Upload 5 files
Browse files- config.json +2 -3
- generation_config.json +1 -1
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
@@ -51,8 +51,7 @@
|
|
51 |
"scale_embedding": true,
|
52 |
"static_position_embeddings": false,
|
53 |
"tokenizer_class": "MBart50Tokenizer",
|
54 |
-
"
|
55 |
-
"transformers_version": "4.32.0",
|
56 |
"use_cache": true,
|
57 |
"vocab_size": 250054
|
58 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large-many-to-many/",
|
3 |
"_num_labels": 3,
|
4 |
"activation_dropout": 0.0,
|
5 |
"activation_function": "relu",
|
|
|
51 |
"scale_embedding": true,
|
52 |
"static_position_embeddings": false,
|
53 |
"tokenizer_class": "MBart50Tokenizer",
|
54 |
+
"transformers_version": "4.9.0.dev0",
|
|
|
55 |
"use_cache": true,
|
56 |
"vocab_size": 250054
|
57 |
}
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
"max_length": 200,
|
9 |
"num_beams": 5,
|
10 |
"pad_token_id": 1,
|
11 |
-
"transformers_version": "4.
|
12 |
}
|
|
|
8 |
"max_length": 200,
|
9 |
"num_beams": 5,
|
10 |
"pad_token_id": 1,
|
11 |
+
"transformers_version": "4.27.0.dev0"
|
12 |
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "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", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"src_lang": null, "tgt_lang": null, "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"}, "bos_token": "<s>", "tokenizer_file": null, "language_codes": "ML50", "special_tokens_map_file": "/home/suraj/projects/mbart-50/mbart-50/special_tokens_map.json", "name_or_path": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large-many-to-many/"}
|