ajout des modèles

.gitattributes

@@ -33,3 +33,4 @@ 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
+models/xlmr_base/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

models/camembert_large/config.yaml

@@ -0,0 +1,19 @@
+architecture: "transformer_text_classifier"
+task: "text_classification"
+
+backbone:
+  framework: "huggingface"
+  model_name: "almanach/camembert-large"
+  add_pooling_layer: false
+
+head:
+  type: "mlp"
+  num_labels: 27
+  mlp_dim: 512
+  pooling: "mean"
+  dropout: 0.15
+
+tokenizer:
+  max_length: 384
+  truncation: true
+  padding: true

models/camembert_large/metadata.yaml

@@ -0,0 +1,18 @@
+training:
+  epoch: 8
+  val_f1: 0.9183226118776615
+  val_loss: 0.4086824008088587
+
+dataset:
+  name: "Rakuten France Multimodal Product Data Classification"
+  split:
+    train_ratio: 0.9
+    val_ratio: 0.1
+    base_subset: 1.0
+    stratify: true
+    seed: 42
+
+metadata:
+  modality: "texte"
+  language: "fr"
+  description: "CamemBERT-large + MLP head"

models/camembert_large/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997037f09c073b7ef49bc19a251e89ff2c7a1b92654a7664b76994dafd7cddfa
+size 1349103319

models/camembert_large/tokenizer/added_tokens.json

@@ -0,0 +1,32 @@
+{
+  "[DESC]": 32006,
+  "[TITRE]": 32005,
+  "[age_adulte]": 32024,
+  "[age_bébé]": 32022,
+  "[age_enfant]": 32023,
+  "[beaucoup_de_cartes]": 32011,
+  "[beaucoup_de_pièces]": 32021,
+  "[capacity]": 32019,
+  "[energy]": 32018,
+  "[grand_volume]": 32014,
+  "[grande_longueur]": 32030,
+  "[grande_mémoire]": 32034,
+  "[grande_surface]": 32009,
+  "[longueur_moyenne]": 32029,
+  "[mémoire_moyenne]": 32033,
+  "[petit_volume]": 32012,
+  "[petite_longueur]": 32028,
+  "[petite_mémoire]": 32032,
+  "[petite_surface]": 32007,
+  "[peu_de_cartes]": 32010,
+  "[peu_de_pièces]": 32020,
+  "[poids_leger]": 32025,
+  "[poids_lourd]": 32027,
+  "[poids_moyen]": 32026,
+  "[power]": 32017,
+  "[surface_moyenne]": 32008,
+  "[temperature]": 32016,
+  "[tension]": 32015,
+  "[très_grande_longueur]": 32031,
+  "[volume_moyen]": 32013
+}

models/camembert_large/tokenizer/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
+size 808767

models/camembert_large/tokenizer/special_tokens_map.json

@@ -0,0 +1,263 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[TITRE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[DESC]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[petite_surface]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[surface_moyenne]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[grande_surface]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[peu_de_cartes]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[beaucoup_de_cartes]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[petit_volume]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[volume_moyen]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[grand_volume]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[tension]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[temperature]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[power]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[energy]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[capacity]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[peu_de_pièces]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[beaucoup_de_pièces]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[age_bébé]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[age_enfant]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[age_adulte]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[poids_leger]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[poids_moyen]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[poids_lourd]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[petite_longueur]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[longueur_moyenne]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[grande_longueur]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[très_grande_longueur]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[petite_mémoire]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[mémoire_moyenne]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "[grande_mémoire]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/camembert_large/tokenizer/tokenizer_config.json

@@ -0,0 +1,352 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "[TITRE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "[DESC]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "[petite_surface]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "[surface_moyenne]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "[grande_surface]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "[peu_de_cartes]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "[beaucoup_de_cartes]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "[petit_volume]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "[volume_moyen]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "[grand_volume]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "[tension]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "[temperature]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "[power]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "[energy]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "[capacity]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "[peu_de_pièces]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "[beaucoup_de_pièces]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "[age_bébé]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "[age_enfant]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "[age_adulte]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "[poids_leger]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "[poids_moyen]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "[poids_lourd]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "[petite_longueur]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "[longueur_moyenne]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "[grande_longueur]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "[très_grande_longueur]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "[petite_mémoire]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "[mémoire_moyenne]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "[grande_mémoire]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[TITRE]",
+    "[DESC]",
+    "[petite_surface]",
+    "[surface_moyenne]",
+    "[grande_surface]",
+    "[peu_de_cartes]",
+    "[beaucoup_de_cartes]",
+    "[petit_volume]",
+    "[volume_moyen]",
+    "[grand_volume]",
+    "[tension]",
+    "[temperature]",
+    "[power]",
+    "[energy]",
+    "[capacity]",
+    "[peu_de_pièces]",
+    "[beaucoup_de_pièces]",
+    "[age_bébé]",
+    "[age_enfant]",
+    "[age_adulte]",
+    "[poids_leger]",
+    "[poids_moyen]",
+    "[poids_lourd]",
+    "[petite_longueur]",
+    "[longueur_moyenne]",
+    "[grande_longueur]",
+    "[très_grande_longueur]",
+    "[petite_mémoire]",
+    "[mémoire_moyenne]",
+    "[grande_mémoire]"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

models/convnext_base/config.yaml

@@ -0,0 +1,22 @@
+architecture: "timm_image_classifier"
+task: "image_classification"
+
+backbone:
+  library: "timm"
+  model_name: "convnext_base"
+  pretrained: false
+  global_pool: "avg"
+  drop_path_rate: 0.3
+
+head:
+  num_classes: 27
+  hidden_dim: 512
+  dropout: 0.5
+  head_dropout2: 0.3
+
+transform:
+  type: "convnext"
+  img_size: 384
+  normalize:
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]

models/convnext_base/metadata.yaml

@@ -0,0 +1,13 @@
+training:
+  epoch: 26
+  best_val_f1: 0.7417708636028976
+  is_ema: false
+
+dataset:
+  name: "Rakuten France Multimodal Product Data Classification"
+  split_signature: cf53f8eb169b3531
+  classes_fp: cdfa70b13f7390e6
+
+metadata:
+  modality: "image"
+  description: "ConvNeXt-Base + custom MLP head"

models/convnext_base/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84066ddc22643c26b89a81b5ea082ac4b265207dd58ddbcbe158c1251528fe66
+size 352547459

models/fusion/fusion_params.json

@@ -0,0 +1,23 @@
+{
+  "image": {
+    "temperatures": {
+      "convnext": 1.0366606712341309,
+      "swin": 0.9393814206123352
+    },
+    "weights": {
+      "convnext": 0.5009813315915296,
+      "swin": 0.49901866840847037
+    }
+  },
+  "text": {
+    "temperatures": {
+      "camembert": 1.5091458559036255,
+      "xlmr": 1.1880803108215332
+    },
+    "weights": {
+      "camembert": 0.3856692246572912,
+      "xlmr": 0.34737854011528824,
+      "tfidf": 0.26695223522742056
+    }
+  }
+}

models/registry.yaml

@@ -0,0 +1,26 @@
+text:
+  camembert:
+    path: "models/text/camembert_large"
+    preprocess: "numeric_light"
+    temperature_key: "camembert"
+
+  xlmr:
+    path: "models/text/xlmr_base"
+    preprocess: "merge_sep"
+    temperature_key: "xlmr"
+
+image:
+  convnext:
+    path: "models/image/convnext_base"
+    temperature_key: "convnext"
+
+  swin:
+    path: "models/image/swin_base"
+    temperature_key: "swin"
+
+tfidf:
+  vectorizer_path: "models/text/tfidf/vectorizer_svm.joblib"
+  temperature_key: "tfidf"
+
+fusion:
+  params_path: "models/fusion/fusion_params.json"

models/swin_base/config.yaml

@@ -0,0 +1,22 @@
+architecture: "timm_image_classifier"
+task: "image_classification"
+
+backbone:
+  library: "timm"
+  model_name: "swin_base_patch4_window7_224"
+  pretrained: false
+  global_pool: "avg"
+  drop_path_rate: 0.3
+
+head:
+  num_classes: 27
+  hidden_dim: 512
+  dropout: 0.5
+  head_dropout2: 0.3
+
+transform:
+  type: "swin"
+  img_size: 224
+  normalize:
+    mean: [0.485, 0.456, 0.406]
+    std: [0.229, 0.224, 0.225]

models/swin_base/metadata.yaml

@@ -0,0 +1,12 @@
+training:
+  epoch: 30
+  best_val_f1: 0.7286950403251646
+
+dataset:
+  name: "Rakuten France Multimodal Product Data Classification"
+  split_signature: cf53f8eb169b3531
+  classes_fp: cdfa70b13f7390e6
+
+metadata:
+  modality: "image"
+  description: "Swin-Base + custom MLP head"

models/swin_base/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4018c5131ae9b08b63c5ecb842da95fc16af9f5c4b73034253259cfc03e52c5f
+size 349251903

models/xlmr_base/config.yaml

@@ -0,0 +1,19 @@
+architecture: "transformer_text_classifier"
+task: "text_classification"
+
+backbone:
+  framework: "huggingface"
+  model_name: "xlm-roberta-base"
+  add_pooling_layer: false
+
+head:
+  type: "mlp"
+  num_labels: 27
+  mlp_dim: 512
+  pooling: "mean"
+  dropout: 0.15
+
+tokenizer:
+  max_length: 384
+  truncation: true
+  padding: true

models/xlmr_base/metadata.yaml

@@ -0,0 +1,18 @@
+training:
+  epoch: 5
+  val_f1: 0.8847797276301669
+  val_loss: 0.4016371085363276
+
+dataset:
+  name: "Rakuten France Multimodal Product Data Classification"
+  split:
+    train_ratio: 0.85
+    val_ratio: 0.15
+    base_subset: 0.85
+    stratify: true
+    seed: 42
+
+metadata:
+  modality: "texte"
+  language: "multilingual"
+  description: "XLM-R base + MLP head"

models/xlmr_base/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf996d41ec107be423d5c25ef1ef5ab429c40c8ae8958a8ac9e515eb1d0a93b
+size 1113903997

models/xlmr_base/tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[SEP]": 250002
+}

models/xlmr_base/tokenizer/sentencepiece.bpe.model

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

models/xlmr_base/tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

models/xlmr_base/tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba072c18ab5a9b22830654061a6b5fc51cf42cf6eab02fc07e156ec6ae0d7a8
+size 17082916

models/xlmr_base/tokenizer/tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[SEP]"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}