krotima1 commited on
Commit
b0c6b28
1 Parent(s): 0a23ffa

fix: add correct tokenizer

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. sentencepiece.bpe.model +3 -0
  3. tokenizer_config.json +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "checkpoint-860000",
3
  "_num_labels": 3,
4
  "activation_dropout": 0.0,
5
  "activation_function": "gelu",
 
1
  {
2
+ "_name_or_path": "../output/trainModel/multilarge/htext2abstract/ml_F/checkpoint-809000",
3
  "_num_labels": 3,
4
  "activation_dropout": 0.0,
5
  "activation_function": "gelu",
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
tokenizer_config.json CHANGED
@@ -1 +1 @@
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": "cs_CZ", "tgt_lang": "cs_CZ", "additional_special_tokens": null, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/mbart-large-cc25", "tokenizer_class": "MBartTokenizer"}
 
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": "cs_CZ", "tgt_lang": "cs_CZ", "additional_special_tokens": null, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "../output/trainModel/multilarge/htext2abstract/ml_F/checkpoint-809000", "tokenizer_class": "MBartTokenizer"}