0
+precision_score: 0.883
+recall_score: 0.924
+f1_score: 0.903
+matthews_corr_coef: 0.892
+source_lang: en
+target_lang: bg
+porn_removal_file: porn_removal.ftz
+porn_removal_side: sl
+source_lm: lm.en
+target_lm: lm.bg
+lm_type: CHARACTER
+clean_mean_perp: -1.0690557224938897
+clean_stddev_perp: 0.19935068944513884
+noisy_mean_perp: -4.214147563787269
+noisy_stddev_perp: 0.20834659498675456
+classifier_type: xlmr
+classifier_settings:
+    activation: relu
+    base_model: jplu/tf-xlm-roberta-base
+    batch_size: 96
+    calibration_params: [2.12849140, -0.42519179]
+    epochs: 15
+    loss: binary_crossentropy
+    maxlen: 150
+    model_name: bitextor/bicleaner-ai-full-en-bg
+    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 sha256:4472671e3bde04ee9ff00b2adfc0ac9cabd522b305b0c47ab8f7805395e76d5a
+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 @@
+{"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": true}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3873dd49a9c55deec35f2487c9ff6c40ae4d8de392ba88227c2d2dd0c13e6385
+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 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "jplu/tf-xlm-roberta-base", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}