Initial commit

.gitattributes

@@ -0,0 +1,17 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 16,
+  "decoder_attention_heads": 4,
+  "decoder_ffn_dim": 4,
+  "decoder_layerdrop": 0.05,
+  "decoder_layers": 2,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 4,
+  "encoder_ffn_dim": 4,
+  "encoder_layerdrop": 0.05,
+  "encoder_layers": 2,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 20,
+  "model_type": "m2m_100",
+  "num_hidden_layers": 2,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "transformers_version": "4.11.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09355f5f8a9733622d4e286df2680d565e0a8fab5e3e4e4ef954b06ac1685a85
+size 16520597

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dfd1eae4522281b1b839eab877a791befec7a1663a41c814c77d9c89c748f2d
+size 253154

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}, "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN"]}

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"}, "src_lang": null, "tgt_lang": null, "additional_special_tokens": null, "sp_model_kwargs": {}, "keep_accents": true, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "./", "tokenizer_class": "MBartTokenizer"}