cleaning update

config.json

@@ -1,52 +1,33 @@
 {
-  "_name_or_path": "facebook/mgenre-wiki",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
   "architectures": [
-    "BartForConditionalGeneration"
+    "MBartForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "decoder_normalize_before": true,
-  "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
-  "encoder_normalize_before": true,
   "eos_token_id": 2,
-  "eos_token_ids": [
-    2
-  ],
   "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
   "init_std": 0.02,
   "is_encoder_decoder": true,
-  "max_length": 1024,
   "max_position_embeddings": 1024,
-  "min_length": 0,
-  "model_type": "bart",
-  "normalize_embedding": false,
-  "num_beams": 5,
+  "model_type": "mbart",
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": true,
-  "static_position_embeddings": false,
-  "student_decoder_layers": null,
-  "student_encoder_layers": null,
-  "task_specific_params": {},
-  "transformers_version": "4.19.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
   "use_cache": true,
   "vocab_size": 256001
 }

special_tokens_map.json

@@ -1 +1,15 @@
-{"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}}
+{
+  "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5368e45f810725f023451207956a99f324c0253d334f4bdaaeb2ae3dcd331f3d
+oid sha256:4bab0eb292448adec41c255d1b18c7e0eb1f1052b8791328ebfa834156b42a56
 size 2469461956

titles_lang_all105_trie_with_redirect.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af6069f11ec1d2f2ce1ef8f034eec761c0bee5971f663f6355442683e533935
-size 1754513408
+oid sha256:ce296109b89b948c62d2abca9222b145d0587b4af7fda7a6df1b7f066b7331b9
+size 2338474677

tokenizer_config.json

@@ -1 +1,18 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}